DETAILED ACTION
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 . This action is made final.
This office action is in response to the amendments filed on January 19, 2026.
Claims 1, 5, 9, 13, 16, and 18 have been amended
Response to Amendment
The amendment filed January 19, 2026 has been entered. Claims 1-20 remain pending in the application.
Response to Arguments
Response to 101 arguments
Applicant argues that the amended claim 1, 6 and 16 recites a practical application because the claim includes an ESP, a sensor, generation of an alarm based on deviation between recent and predicted behavior, classification of an incident, and performance of a wellbore operation.
However, the amended claims remain directed to analyzing ESP data by determining recent behavior over a time period, generating predicted behavior via a forecasting model, comparing predicted behavior to observed behavior to determine a deviation, and classifying the data as an incident class. These limitations recite evaluating and comparing data over time, including determining behavior, comparing observed and predicted behavior, and clarifying results, which can be performed as mental processes.
Further, reciting an ESP, sensor, alarm, and performing a wellbore operation based on the incident class, do not integrate the abstract idea into a practical application because these elements are claimed at a high level of generality and merely apply the data analysis to generic computer components. MPEP 2106.05(a) indicates that“[I]f it is asserted that the invention improves upon conventional functioning of a computer, or upon conventional technology or technological processes, a technical explanation as to how to implement the invention should be present in the specification,” and that “[a]n indication that the claimed invention provides an improvement can include a discussion in the specification that identifies a technical problem and explains the details of an unconventional technicalsolution expressed in the claim, or identifies technical improvements realized by the claim over the prior art.” The claims do not recite a specific technological improvement to ESP hardware or control mechanisms, but instead generally use the classification result to trigger a wellbore operation. The recitation of performing a wellbore operation based on the incident class merely applies the result of the data analysis to a field-of-use action and does not reflect an improvement to how the wellbore operation itself is performed, as the claims do not recite any modification to the operation, control technique, or underlying technology used to perform the wellbore operation.
Applicant’s arguments do not provide an indication that the claimed invention provides an improvement nor do they show where in the specification a technical problem and explanation of an unconventional solution, as required by the MPEP. Therefore, the claims do not amount to significantly more than the abstract idea, and the rejection under 35 U.S.C. § 101 is maintained.
Response to 103 arguments
Applicant argues that neither Boguslawski nor Beck discloses generating an alarm in response to a deviation between recent ESP behavior and predicted ESP behavior over a corresponding time period, and that the cited art does not teach the recited architecture.
Boguslawski teaches monitoring ESP operational parameters over successive time windows, determining parameter behavior within each window, and generating an indicator/alarm when the computed operational behavior deviates from acceptable values. Therefore, Boguslawski teaches determining recent ESP behavior over a time period and generating an alarm in response to deviation in that behavior.
Beck teaches determining predicted ESP behavior via a forecasting model, as the disclosed deep learning model outputs a [prediction of an operating condition at a future time based on sensor-derived operating condition data. It further teaches that the model outputs a classification state of the ESP and that a motor controller adjusts operation of the ESP based on that classification state. Accordingly, Bec k teaches generating predicted ESP behavior over time via a machine learning forecasting model and a performing a wellbore operation based on the determined condition.
The rejection does not relay on either reference alone to disclose all aspects of the limitation. Rather, the limitation is satisfied by the combination of the cited references under 35 U.S.C. 103 (See MPEP 2143).
It would have been obvious to incorporate Boguslawski’s ESP monitoring framework with Beck’s predictive deep learning model to use predicted operating condition as an expected baseline and generate an alarm when monitored ESP behavior over a test time period deviates from the predicted behavior. Both references address monitoring and controlling ESP operation using sensor-0derived data and machine learning techniques to detect abnormal conditions and adjust pump behavior. The combination teaches generating an alarm in response to deviations between recent behavior and predicted ESP behavior.
Applicant further argues that Beck does not teach performing classification as a post-alarm analytical step responsive to deviation. However, Beck discloses that the deep learning model outputs a classification state of the ESP based on operational data and that the motor controller adjusts ESP operation based on that classification state. The claim does not require a specific casual sequencing beyond “after the alarm is generated”, and the combine teachings of Boguslawski and Beck render it obvious to perform classification of ESP condition and adjust operation following detection of abnormal behavior.
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.
To determine if a claim is directed to patent ineligible subject matter, the Court has guided the Office to apply the Alice/Mayo test, which requires:
Step 1: Determining if the claim falls within a statutory category.
Step 2A: Determining if the claim is directed to a patent ineligible judicial exception consisting of a law of nature, a natural phenomenon, or abstract idea; and Step 2A is a two prong inquiry. MPEP 2106.04(II)(A). Under the first prong, examiners evaluate whether a law of nature, natural phenomenon, or abstract idea is set forth or described in the claim. Abstract ideas include mathematical concepts, certain methods of organizing human activity, and mental processes. MPEP 2104.04(a)(2). The second prong is an inquiry into whether the claim integrates a judicial exception into a practical application. MPEP 2106.04(d).
Step 2B: If the claim is directed to a judicial exception, determining if the claim recites limitations or elements that amount to significantly more than the judicial exception. (See MPEP 2106).
Claims 1-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
Step 1: Claims 1-8 are directed to a method (a process), Claim 9-15 is directed to a non-transitory computer-readable medium (a manufacture), and Claims 16-20 is directed to a system comprising a processor and computer-readable medium (a machine). Therefore, Claims 1-20 are directed to a process, machine or manufacture or composition of matter.
Regarding claim 1
Step 2A Prong 1
Claim 1 recites the following mental processes, that in each case under the broadest reasonable interpretation, covers performance of the limitation in the mind (including observation, evaluation, judgement, opinion) or with the aid of pencil and paper but for recitation of generic computer components (e.g., “machine learning model”) [see MPEP 2106.04(a)(2)(III)].
“determining, from the ESP data, recent ESP behavior over a test time period” (e.g., a human can compare data from the same source, gathered over a period of time and determine differences in its functioning)
“determining, …, an incident class based on the ESP data”(e.g., a human can decide what levels to assign different anomalies depending on received alarms)
“wherein the alarm is generated in response to a deviation between the recent ESP behavior over the test time period and a predicted ESP behavior over the test time period, the predicted ESP behavior being determined based on the ESP data via a forecasting model” (e.g., evaluation of numerical relationships, to compare values for determination of a deviation)
Accordingly, at Step 2A, prong one, the claim recites an abstract idea.
Step 2A Prong 2
The judicial exception is not integrated into a practical application. In particular, the claim recites the additional elements of “machine learning model”, which is recited at a high-level of generality such that it amounts to no more than mere instructions to apply the exception using generic computer components (See MPEP 2106.05(f)). The Examiner notes that this is used throughout the claim limitations, and is rejected thusly for each claim which recites the same language.
Regarding the “obtaining ESP data from a sensor of the ESP” limitation, the additional element is recited at a high-level of generality and amounts to extra-solution activity of obtaining data to input for a model, i.e., pre-solution activity of data gathering (see MPEP 2106.05(g)). The examiner notes that specifying that the data is specific to, “ESP data”, is a field of use, and is discussed below.
Regarding the “ESP data” which is recited at a high-level of generality such that it amounts to no more than generally linking the use of abstract idea to a particular technological environment or field of use using a generic computer component (See MPEP 2106.05(h)), as it limits the data collection to a particular technological environment. The Examiner notes that this is used throughout the claim limitations, and is rejected thusly for each claim which recites the same language.
Regarding the “generating an alarm based on the ESP data” limitation, the additional element is recited at a high-level of generality and amounts to extra-solution activity of determining a threshold and creating an alarm based on what threshold is met/surpassed, i.e., post-solution activity of selecting a particular data source or type of data to be manipulated (see MPEP 2106.05(g)).
Regarding the “the predicted ESP behavior being determined based on the ESP data via a forecasting model” which is recited at a high-level of generality such that it amounts to no more than mere instructions to apply the exception using generic computer components (See MPEP 2106.05(f)).
Regarding the “inputting the ESP data into a trained machine learning model” limitation, the additional element is recited at a high-level of generality and amounts to extra-solution activity of obtaining data to input for a model, i.e., pre-solution activity of data gathering (see MPEP 2106.05(g)).
Regarding the “performing a wellbore operation based on the incident class” limitation, which is recited at a high-level of generality such that it amounts to no more than mere instructions to apply the exception using generic computer components (See MPEP 2106.05(f)).
Accordingly, at Step 2A, prong two, the additional elements individually or in combination do not integrate the judicial exception into a practical application.
Step 2B
In accordance with Step 2B, the claim does not include additional elements that are sufficient to amount to significantly more that the judicial exception. As discussed above, the additional element of a “machine learning model”, which is recited at a high-level of generality such that it amounts to no more than mere instructions to apply the exception using a generic computer component (See MPEP 2106.05(f)).
Regarding the “obtaining ESP data from the ESP”, “generating an alarm based on the ESP data “, and “inputting the ESP data into a trained machine learning model”, limitations, these additional elements are recited at a high-level of generality and amounts to extra-solution activity of data gathering, and data manipulation. The courts have found limitations directed to obtaining information electronically, recited at a high-level of generality, to be well-understood, routine, and conventional (see MPEP 2106.05(d)(II), “receiving or transmitting data over a network”, "electronic record keeping," and "storing and retrieving information in memory").
Regarding the “ESP data” which is recited at a high-level of generality such that it amounts to no more than generally linking the use of abstract idea to a particular technological environment or field of use using a generic computer component (See MPEP 2106.05(h)).
Regarding the “the predicted ESP behavior being determined based on the ESP data via a forecasting model” which is recited at a high-level of generality such that it amounts to no more than mere instructions to apply the exception using generic computer components (See MPEP 2106.05(f)).
Regarding the “performing a wellbore operation based on the incident class” limitation, which is recited at a high-level of generality such that it amounts to no more than mere instructions to apply the exception using generic computer components (See MPEP 2106.05(f)).
Accordingly, at Step 2B, the additional element individually or in combination does not amount to significantly more than the judicial exception.
Regarding claim 2
Step 2A Prong 1
Claim 2 recites the following mental processes, that in each case under the broadest reasonable interpretation, covers performance of the limitation in the mind (including observation, evaluation, judgement, opinion) or with the aid of pencil and paper but for recitation of generic computer components (e.g., “machine learning model”) [see MPEP 2106.04(a)(2)(III)].
determining at least one mitigation activity from a plurality of historical
“determining at least one mitigation activity from a plurality of historical mitigation activities based on the incident class” (e.g., a human can determine what mitigation to take to prevent further issues based on different incidents that occurred)
Accordingly, at Step 2A, prong one, the claim recites an abstract idea.
Step 2A Prong 2
In accordance with Step 2A, Prong 2, the claim does not include any additional elements and the judicial exception is not integrated into a practical application.
Step 2B
In accordance with Step 2B, the claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception.
Regarding claim 3
Step 2A Prong 1
Claim 3 does not introduce any new abstract ideas, but recites the abstract idea identified in claim 1 and claim 2.
Accordingly, at Step 2A, prong one, the claim recites an abstract idea.
Step 2A Prong 2
The judicial exception is not integrated into a practical application. In particular, the claim recites the additional element of a “inputting the incident class and the plurality of historical mitigation activities into a correlation model to determine the at least one mitigation activity”, limitation, the additional element is recited at a high-level of generality and amounts to extra-solution activity of gathering an incident class to then input into a model for further processing, i.e., pre-solution activity of gathering data to input into a model (see MPEP 2106.05(g)).
Accordingly, at Step 2A, prong two, the additional elements individually or in combination do not integrate the judicial exception into a practical application.
Step 2B
In accordance with Step 2B, the claim does not include additional elements that are sufficient to amount to significantly more that the judicial exception. As discussed above, the additional element of a “inputting the incident class and the plurality of historical mitigation activities into a correlation model to determine the at least one mitigation activity”, limitation, the additional element is recited at a high-level of generality and amounts to extra-solution activity of data gathering, and data manipulation. The courts have found limitations directed to obtaining information electronically, recited at a high-level of generality, to be well-understood, routine, and conventional (see MPEP 2106.05(d)(II), “receiving or transmitting data over a network”, "electronic record keeping," and "storing and retrieving information in memory").
Accordingly, at Step 2B, the additional element individually or in combination does not amount to significantly more than the judicial exception.
Regarding claim 4
Step 2A Prong 1
Claim 4 recites the following mental processes, that in each case under the broadest reasonable interpretation, covers performance of the limitation in the mind (including observation, evaluation, judgement, opinion) or with the aid of pencil and paper but for recitation of generic computer components (e.g., “machine learning model”) [see MPEP 2106.04(a)(2)(III)].
determining at least one mitigation activity from a plurality of historical
“updating the alarm based on the incident class” (e.g., a human can determine what incident level is necessary to then adjust alarm levels depending on their severity)
Accordingly, at Step 2A, prong one, the claim recites an abstract idea.
Step 2A Prong 2
In accordance with Step 2A, Prong 2, the claim does not include any additional elements and the judicial exception is not integrated into a practical application.
Step 2B
In accordance with Step 2B, the claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception.
Regarding claim 5
Step 2A Prong 1
Claim 5 recites the following mental processes, that in each case under the broadest reasonable interpretation, covers performance of the limitation in the mind (including observation, evaluation, judgement, opinion) or with the aid of pencil and paper but for recitation of generic computer components (e.g., “machine learning model”) [see MPEP 2106.04(a)(2)(III)].
determining at least one mitigation activity from a plurality of historical
“separating the recent ESP behavior from at least a portion of the ESP data to generate a training dataset” (e.g., a human can identify and separate data based on recent information and create a spreadsheet of datasets)
“generating an ESP health score based on a comparison of the recent ESP behavior and the predicted ESP behavior, wherein the comparison is based on attributes including a prediction interval and distance metrics” (e.g., a human can compare recent data from a pump and what it should be at and determine its health)
Accordingly, at Step 2A, prong one, the claim recites an abstract idea.
Step 2A Prong 2
The judicial exception is not integrated into a practical application. In particular, the claim recites the additional element of a “inputting the training dataset into the forecasting model to determine the predicted ESP behavior”, limitation, the additional element is recited at a high-level of generality and amounts to extra-solution activity of gathering and inputting data into a model for further processing, i.e., post-solution activity of selecting a particular data source or type of data to be manipulated (see MPEP 2106.05(g)).
Regarding the “generating the alarm based on the ESP health score” limitation, the additional element is recited at a high-level of generality and amounts to extra-solution activity of determining a threshold and creating an alarm based on what threshold is met/surpassed, i.e., post-solution activity of selecting a particular data source or type of data to be manipulated (e.g., obtaining information for processing in a computer system (see MPEP 2106.05(g)).
Accordingly, at Step 2A, prong two, the additional elements individually or in combination do not integrate the judicial exception into a practical application.
Step 2B
In accordance with Step 2B, the claim does not include additional elements that are sufficient to amount to significantly more that the judicial exception. As discussed above, the additional element of a “inputting the training dataset into the forecasting model to determine the predicted ESP behavior”, limitation, the additional element is recited at a high-level of generality and amounts to extra-solution activity of data gathering, and data manipulation. The courts have found limitations directed to obtaining information electronically, recited at a high-level of generality, to be well-understood, routine, and conventional (see MPEP 2106.05(d)(II), “receiving or transmitting data over a network”, "electronic record keeping," and "storing and retrieving information in memory").
Regarding the “generating the alarm based on the ESP health score”, limitation, the additional element is recited at a high-level of generality and amounts to extra-solution activity of data manipulation. The courts have found limitations directed to obtaining information electronically, recited at a high-level of generality, to be well-understood, routine, and conventional (see MPEP 2106.05(d)(II), “receiving or transmitting data over a network”, "electronic record keeping," and "storing and retrieving information in memory").
Accordingly, at Step 2B, the additional element individually or in combination does not amount to significantly more than the judicial exception.
Regarding claim 6
Step 2A Prong 1
Claim 6 recites the following mental processes, that in each case under the broadest reasonable interpretation, covers performance of the limitation in the mind (including observation, evaluation, judgement, opinion) or with the aid of pencil and paper but for recitation of generic computer components (e.g., “machine learning model”) [see MPEP 2106.04(a)(2)(III)].
determining at least one mitigation activity from a plurality of historical
“determining, …, a feature set, wherein the feature set includes an ESP data feature” (e.g., a human can identify and separate data to create a dataset(examiner notes, that specifying the feature set includes an ESP data feature merely limits the data to a particular technological environment/field of use))
Accordingly, at Step 2A, prong one, the claim recites an abstract idea.
Step 2A Prong 2
The judicial exception is not integrated into a practical application. In particular, the claim recites the additional element of a “configuring the first machine learning model to receive the feature set as input”, limitation, the additional element is recited at a high-level of generality and amounts to extra-solution activity of gathering data for training of a model, i.e., post-solution activity of data gathering (see MPEP 2106.05(g)).
Regarding the “generating training samples”, limitation, the additional element is recited at a high-level of generality and amounts to extra-solution activity of producing datasets for training of a model, i.e., post-solution activity of data outputting (see MPEP 2106.05(g)).
Regarding the “training the first machine learning model based on the training samples to generate the trained machine learning model, wherein each training sample includes an incident class sample that is associated with at least one cluster sample”, limitation, which is recited at a high-level of generality such that it amounts to no more than mere instructions to apply the exception using generic computer components (See MPEP 2106.05(f)).
Accordingly, at Step 2A, prong two, the additional elements individually or in combination do not integrate the judicial exception into a practical application.
Step 2B
In accordance with Step 2B, the claim does not include additional elements that are sufficient to amount to significantly more that the judicial exception. As discussed above, the additional element of a “configuring the first machine learning model to receive the feature set as input”, and “generating training samples”, limitations, these additional elements are recited at a high-level of generality and amounts to extra-solution activity of data gathering, and data outputting. The courts have found limitations directed to obtaining information electronically, recited at a high-level of generality, to be well-understood, routine, and conventional (see MPEP 2106.05(d)(II), “receiving or transmitting data over a network”, "electronic record keeping," and "storing and retrieving information in memory").
Regarding the “training the first machine learning model based on the training samples to generate the trained machine learning model, wherein each training sample includes an incident class sample that is associated with at least one cluster sample”, limitation, which is recited at a high-level of generality such that it amounts to no more than mere instructions to apply the exception using generic computer components (See MPEP 2106.05(f)).
Accordingly, at Step 2B, the additional element individually or in combination does not amount to significantly more than the judicial exception.
Regarding claim 7
Step 2A Prong 1
Claim 7 recites the following mental processes, that in each case under the broadest reasonable interpretation, covers performance of the limitation in the mind (including observation, evaluation, judgement, opinion) or with the aid of pencil and paper but for recitation of generic computer components (e.g., “machine learning model”) [see MPEP 2106.04(a)(2)(III)].
“labelling each of the at least one cluster samples with an incident class sample to generate the training samples”(e.g., a human can label different outputs of a set for creating further training sets)
Accordingly, at Step 2A, prong one, the claim recites an abstract idea.
Step 2A Prong 2
The judicial exception is not integrated into a practical application. In particular, the claim recites the additional element of a “obtaining a historical ESP data sample”, and “inputting the processed dataset into a second machine learning mode” limitations, these additional elements are recited at a high-level of generality and amounts to extra-solution activity of obtaining data to input for a model, i.e., pre-solution activity of data gathering (see MPEP 2106.05(g)).
Regarding the “historical ESP data” which is recited at a high-level of generality such that it amounts to no more than generally linking the use of abstract idea to a particular technological environment or field of use using a generic computer component (See MPEP 2106.05(h)), as it limits the data collection to a particular technological environment.
Regarding the “generating a processed dataset based on the historical ESP data sample”, and “generating, with the second machine learning model, at least one cluster sample based on the processed dataset”, limitations, these additional elements are recited at a high-level of generality and amounts to extra-solution activity of generating processed data, i.e., post-solution activity of data outputting (see MPEP 2106.05(g)).
Accordingly, at Step 2A, prong two, the additional elements individually or in combination do not integrate the judicial exception into a practical application.
Step 2B
In accordance with Step 2B, the claim does not include additional elements that are sufficient to amount to significantly more that the judicial exception. As discussed above, the additional element of a “obtaining a historical ESP data sample”, “inputting the processed dataset into a second machine learning mode”, “generating a processed dataset based on the historical ESP data sample”, and “generating, with the second machine learning model, at least one cluster sample based on the processed dataset”, limitations, these additional elements are recited at a high-level of generality and amounts to extra-solution activity of data gathering, and data outputting. The courts have found limitations directed to obtaining information electronically, recited at a high-level of generality, to be well-understood, routine, and conventional (see MPEP 2106.05(d)(II), “receiving or transmitting data over a network”, "electronic record keeping," and "storing and retrieving information in memory").
Regarding the “historical ESP data” which is recited at a high-level of generality such that it amounts to no more than generally linking the use of abstract idea to a particular technological environment or field of use using a generic computer component (See MPEP 2106.05(h)), as it limits the data collection to a particular technological environment.
Accordingly, at Step 2B, the additional element individually or in combination does not amount to significantly more than the judicial exception.
Regarding claim 8
Step 2A Prong 1
Claim 8 does not introduce any new abstract ideas, but recites the abstract idea identified in claim 7.
Accordingly, at Step 2A, prong one, the claim recites an abstract idea.
Step 2A Prong 2
The judicial exception is not integrated into a practical application. In particular, the claim recites the additional element of a “wherein the second machine learning model comprises unsupervised clustering”, limitation, which is recited at a high-level of generality such that it amounts to no more than mere instructions to apply the exception using generic computer components (See MPEP 2106.05(f)).
Accordingly, at Step 2A, prong two, the additional elements individually or in combination do not integrate the judicial exception into a practical application.
Step 2B
In accordance with Step 2B, the claim does not include additional elements that are sufficient to amount to significantly more that the judicial exception. As discussed above, the additional element of a “wherein the second machine learning model comprises unsupervised clustering”, limitation, which is recited at a high-level of generality such that it amounts to no more than mere instructions to apply the exception using generic computer components (See MPEP 2106.05(f)).
Accordingly, at Step 2B, the additional element individually or in combination does not amount to significantly more than the judicial exception.
Regarding claims 9-12
Claims 9-12 recites a non-transitory computer-readable medium. Which corresponds directly to the method steps of claims 1-4, respectively, with the addition on hardware and computer-readable instructions which are insufficient to render the claims subject matter eligible for the same reasons described above.
Regarding claims 13-15
Claims 13-15 recites a non-transitory computer-readable medium. Which corresponds directly to the method steps of claims 5-7, respectively, with the addition on hardware and computer-readable instructions which are insufficient to render the claims subject matter eligible for the same reasons described above.
Regarding claims 16, and 17
Claims 16, and 17 recites a system comprising a processor and computer-readable medium. Which corresponds directly to the method steps of claims 1, and 2, respectively, with the addition on hardware and computer-readable instructions which are insufficient to render the claims subject matter eligible for the same reasons described above.
Regarding claims 18-20
Claims 18-20 recites a system comprising a processor and computer-readable medium. Which corresponds directly to the method steps of claims 5-7, respectively, with the addition on hardware and computer-readable instructions which are insufficient to render the claims subject matter eligible for the same reasons described above.
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.
Claim(s) 1-5, 9-13, 16, 17, and 18 is/are rejected under 35 U.S.C. 103 as being unpatentable over Boguslawski et al. (US 20230095709 A1, referred to as Boguslawski) in view of Beck et al. (US 11480039 B2, referred to as Beck).
Regarding claim 1, Boguslawski teaches a computer-implemented method for monitoring an electrical submersible pump (ESP) disposed in a wellbore ([0040-0041]: Describes an ESP installed in downhole in a wellbore then details the surface control/PAC receives ESP operation data and data from sensors/ I/O devices positioned around/within the wellbore.), the method comprising:
obtaining ESP data from a sensor of the ESP([0041]: Describes receiving ESP/wellbore operational data from a sensor of the ESP because operational parameters (flow rate, pressure, temperature, current/voltage, vibration) are provided by I/O devices including temperature/pressure/flow/current/vibration0sensors positioned around and within the wellbore, form which data is acquired for monitoring ESP operation.);
determining, form the ESP data, recent ESP behavior over a test time period (FIG. 10, FIG. 11, [0072-73]: Describes determining, performing event detection/prediction on a stepwise basis using successive time windows over the operational data (windows starting at tie t, t + 1, etc.) and determines parameter behavior within each window by performing slope determinations on a per-window basis (with window sizes on the order of seconds, minutes, hours, or days).);
generating an alarm based on the ESP data, wherein the alarm is generated in response to a deviation between the recent ESP behavior over the test time period ([Boguslawski [0096-0100]: Describes generating an alarm based on ESP data because operational parameters are processed to derive correlated probabilities and a resultant probability vector P, which is compared to a preselected threshold value. When the resultant probability fails to meet the threshold, an indicator of abnormal operation is displayed. It monitors probability trends and identifies deviation from a stable operating region, including estimating time remaining until threshold violation and issuing an indicator if abnormal operation is imminent.)
Although Boguslawski teaches obtaining ESP data from a sensor of the ESP, determining, form the ESP data, recent ESP behavior over a test time period, and generating an alarm based on the ESP data triggered from a deviation. It does not teach that the deviation is based on the combination of the deviation based on predicted ESP behavior over the test time period, the predicted ESP behavior being determined based on the ESP data via a forecasting model.
Beck teaches, a predicted ESP behavior over the test time period, the predicted ESP behavior being determined based on the ESP data via a forecasting model (Col. 8, lines 35-57: Describes determining predicted ESP behavior via a forecasting model because the deep learning model outputs a prediction of an operating condition at a future time (flow rate or gas lock in the future) based on sensor-derived operating condition data, which provides predicted ESP behavior over a time period via a model.);
It would have been obvious to cone of ordinary skill in the art at the time if the claimed invention to have combined the ESP monitoring system of Boguslawski with the deep learning predictive model. Doing so would have enabled the system to proactively detect abnormal operation, to improve ESP monitoring and control based on sensor-derived operating conditions. Using Beck’s predicted operating conditions as the expected baseline in Bougslawski’s monitoring/alarm framework, and generating an alarm when the monitored recent behaviors deviates form that predicted/expected condition.
Beck further teaches, performing the following after the alarm is generated,
inputting the ESP data into a trained machine learning model (Beck Col. 9, lines 63-67 Cont. Col. 10, lines 1-7: Describes that the machine learning model receives inputs from ESP sensors, where ESP data is input into a trained model.; Col. 11, lines 8-13: Describes that the models input stage receives inputs form sensors for ESP data.);
determining, with the trained machine learning model, an incident class
based on the ESP data (Col. 10, lines 8-43: Describes a trained model which outputs a classification state (incident class) derived from ESP inputs and used operationally. It further describes a “Gas Lock” as a classification state, which is produced by the model for a condition of a ESP diagnosis. ); and performing a wellbore operation based on the incident class (Col. 1, lines 23-40, Col. 2, lines 35-67 cont. Col. 3, lines 1-23: Describes that the deep learning model outputs a classification state of the ESP, and the motor controller adjusts operation of the motor/ESP which includes adjusting operating parameters to control pumping of fluid.).
Regarding claim 2, Boguslawski in view of Beck teaches, the method of claim 1.
Beck teaches, determining at least one mitigation activity from a plurality of historical
mitigation activities based on the incident class (Beck Col 14, lines 1-38: Describes that system identifies a classification state, then depending on that state sends a signal to a controller adjustment (mitigation action) for the pump, indicating that a mitigation is done depending on a particular incident. ; Col. 14, lines 39-67: Describes that the system contains a centralized logging database of past states/inputs which includes classification states and supervisory input/actions. This shows the system keeps historical data that can be used for future mitigation takes from similar classification states of the past.).
Regarding claim 3, Boguslawski in view of Beck teaches the method of claim 2.
wherein determining the at least one mitigation activity comprises inputting the
incident class and the plurality of historical mitigation activities(Col. 6, lines 13-50: Describes labels, tied to each recorded situation, these same logged records include the action taken (mitigation) giving the historical class to action pair. ;Col. 14, lines 39-67: Describes a centralized history of classification states and supervisory input. Corresponding to a plurality of historical mitigation activities.; ).
Although Beck teaches an incident class and the plurality of historical mitigation activities. It does not teach an into a correlation model to determine the at least one mitigation activity.
Boguslawski teaches into a correlation model to determine the at least one mitigation activity ([0064-0065]: Describes a correlation model maintained by the database that relates observed patterns to event types/causes and it is iteratively updated from field experience. The selection mechanism computes similarity to past events, associating to the known class, then reuses the historical mitigation which resolved that incident.)
It would have been obvious to one of ordinary skill in the art at the time of the claimed invention to combine Boguslawski’s correlation model with the historical mitigation of Beck. Doing so would have enabled the system to determine the proper mitigation task as needed depending on the current situation based on past experiences.
Regarding claim 4, Boguslawski in view of Beck teaches, the method of claim 1.
Boguslawski in view of Beck teaches, updating the alarm based on the incident class (Boguslawski [0094]: Describes that the system supports different alarm severities (medium vs high) and different alarm types/indicates depending on conditions, the annunciation is updated according to the detected situation.; [0100]: Describes different alarm types presented for different detected events.; Beck Col. 9, lines 54-67 Cont. Col 10, lines 1-57: Describes that the system produces a class, and once that class is known it is routine to configure the annunciation (type/severity) to reflect that class.).
It would have been obvious to one of ordinary skill in the art at the time of the claimed invention to combine Boguslawski’s alarm type with the classification system of Beck. Doing so would have enabled the system to determine the proper alarm based on the current incident enhancing the prediction capability of the system.
Regarding claim 5, Boguslawski in view of Beck teaches, the method of claim 1.
Boguslawski in view of Beck teaches, separating the recent ESP behavior from at least a portion of the ESP data to generate a training dataset (Beck, Col. 5, lines 66-67 Cont. Col. 6, lines 1-12: Describes stored training data compared to current/recent data. Differentiating real time and earlier data. ;Col. 14, lines 39-67: Describes a training dataset (in a training database) composed of stored ESP data/labels. Which inherently distinguishes stored (historical) data used for training from current data used for inference control.);
inputting the training dataset into the forecasting model to determine the predicted ESP behavior (Beck, Col. 14, lines 39-67: Describes that the training dataset is input to the model for training. ; Col 20, lines 15-18: Describes that the model produces a forecast/prediction of ESP behavior. Which corresponds to training a dataset from a model to predict future ESP behavior.)
Although Beck teaches separating recent ESP behavior from at least a portion of the ESP data to generate a training dataset and inputting the training dataset into a forecasting model to determine a predicted ESP behavior. It does not teach generating an ESP health score based on a comparison of the recent ESP behavior and the predicted ESP behavior, wherein the comparison is based on attributes including a prediction interval and distance metrics and generating the alarm based on the ESP health score.
Boguslawski teaches, generating an ESP health score based on a comparison of the recent ESP behavior and the predicted ESP behavior, wherein the comparison is based on attributes including a prediction interval and distance metrics ( [0061-0064]: Describes using a distance metric to compare observed behavior (current/recent slope vector x) against an expected distribution and converts that distance into a probability P via the x2 relationship. The P is your health score, a high P is normal, and low P is abnormal. The comparison uses a plurality of attributes (multiple ESP parameters/slopes), each scored, then combined into a resultant probability/health value. The probability region corresponds to the prediction interval, with thresholds that stage severity. This is the same construct as a prediction/confidence interval used to decide if the recent behavior is inside/outside the expected region.); and
generating the alarm based on the ESP health score ( [0093]: Describes how the annunciation is tied to the health score (resultant probability) and shows severity/type selection derived from that score.;[0096-0097]: The resultant probability vector P corresponds to the health score, when that score crosses the threshold, the system generates an indicator (alarm), which means the alarm is based on the score.).
Regarding claims 9-13. Which recites substantially the same limitations as claims 1-5. Claims 9-13 further recites a non-transitory computer-readable medium (Boguslawski [0106]: Describes a non-transitory medium comprising computer hardware to execute store instructions to perform method steps.) to perform the method steps of claims 1-5, respectively, and are therefore rejected on the same premise.
Regarding claims 16-17. Which recites substantially the same limitations as claims 1-2. Claims 16-17 further recites a system comprising: an electrical submersible pump (ESP) to be disposed in a wellbore; a processor; and a computer-readable medium having instructions (Boguslawski [0036] and [0106-0107]: Describes computers with their hardware to perform instructions and methods based on ESP data.) to perform the method steps of claims 1-2, respectively, and are therefore rejected on the same premise.
Regarding claim 18. Which recites substantially the same limitations as claim 5. Claim 18 further recites a system comprising: an electrical submersible pump (ESP) to be disposed in a wellbore; a processor; and a computer-readable medium having instructions (Boguslawski [0036], and [0106-0107]) to perform the method steps of claim 5, respectively, and are therefore rejected on the same premise.
Claim(s) 6-8, 14-15, and 19-20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Boguslawski et al. (US 20230095709 A1, referred to as Boguslawski), in view of Beck et al. (US 11480039 B2, referred to as Beck), in view of Zhu (US 20130211811 A1, referred to as Zhu).
Regarding claim 6, Boguslawski in view of Beck teaches, the method of claim 1.
Beck teaches, determining, for a first machine learning model, a feature set, wherein the feature set includes an ESP data feature (Col. 9, lines 63-67 Cont. Col 10, lines 1-7, and Col. 14, lines 39-67: Describes determining a feature set for the model, as it specifies categories of inputs used by the ESP deep-learning model and stores that schema in the training database for model generation, the practitioner must select/define those features up front.);
configuring the first machine learning model to receive the feature set as input (Col. 9, lines 63-67 Cont. Col 10, lines 1-7: Describes that the model receives feature set categories as inputs.);
training the first machine learning model based on the training samples to generate the trained machine learning model, wherein each training sample includes an incident class sample that is associated with at least one cluster sample (Col. 14, lines 39-67: Describes training datasets are used to train and generate a trained model. The training samples include a classification state (incident class sample).).
Although Beck teaches, determining, for a first machine learning model, a feature set, wherein the feature set includes an ESP data feature, configuring the first machine learning model to receive the feature set as input and training the first machine learning model based on the training samples to generate the trained machine learning model, wherein each training sample includes an incident class sample that is associated with at least one cluster sample. It does not teach generating training samples.
Zhu teaches, generating training samples ([0034-0035]: Describes each generated input/output pair becomes one data row in a training dataset (training sample). It repeatedly creates those rows to obtain the training dataset.);
It would have been obvious to one of ordinary skill in the art at the time of the claimed invention to combine Beck’s deep learning model with the training samples of Zhu. Doing so would have enabled the model to generate larger, balanced datasets without expensive field collection, accelerating training and improving robustness of the model.
Regarding claim 7, Boguslawski in view of Beck, in view of Zhu teaches, the method of claim 6. Zhu further teaches, generating the training samples further comprises:
obtaining a historical ESP data sample;
generating a processed dataset based on the historical ESP data sample ([0031-0033]: Describes that measured ESP parameters are pulled from a repository. This upstream dataset is used by the later model steps for use in model generation.);
inputting the processed dataset into a second machine learning model ([0036]: Describes that unsupervised second model where input is received and then a finite set of clusters is produced as output. Which each represent a group of similar samples.);
generating, with the second machine learning model, at least one cluster sample based on the processed dataset( [0041]: Describes that each measured row is mapped to a winning cluster, rows are associated with that cluster.);
Although Zhu teaches obtaining a historical ESP data sample generating a processed dataset based on the historical ESP data sample inputting the processed dataset into a second machine learning model generating, with the second machine learning model, at least one cluster sample based on the processed dataset. It does not teach, labelling each of the at least one cluster samples with an incident class sample to generate the training samples.
Beck teaches, labelling each of the at least one cluster samples with an incident class sample to generate the training samples(Beck Col. 8, lines 51-57: Describes that each training sample may include a classification state as part of the input/output that is stored in the training dataset. This shows that each stored training row (sample) includes the incident class label. ; Col. 14, lines 39-67: Describes that deep learning model is generated based on the training dataset. The rows in that dataset are training samples used to produce the trained model.).
It would have been obvious to one of ordinary skill in the art at the time of the claimed invention to combine Beck’s training datasets formation with the organized mapping of Zhu. Doing so would have enabled the system to create a predictable dataset, organized by improving class consistent groupings, reducing duplicate rows and outlier isolation. Simplifying training and yielding a more stable model performance.
Regarding claim 8, Boguslawski in view of Beck, in view of Zhu teaches, the method of claim 7
Zhu further teaches, wherein the second machine learning model comprises unsupervised clustering ([0036]: Describes performing self-organizing mapping (SOM) or other cluster analysis on the dataset. ;[0041]: Describes that each measured row is mapped to a winning cluster (per-sample cluster association). This corresponds to unsupervised clustering and the association of each data row to at least on cluster sample.).
Regarding claims 14 and 15. Which recites substantially the same limitations as claims 6 and 7. Claims 14 and 15 further recites a non-transitory computer-readable medium (Boguslawski [0106-0107]) to perform the method steps of claims 6 and 7, respectively, and are therefore rejected on the same premise.
Regarding claims 19 and 20. Which recites substantially the same limitations as claims 6 and 7. Claims 19 and 20 further recites a system comprising: an electrical submersible pump (ESP) to be disposed in a wellbore; a processor; and a computer-readable medium having instructions (Boguslawski [0036], and [0106-0107]) to perform the method steps of claims 6 and 7, respectively, and are therefore rejected on the same premise.
Conclusion
THIS ACTION IS MADE FINAL. 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 DONALD T RODEN whose telephone number is (571)272-6441. The examiner can normally be reached Mon-Thur 8:00-5:00 EST.
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, Omar Fernandez Rivas can be reached at (571) 272-2589. 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.
/D.T.R./Examiner, Art Unit 2128
/OMAR F FERNANDEZ RIVAS/Supervisory Patent Examiner, Art Unit 2128