DETAILED ACTION
This action is in response to communications filed on 01/05/2026. Claims 1, 4, 5, 9, 13, 16, and 17 have been amended. Claims 3 and 15 have been cancelled. No new claims have been added. Claims 1-4, 5-14, and 16-20 are currently presented for examination.
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Response to Amendment
Applicant submits that no new matter has been added by way of amendment and provided citations to the originally filed specification in at least paragraphs 13-15, 18, and 29, as well as in originally filed claimed 3 and 15.
The cited sections of the originally filed disclosure have been evaluated to determine if the amendments to the claims are adequately supported.
The majority of the amended matter into the independent claims incorporates matter that was previously presented in now cancelled claims such that it is apparent to the examiner no new matter has been introduced by the incorporation of the matter in the prior dependent claims.
The applicant did introduce a limitation which was not previously claimed: wherein the predicted output value is a higher-order derivative of the inputs.
This limitation was previously discussed between the examiner and the applicant in the interview on 12/18/2025, where concerns of adequate support were raised by the examiner. The applicant referenced paragraphs [0013] and [0029] of the specification as having support for this limitation. In the response to this action, the applicant provided additional citations to the specification that allegedly demonstrate adequate support for the newly added limitations, particularly citing [0013]-[0015], [0018], and [0029]. It is not apparent that the cited references necessarily support the limitation, however, the cited references in conjunction with the disclosed matter in paragraphs 42 and 56 reasonably convey that the predicted output values would be understood by a person having skill to be higher order derivatives of the exemplary inputs.
Examiner concurs that the claimed matter is adequately supported such that it is apparent the applicant had possession of the claimed invention at the time of filing. No new mater has been introduced by way of amendment.
Response to Arguments
Rejections under 35 U.S.C. § 112(b)
Applicant has amended claim 9 in response to the previously set forth rejection under 35 U.S.C. § 112(b) from “determining an accuracy the prediction” to “determining an accuracy the predicted output value”. This amendment does clarify the antecedent basis issue under 35 U.S.C. § 112(b) such that the claim element clearly refers to an element which has been previously introduced. Accordingly, the rejection has been withdrawn.
However, the claim remains objected to for informality reasons as stated in this action- Examiner suggests inclusion of the word “of” for grammatical correctness (“…determining an accuracy of the predicted output value.”)
Rejections under 35 U.S.C. § 101
Applicant traverses the rejections under 35 U.S.C. § 101 but does not provide arguments in support of the position. Applicant has amended the claims in response to the rejection under 35 U.S.C. § 101 and submits that the amendments render the rejections moot but does not provide explicit arguments in support of the submission.
The amendments to the independent claims 1 and 13 incorporate subject matter from previously presented claims 3 and 15 respectively, which have been cancelled in the present claims. As stated in the previous action the limitations taken from 3 and 15 do not integrate the judicial exception into a practical application or amount to significantly more than the judicial exception. The remaining additional elements which are newly-added to the claim likewise do not further impose meaningful limits on the claim such that they would integrate the judicial exception into a practical application nor amount to significantly more than the judicial exception. Particularly, the inclusion of “conducting a wellbore operation” and “and wherein the predicted output value is a higher order derivative of the inputs” merely links the use of the judicial exception to a particular technological environment and field of use. The limitations describe the environment by which the judicial exception operates but do not provide an inventive concept. The inventive concept appears to be the prediction of an output value (which is a mental process since a human being is capable of making judgements for predicting values). This objective of the claims is achieved through the use of generic computing components (machine learning model) recited at a high level of generality as a mechanism/tool by which to perform the abstract procedure. The claims as a whole do not appear to include limitations that demonstrate an improvement to the functioning of the computer (machine learning model claimed) and further do not appear to reflect additional elements that would set forth an improvement to the technical field.
According to the background of the specification, existing methods include performing ex-situ experiments to obtain information to understand petrophysical and hydraulic properties of reservoirs. The background further asserts that forecasting and planning of maintenance for existing sensors in a wellbore is limited to a-priori scheduling and assumptions. The disclosed invention instead . The present claims do not contain limitations that reflect the disclosed improvement. For example, in claim 1, “predicting the output value of the virtual sensor using the machine learning model, the predicted output values is indicative of at least one of sub-surface formation or fluid properties inside the wellbore” does not necessitate that such indicative information would yield insights to understanding petrophysical and hydraulic properties of reservoirs, as existing methods do. Furthermore, there are no limitations that reflect the disclosed improvement of forecasting and planning maintenance of existing sensors in a wellbore. At best, claim 7 discloses the determination of if the predicted output constitutes an outlier and claim 8 discloses the generation of a notification for evaluating of a physical sensor. There are no limitations that necessitate planning or action based on such generated notification, which would more clearly reflect the alleged improvement.
Accordingly, for the reasons stated in this response, in conjunction with the updated rejection stated in this action, the claims remain rejected under 35 U.S.C. § 101.
Rejections under 35 U.S.C. § 103
Applicant has amended the independent claims in response to the rejection previously set forth under 35 U.S.C. § 103. Applicant argues that the claims, as amended, include features that are not taught or suggested by the prior art of record, specifically regarding the teachings of Vittal and Schultz. The features argued as not being taught by the noted references include generating a machine learning model for predicting an output value of a virtual sensor using inputs comprising: information associated with structural mechanics of sub-surface rocks in a wellbore resulting from hydraulic induced changes; information associated with injection of fluids inside the wellbore and changes to flow to and from the wellbore; and physical parameters of and prior measurements by a physical sensor positioned in the wellbore", "performing one of retraining the machine learning model for predicting the output value of the virtual sensor or predicting the output value of the virtual sensor ", and "wherein the predicted output value is a higher-order derivative of the inputs." (emphasis added).
A large portion of the amended matter in the independent claim includes limitations which were in previously presented claim 3. As discussed in the previous action, Vittal and Schultz alone were not relied upon to teach the entirety of the limitations. Rather, the combination of Vittal and Schultz, in conjunction with the teachings of Lakings, were relied upon to disclose all of the limitations. Nonetheless, the introduction of the newly-added limitation wherein the predicted output value is a higher-order derivative of the inputs altered the scope of the previously presented claims such that further search was necessitated. Further search revealed that the entirety of the claimed limitations for the independent claims are disclosed by the combined teachings of Vittal, Schultz, and Cella.
Applicant particularly argues that Vittal’s teachings and suggestions of a “virtual sensor” are to predict a mere and generic change in a submersible pumping system in a reservoir which is not the same as what is recited in the claims.
Examiner acknowledges that the previous mapping of the claims equated the output of the virtual sensor disclosed by Vittal as the prediction of a state change occurrence. By this definition, the Examiner agrees with the argument presented by the applicant. However, because the scope of the claim has been changed by the inclusion of output value … wherein the predicted output values is a higher-order derivative of the inputs, the examiner’s interpretation of Vittal has likewise changed. In addition to Vittal’s virtual sensor outputting a prediction of a state change, Vittal’s virtual sensor includes additional outputs. Vittal describes the virtual sensor as being composed of statistical models- namely the reservoir state model and the electric submersible pumping system anomaly model. The outputs of these models are used to derive the condition prediction ((Vittal, ¶5) " In this sense, the electric submersible pumping systems act as "virtual sensors" by providing field data field to the statistical models, which can then be used to predict the condition of the individual electric submersible pumping systems and the condition of the reservoir. "); ((Vittal, ¶6) " The process continues with the steps of receiving field data from the electric submersible pumping system deployed in the reservoir and applying the field data to the reservoir state model and electric submersible pumping system anomaly model. The process concludes by generating an output representative of the likelihood that the reservoir has changed states. "). The output/results of the statistical models is compared to baseline data in order to inform the prediction of the state change, thereby indicating that additional outputs are generated in addition to the state change prediction ((Vittal, ¶35) " Once the tests have been concluded, the stage of deploying the models to the field 208 continues at step 226 by comparing the results of the tests against the baseline data library using a truth table or logic rule to determine the likelihood that: (1) the reservoir 136 has changed state; (2) the electric submersible pumping system 100 has become faulty or is otherwise operating outside an expected condition; or (3) both the reservoir 136 and the electric submersible pumping system 100 have changed from the baseline state. "). The baseline data library includes health indices which can be expressed as a function of the reservoir variables ((Vittal, ¶28) " The measured and stored parameters are denoted as electric submersible pumping system "health indices" that can be expressed as a function of the reservoir variables. The "health indices" determined as a result of the tests conducted on healthy electric submersible pumping systems 100 provide a library of reference data across a range of reservoir conditions. "). In knowing that the statistical models produce an output that is directly compared to the reference data library of health indices expressed as a function of reservoir variables, it is reasonably suggested that the outputs of the statistical models comprise a health index value or its respective function of the reservoir variables, thereby indicating that the virtual sensor does produce output values. Vittal is not relied upon to disclose wherein the predicted output values is a higher-order derivative of the inputs and Schultz does not cure this deficiency; however, Cella provides a teaching that sensor data may be processed to evaluate the health of components, wherein changes of a directly measured value are indicative of the health status (See Cella 583). The examiner understands higher order derivatives of values to be indicative of the rate at which the previous derivative changes. Accordingly, Cella’s teachings of processing sensor data to reveal insights regarding changes in the sensor data could be applied to the teachings of Vittal and Schultz. Particularly, by employing the machine learning model disclosed by the combination of Vittal and Schultz as the mechanism by which to process the sensor data of Cella, one having skill would have arrived at the claimed invention. It would have been obvious to make such an association because Vittal notes that the statistical models receive sensor data as inputs and subsequently output data that is compared directly to health index data and Cella provides an explicit discussion noting that raw sensor data can be processed to reveal health information of pump components by capitalizing on the rate of change of the sensor data to reveal such insights and further Cella states that the methodologies disclosed therein can be applied to generate output of a virtual sensor.
Accordingly, the claims remain rejected under 35 U.S.C. § 103, under a new grounds of rejection set forth in this action, necessitated by applicant’s amendment.
Claim Objections
Claim 9 is objected to because of the following informalities:
The grammatical correctness of the claim is lacking. Examiner suggests inclusion of the word “of” for grammatical correctness (“…determining an accuracy of the predicted output value.”). Appropriate correction is required.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-2, 4-14, and 16-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more. The following section follows the 2019 Patent Eligibility Guidance (PEG) for analyzing subject matter eligibility:
Step 1 - Statutory Category:
Step 1 of the PEG analysis entails considering whether the claimed subject matter falls within the four statutory categories of patentable subject matter identified by 35 U.S.C. 101 (process, machine, manufacture, or composition of matter).
Step 2A Prong 1 - Judicial exception:
In Step 2A Prong 1, examiners evaluate whether the claim recites a judicial exception (an abstract idea, law of nature, or a natural phenomenon).
Step 2a Prong 2 - Integration into a practical application:
If claims recite a judicial exception, the claim requires further analysis in Step 2A Prong 2. In Step 2A Prong 2, examiners evaluate whether the claim as a whole integrates the exception into a practical application.
Step 2B - Significantly More:
If the additional elements identified in Step 2A Prong 2 do not integrate the exception into a practical application, then the claim is directed to the recited judicial exception and requires further analysis under Step 2B- Significantly More.
As noted in the MPEP 2106.05(II): The identification of the additional element(s) in the claim from Step 2A Prong 2, as well as the conclusions from Step 2A Prong 2 on the considerations discussed in MPEP 2106.05(a) -(c), (e), (f), and (h) are to be carried over. Claim limitations identified as Insignificant Extra-Solution Activities are further evaluated to determine if the elements are beyond what is well -understood, routine, and conventional (WURC) activity, as dictated by MPEP 2106.05(II).
Independent Claims:
Claim 1:
Step 1: Claim 1 and its dependent claims 2 and 4-12 are directed to a method which falls within one of the four statutory categories of a process.
Step 2A Prong 1: Claim 1 recites a judicial exception, noted in bold:
detecting a change to a system of the wellbore operation to yield a determination. The claim limitation can be reasonably read to entail observing and evaluating a change to a system to make a judgement regarding the observations. This task can be practically performed in the human mind because a human can observe and evaluate changes of a system and further draw conclusions or make judgements about the observations. Therefore, this claim limitation includes the recitation of the judicial exception of abstract ideas of a mental process.
based on the determination, The claim limitation can be reasonably read to entail further evaluating the determined value to inform subsequent action. This task can be practically performed in the human mind because a human is capable of using a determination as a basis to inform subsequent decisions. Therefore, this claim limitation includes the recitation of the judicial exception of abstract ideas of a mental process.
predicting the output value of the virtual sensor model. The claim limitation can be reasonably read to entail using a machine learning model to make a prediction. The claim limitation invokes the use of a generic computing component (a machine learning model) to perform the mental process. The claim limitation, as drafted, is a process that, but for the recitation of generic computing components, under broadest reasonable interpretation, covers performance of the mind. The courts do not distinguish between mental processes that are performed entirely in the human mind and mental processes that are performed on a computer. A human being is capable of observing data and making a prediction based on the observations. Therefore, this claim limitation includes the recitation of the judicial exception of abstract ideas of a mental process.
Therefore, the claim recites a judicial exception.
Step 2A Prong 2: Additional elements were identified and are noted in italics.
conducting a wellbore operation; - This limitation has been identified as Field of Use and Technological Environment (MPEP 2106.05(h)) for generally linking the use of the judicial exception to a particular technological environment or field of use
generating a machine learning model for predicting an output value of a virtual sensor using inputs comprising: This limitation has been identified as Mere Instructions to Apply an Exception (MPEP 2106.05(f)) because the limitation merely invokes the use of computing components to perform the recited judicial exception
information associated with structural mechanics of sub-surface rocks in a well bore resulting from hydraulic induced changes; This limitation has been identified as Field of Use and Technological Environment (MPEP 2106.05(h)) for generally linking the use of the judicial exception to a particular technological environment or field of use
information associated with injection of fluids inside the wellbore and changes to flow to and from the well bore; and This limitation has been identified as Field of Use and Technological Environment (MPEP 2106.05(h)) for generally linking the use of the judicial exception to a particular technological environment or field of use
physical parameters of and prior measurements by a physical sensor positioned in the wellbore; This limitation has been identified as Field of Use and Technological Environment (MPEP 2106.05(h)) for generally linking the use of the judicial exception to a particular technological environment or field of use
wherein the system includes the virtual sensor, and wherein the virtual sensor includes the physical sensor for collecting one or more physical properties inside the wellbore; and- This limitation has been identified as Field of Use and Technological Environment (MPEP 2106.05(h)) because the element generally links the use of the judicial exception to a particular field of use and technological environment.
performing one of retraining the machine learning model for predicting the output of the virtual sensor or- This limitation has been identified as Mere Instructions to Apply an Exception (MPEP 2106.05(f)) because the element amounts to invoking computers as merely a tool to perform an existing process. The retraining of the machine learning model is not claimed in any inventive way and is a standard function of machine learning models operating and their normal capacity
using the machine learning model – This limitation has been identified as Mere Instructions to Apply an Exception (MPEP 2106.05(f)) for invoking the use of generically-claimed computing components to perform the recited judicial exception
the predicted output value is indicative of at least one of sub-surface formation or fluid properties inside the wellbore, and wherein the predicted output value is a higher order derivative of the inputs - This limitation has been identified as Field of Use and Technological Environment (MPEP 2106.05(h)) because the element generally links the use of the judicial exception to a particular field of use and technological environment.
The courts have found that merely including instructions to implement an abstract idea on a computer or merely using a computer as a tool to perform an abstract idea (Mere Instructions to Apply an Exception (MPEP 2106.05(f))); and generally linking the use of a judicial exception to a particular technological environment or field of use (Field of Use and Technological Environment (MPEP 2106.05(h))) does not integrate the judicial exception into a practical application.
When viewed independently and within the claim as a whole, the additional elements do not appear to integrate the judicial exception into a practical application.
Step 2B: In Step 2A Prong 2, no additional elements were identified as Insignificant Extra Solution Activity (MPEP 2106.05(g)) and therefore no further evaluation is required to determine if the elements amount to more that WURC activity. Additional elements identified otherwise and conclusions from Step 2A Prong 2 are carried over for evaluating if the claim, as a whole, amounts to an inventive concept that is significantly more than the judicial exception:
The additional elements were identified as Mere Instructions to Apply an Exception (MPEP 2106.05(f)) and Field of Use and Technological Environment (MPEP 2106.05(h)), as stated previously. The courts have found that invoking the use of a computer as a tool to perform a mental process and generally linking the use of a judicial exception to a particular technological environment does not qualify the limitations as “significantly more” than the recited judicial exception.
With the additional elements viewed independently and as part of the ordered combination, the claim as a whole does not appear to amount to significantly more than the recited judicial exception because the claim is using generic computing components recited at a high level of generality to enable the performance of a task that can practically be performed within the human mind or using pen and paper as an assistive physical aid. The particular details of the field of use and technological environment recited in the claim do not further meaningfully limit the claim because the elements are an attempt to limit the use of the judicial exception to the particular technological environment and field of use of wellbore operations. Therefore, the claim does not include additional elements, alone or in combination that are sufficient to amount to significantly more than the recited judicial exception.
Conclusion: Based on this rationale, the claim has been deemed to be ineligible subject matter under 35 U.S.C. 101.
Claim 13:
Step 1: Claim 13 and its dependent claims 14 and 16-20 are directed to a controller which falls within one of the four statutory categories of a machine.
Step 2A Prong 1: Claim 13 recites a judicial exception, noted in bold:
detect a change to a system of a wellbore operation to yield a determination. The claim limitation can be reasonably read to entail observing and evaluating a change to a system to make a judgement regarding the observations. This task can be practically performed in the human mind because a human can observe and evaluate changes of a system and further draw conclusions or make judgements about the observations. Therefore, this claim limitation includes the recitation of the judicial exception of abstract ideas of a mental process.
based on the determination, The claim limitation can be reasonably read to entail further evaluating the determined value to inform subsequent action. This task can be practically performed in the human mind because a human is capable of using a determination as a basis to inform subsequent decisions. Therefore, this claim limitation includes the recitation of the judicial exception of abstract ideas of a mental process.
predicting the output value of the virtual sensor The claim limitation can be reasonably read to entail using a machine learning model to make a prediction. The claim limitation invokes the use of a generic computing component (a machine learning model) to perform the mental process. The claim limitation, as drafted, is a process that, but for the recitation of generic computing components, under broadest reasonable interpretation, covers performance of the mind. The courts do not distinguish between mental processes that are performed entirely in the human mind and mental processes that are performed on a computer. A human being is capable of observing data and making a prediction based on the observations. Therefore, this claim limitation includes the recitation of the judicial exception of abstract ideas of a mental process.
Therefore, the claim recites a judicial exception.
Step 2A Prong 2: Additional elements were identified and are noted in italics.
memory having computer-readable instructions stored therein; and -This limitation has been identified as Mere Instructions to Apply an Exception (MPEP 2106.05(f)) because the element amounts to invoking computers as merely a tool to perform an existing process.
one or more processors configured to execute the computer-readable instructions to:- This limitation has been identified as Mere Instructions to Apply an Exception (MPEP 2106.05(f)) because the element amounts to invoking computers as merely a tool to perform an existing process.
generate a machine learning model for predicting an output value of a virtual sensor using inputs comprising: -This limitation has been identified as Mere Instructions to Apply an Exception (MPEP 2106.05(f)) because the limitation merely invokes the use of computing components to perform the recited judicial exception
information associated with structural mechanics of sub-surface rocks in a wellbore resulting from hydraulic induced changes;- This limitation has been identified as Field of Use and Technological Environment (MPEP 2106.05(h)) for generally linking the use of the judicial exception to a particular technological environment or field of use
information associated with injection of fluids inside the wellbore and changes to flow to and from the wellbore; and -This limitation has been identified as Field of Use and Technological Environment (MPEP 2106.05(h)) for generally linking the use of the judicial exception to a particular technological environment or field of use
physical parameters of and prior measurements by a physical sensor positioned in the wellbore; - This limitation has been identified as Field of Use and Technological Environment (MPEP 2106.05(h)) for generally linking the use of the judicial exception to a particular technological environment or field of use
wherein the system includes the virtual sensor, and wherein the virtual sensor includes the physical sensor for collecting one or more physical properties inside the wellbore; and- This limitation has been identified as Field of Use and Technological Environment (MPEP 2106.05(h)) because the element generally links the use of the judicial exception to a particular field of use and technological environment.
performing one of retraining the machine learning model for predicting the output value of the virtual sensor or- This limitation has been identified as Mere Instructions to Apply an Exception (MPEP 2106.05(f)) because the element amounts to invoking computers as merely a tool to perform an existing process. The retraining of the machine learning model is not claimed in any inventive way and is a standard function of machine learning models operating and their normal capacity
using the machine learning model - This limitation has been identified as Mere Instructions to Apply an Exception (MPEP 2106.05(f)) for invoking the use of generically-claimed computing components to perform the recited judicial exception
the predicted output value is indicative of at least one of sub-surface formation or fluid properties inside the wellbore, and wherein the predicted output value is a higher-order derivative of the inputs - This limitation has been identified as Field of Use and Technological Environment (MPEP 2106.05(h)) because the element generally links the use of the judicial exception to a particular field of use and technological environment.
The courts have found that merely including instructions to implement an abstract idea on a computer or merely using a computer as a tool to perform an abstract idea (Mere Instructions to Apply an Exception (MPEP 2106.05(f))); and generally linking the use of a judicial exception to a particular technological environment or field of use (Field of Use and Technological Environment (MPEP 2106.05(h))) does not integrate the judicial exception into a practical application.
When viewed independently and within the claim as a whole, the additional elements do not appear to integrate the judicial exception into a practical application.
Step 2B: In Step 2A Prong 2, no additional elements were identified as Insignificant Extra Solution Activity (MPEP 2106.05(g)) and therefore no further evaluation is required to determine if the elements amount to more that WURC activity. Additional elements identified otherwise and conclusions from Step 2A Prong 2 are carried over for evaluating if the claim, as a whole, amounts to an inventive concept that is significantly more than the judicial exception:
The additional elements were identified as Mere Instructions to Apply an Exception (MPEP 2106.05(f)) and Field of Use and Technological Environment (MPEP 2106.05(h)), as stated previously. The courts have found that invoking the use of a computer as a tool to perform a mental process and generally linking the use of a judicial exception to a particular technological environment does not qualify the limitations as “significantly more” than the recited judicial exception.
With the additional elements viewed independently and as part of the ordered combination, the claim as a whole does not appear to amount to significantly more than the recited judicial exception because the claim is using generic computing components recited at a high level of generality and functioning in their normal capacity to enable the performance of a task that can practically be performed within the human mind or using pen and paper as an assistive physical aid. The particular details of the field of use and technological environment recited in the claim do not further meaningfully limit the claim because the elements are an attempt to limit the use of the judicial exception to the particular technological environment and field of use of wellbore operations. Therefore, the claim does not include additional elements, alone or in combination that are sufficient to amount to significantly more than the recited judicial exception.
Conclusion: Based on this rationale, the claim has been deemed to be ineligible subject matter under 35 U.S.C. 101.
Dependent Claims:
Examiner notes limitations identified as judicial exceptions are indicated in italicized bold and limitations identified as additional elements are indicated using italics.
Claim 2
Step 1: Regarding dependent claim 2, the judicial exception of independent claim 1 is further incorporated. The claim falls within the corresponding statutory category as stated previously.
Step 2A Prong 1: Claim 2 does not recite any additional judicial exceptions.
Step 2A Prong 2: Claim 2 additionally recites the limitation wherein the change is one or more of an injection of a fluid or material into the wellbore or a physical change to a system for operating the wellbore. This limitation has been identified as Field of Use and Technological Environment (MPEP 2106.05(h)). The courts have ruled generally linking the use of a judicial exception to a particular technological environment or field of use does not integrate the judicial exception into a practical application. With the additional element viewed in conjunction with the other limitations, the claim as a whole does not appear to integrate the judicial exception into a practical application.
Step 2B: The courts have found that limitations that amount to generally linking the use of the judicial exception to a particular technical environment or field of use are not enough to qualify the claim as significantly more than the abstract idea. Therefore, the claim does not include additional elements, alone or in the ordered combination that are sufficient to amount to significantly more than the recited judicial exception.
This claim is not eligible subject matter under 35 U.S.C. 101.
Claim 4
Step 1: Regarding dependent claim 4, the judicial exception of independent claim 1 is further incorporated. The claim falls within the corresponding statutory category as stated previously.
Step 2A Prong 1: Claim 4 does not recite any additional judicial exceptions.
Step 2A Prong 2: Claim 4 additionally recites the limitation wherein the prior measurements include temperature and pressure measurements in the wellbore. This limitation has been identified as Field of Use and Technological Environment (MPEP 2106.05(h)) because the limitation generally links the use of the judicial exception to a particular technological environment or field of use. The courts have ruled generally linking the use of a judicial exception to a particular technological environment or field of use does not integrate the judicial exception into a practical application. With the additional element viewed in conjunction with the other limitations, the claim as a whole does not appear to integrate the judicial exception into a practical application.
Step 2B: The courts have found that limitations that amount to generally linking the use of the judicial exception to a particular technological environment or field of use are not enough to qualify the claim as significantly more than the abstract idea. Therefore, the claim does not include additional elements, alone or in the ordered combination that are sufficient to amount to significantly more than the recited judicial exception.
This claim is not eligible subject matter under 35 U.S.C. 101.
Claim 5
Step 1: Regarding dependent claim 5, the judicial exception of independent claim 1 is further incorporated. The claim falls within the corresponding statutory category as stated previously.
Step 2A Prong 1: Claim 5 additionally recites wherein if the determination indicates that the change to the virtual sensor has occurred, which can reasonably be read to entail evaluating if a change has occurred to subsequently make a judgement as to what actions should occur next. This task can be practically performed within the human mind. Therefore, this claim limitation includes the recitation of the judicial exception of abstract ideas of a mental process.
Step 2A Prong 2: Claim 5 additionally recites the limitation the method includes retraining the machine learning model based on the change. This limitation has been identified as Mere Instructions to Apply an Exception (MPEP 2106.05(f)).The courts have ruled merely invoking the use of a computer to perform the mental process does not integrate the judicial exception into a practical application. With the additional element viewed in conjunction with the other limitations, the claim as a whole does not appear to integrate the judicial exception into a practical application.
Step 2B: The courts have found that limitations that amount to merely invoking computers as a tool to perform an existing process are not enough to qualify the claim as significantly more than the abstract idea. Therefore, the claim does not include additional elements, alone or in the ordered combination that are sufficient to amount to significantly more than the recited judicial exception.
This claim is not eligible subject matter under 35 U.S.C. 101.
Claim 6
Step 1: Regarding dependent claim 6, the judicial exception of independent claim 1 and the additional elements of dependent claim 5 are further incorporated. The claim falls within the corresponding statutory category as stated previously.
Step 2A Prong 1: Claim 6 does not recite any additional judicial exceptions.
Step 2A Prong 2: Claim 6 additionally recites the limitation performing reinforcement learning of the machine learning model based on inputs from a system operator, historical data and data from at least one neighboring wellbore. This limitation has been identified as Mere Instructions to Apply an Exception (MPEP 2106.05(f)). The courts have ruled that merely invoking computers as a tool to perform a mental process does not integrate the judicial exception into a practical application. With the additional element viewed in conjunction with the other limitations, the claim as a whole does not appear to integrate the judicial exception into a practical application.
Step 2B: The courts have found that limitations that amount to invoking computers as tools to perform an existing mental process are not enough to qualify the claim as significantly more than the abstract idea. Therefore, the claim does not include additional elements, alone or in the ordered combination that are sufficient to amount to significantly more than the recited judicial exception.
This claim is not eligible subject matter under 35 U.S.C. 101.
Claim 7
Step 1: Regarding dependent claim 7, the judicial exception of independent claim 1 and the additional elements of claim 2 are further incorporated. The claim falls within the corresponding statutory category as stated previously.
Step 2A Prong 1: Claim 7 additionally recites the limitation wherein if the determination indicates no change to the virtual sensor, the method includes: which can reasonably be read to entail evaluating if a change has occurred to subsequently make a judgement as to what actions should occur next. This task can be practically performed within the human mind. The claim further recites the limitation predicting the output of the virtual sensor; and which can reasonably be read to entail evaluating data and making a prediction, which can practically be performed in the human mind. The claim lastly recites the limitation determining if the predicted output constitutes an outlier or is indicative of a sub-surface change within the wellbore which can be reasonably read to entail evaluating the predicted output to make a judgment as to whether the output stands apart from that which is expected or if the output indicates a change in the wellbore. This task can be practically performed in the human mind, as humans are capable of observing output and making judgements as to what the data output indicates. Therefore, this claim limitation includes the recitation of the judicial exception of abstract ideas of a mental process.
Step 2A Prong 2 & Step 2B: Claim 7 does not recite any additional elements that would integrate the judicial exceptions into a practical application nor amount to significantly more than the judicial exception.
This claim is not eligible subject matter under 35 U.S.C. 101.
Claim 8
Step 1: Regarding dependent claim 8, the judicial exception of independent claim 1 and dependent claim 7, as well as the additional elements of claim 2 are further incorporated. The claim falls within the corresponding statutory category as stated previously.
Step 2A Prong 1: Claim 8 additionally recites the limitation wherein upon determining that the predicted output constitutes an outlier, the method further comprises, which can reasonably be read to entail evaluating the determination as to whether the predicted output constitutes an outlier in order to make a judgement as to the subsequent operations to occur. This task can be practically performed within the human mind, as a human being is capable of making observations and judgements based on prior determinations. Therefore, this claim limitation includes the recitation of the judicial exception of abstract ideas of a mental process.
Step 2A Prong 2: Claim 8 additionally recites the limitation generating a notification for evaluating the physical sensor. This limitation has been identified as Insignificant Extra Solution Activity (MPEP 2106.05(g)) of mere data outputting. The courts have ruled appending insignificant extra solution activity to a judicial exception does not integrate the judicial exception into a practical application. With the additional element viewed in conjunction with the other limitations, the claim as a whole does not appear to integrate the judicial exception into a practical application.
Step 2B: Because the limitation generating a notification for evaluating the physical sensor was identified as Insignificant Extra Solution Activity (MPEP 2106.05(g)), the element requires further evaluation to determine if the element amounts to more than well-understood, routine, and conventional activity. The courts recognize the computer function of transmitting data over a network, such as in generating a notification, as well-understood, routine, and conventional activity when recited in a generic way. The courts have found that limitations that amount to appending well-understood, routine, and conventional activity to a judicial exception is not enough to qualify the claim as significantly more than the abstract idea. Therefore, the claim does not include additional elements, alone or in the ordered combination that are sufficient to amount to significantly more than the recited judicial exception.
This claim is not eligible subject matter under 35 U.S.C. 101.
Claim 9
Step 1: Regarding dependent claim 9, the judicial exception of independent claim 1 and dependent claim 7, as well as the additional elements of claim 2 are further incorporated. The claim falls within the corresponding statutory category as stated previously.
Step 2A Prong 1: Claim 9 additionally recites the limitation determining an accuracy the predicted output value which can reasonably be read to entail evaluating the prediction to make a judgment as to the accuracy of the prediction. This task can be performed within the human mind or using a pen and paper as an assistive physical aid. Therefore, this claim limitation includes the recitation of the judicial exception of abstract ideas of a mental process. Furthermore, this task recites the concept of mathematical relationships between values to yield an accuracy value. Therefore, this claim limitation includes the additional recitation of the judicial exception of abstract ideas as a mathematical concept.
Step 2A Prong 2: Claim 9 does not recite any additional elements that would integrate the judicial exception into a practical application nor amount to significantly more than the recited judicial exceptions.
This claim is not eligible subject matter under 35 U.S.C. 101.
Claim 10
Step 1: Regarding dependent claim 10, the judicial exception of independent claim 1 , dependent claims 9 and 7, and additional elements of claim 2 are further incorporated. The claim falls within the corresponding statutory category as stated previously.
Step 2A Prong 1: Claim 10 additionally recites the limitation wherein if the accuracy does not meet a threshold, which can reasonably be read to entail evaluating the accuracy values with respect to a threshold. This task can be practically performed within the human mind, as a human is capable of observing the accuracy and the threshold values and performing a judgement as to whether the accuracy meets the threshold. Therefore, this claim limitation includes the recitation of the judicial exception of abstract ideas of a mental process. Furthermore, this limitation recites the concept of mathematical relationships of comparing two values against one another. Therefore, this claim limitation additionally includes the recitation of the judicial exception of abstract ideas as a mathematical concept.
Step 2A Prong 2: Claim 10 additionally recites the limitation the accuracy is stored for use in retraining the machine learning model upon detection of a subsequent change to the system. This limitation has been identified as Insignificant Extra Solution Activity (MPEP 2106.05(g)) of mere data outputting. The courts have ruled appending insignificant extra solution activity to the judicial exception does not integrate the judicial exception into a practical application. With the additional element viewed in conjunction with the other limitations, the claim as a whole does not appear to integrate the judicial exception into a practical application.
Step 2B: Because the limitation the accuracy is stored for use in retraining the machine learning model upon detection of a subsequent change to the system was identified as Insignificant Extra Solution Activity (MPEP 2106.05(g)), the element requires further evaluation to determine if the element amounts to more than well-understood, routine, and conventional activity. The courts have found the computer function of storing and retrieving data in memory is a computer function that is well-understood, routine, and conventional activity when claimed in a merely generic manner. The courts have found that limitations that amount to well-understood, routine, and conventional activity are not enough to qualify the claim as significantly more than the abstract idea. Therefore, the claim does not include additional elements, alone or in the ordered combination that are sufficient to amount to significantly more than the recited judicial exception.
This claim is not eligible subject matter under 35 U.S.C. 101.
Claim 11
Step 1: Regarding dependent claim 11, the judicial exception of independent claim 1 is further incorporated. The claim falls within the corresponding statutory category as stated previously.
Step 2A Prong 1: Claim 11 does not recite any additional judicial exceptions.
Step 2A Prong 2: Claim 11 additionally recites the limitation wherein determining the change to the system is performed periodically. This limitation has been identified as Field of Use and Technological Environment (MPEP 2106.05(h)). The courts have ruled generally linking the use of a judicial exception to a particular technological environment or field of use does not integrate the judicial exception into a practical application. With the additional element viewed in conjunction with the other limitations, the claim as a whole does not appear to integrate the judicial exception into a practical application.
Step 2B: The courts have found that limitations that amount to generally linking the use of a judicial exception to a particular technological environment or field of use are not enough to qualify the claim as significantly more than the abstract idea. Therefore, the claim does not include additional elements, alone or in the ordered combination that are sufficient to amount to significantly more than the recited judicial exception.
This claim is not eligible subject matter under 35 U.S.C. 101.
Claim 12
Step 1: Regarding dependent claim 12, the judicial exception of independent claim 1 is further incorporated. The claim falls within the corresponding statutory category as stated previously.
Step 2A Prong 1: Claim 12 does not recite any additional judicial exceptions.
Step 2A Prong 2: Claim 12 additionally recites the limitation generating a reservoir simulation model using the predicted output. This limitation has been identified as Mere Instructions to Apply an Exception (MPEP 2106.05(f)). The courts have ruled that reciting the words “apply it’ or equivalent with respect to the judicial exception does not integrate the judicial exception into a practical application. With the additional element viewed in conjunction with the other limitations, the claim as a whole does not appear to integrate the judicial exception into a practical application.
Step 2B: The courts have found that limitations that amount to merely reciting the words “apply it” with regard for the judicial exception are not enough to qualify the claim as significantly more than the abstract idea. Therefore, the claim does not include additional elements, alone or in the ordered combination that are sufficient to amount to significantly more than the recited judicial exception.
This claim is not eligible subject matter under 35 U.S.C. 101.
Claim 14
Regarding dependent claim 14, the judicial exception of independent claim 13 is further incorporated. The claim falls within the corresponding statutory category as stated previously. The limitations are substantially similar to that recited in claim 2. For brevity, this claim is rejected under the same rationale as provided for claim 2 but with respect to independent claim 13.
This claim is not eligible subject matter under 35 U.S.C. 101.
Claim 16
Regarding dependent claim 16, the judicial exception of independent claim 13 is further incorporated. The claim falls within the corresponding statutory category as stated previously. The limitations are substantially similar to that recited in claim 4. For brevity, this claim is rejected under the same rationale as provided for claim 4 but with respect to independent claim 13.
This claim is not eligible subject matter under 35 U.S.C. 101.
Claim 17
Regarding dependent claim 17, the judicial exception of independent claim 13 is further incorporated. The claim falls within the corresponding statutory category as stated previously. The limitations are substantially similar to that recited in claim 5. For brevity, this claim is rejected under the same rationale as provided for claim 5 but with respect to independent claim 13.
This claim is not eligible subject matter under 35 U.S.C. 101.
Claim 18
Regarding dependent claim 18, the judicial exception of independent claim 13 is further incorporated. The claim falls within the corresponding statutory category as stated previously. The limitations are substantially similar to that recited in claim 6. For brevity, this claim is rejected under the same rationale as provided for claim 6 but with respect to independent claim 13.
This claim is not eligible subject matter under 35 U.S.C. 101.
Claim 19
Regarding dependent claim 19, the judicial exception of independent claim 13 is further incorporated. The claim falls within the corresponding statutory category as stated previously. The limitations are substantially similar to that recited in claim 7. For brevity, this claim is rejected under the same rationale as provided for claim 7 but with respect to independent claim 13.
This claim is not eligible subject matter under 35 U.S.C. 101.
Claim 20
Regarding dependent claim 20, the judicial exception of independent claim 13 and dependent claim 19 is further incorporated. The claim falls within the corresponding statutory category as stated previously. The limitations are substantially similar to that recited in claim 8. For brevity, this claim is rejected under the same rationale as provided for claim 8 but with respect to independent claim 13.
This claim is not eligible subject matter under 35 U.S.C. 101.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claims 1-2, 4, 7-9, 11, 13-14, 16 and 19-20 are rejected under 35 U.S.C. 103 as being unpatentable over Vittal et al (US Patent Publication No. US 20180066503 A1), hereinafter referred to as Vittal, further in view of Schultz et al (US Patent Publication No. 20020152030 A1), hereinafter referred to as Schultz, and further in view of Cella et al (US Patent Publication No. 20180284758 A1), hereinafter referred to as Cella.
Regarding claim 1, Vittal discloses (except the limitations surrounded by brackets ([[..]])) A method comprising: A method is disclosed ((Vittal, ¶25) "Turning to FIG. 4, shown therein is a process flow diagram for a preferred embodiment of a method 200 of using electric submersible pumping systems 100 as virtual sensors.")
conducting a wellbore operation; ((Vittal, ¶17) " The preferred embodiments include measuring the operation and condition of components within a discrete electric submersible pumping system, accumulating these measurements across a field of electric submersible pumping systems, performing statistical analysis on the accumulated measurements and producing one or more selected outputs from the group statistical analysis"); ((Vittal, ¶17) " In accordance with an embodiment of the present invention, FIG. 1 shows an elevational view of a submersible pumping system 100 attached to production tubing 102. The pumping system 100 and production tubing 102 are disposed in a wellbore 104, which is drilled for the production of a fluid such as water or petroleum.")
generating a [[machine learning]] model for predicting an output value of a virtual sensor using inputs comprising: The combination of the reservoir state model and the submersible pumping system anomaly model are components which form the virtual sensor, wherein these models are statistical models ((Vittal, ¶25) " As used herein, the phrase "virtual sensor" will be understood to refer to the analytical and predictive use of data produced by one or more electric submersible pumping systems 100 for evaluating changing conditions within an electric submersible pumping system 100 or within a reservoir or field.[[…]] The software models, computer systems 138 and electric submersible pumping systems 100 collectively define a virtual sensor network 140 (shown in FIG. 3) configured to monitor the condition of the electric submersible pumping systems 100 and reservoir 136."). The models characterizing the virtual sensor output results that indicate the most likely reservoir state as well as the likelihood that the reservoir has changed (as output values) ((Vittal, ¶7) "The process continues with the steps of applying the field data to the reservoir state statistical model to determine a most likely reservoir state result, comparing the most likely reservoir state result against the baseline data library and generating an output that expresses the likelihood that the reservoir has changed.");(Vittal, Claim 21) "applying the field data to the reservoir state statistical model to determine a most likely reservoir state result;")
[[information associated with structural mechanics of sub-surface rocks in a wellbore resulting from hydraulic induced changes;]]
[[information associated with injection of fluids inside the wellbore and changes to flow to and from the wellbore; and]]
physical parameters and prior measurements by a physical sensor positioned in the wellbore; Measured parameters are used to create a library of reference data that is used to create the reservoir state model noted previously ((Vittal, ¶28) " Measured parameters include, but are not limited to, static fluid pressure, flowing fluid pressure, three-phase current, three-phase voltage, vibration, speed and phase angle. The measured and stored parameters are denoted as electric submersible pumping system "health indices" that can be expressed as a function of the reservoir variables. The "health indices" determined as a result of the tests conducted on healthy electric submersible pumping systems 100 provide a library of reference data across a range of reservoir conditions. This reference library data provides the basis for developing the reservoir state model at stage 204 and the electric submersible pumping system anomaly model at stage 206."); A pumping system (virtual sensor) is described as being instrumented with a sensor array ((Vittal, ¶19) "The pumping system 100, in an embodiment, includes some combination of a pump assembly 108, a motor assembly 110, a seal section 112 and a sensor array 114."). The pumping system is disposed in the wellbore ((Vittal, ¶18) "The pumping system 100 and production tubing 102 are disposed in a wellbore 104, which is drilled for the production of a fluid such as water or petroleum."); (See also Vittal, Figure 1 that shows the sensor array 114 inside the wellbore 104.) Measurements are received from the wellbore and the sensors ((Vittal, ¶22) "The controls interface 124 is configured for connection to the variable speed drive 116 and directly or indirectly to the sensor array 114. The controls interface 124 receives measurements from the wellbore 104 and the various sensors within the electric submersible pumping system 100.")
detecting a change to a system of the wellbore operation to yield a determination, Likelihood of changes to the electric submersible pumping system are determined ((Vittal, ¶35) "Once the tests have been concluded, the stage of deploying the models to the field 208 continues at step 226 by comparing the results of the tests against the baseline data library using a truth table or logic rule to determine the likelihood that: (1) the reservoir 136 has changed state; (2) the electric submersible pumping system 100 has become faulty or is otherwise operating outside an expected condition; or (3) both the reservoir 136 and the electric submersible pumping system 100 have changed from the baseline state."). The likelihood is presented to an operator, wherein the prediction may be used by the operator to determine (to yield a determination) failure or to determine preventative maintenance activities, the need for modification of operating parameters, or the adjustment of economic forecasts ((Vittal, ¶35) "The stage of deploying the models to the field 208 concludes at step 228 by outputting a prediction to the operator that a state change has occurred in the reservoir 136 or electric submersible pumping system 100. The prediction can be presented to the operator in any suitable format, including printed reports and computer-displayed charts and spreadsheets. Notably, the prediction about whether a particular electric submersible pumping system 100 has undergone a change in condition may precede the actual failure of the electric submersible pumping system 100. The prediction of state changes at individual electric submersible pumping systems 100 and of changes to the reservoir 136 can be used by the operator to schedule preventive maintenance, modify operating parameters of the electric submersible pumping systems 100 and adjust economic forecasts based on the state of the reservoir 136.")
wherein the system includes the virtual sensor, The electric submersible pumping system is used as a virtual sensor ((Vittal, ¶25) "Turning to FIG. 4, shown therein is a process flow diagram for a preferred embodiment of a method 200 of using electric submersible pumping systems 100 as virtual sensors."). and wherein the virtual sensor includes the physical sensor A pumping system (virtual sensor) is described as being instrumented with a sensor array ((Vittal, ¶19) "The pumping system 100, in an embodiment, includes some combination of a pump assembly 108, a motor assembly 110, a seal section 112 and a sensor array 114."). The pumping system is disposed in the wellbore ((Vittal, ¶18) "The pumping system 100 and production tubing 102 are disposed in a wellbore 104, which is drilled for the production of a fluid such as water or petroleum."); (See also Vittal, Figure 1 that shows the sensor array 114 inside the wellbore 104.) for collecting one or more physical properties inside the wellbore; and Measurements are received from the wellbore and the sensors ((Vittal, ¶22) "The controls interface 124 is configured for connection to the variable speed drive 116 and directly or indirectly to the sensor array 114. The controls interface 124 receives measurements from the wellbore 104 and the various sensors within the electric submersible pumping system 100.")
based on the determination, The likelihood of a change occurring dictates a determination and associated action by the operator ((Vittal, ¶35) "The stage of deploying the models to the field 208 concludes at step 228 by outputting a prediction to the operator that a state change has occurred in the reservoir 136 or electric submersible pumping system 100. The prediction can be presented to the operator in any suitable format, including printed reports and computer-displayed charts and spreadsheets. Notably, the prediction about whether a particular electric submersible pumping system 100 has undergone a change in condition may precede the actual failure of the electric submersible pumping system 100. The prediction of state changes at individual electric submersible pumping systems 100 and of changes to the reservoir 136 can be used by the operator to schedule preventive maintenance, modify operating parameters of the electric submersible pumping systems 100 and adjust economic forecasts based on the state of the reservoir 136.") performing one of [[retraining the machine learning model for predicting the output of the virtual sensor]] or predicting the output value of the virtual sensor [[using the machine learning model]], Data is obtained from the virtual sensor on a continuous basis, thereby indicating that virtual sensor data is produced regardless of if a change to the virtual sensor has been indicated or not to yield a determination by the operator ((Vittal, ¶33) "FIG. 8. At step 222, the computer systems 138 within the virtual sensor network 140 acquire from the electric submersible pumping systems 100 on a continuous or periodic basis field data representative of conditions in the wellbore 104 and within the electric submersible pumping system 100.") A series of tests are applied to the models that compose the virtual sensor, wherein test results are produced ((Vittal, ¶34-35) " Next, at step 224, the field data is applied to the reservoir state and electric submersible pumping system anomaly models. In a preferred embodiment, the data is applied to the models on a periodic basis through a series of tests. In a particularly preferred embodiment, the tests begin by running the mixture distribution determined at step 220 to calculate the probability of a sensor data vector being anomalous. In the preferred embodiments, the identification of an anomalous condition is not triggered until the probability of the sensor data vector being anomalous exceeds a preset threshold. During the next test, the field data within the sensor vector is compared to the library of known reservoir states using similarity measures. In a particularly preferred embodiment, the comparison of the field data against the reservoir state model is conducted using Cosine or Parzen similarity functions. During the last test, the comparative analysis of the field data is also used to classify the reservoir 136 into a most likely reservoir state using the ensemble model. It will be appreciated that additional or fewer tests may be conducted at step 224. Once the tests have been concluded, the stage of deploying the models to the field 208 continues at step 226 by comparing the results of the tests against the baseline data library using a truth table or logic rule to determine the likelihood that: (1) the reservoir 136 has changed state; (2) the electric submersible pumping system 100 has become faulty or is otherwise operating outside an expected condition; or (3) both the reservoir 136 and the electric submersible pumping system 100 have changed from the baseline state.") the predicted output value is indicative of at least one of sub-surface formation or fluid properties inside the wellbore, The library of baseline data that is used as a direct comparison to model outputs (See Vittal, Fig. 8), includes information characterizing the reservoir, including fluid properties, thereby indicating that the output of the prediction is associated with the properties ((Vittal, ¶27) "The stage begins at step 210 by operating a one or more healthy electric submersible pumping systems 100 in one or more test wells under a range of prescribed reservoir conditions. In a particularly preferred embodiment, the prescribed range of reservoir conditions include, but are not limited to, downhole fluid pressure, fluid viscosity, gas-to-oil ratio, water-to-oil ratio, fraction of solid contaminants, and radiation levels, which are measured as control variables."); ((Vittal, ¶28) "At step 212, the corresponding high-frequency time series of parameters for the electric submersible pumping systems 100 undergoing the tests are measured and stored for each test setting. Measured parameters include, but are not limited to, static fluid pressure, flowing fluid pressure, three-phase current, three-phase voltage, vibration, speed and phase angle."); ((Vittal, ¶34) " During the next test, the field data within the sensor vector is compared to the library of known reservoir states using similarity measures. In a particularly preferred embodiment, the comparison of the field data against the reservoir state model is conducted using Cosine or Parzen similarity functions. During the last test, the comparative analysis of the field data is also used to classify the reservoir 136 into a most likely reservoir state using the ensemble model."). [[and wherein the predicted output value is a higher-order derivative of the inputs.]]
Vittal does not disclose explicitly that the models characterizing the virtual sensor are machine learning models, though it is stated that a library of reference data is generated through machine learning algorithms and the models characterizing the virtual sensor are developed from the library of reference data. Vittal further does not mention input data pertaining to hydraulic induced changes or changes in fluid flow with regard to the wellbore. Further Vittal does not describe retraining the machine learning model based on the output of the virtual sensor.
However, Schultz discloses using a machine learning model to produce sensor output for a virtual sensor. A neural network (which is a type of machine learning model) is utilized to output downhole sensor outputs ((Schultz, ¶36) " That is, the neural network 26 when successfully trained outputs the downhole sensor outputs of a particular training data set (within an acceptable margin of error) when the surface sensor outputs and valve positions of that training data set are input to the neural network. "). The sensor output produced by the neural network is described as being that of a virtual sensor ((Schultz, ¶55) " The neural network 42 determines the "virtual" flow rate sensor output based on the outputs of the other downhole sensors DSl, DS2, DS3, DS4 and the corresponding positions of the valves Vl, V2. ").
Schultz further discloses providing to the neural network input (except the limitations surrounded by brackets ([[..]])) information associated with [[structural mechanics of sub-surface rocks in]] a wellbore resulting from hydraulic induced changes; Hydraulic actuators of the valves are described as causing the valves to change position and the positioning of the valves (information associated with) is known ((Schultz, ¶31) "For example, the valves Vl, V2 may include position sensors (not shown) connected to the lines 16, or a particular pressure applied to certain of the lines 16 may cause hydraulic actuators (not shown) of the valves to position the valves in a known manner, or a conventional shifting tool (not shown) may be used to position the valves in known positions, etc. Thus, it will be appreciated that any technique may be used to actuate the valves Vl, V2 and to know the valves' positions."); ((Schultz, ¶55) " The neural network 42 determines the "virtual" flow rate sensor output based on the outputs of the other downhole sensors DSl, DS2, DS3, DS4 and the corresponding positions of the valves Vl, V2. ").
Schultz discloses further providing to the neural network training information associated with injection of fluids inside the wellbore and changes to flow to and from the wellbore; and Flow rate sensors are used to obtain information for training the neural network and for long term monitoring of production from zones 12 and 14 ((Schultz, ¶33) " The sensors SSl, SS2 may be any type of sensors. For example, the surface sensor SSl may be a pressure and temperature sensor, and the surface sensor SS2 may be a flow rate sensor. These sensors SSl, SS2 are also connected to the computer system (not shown) described above for training the neural network, and for long term monitoring of production from the zones 12, 14 after the neural network has been trained, as described below."). Flow valve positions are likewise known ((Schultz, ¶25) " In FIG. 3, the first training data set includes the first position of valve Vl ( depicted as Vl,1 ), the first position of valve V2 (depicted as V2,1), the corresponding outputs of surface sensors SSl, SS2 (depicted as SSl,1 and SS2,1, respectively) and the corresponding outputs of the downhole sensors DSl, DS2, DS3, DS4 (depicted as DSl,1, DS2,1, DS3,1 and DS4,1, respectively). That is, the first training data set includes the first positions of the valves Vl, V2 (positions Vl,1 and V2,1) and the outputs of the sensors SSl, SS2, DSl, DS2, DS3, DS4 while the valves are in those positions (sensor outputs SSl,1, SS2,1, DSl,1, DS2,1, DS3,1 and DS4,1)."). The methodology is indicated as applicable to both production and injection wells, thereby suggesting that the flow rate sensors employed in a tubing string would be capable of capturing information relevant to injection of fluids flowing into the tubing string situated within the wellbore ((Schultz, ¶24) " Additionally, it is to be understood that the various embodiments of the present invention described herein may be utilized in various orientations, such as inclined, inverted, horizontal, vertical, etc., in conjunction with various types of wells, including open hole, cased, production, injection, etc. wells, and in various configurations, without departing from the principles of the present invention."); ((Schultz, ¶29) " FIG. 1 for sensing parameters of fluid flowing into the tubing string via a valve Vl from the zone 14, and positioned above the zone 12 as shown in FIG. 2 for sensing parameters of fluid flowing into the tubing string via a valve V2 from the zone 12.")
Schultz further discloses retraining a machine learning model for predicting an output of the virtual sensor A neural network is trained to output sensor output ((Schultz, ¶47) "The neural network 36 is trained to output the sensor S5 outputs corresponding to outputs of the sensors Sl, S2, S3, S4 input to the neural network. That is, the neural network 36 will, after training, produce the sensor S5 output of a particular training data set when the corresponding outputs of the other sensors Sl, S2, S3, S4 in the training data set are input to the neural network (with an acceptable margin of error)."); ((Schultz, ¶12) "In a further aspect of the invention, methods are provided whereby a "virtual" sensor is created downhole. That is, the output of a nonexistent downhole sensor is determined in response to inputting the outputs of other sensors, etc., to a trained neural network."). The neural network training can be refined or optimized, thereby indicating retraining ((Schultz, ¶37) " In addition, any techniques may be used to refine or optimize the neural network 26 training, such as by using tapped delay lines (not shown), etc.").
using the machine learning model, A neural network (which is a type of machine learning model) is utilized to output downhole sensor outputs ((Schultz, ¶36) " That is, the neural network 26 when successfully trained outputs the downhole sensor outputs of a particular training data set (within an acceptable margin of error) when the surface sensor outputs and valve positions of that training data set are input to the neural network. "). The sensor output produced by the neural network is described as being that of a virtual sensor ((Schultz, ¶55) " The neural network 42 determines the "virtual" flow rate sensor output based on the outputs of the other downhole sensors DSl, DS2, DS3, DS4 and the corresponding positions of the valves Vl, V2. ").
Vittal and Schultz are analogous arts because they are both related to the same field of endeavor of providing virtual sensor solutions for wellbore applications. It would have been obvious to one of ordinary skill to which said subject matter pertains at the time the invention was filed to have modified the prior art reference Vittal with the teachings of Schultz because a simple substitution of one known element for another to obtain predictable results would have led on having skill in the art to do so. Vittal describes generating predicted output of a virtual sensor using computerized statistical modeling ((Vittal, ¶5) " Through computerized statistical modeling, the system outputs a prediction about whether individual electric submersible pumping systems and the reservoir have undergone changes in condition. In this sense, the electric submersible pumping systems act as "virtual sensors" by providing field data field to the statistical models, which can then be used to predict the condition of the individual electric submersible pumping systems and the condition of the reservoir."). Schultz discloses using a neural network for generating output of a virtual sensor ((Schultz, ¶12) " In a further aspect of the invention, methods are provided whereby a "virtual" sensor is created downhole. That is, the output of a nonexistent downhole sensor is determined in response to inputting the outputs of other sensors, etc., to a trained neural network."). Statistical modeling and neural networks are both tools known in the art that can be used for generating predictions. Schultz effectively demonstrates utilizing a neural network to make predictions as a virtual sensor in a well application. Therefore, by performing a simple substitution of the statistical modeling element, as disclosed by Vittal, for the neural network element, as disclosed by Schultz, one having skill in the art would arrive at the claimed invention, such that the substitution would reasonably yield predictable results.
The proposed combination fails to explicitly disclose using information associated with structural mechanics of sub-surface rocks in a wellbore resulting from hydraulic induced changes, though the proposed combination in light of Schultz discloses hydraulic induced changes in the wellbore. Cella, however, discloses collecting information from sensors in a boring process, wherein the boring machinery introduces hydraulic-induced changes into the rock formations and the sensors detect forces experienced by the tips of the boring machinery in contact with the rock formations. information associated with structural mechanics of sub-surface rocks in a wellbore resulting from hydraulic induced changes ((Cella, ¶1229) " In embodiments, a system for data collection in an industrial environment may facilitate displaying a heat map related to data collected from boring machinery for mining in an augmented reality view of a portion of the environment. Boring machinery, and in particular multi-tip circular boring heads may experience a range of rock formations at the same time. Sensors may be placed proximal to each boring tip that may detect forces experienced by the tips."). Sensor data collecting in an industrial drilling environment is described as being used as inputs to neural network models for detecting anomalous conditions ((Cella, ¶5) " In embodiments, a monitoring system for data collection in an industrial drilling environment may comprise a data collector communicatively coupled to a plurality of input channels, wherein a subset of the plurality of input channels are communicatively coupled to sensors measuring operational parameters from an industrial drilling component; a data storage structured to store a plurality of collector routes and collected data that correspond to the plurality of input channels, wherein the plurality of collector routes each comprise a different data collection routine; a data acquisition circuit structured to interpret a plurality of detection values from the collected data, each of the plurality of detection values corresponding to at least one of the plurality of input channels; a data analysis circuit structured to analyze the collected data from the plurality of input channels to detect an anomalous condition associated with the industrial drilling component; and a data response circuit structured to switch one of the data collection routines from a first data collection routine to a second collection routine based on the detection of the anomalous condition. [[…]] The data analysis circuit may be further structured to utilize a neural network model to detect the anomalous condition.")
While the proposed combination of Vittal in view of Schultz does not explicitly disclose the predicted output value is a higher-order derivative of the inputs, the proposed combination in light of Vittal describes the predicted output of the reservoir state model as “health indices” but does not particularly note what the health indices are aside from a function of reservoir variables ((Vittal, ¶28) "Measured parameters include, but are not limited to, static fluid pressure, flowing fluid pressure, three-phase current, three-phase voltage, vibration, speed and phase angle. The measured and stored parameters are denoted as electric submersible pumping system "health indices" that can be expressed as a function of the reservoir variables. The "health indices" determined as a result of the tests conducted on healthy electric submersible pumping systems 100 provide a library of reference data across a range of reservoir conditions."). What is not given explicitly by the combination of Vittal and Schultz is given by Cella, wherein Cella discloses and wherein the predicted output value is a higher-order derivative of the inputs. Changes and changes in raw sensor data (as a higher order derivative of sensor data) are used to evaluate the health of components, wherein the changes are determined (output) from an analysis circuit of a monitoring device and wherein the analysis circuit may be a neural network ((Cella, ¶6) " The data analysis circuit may be further structured to utilize a neural network model to detect the anomalous condition.");((Cella, ¶583) " Because these production lines may be continuous process lines, it may be desirable to perform proactive maintenance rather than wait for a component to fail. Variations in pump speed and pressure may have the potential to negatively impact the final product, and the ability to identify issues in the final product may lag the actual component deterioration by an unacceptably long period. In embodiments, an industrial pump may be equipped with a plurality of sensors for measuring attributes associated with the pump such as temperature of bearings or pump housing, vibration of a driveshaft associated with the pump, vibration of input or output lines, pressure, flow rate, fluid particulate measures, vibrations of the pump housing, and the like. These sensors may be connected either directly to a monitoring device or through an intermediary device using a mix of wired and wireless connection techniques. A monitoring device may have access to detection values corresponding to the sensors where the detection values correspond directly to the sensor output of a processed version of the data output such as a digitized or sampled version of the sensor output. The monitoring device may access and process the detection values using methods discussed elsewhere herein to evaluate the health of the pump overall, evaluate the health of pump components, predict potential down line issues arising from atypical pump performance, or changes in fluid being pumped. The monitoring device may process the detection values to identify torsion on the drive shaft of the pump. The identified torsion may then be evaluated relative to expected torsion based on the specific geometry of the pump and how it is installed in the equipment relative to other components on the assembly line. Unexpected torsion may put undue stress on the driveshaft and may be a sign of deteriorating health of the pump. Vibration of the inlet and outlet pipes may also be evaluated for unexpected or resonant vibrations which may be used to drive process controls to avoid certain pump frequencies. Changes in vibration may also be due to changes in fluid composition or density, amplifying or dampening vibrations at certain frequencies. The monitoring device may process the detection values to identify unexpected vibrations in the shaft, unexpected temperature values, or temperature changes in the bearings or in the housing in proximity to the bearings..")
Cella is analogous to the claimed invention because it is related to the same field of endeavor of using data analytics from sensor data for real time monitoring of risk and failure, particularly for proactive maintenance purposes and particularly in applications in drilling and gas environments. It would have been obvious to one of ordinary skill to which said subject matter pertains at the time the invention was filed to have incorporated the teachings of Cella into the proposed combination because some teaching, suggestion, or motivation would have led one having ordinary skill to do so in order to arrive at the claimed invention. Vittal discloses using sensor data as input to a statistical model to predict a value that is directly compared with health indices, represented by a function of reservoir variables. Vittal notes that such derived insights are useful in detecting changes of the system and environment which can be used for scheduling preventative maintenance or modifying operating parameters. Cella discloses acquiring a multitude of sensor data in an oil and gas environment and describes processing the raw sensor data to predict changes in the measurements, whereby the processing component may be that of a neural network. Cella further discloses that understanding the dynamics of sensor data yields insights about system component deterioration (See Cella ¶582). Cella also explicitly suggests that detection values from sensors can be fused to create detection values for a virtual sensor and that the methods disclosed therein can be used to produce a virtual sensor output value ((Cella, ¶709) " In some embodiments, two or more sets of detection values may be fused to create detection values for a virtual sensor."); ((Cella,, ¶1065) " Example and non-limiting values of interest include: a virtual sensor output value; a process prediction value; a process state value; a component prediction value; a component state value; and/or a model output value having the sensor data values from the fused plurality of sensors as an input."). Accordingly, because Cella explicitly suggests that the methods disclosed therein can be used to produce output values of a virtual sensor and Vittal/Schultz also disclose methods for producing output values of a virtual sensor, the combination would have accordingly been obvious, as Cella provides more comprehensive examples for input/output value pairs that would have been desirable to one having skill in the art.
Regarding claim 2, The method of claim 1, is disclosed, as stated previously. wherein the change is one or more of [[an injection of]] a fluid or material into the wellbore or a physical change to a system for operating the wellbore. Changes are monitored for reservoir conditions and electric submersible pumping systems ((Vittal, ¶17) "The preferred embodiments represent an advancement over the prior art for a number of reasons, including that the systems and methods are capable of simultaneously monitoring and predicting changes in reservoir conditions and conditions within individual electric submersible pumping systems."). Conditions include fluid conditions ((Vittal, ¶27) " In a particularly preferred embodiment, the prescribed range of reservoir conditions include, but are not limited to, downhole fluid pressure, fluid viscosity, gas-to-oil ratio, water-to-oil ratio, fraction of solid contaminants, and radiation levels, which are measured as control variables."); ((Vittal, ¶28) " Measured parameters include, but are not limited to, static fluid pressure, flowing fluid pressure, three-phase current, three-phase voltage, vibration, speed and phase angle. ")
Vittal does not explicitly disclose; however Schultz discloses an injection of Use of an injection well is described as being applicable to the invention, wherein it would be understood by one having ordinary skill in the art that the inclusion of an injection well suggests its usage in a standard manner, wherein fluids are injected as part of the standard functionality ((Schultz, ¶24) "Additionally, it is to be understood that the various embodiments of the present invention described herein may be utilized in various orientations, such as inclined, inverted, horizontal, vertical, etc., in conjunction with various types of wells, including open hole, cased, production, injection, etc. wells, and in various configurations, without departing from the principles of the present invention.")
It would have been obvious to one of ordinary skill to which said subject matter pertains at the time the invention was filed to have incorporated an injection well operating under its normal functions as disclosed by Schultz as part of the well system disclosed by Vittal because a suggestion in the prior art would have led one having ordinary skill in the art to modify the prior art reference further to arrive at the claimed invention. Vittal suggests that the present invention can be applied to other systems than the electric submersible pumping system disclosed ((Vittal, ¶36) "It will be appreciated by those skilled in the art that the teachings of the present invention can be applied to other systems without departing from the scope and spirit of the present invention. For example, although the preferred embodiments are described in connection with electric submersible pumping systems, it will be appreciated that the novel systems and methods disclosed herein can find equal applicability to other examples of groups of distributed equipment within a common environment. The novel systems and methods disclosed herein can be used to monitor, evaluate and optimize the performance of fleet vehicles, natural gas compressors, refinery equipment and other remotely disposed industrial equipment."). Schultz provides alternative equipment to which the methodologies (virtual sensors) can be applied, to include an injection well. Therefore, because the prior art suggests that the methods can be applied to other equipment, including injection wells, it would have been obvious to one having ordinary skill in the art to modify the prior art reference further to arrive at the claimed invention.
Regarding claim 4, The method of claim 1, is disclosed, as stated previously.
The proposed combination discloses in further view of Vittal (except the limitations surrounded by brackets ([[..]])) wherein the prior measurements include [[temperature]] and pressure measurements in the wellbore. The library of reference baseline data includes downhole fluid pressure ((Vittal, ¶27) "The stage begins at step 210 by operating a one or more healthy electric submersible pumping systems 100 in one or more test wells under a range of prescribed reservoir conditions. In a particularly preferred embodiment, the prescribed range of reservoir conditions include, but are not limited to, downhole fluid pressure, fluid viscosity, gas-to-oil ratio, water-to-oil ratio, fraction of solid contaminants, and radiation levels, which are measured as control variables.")
Vittal does not disclose; however, the proposed combination in further view of Schultz discloses [[temperature]] Measured temperature data obtained from sensors are used for creating training datasets ((Schultz, ¶80) "Multiple training data sets 86 are obtained while the temporary sensors Pl, Tl are in the well. As depicted in FIG. 22, the training data sets 86 include outputs of the pressure and temperature sensors Pl, Tl, P2, T2, P3, T3, P4, the size of the surface choke C and the corresponding position of the valve V. ")
Regarding claim 7, The method of claim 2, is disclosed, as stated previously.
The proposed combination in further view of Vittal discloses wherein if the determination indicates no change to the virtual sensor, the method includes: Data is obtained from the virtual sensor on a continuous basis, thereby indicating that virtual sensor data is produced regardless of if a change to the virtual sensor has been indicated or not ((Vittal, ¶33) "FIG. 8. At step 222, the computer systems 138 within the virtual sensor network 140 acquire from the electric submersible pumping systems 100 on a continuous or periodic basis field data representative of conditions in the wellbore 104 and within the electric submersible pumping system 100.")
predicting the output of the virtual sensor; and A series of tests are applied to the models that compose the virtual sensor, wherein test results are produced ((Vittal, ¶34-35) " Next, at step 224, the field data is applied to the reservoir state and electric submersible pumping system anomaly models. In a preferred embodiment, the data is applied to the models on a periodic basis through a series of tests. In a particularly preferred embodiment, the tests begin by running the mixture distribution determined at step 220 to calculate the probability of a sensor data vector being anomalous. In the preferred embodiments, the identification of an anomalous condition is not triggered until the probability of the sensor data vector being anomalous exceeds a preset threshold. During the next test, the field data within the sensor vector is compared to the library of known reservoir states using similarity measures. In a particularly preferred embodiment, the comparison of the field data against the reservoir state model is conducted using Cosine or Parzen similarity functions. During the last test, the comparative analysis of the field data is also used to classify the reservoir 136 into a most likely reservoir state using the ensemble model. It will be appreciated that additional or fewer tests may be conducted at step 224. Once the tests have been concluded, the stage of deploying the models to the field 208 continues at step 226 by comparing the results of the tests against the baseline data library using a truth table or logic rule to determine the likelihood that: (1) the reservoir 136 has changed state; (2) the electric submersible pumping system 100 has become faulty or is otherwise operating outside an expected condition; or (3) both the reservoir 136 and the electric submersible pumping system 100 have changed from the baseline state.")
determining if the predicted output constitutes an outlier or is indicative of a sub-surface change within the wellbore. The results of the tests (output) are evaluated in step 226 to determine if the reservoir has changed state (subsurface change within the wellbore) or of the system is operating outside an expected condition (constitutes an outlier) ((Vittal, ¶35) " Once the tests have been concluded, the stage of deploying the models to the field 208 continues at step 226 by comparing the results of the tests against the baseline data library using a truth table or logic rule to determine the likelihood that: (1) the reservoir 136 has changed state; (2) the electric submersible pumping system 100 has become faulty or is otherwise operating outside an expected condition; or (3) both the reservoir 136 and the electric submersible pumping system 100 have changed from the baseline state.")
Regarding claim 8, The method of claim 7, is disclosed, as stated previously.
The proposed combination further in view of Vittal discloses wherein upon determining that the predicted output constitutes an outlier, the method further comprises: The predicted likelihood if a state change has occurred may be based on the electric submersible pumping system operating outside an expected condition (as an outlier) ((Vittal, ¶35) "Once the tests have been concluded, the stage of deploying the models to the field 208 continues at step 226 by comparing the results of the tests against the baseline data library using a truth table or logic rule to determine the likelihood that: (1) the reservoir 136 has changed state; (2) the electric submersible pumping system 100 has become faulty or is otherwise operating outside an expected condition; or (3) both the reservoir 136 and the electric submersible pumping system 100 have changed from the baseline state. The stage of deploying the models to the field 208 concludes at step 228 by outputting a prediction to the operator that a state change has occurred in the reservoir 136 or electric submersible pumping system 100.”)
generating a notification for evaluating the physical sensor. At step 228, a prediction that a change has occurred can be presented to an operator in any format (as a notification) and the information can further be used by the operator to schedule preventative maintenance ((Vittal, ¶35) "The stage of deploying the models to the field 208 concludes at step 228 by outputting a prediction to the operator that a state change has occurred in the reservoir 136 or electric submersible pumping system 100. The prediction can be presented to the operator in any suitable format, including printed reports and computer-displayed charts and spreadsheets. Notably, the prediction about whether a particular electric submersible pumping system 100 has undergone a change in condition may precede the actual failure of the electric submersible pumping system 100. The prediction of state changes at individual electric submersible pumping systems 100 and of changes to the reservoir 136 can be used by the operator to schedule preventive maintenance, modify operating parameters of the electric submersible pumping systems 100 and adjust economic forecasts based on the state of the reservoir 136."). The pumping system may include a sensor array to which preventative maintenance tasks may be applied ((Vittal, ¶19) "The pumping system 100, in an embodiment, includes some combination of a pump assembly 108, a motor assembly 110, a seal section 112 and a sensor array 114.")
Regarding claim 9, The method of claim 7, further comprising: is disclosed, as stated previously.
The proposed combination further in view of Schultz discloses determining an accuracy the predicted output value. The neural network outputs sensor data within an acceptable margin of error, thereby indicating that the accuracy has been determined and subsequently evaluated against an error margin ((Schultz, ¶36) "That is, the neural network 26 when successfully trained outputs the downhole sensor outputs of a particular training data set (within an acceptable margin of error) when the surface sensor outputs and valve positions of that training data set are input to the neural network.").
Regarding claim 11, The method of claim 1, is disclosed, as stated previously. wherein determining the change to the system is performed periodically. Sensor data is collected on a periodic basis ((Vittal, ¶33) "At step 222, the computer systems 138 within the virtual sensor network 140 acquire from the electric submersible pumping systems 100 on a continuous or periodic basis field data representative of conditions in the wellbore 104 and within the electric submersible pumping system 100."). The sensor data is utilized to compare model outputs against the baseline library in step 226 which is used to make the determination of the change, as stated previously ((Vittal, ¶35) "Once the tests have been concluded, the stage of deploying the models to the field 208 continues at step 226 by comparing the results of the tests against the baseline data library using a truth table or logic rule to determine the likelihood that: (1) the reservoir 136 has changed state; (2) the electric submersible pumping system 100 has become faulty or is otherwise operating outside an expected condition; or (3) both the reservoir 136 and the electric submersible pumping system 100 have changed from the baseline state. "); (See also Vittal , Fig. 8). Therefore, if receiving sensor data on a periodic basis and the sensor data is used to determine changes in the system, it follows likewise that the determination is performed periodically as sensor data is received.
Regarding claim 13, Vittal discloses A controller comprising: A computer system is disclosed for performing a computerized process ((Vittal, ¶7) "In another aspect, the preferred embodiments include a computerized process for predicting changes in a subterranean reservoir."); ((Vittal, ¶5) "Embodiments of the present invention include a system that includes one or more electric submersible pumping systems deployed in a reservoir and a computer system that receives data from the one or more electric submersible pumping systems.")
memory having computer-readable instructions stored therein; and Computer software is described as residing on a computer system ((Vittal, ¶25) "It will be appreciated that the method 200 relies on the creation and deployment of analytical models that are, in an embodiment, automated as computer software that resides and operates on one or more computer systems 138 located at the central data center 134, in the reservoir 136 or at both the central data center 134 and the reservoir 136.")
one or more processors configured to execute the computer-readable instructions to: The computer software is described as operating on a computer system ((Vittal, ¶25) "It will be appreciated that the method 200 relies on the creation and deployment of analytical models that are, in an embodiment, automated as computer software that resides and operates on one or more computer systems 138 located at the central data center 134, in the reservoir 136 or at both the central data center 134 and the reservoir 136."). The computer systems are configured to monitor the condition of the electric submersible pumping systems and reservoir ((Vittal, ¶25) "The software models, computer systems 138 and electric submersible pumping systems 100 collectively define a virtual sensor network 140 (shown in FIG. 3) configured to monitor the condition of the electric submersible pumping systems 100 and reservoir 136.")
The remaining limitations are substantially similar to that recited in claim 1 and are thus rejected under the same rationale: generate a machine learning model for predicting an output value of a virtual sensor using inputs comprising:
information associated with structural mechanics of sub-surface rocks in a wellbore resulting from hydraulic induced changes;
information associated with injection of fluids inside the wellbore and
changes to flow to and from the wellbore; and
physical parameters of and prior measurements by a physical sensor
positioned in the wellbore;
detect a change to a system of a wellbore operation to yield a determination, wherein the system includes the virtual sensor, and wherein the virtual sensor includes the physical sensor for collecting one or more physical properties inside the wellbore; and
based on the determination, perform one of retraining the machine learning model
for predicting the output value of the virtual sensor or predicting the output of the virtual sensor using the machine learning model, the predicted output value is indicative of at least one of sub-surface formation or fluid properties inside the wellbore, and wherein the predicted output value is a higher-order derivative of the inputs.
Regarding claim 14, The controller of claim 13, is disclosed, as stated previously. The remaining limitations are substantially similar to that as recited in claim 2 but with respect to claim 13 and are thus rejected under the same rationale wherein the change is one or more of an injection of a fluid or material into the wellbore or a physical change to a system for operating the wellbore.
Regarding claim 16, The controller of claim 13, is disclosed, as stated previously. The remaining limitations are substantially similar to that as recited in claim 4 but with respect to claim 13 and are thus rejected under the same rationale: wherein the prior measurements include temperature and pressure measurements in the wellbore.
Regarding claim 19, The controller of claim 14, is disclosed, as stated previously. The remaining limitations are substantially similar to that as recited in claim 7 but with respect to claim 14 and are thus rejected under the same rationale: wherein if the determination indicates no change to the virtual sensor, the one or more processors are configured to execute the computer-readable instructions to:
predict the output of the virtual sensor; and
determine if the predicted output constitutes an outlier or is indicative of a sub-surface change within the wellbore.
Regarding claim 20, The controller of claim 19, is disclosed, as stated previously. The remaining limitations are substantially similar to that as recited in claim 8 but with respect to claim 19 and are thus rejected under the same rationale: wherein upon determining that the predicted output constitutes an outlier, the one or more processors are configured to execute the computer-readable instructions to generate a notification for evaluating the physical sensor.
Claims 5, 10, and 17 are rejected under 35 U.S.C. 103 as being unpatentable over Vittal in view of Schultz and Cella as applied to claims 1 and 13 above, and further in view of Luigi (Luigi, “The Ultimate Guide to Model Retraining”, June 10, 2019, ML in Production, mlinproduction.com/model-retraining/), hereinafter referred to as Luigi.
Regarding claim 5, The method of claim 1, is disclosed, as stated previously.
The proposed combination in further view of Vittal discloses (except the limitations surrounded by brackets ([[..]])) [[wherein if]] the determination indicates that the change to the virtual sensor has occurred, [[the method includes retraining the machine learning model based on the change.]] A prediction is output indicating a change of the electric submersible system (virtual sensor) ((Vittal, ¶35) "The stage of deploying the models to the field 208 concludes at step 228 by outputting a prediction to the operator that a state change has occurred in the reservoir 136 or electric submersible pumping system 100.")
The proposed combination in further view of Vittal does not disclose; however, in view of Schultz discloses (except the limitations surrounded by brackets ([[..]])) [[wherein if]] ... the method includes retraining the machine learning model [[based on the change.]] A neural network is employed as the machine learning model that can be refined or optimized via training, as stated previously ((Schultz, ¶37) "Furthermore, any technique known to those skilled in the art for training the neural network 26 may be used. For example, the neural network 26 may be a perceptron network, Hopfield network, Kohonen network, etc., and the training technique may utilize a back propagation algorithm, or one of the special algorithms used to train Hopfield and Kohonen networks, etc. The neural network 26 may take any form, for example, it may be "virtual" in that it exists in a computer memory or in computer readable form and may be manipulated using computer software, or the neural network may be a physical network of electronic components, etc. In addition, any techniques may be used to refine or optimize the neural network 26 training, such as by using tapped delay lines (not shown), etc.").
The proposed combination in further view of Vittal and Schultz does not disclose; however, in further view of Luigi discloses wherein if … based on the change. Retraining is performed with the current reality in mind, indicating that the retraining is performed based on a detected change ((Luigi, ¶24) "If a model’s predictive performance has fallen due to changes in the environment, the solution is to retrain the model on a new training set which reflects the current reality."). Online learning may be used to retrain the machine learning model as new data arrives, wherein a change to the system would be understood to be represented by new data ((Luigi, ¶28) " These problems may benefit from online learning where the model is updated incrementally as new data becomes available."); ((Luigi, ¶33) " Finally, it may make sense to utilize online learning techniques to update the model that is currently in production. This approach relies on "seeding" a new model with the model that is currently deployed. As new data arrives, the model parameters are updated with the new training data.")
Luigi is analogous art because it is related to the same field of endeavor of machine learning techniques, which are employed by the instant application. It would have been obvious to one of ordinary skill to which said subject matter pertains at the time the invention was filed to have incorporated the teachings of Luigi into that disclosed by the proposed combination because some teaching, suggestion, or motivation in the prior art references would have led one having ordinary skill in the art to do so to arrive at the claimed invention. Vittal discloses a method for determining if a change has occurred for a virtual sensor using a statistical model. Schultz discloses the utilization of a neural network machine learning model, which could be substituted for the statistical model of Vittal, as stated previously in the rationale for the rejection of Claim 1. Schultz further discloses that the neural network can be trained and wherein the training can be refined or optimized but does not particularly disclose how. Luigi notes that models may be need to be retrained as environment factors affect the performance of the model. Luigi particularly offers retraining strategies, such as online learning, that can mitigate model drift, which impacts model accuracy, by accounting for the changes ((Luigi, ¶3) "Since we expect the world to change over time, model deployment should be treated as a continuous process. Rather than deploying a model once and moving on to another project, machine learning practitioners need to retrain their models if they find that the data distributions have deviated significantly from those of the original training set. This concept, known as model drift, can be mitigated but involves additional overhead in the forms of monitoring infrastructure, oversight, and process."). One having skill in the art with the teachings of Vittal, Schultz, and Luigi before them would be compelled to further modify the prior art reference to include the retraining of the machine learning model based on environmental changes disclosed by Luigi into the proposed combination because Luigi explicitly notes that such strategies are useful to mitigate model drift and maintain model accuracy as the environment changes over time.
Regarding claim 10, The method of claim 9, is disclosed, as stated previously. The proposed combination further in view of Schultz discloses (except the limitations surrounded by brackets ([[..]])) [[wherein if]] the accuracy [[does not meet]] a threshold, the accuracy The output sensor data is evaluated against the training data (as an accuracy value) and is further evaluated with respect to a margin of error (as a threshold) ((Schultz, ¶36) "That is, the neural network 26 when successfully trained outputs the downhole sensor outputs of a particular training data set (within an acceptable margin of error) when the surface sensor outputs and valve positions of that training data set are input to the neural network."). [[is stored for use in]] retraining the machine learning model A neural network is employed as the machine learning model that can be refined or optimized via training, as stated previously ((Schultz, ¶37) " Furthermore, any technique known to those skilled in the art for training the neural network 26 may be used. For example, the neural network 26 may be a perceptron network, Hopfield network, Kohonen network, etc., and the training technique may utilize a back propagation algorithm, or one of the special algorithms used to train Hopfield and Kohonen networks, etc. The neural network 26 may take any form, for example, it may be "virtual" in that it exists in a computer memory or in computer readable form and may be manipulated using computer software, or the neural network may be a physical network of electronic components, etc. In addition, any techniques may be used to refine or optimize the neural network 26 training, such as by using tapped delay lines (not shown), etc."). [[upon detection of a subsequent change to the system.]]
The proposed combination in further view of Schultz does not disclose; however, Luigi discloses wherein if … does not meet … is stored for use in … Diagnostics are tracked continuously (stored for use) for the model and evaluated against a threshold to determine if divergence exceeds the threshold ((Luigi, ¶27) "This solution requires tracking diagnostics and then triggering model retraining when the diagnostics on live data diverge from the training data diagnostics. But this approach is not without it’s own challenges. First, you need to determine a threshold of divergence that will trigger model retraining. "). upon detection of a subsequent change to the system. The world is described as changing over time and models are retrained if the data distributions have deviated significantly as a result of environmental changes ((Luigi, ¶3) "Since we expect the world to change over time, model deployment should be treated as a continuous process. Rather than deploying a model once and moving on to another project, machine learning practitioners need to retrain their models if they find that the data distributions have deviated significantly from those of the original training set. "); ((Luigi, ¶24) "If a model’s predictive performance has fallen due to changes in the environment, the solution is to retrain the model on a new training set which reflects the current reality.")
Luigi is analogous art because it is related to the same field of endeavor of machine learning techniques, which are employed by the instant application. It would have been obvious to one of ordinary skill to which said subject matter pertains at the time the invention was filed to have incorporated the teachings of Luigi into that disclosed by the proposed combination because some teaching, suggestion, or motivation in the prior art references would have led one having ordinary skill in the art to do so to arrive at the claimed invention. Schultz discloses the evaluation and quantification of model output data with regard for an error margin as a threshold. Schultz further discloses that the neural network can be trained and wherein the training can be refined or optimized but does not particularly disclose how. Luigi discloses the utilization of a threshold of divergence that can be used to trigger model retraining. Luigi particularly notes that monitoring for deviated distributions of target variable values and retraining models to account for deviations are effective mitigation strategies for overcoming model drift, which is a model’s predictive performance degradation over time ((Luigi, ¶3) "Since we expect the world to change over time, model deployment should be treated as a continuous process. Rather than deploying a model once and moving on to another project, machine learning practitioners need to retrain their models if they find that the data distributions have deviated significantly from those of the original training set. This concept, known as model drift, can be mitigated but involves additional overhead in the forms of monitoring infrastructure, oversight, and process."). One having skill in the art with the teachings of Schultz and Luigi before them would be compelled to further modify the prior art reference to include the monitoring and retraining aspect disclosed by Luigi into the proposed combination because Luigi explicitly notes that such strategies are useful to mitigate model drift and maintain model accuracy as the environment changes over time. By applying the mitigation strategies of Luigi to the accuracy metric disclosed by Schultz, one would have arrived at the invention as claimed.
Regarding claim 17, The controller of claim 13, is disclosed, as stated previously. The remaining limitations are substantially similar to that as recited in claim 5 but with respect to claim 13 and are thus rejected under the same rationale: wherein if the determination indicates that the change to the virtual sensor has occurred, the one or more processors are configured to execute the computer-readable instructions to retrain the machine learning model based on the change.
Claims 6 and 18 are rejected under 35 U.S.C. 103 as being unpatentable over the proposed combination as applied to claims 5 and 17 respectively above, and further in view of Pollock et al (Pollock, J., Stoecker-Sylvia, Z. Veedu, V., Panchal, N., and Elshahawi, H., “Machine Learning for Improved Directional Drilling”, April 2018, Offshore Technology Conference, doi.org/10.4043/28633-MS), hereinafter referred to as Pollock.
Regarding claim 6, The method of claim 5, further comprising: is disclosed, as stated previously.
The proposed combination is not relied upon to disclose; however Pollock discloses performing reinforcement learning of the machine learning model Reinforcement learning is performed to refined neural networks of a drilling system ((Pollock, Page 4, ¶3) "Reinforcement learning was used to refine the neural nets of the directional drilling system based on the results of an appropriate drilling simulator") based on inputs from a system operator, historical data The neural network that is refined is trained using historical data, wherein the historical data includes data from a plurality of horizonal wells in a given region. ((Pollock, Page 4, ¶5) "Historical directional drilling data, including that from measurement while drilling (MWD), were compiled from fourteen horizontal wells in Appalachia and the Permian Basin. In addition to time/date stamps, the data included bit depth, hole depth, hook load, weight on bit, differential pressure, gravity tool face, magnetic tool face, tool face angle, ROP, rotary RPM, rotary torque, standpipe pressure, total pump output, and other, more extraneous categories. The datasets were then unified and cleansed for use in training and validation (Figure 2). "). and data from at least one neighboring wellbore. The reinforcement learning is also based on simulation data which includes corresponding information and actions taken by directional drillers ((Pollock, Page 3, ¶1) "The deep learning system will ingest historical and simulation data corresponding to the information used and actions taken by expert directional drillers and use that data to generate decisions that correspond with those experts would have made when presented with new situations.").
Pollock is analogous art because it is related to the same field of endeavor of the instant application of employing machine learning technologies to wellbore operations to improve processes. Pollock discloses the utilization of reinforcement learning to refine neural networks that are trained on collected data from drilling logs, wherein the drilling log information provides data regarding actions taken by a drilling operator, historical information about the state of the drilling operation, and wherein the drilling operation is performed in a wellbore. It would have been obvious to one of ordinary skill to which said subject matter pertains at the time the invention was filed to have incorporated reinforcement learning using a comprehensive data source, as disclosed by Pollock, on the neural network disclosed by the proposed combination because some teachings, suggestion, or motivation in the prior art reference would have led one of ordinary skill in the art to do so. Pollock demonstrates that the utilization of reinforcement learning enables the refinement of neural networks trained on historical data ((Pollock, ¶Abstract) "The neural network developed could replicate the decisions of expert directional drillers within a small error (<3%). Reinforcement learning was then successfully used to improve network performance particularly for conditions not previously considered."). Therefore, it would have been obvious to one having skill in the art and seeking to refine the performance of the neural network would employ reinforcement learning using comprehensive data to be able to do so.
Regarding claim 18, The controller of claim 17, is disclosed, as stated previously. The remaining limitations are substantially similar to that as recited in claim 6 but with respect to claim 13 and are thus rejected under the same rationale: wherein the one or more processors are configured to execute the computer-readable instructions to perform reinforcement learning of the machine learning model based on inputs from a system operator, historical data and data from at least one neighboring wellbore.
Claim 12 is rejected under 35 U.S.C. 103 as being unpatentable over Vittal in view of Schultz as applied to claim 1 above, and further in view of Disko et al (US Patent Publication No. (US 20180058202 A1), hereinafter referred to as Disko.
Regarding claim 12, the proposed combination discloses The method of claim 1, stated previously.
The proposed combination is not further relied upon to disclose; however, Disko discloses further comprising: generating a reservoir simulation model using the predicted output. A reservoir model is built from measured parameters ((Disko, ¶122) "Reservoir formation model: As used herein, the term “reservoir model” refers to models that are built upon measured parameters and derived properties of the reservoir formation to estimate the amount of hydrocarbon present in the reservoir, the rate at which that hydrocarbon can be produced to the Earth's surface through wellbores, and the fluid flow in rocks."). Measured parameters may be generated from virtual sensors ((Disko, ¶253) "The reservoir formation parameters can be detected by sensors residing along a tubular, including for example, production tubing. The sensors may include, but are not limited to, any one or more of: (i) fluid velocity measurement devices residing inside of the production tubing; (ii) temperature sensors that measure temperature of fluids flowing inside of the production tubing; (iii) pressure sensors that measure pressure inside of the production tubing, or pressure drop; (iv) fluid density sensors that measure the density of fluids inside of the production tubing; (v) microphones that provide passive acoustic monitoring to listen for the sound of gas entry into the production tubing or the opening and closing of the gas lift valve; (vi) ultrasound sensors that correlate changes in gas transmission with gas flows, bubbles, solids and other properties of flow along gas inlets; (vii) Doppler shift sensors; (viii) chemical sensors; (ix) an imaging device; and (x) combinations thereof to produce direct or “virtual” sensors of flows of gas, liquids and solids."). The reservoir model may be used in a simulation ((Disko, ¶245) "In yet another aspect, analyzing the signals means acquiring numerical data and entering it into reservoir simulation software. The reservoir simulator may then be used to predict future pressure changes, earth subsidence (which influences hardware integrity), fluid flow trends, or other factors.")
Disko is analogous art because it is related to the same field of endeavor of improving well operations using sensor data. It would have been obvious to one of ordinary skill to which said subject matter pertains at the time the invention was filed to have incorporated the utilization of a reservoir simulation model into the proposed combination because some teaching, suggestion, or motivation in the prior art would have led one of ordinary skill to do so to arrive at the claimed invention. The proposed combination of Vittal and Schultz discloses the utilization of virtual sensors in well applications. Disko discloses the utilization of virtual sensor output to characterize a reservoir model for simulation purposes to characterize the reservoir. Disko notes that characterization of the reservoir is critical in production zone assessment and optimization ((Disko, ¶7) "Reservoir and formation characterization is critical to production zone assessment and optimization. For example, information regarding reservoir rock conditions, such as porosity, permeability, and hydrocarbon accumulation are important reservoir properties. Understanding of reservoir rock properties is crucial in developing a prospect."). Therefore, because Disko notes that characterization of a reservoir is critical for production optimization and further provides a mechanism by which to characterize the reservoir using virtual sensor data in a reservoir simulation, it would accordingly be obvious to one having skill in the art to combine the prior art references to arrive at the claimed invention.
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to EMILY GORMAN LEATHERS whose telephone number is (571)272-1880. The examiner can normally be reached Monday-Friday, 9:00 am-5:00 pm ET.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, EMERSON PUENTE can be reached at (571) 272-3652. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/E.G.L./Examiner, Art Unit 2187
/JOHN E JOHANSEN/Examiner, Art Unit 2187