DETAILED ACTION
This action is in response to Applicant’s Amendment ("Response”) received on June 23, 2026 in response to the Office Action dated May 6, 2026. This action is made Final.
Claims 1-14 are pending.
Claims 1 and 8 are independent claims.
Claims 1-14 are rejected.
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 .
Applicant’s Response
In Applicant’s Response, Applicant amended claims 1-4 and 8-11, and submitted arguments against the prior art in the Office Action dated May 6, 2026.
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(d):
(d) REFERENCE IN DEPENDENT FORMS.—Subject to subsection (e), a claim in dependent form shall contain a reference to a claim previously set forth and then specify a further limitation of the subject matter claimed. A claim in dependent form shall be construed to incorporate by reference all the limitations of the claim to which it refers.
The following is a quotation of pre-AIA 35 U.S.C. 112, fourth paragraph:
Subject to the following paragraph [i.e., the fifth paragraph of pre-AIA 35 U.S.C. 112], a claim in dependent form shall contain a reference to a claim previously set forth and then specify a further limitation of the subject matter claimed. A claim in dependent form shall be construed to incorporate by reference all the limitations of the claim to which it refers.
Claims 3, 4, 10, and 11 are rejected under 35 U.S.C. 112(d) or pre-AIA 35 U.S.C. 112, 4th paragraph, as being of improper dependent form for failing to further limit the subject matter of the claim upon which it depends. The Examiner notes that claims 3, 4, 10, and 11 do not appear to be further limiting as each limitation is already recited in independent claims 1 and 8. Applicant may cancel the claim(s), amend the claim(s) to place the claim(s) in proper dependent form, rewrite the claim(s) in independent form, or present a sufficient showing that the dependent claim(s) complies with the statutory requirements.
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 1-14 are rejected under 35 U.S.C. 101 because the claimed invention is directed to a judicial exception (i.e., a law of nature, a natural phenomenon, or an abstract idea) without significantly more.
Step 1: Independent claims 1 and 8 are directed towards a method and medium (Spec para. 0025 excluding transitory media), respectively. Therefore, these claims, as well as their dependent claims, are directed towards one of the four statutory categories (process, machine (i.e. apparatus), manufacture, or composition of matter.
With respect to claim 1:
2A Prong 1:
Claim 1 recites the following judicial exceptions:
determining a choke opening baseline (mental process –can be performed in the human mind, or by a human using a pen and paper (e.g. a person may use data to determine valve opening baseline information.).
determining a ... choke opening curve (mental process –can be performed in the human mind, or by a human using a pen and paper (e.g. a person may use data to determine and plot a choke valve opening curve.).
comparing the choke opening baseline to the ... choke opening curve (mental process –can be performed in the human mind, or by a human using a pen and paper (e.g. a person may use data to determine valve opening baseline information, use data to determine and plot a choke valve opening curve, and then compare).
providing an assessment of choke lifetime as a function of said comparing (see mental process –can be performed in the human mind, or by a human using a pen and paper (e.g. a person may use data to determine valve opening baseline information, use data to determine and plot a choke valve opening curve, compare, and then produce an evaluation of choke lifespan based on the comparison.).
2A Prong 2: The additional elements recited in the claim do not integrate the judicial exception into a practical application.
Additional elements:
by applying a first machine learning (ML) model to acquired real-time well dynamic data including flowrate, choke upstream pressure (U/S) and temperature and choke downstream (D/S) pressure and temperature as input (mere instructions to apply the exception or implement the exception on a computer (e.g. – a computer with a generic machine learning algorithm may be used to carry out the judicial exception at the time the data is recieved; see MPEP §2106.05(f).). Further, generally linking the use of a judicial exception to a particular technological environment or field of use (e.g. using machine learning algorithm; see MPEP §2106.05(h).). The additional elements do not effectively integrate the abstract idea into a practical application. 2B: revisiting the additional elements, the additional elements do not amount to significantly more than the judicial exception – recited high level of generality and corresponds to storing and retrieving information and performing calculations.).
by applying a second ML sub-model to the acquired real-time well dynamic data (mere instructions to apply the exception or implement the exception on a computer (e.g. – a computer with a generic machine learning algorithm may be used to carry out the judicial exception at the time the data is recieved; see MPEP §2106.05(f).). Further, generally linking the use of a judicial exception to a particular technological environment or field of use (e.g. using machine learning algorithm; see MPEP §2106.05(h).). The additional elements do not effectively integrate the abstract idea into a practical application. 2B: revisiting the additional elements, the additional elements do not amount to significantly more than the judicial exception – recited high level of generality and corresponds to storing and retrieving information and performing calculations.).
a realtime ... realtime (mere instructions to apply the exception or implement the exception on a computer (e.g. – a computer may be used to carry out the judicial exception at the time the data is recieved; see MPEP §2106.05(f).). The additional elements do not effectively integrate the abstract idea into a practical application. 2B: revisiting the additional elements, the additional elements do not amount to significantly more than the judicial exception – recited high level of generality and corresponds to storing and retrieving information in memory and performing calculations.).
With respect to claim 2:
2A Prong 2: The additional elements recited in the claim do not integrate the judicial exception into a practical application.
Additional elements:
whose input data includes specific well completion size/type, produced gas properties and chole type/size from historic data (mere instructions to apply the exception or implement the exception on a computer (e.g. – a computer may be used to carry out the judicial exception at the time the data is recieved; see MPEP §2106.05(f).). The additional elements do not effectively integrate the abstract idea into a practical application. 2B: revisiting the additional elements, the additional elements do not amount to significantly more than the judicial exception – recited high level of generality and corresponds to storing and retrieving information in memory and performing calculations.).
constructing the first ML model using training algorithms (generally linking the use of a judicial exception to a particular technological environment or field of use (e.g. generating and updating machine learning algorithm; see MPEP §2106.05(h).). The additional elements do not effectively integrate the abstract idea into a practical application. 2B: revisiting the additional elements, the additional elements do not amount to significantly more than the judicial exception – recited high level of generality and corresponds to storing and retrieving information and performing calculations.).
With respect to claim 3:
2A Prong 2: The additional elements recited in the claim do not integrate the judicial exception into a practical application.
Additional elements:
applying the first ML model to acquired real-time well dynamic data including flowrate, choke upstream pressure (U/S) and temperature and chole downstream (D/S) pressure and temperature as input (mere instructions to apply the exception or implement the exception on a computer (e.g. – a computer with a generic machine learning algorithm may be used to carry out the judicial exception at the time the data is recieved; see MPEP §2106.05(f).). Further, generally linking the use of a judicial exception to a particular technological environment or field of use (e.g. using machine learning algorithm; see MPEP §2106.05(h).). The additional elements do not effectively integrate the abstract idea into a practical application. 2B: revisiting the additional elements, the additional elements do not amount to significantly more than the judicial exception – recited high level of generality and corresponds to storing and retrieving information and performing calculations.).
With respect to claim 4:
2A Prong 2: The additional elements recited in the claim do not integrate the judicial exception into a practical application.
Additional elements:
applying the second ML sub-model to acquired real-time well dynamic data including flowrate, choke upstream pressure (U/S) and temperature and chole downstream (D/S) pressure and temperature as input (mere instructions to apply the exception or implement the exception on a computer (e.g. – a computer with a generic machine learning algorithm may be used to carry out the judicial exception at the time the data is recieved; see MPEP §2106.05(f).). Further, generally linking the use of a judicial exception to a particular technological environment or field of use (e.g. using machine learning algorithm; see MPEP §2106.05(h).). The additional elements do not effectively integrate the abstract idea into a practical application. 2B: revisiting the additional elements, the additional elements do not amount to significantly more than the judicial exception – recited high level of generality and corresponds to storing and retrieving information and performing calculations.).
With respect to claim 5:
2A Prong 2: The additional elements recited in the claim do not integrate the judicial exception into a practical application.
Additional elements:
configured to receive the real-time well dynamic data (mere instructions to apply the exception or implement the exception on a computer (e.g. – a computer may be used to carry out the judicial exception at the time the data is recieved; see MPEP §2106.05(f).). The additional elements do not effectively integrate the abstract idea into a practical application. 2B: revisiting the additional elements, the additional elements do not amount to significantly more than the judicial exception – recited high level of generality and corresponds to storing and retrieving information in memory and performing calculations.).
wherein the ML sub-model constructed by training algorithms (generally linking the use of a judicial exception to a particular technological environment or field of use (e.g. generating and updating machine learning algorithm; see MPEP §2106.05(h).). The additional elements do not effectively integrate the abstract idea into a practical application. 2B: revisiting the additional elements, the additional elements do not amount to significantly more than the judicial exception – recited high level of generality and corresponds to storing and retrieving information and performing calculations.).
With respect to claim 6:
2A Prong 2: The additional elements recited in the claim do not integrate the judicial exception into a practical application.
Additional elements:
wherein the training algorithms are selected from XGboost, artificial neural networks (ANN), recurrent neural networks (generally linking the use of a judicial exception to a particular technological environment or field of use (e.g. generating and updating machine learning algorithm; see MPEP §2106.05(h).). The additional elements do not effectively integrate the abstract idea into a practical application. 2B: revisiting the additional elements, the additional elements do not amount to significantly more than the judicial exception – recited high level of generality and corresponds to storing and retrieving information and performing calculations.).
With respect to claim 7:
2A Prong 2: The additional elements recited in the claim do not integrate the judicial exception into a practical application.
Additional elements:
wherein the training algorithms are selected from XGboost, artificial neural networks (ANN), recurrent neural networks (generally linking the use of a judicial exception to a particular technological environment or field of use (e.g. generating and updating machine learning algorithm; see MPEP §2106.05(h).). The additional elements do not effectively integrate the abstract idea into a practical application. 2B: revisiting the additional elements, the additional elements do not amount to significantly more than the judicial exception – recited high level of generality and corresponds to storing and retrieving information and performing calculations.).
With respect to claim 8:
Claim 8 corresponds to Claim 1 and are thus rejected under the same rationale.
With respect to claim 9:
Claim 9 corresponds to Claim 2 and are thus rejected under the same rationale.
With respect to claim 10:
Claim 10 corresponds to Claim 3 and are thus rejected under the same rationale.
With respect to claim 11:
Claim 11 corresponds to Claim 4 and are thus rejected under the same rationale.
With respect to claim 12:
Claim 12 corresponds to Claim 5 and us rejected under the same rationale.
With respect to claim 13:
Claim 13 corresponds to Claim 6 and are thus rejected under the same rationale.
With respect to claim 14:
Claim 14 corresponds to Claim 7 and are thus rejected under the same rationale.
2B continued: After considering all claim elements individually and as an ordered combination, it is determined that the claims do not include any additional elements that are sufficient to amount to significantly more than the judicial exception.
Claim Rejections - 35 USC § 103
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) 1-14 is/are rejected under 35 U.S.C. 103 as being unpatentable over An et al., US Publication 2025/0109652 (“An”), and further in view of Nistala et al., US Publication 2022/0214474 (“Nistala”).
Claim 1:
An teaches or suggests a method for forecasting the lifetime of a choke comprising:
determining a choke opening baseline by applying a … model to acquired real-time well dynamic data including flowrate, choke upstream pressure (U/S) and temperature and choke downstream (D/S) pressure and temperature as input (see Fig. 5, 10-12; para. 0042 - a choke valve 670, one or more sensor devices 660-1 located upstream of the choke valve 670, and one or more sensor devices 660-2 located downstream of the choke valve 670; para. 0044 - parameters that can be used for differential measurement include, but are not limited to, pressure; para. 0056 - configured to determine and communicate, in real time, an adjustment that can be made to the choke valve 670 to improve the performance of the choke valve 670 and extend the useful life of the choke valve 670. a previously-established performance curve corresponding to a predicted flow area of the choke valve 670; para. 0059 – data point (as generated by the controller 704 using measurements from at least some of the sensor devices 660 and one or more algorithms 733); para. 0061 - algorithms 733 of the storage repository 730 can be any formulas, mathematical models, forecasts, simulations, and/or other similar tools that the control engine 706 of the controller 704 uses to reach a computational conclusion. model that estimates, in real time, a flow area through the choke valve 670 in real time using parameters (e.g., pressure, temperature, flow rate, flow properties) measured by at least some of the sensor devices 660; para. 0062 - one or more algorithms 733 can be or include a model that determines an amount of adjustment of the position of the plug of the choke valve 670 that should be made to extend the useful life of the choke valve 670 by reducing the amount of erosion or obstruction that the choke valve 670 experiences; para. 0063 - Such data can be any type of data, including but not limited to historical data, current data, and forecasts; para. 0107 - systems for evaluating the performance of a choke valve (e.g., choke valve 670) in real time during a subterranean field operation. baseline performance data of a choke valve 670 during a first time period is collected; para. 0108 - during which the choke valve 670 is unlikely to experience any appreciable erosion or congestion as multiphase fluid flow therethrough; para. 0112 - measurements can be differential measurements of parameters (e.g., pressure, temperature, flow rate) made by the sensor devices 660-1 (downstream of the choke valve 670) and the sensor devices 660-2 (upstream of the choke valve 670). three of the sensor devices 660-1 can measure pressure, temperature, flow rate upstream of the choke valve 670 at a point in time, and three of the sensor devices 660-2 can measure pressure, temperature, flow rate downstream of the choke valve 670; Claim 1 - collecting baseline performance data for the choke valve during a first time period during the field operation, wherein the choke valve has a fluid flowing therethrough during the first time period.);
determining a realtime choke opening curve by applying … sub-model to the acquired real-time well dynamic data (see Fig. 5, 10-12; para. 0040 - FIG. 5 shows a graph 595 of a performance curve 563 for a choke valve (e.g., choke valve 370); para. 0042 - a choke valve 670, one or more sensor devices 660-1 located upstream of the choke valve 670, and one or more sensor devices 660-2 located downstream of the choke valve 670; para. 0044 - parameters that can be used for differential measurement include, but are not limited to, pressure; para. 0045 - provide for real time evaluation of the performance of a choke valve; para. 0056 - sensor measurements to evaluate the performance of the choke valve 670 during a subterranean field operation in real time; configured to determine and communicate, in real time, an adjustment that can be made to the choke valve 670 to improve the performance of the choke valve 670 and extend the useful life of the choke valve 670. The controller can further be configured to adjust a performance curve of the choke valve 670. based on an estimated flow area of the choke valve 670 (using measurements made by the sensor devices 660) and a previously-established performance curve corresponding to a predicted flow area of the choke valve 670; para. 0061 - model that estimates, in real time, a flow area through the choke valve 670 in real time using parameters (e.g., pressure, temperature, flow rate, flow properties) measured by at least some of the sensor devices 660; para. 0063 - Such data can be any type of data, including but not limited to historical data, current data, and forecasts; para. 0070 - estimate, in real time, a flow area through the choke valve 670 in real time using parameters (e.g., pressure, temperature, flow rate) measured by at least some of the sensor devices 660; para. 0112 - measurements can be differential measurements of parameters (e.g., pressure, temperature, flow rate) made by the sensor devices 660-1 (downstream of the choke valve 670) and the sensor devices 660-2 (upstream of the choke valve 670). three of the sensor devices 660-1 can measure pressure, temperature, flow rate upstream of the choke valve 670 at a point in time, and three of the sensor devices 660-2 can measure pressure, temperature, flow rate downstream of the choke valve 670; para. 0134 - provide for real time evaluation of the performance of a choke valve.);
comparing the choke opening baseline to the choke opening curve (see Fig. 5, 10-12; para. 0056 - based on an estimated flow area of the choke valve 670 (using measurements made by the sensor devices 660) and a previously-established performance curve corresponding to a predicted flow area of the choke valve 670; para. 0062 – based on an estimated flow area of the choke valve 670 (using measurements made by the sensor devices 660) and a previously-established performance curve corresponding to a predicted flow area of the choke valve 670; para. 0063 - Such data can be any type of data, including but not limited to historical data, current data, and forecasts; para. 0119 - If one or more channels of the choke valve are eroded, as shown in FIG. 4B, then plot points land in the area 1164 above the performance curve 1163. Similarly, if one or more channels of the choke valve are congested, as shown in FIG. 4C, then plot points land in the area 1165 below the performance curve 1163; Claim 1 - comparing the estimated flow area with the predicted flow area for the second time period.); and
providing an assessment of choke lifetime as a function of said comparing (see Fig. 5, 10-12; para. 0056 - use these sensor measurements to evaluate the performance of the choke valve 670 during a subterranean field operation in real time. The controller 704 can also be configured to determine and communicate, in real time, an adjustment that can be made to the choke valve 670 to improve the performance of the choke valve 670 and extend the useful life of the choke valve 670. The controller can further be configured to adjust a performance curve of the choke valve 670 for a forward-looking period of time based on an estimated flow area of the choke valve 670 (using measurements made by the sensor devices 660) and a previously-established performance curve corresponding to a predicted flow area of the choke valve 670; para. 0116 - communication can be generated by the controller 704 and sent to one or more users 750 to communicate that the performance of the choke valve 670 is no longer within a range of acceptable performance values. This communication can include any of a number of different types of information, including but not limited to a basic statement that the choke valve 670 is failing or operating sub-optimally, whether the choke valve 670 is experiencing erosion or congestion, the severity of the erosion or congestion of the choke valve 670, and specific actions.).
An does not explicitly disclose by applying a first machine learning (ML) model; by applying a second ML sub-model.
Nistala teaches or suggests by applying a first machine learning (ML) model; by applying a second ML sub-model (see para. 0007 - the plurality of parameters comprises: a flow rate of oil, gas and brine produced from each well in the connected oil and gas wells, a pressure, a temperature distribution and a velocity distribution in multiphase flow from each well of the connected oil and gas wells; para. 0031 - parameters comprises: a mass flow rate of oil, gas and brine coming out from each well of the connected oil and gas wells, a pressure and temperature, and velocity distribution in the multiphase flow from each well of the connected oil and gas wells; para. 0032 - well and wellhead assets include such as choke control valves; para. 0035 – Real time diagnostics of performance drift is performed using data-driven diagnostic models built using one or more of the statistical and machine learning techniques; para. 0037 - configured to monitor performance of all well surveillance models in real-time using actual measurements, whenever available, to detect drifts/drop in accuracy. Self-learning is performed using the historical as well as the latest available data from all the data sources. re-training the well surveillance models by tuning the weights and hyperparameters in the models, modifying the machine learning technique used in the models and changing the features used in the models; para. 0048 – Models for forecasting the well performance are physics-guided artificial neural network (ANN) models that incorporate the physics-based model equations corresponding to multiphase flow in the wells. Models for estimating the health of well and wellhead assets are built using one or more of the statistical and machine learning techniques including ... artificial neural networks and its variants. Models for estimating the health of well and wellhead assets are built using one or more of the statistical and machine learning techniques; para. 0053 - initially the plurality of physics-guided well surveillance model generation is a one-time process, but later plurality of physics-guided well surveillance model can be retrained or retuned whenever there is a performance drop. The plurality of parameters comprises: a flow rate of oil, gas and brine coming out of each well in the connected oil and gas wells, a pressure, temperature distribution and velocity distribution in the multiphase flow from each well of the connected oil and gas wells.).
Accordingly, it would have been obvious to one having ordinary skill before the effective filing date of the claimed invention to modify the system and method, taught in An, to include by applying a first machine learning (ML) model; by applying a second ML sub-model for the purpose of efficiently training and retraining models for well asset including choke valves based on large amounts of pertinent data, improving model performance to provide diagnostics and prediction, as taught by Nistala (0035, 0037, 0048).
Claim(s) 8:
Claim(s) 8 correspond to Claim 1, and thus, An and Nistala teach or suggest the limitations of claim(s) 8 as well.
Claim 2:
An further teaches or suggests constructing the ... model ... whose input data includes specific well completion size/type, produced gas properties and choke type/size from historic data (see para. 0064 - Stored data 734 of the storage repository 730 can be any data (e.g., nameplate data, manufacturing information) associated with a component (e.g., each sensor device 660, the choke valve 670) of the system 600 used during a subterranean field operation, any measurements made by the sensor devices 660, threshold values, PVT tables for one or more subterranean fields, results of previously run or calculated algorithms 733, data (e.g., sensor measurements, results of algorithms, predicted flow area through a choke valve, estimated flow area through a choke valve) associated with other field operations having subterranean characteristics and/or choke valves similar to those of the present subterranean field operation. Such data can be any type of data, including but not limited to historical data, current data, and forecasts; para. 0108 - measurements of parameters (e.g., flow rate, temperature, pressure) made by the sensor devices 660, the position of the choke valve 670, nameplate data for the choke valve 670, manufacturing performance curves for the choke valve 670, historical data associated with other choke valves having the same make and manufacturer as the choke valve 670 used in the present subterranean field operation, and data associated with other subterranean field operations; para. 0043 - pressure and/or other factors that can lead to a pressure, a flow rate, a temperature, and flow properties; para. 0134 - used to provide for real time evaluation of the performance of a choke valve used in subterranean field operations, particularly when the choke valve is part of a Christmas tree.).
Nistala further teaches or suggests constructing the first ML model using training algorithms whose input data includes ... produced gas properties (see para. 0007 - the plurality of parameters comprises: a flow rate of oil, gas and brine produced from each well in the connected oil and gas wells, a pressure, a temperature distribution and a velocity distribution in multiphase flow from each well of the connected oil and gas wells; para. 0031 - parameters comprises: a mass flow rate of oil, gas and brine coming out from each well of the connected oil and gas wells, a pressure and temperature, and velocity distribution in the multiphase flow from each well of the connected oil and gas wells; para. 0032 - well and wellhead assets include such as choke control valves; para. 0035 – Real time diagnostics of performance drift is performed using data-driven diagnostic models built using one or more of the statistical and machine learning techniques; para. 0037 - configured to monitor performance of all well surveillance models in real-time using actual measurements, whenever available, to detect drifts/drop in accuracy. Self-learning is performed using the historical as well as the latest available data from all the data sources. re-training the well surveillance models by tuning the weights and hyperparameters in the models, modifying the machine learning technique used in the models and changing the features used in the models; para. 0048 – Models for forecasting the well performance are physics-guided artificial neural network (ANN) models that incorporate the physics-based model equations corresponding to multiphase flow in the wells. Models for estimating the health of well and wellhead assets are built using one or more of the statistical and machine learning techniques including ... artificial neural networks and its variants; para. 0053 - initially the plurality of physics-guided well surveillance model generation is a one-time process, but later plurality of physics-guided well surveillance model can be retrained or retuned whenever there is a performance drop. The plurality of parameters comprises: a flow rate of oil, gas and brine coming out of each well in the connected oil and gas wells, a pressure, temperature distribution and velocity distribution in the multiphase flow from each well of the connected oil and gas wells.).
Accordingly, it would have been obvious to one having ordinary skill before the effective filing date of the claimed invention to modify the system and method, taught in An, to include constructing the first ML model using training algorithms whose input data includes ... produced gas properties for the purpose of efficiently training and retraining models for well asset including choke valves based on large amounts of pertinent data, improving model performance to provide diagnostics and prediction, as taught by Nistala (0035, 0037, 0048).
Claim(s) 9:
Claim(s) 9 correspond to Claim 2, and thus, An and Nistala teach or suggest the limitations of claim(s) 9 as well.
Claim 3:
An further teaches or suggests wherein determining the choke opening baseline comprises applying the ... model to acquired real-time well dynamic data including flowrate, choke upstream pressure (U/S) and temperature and choke downstream (D/S) pressure and temperature as input (see Fig. 5, 10-12; para. 0042 - a choke valve 670, one or more sensor devices 660-1 located upstream of the choke valve 670, and one or more sensor devices 660-2 located downstream of the choke valve 670; para. 0044 - parameters that can be used for differential measurement include, but are not limited to, pressure; para. 0056 - configured to determine and communicate, in real time, an adjustment that can be made to the choke valve 670 to improve the performance of the choke valve 670 and extend the useful life of the choke valve 670. a previously-established performance curve corresponding to a predicted flow area of the choke valve 670; para. 0059 – data point (as generated by the controller 704 using measurements from at least some of the sensor devices 660 and one or more algorithms 733); para. 0061 - algorithms 733 of the storage repository 730 can be any formulas, mathematical models, forecasts, simulations, and/or other similar tools that the control engine 706 of the controller 704 uses to reach a computational conclusion. model that estimates, in real time, a flow area through the choke valve 670 in real time using parameters (e.g., pressure, temperature, flow rate, flow properties) measured by at least some of the sensor devices 660; para. 0062 - one or more algorithms 733 can be or include a model that determines an amount of adjustment of the position of the plug of the choke valve 670 that should be made to extend the useful life of the choke valve 670 by reducing the amount of erosion or obstruction that the choke valve 670 experiences; para. 0063 - Such data can be any type of data, including but not limited to historical data, current data, and forecasts; para. 0107 - systems for evaluating the performance of a choke valve (e.g., choke valve 670) in real time during a subterranean field operation. baseline performance data of a choke valve 670 during a first time period is collected; para. 0108 - during which the choke valve 670 is unlikely to experience any appreciable erosion or congestion as multiphase fluid flow therethrough; para. 0112 - measurements can be differential measurements of parameters (e.g., pressure, temperature, flow rate) made by the sensor devices 660-1 (downstream of the choke valve 670) and the sensor devices 660-2 (upstream of the choke valve 670). three of the sensor devices 660-1 can measure pressure, temperature, flow rate upstream of the choke valve 670 at a point in time, and three of the sensor devices 660-2 can measure pressure, temperature, flow rate downstream of the choke valve 670; Claim 1 - collecting baseline performance data for the choke valve during a first time period during the field operation, wherein the choke valve has a fluid flowing therethrough during the first time period.);
Nistala further teaches or suggests applying the first ML to acquired real-time well dynamic data (see para. 0007 - the plurality of parameters comprises: a flow rate of oil, gas and brine produced from each well in the connected oil and gas wells, a pressure, a temperature distribution and a velocity distribution in multiphase flow from each well of the connected oil and gas wells; para. 0031 - parameters comprises: a mass flow rate of oil, gas and brine coming out from each well of the connected oil and gas wells, a pressure and temperature, and velocity distribution in the multiphase flow from each well of the connected oil and gas wells; para. 0032 - well and wellhead assets include such as choke control valves; para. 0035 – Real time diagnostics of performance drift is performed using data-driven diagnostic models built using one or more of the statistical and machine learning techniques; para. 0037 - configured to monitor performance of all well surveillance models in real-time using actual measurements, whenever available, to detect drifts/drop in accuracy. Self-learning is performed using the historical as well as the latest available data from all the data sources. re-training the well surveillance models by tuning the weights and hyperparameters in the models, modifying the machine learning technique used in the models and changing the features used in the models; para. 0048 – Models for forecasting the well performance are physics-guided artificial neural network (ANN) models that incorporate the physics-based model equations corresponding to multiphase flow in the wells. Models for estimating the health of well and wellhead assets are built using one or more of the statistical and machine learning techniques including ... artificial neural networks and its variants. Models for estimating the health of well and wellhead assets are built using one or more of the statistical and machine learning techniques; para. 0053 - initially the plurality of physics-guided well surveillance model generation is a one-time process, but later plurality of physics-guided well surveillance model can be retrained or retuned whenever there is a performance drop. The plurality of parameters comprises: a flow rate of oil, gas and brine coming out of each well in the connected oil and gas wells, a pressure, temperature distribution and velocity distribution in the multiphase flow from each well of the connected oil and gas wells.).
Accordingly, it would have been obvious to one having ordinary skill before the effective filing date of the claimed invention to modify the system and method, taught in An, to include applying the first ML to acquired real-time well dynamic data for the purpose of efficiently training and retraining models for well asset including choke valves based on large amounts of pertinent data, improving model performance to provide diagnostics and prediction, as taught by Nistala (0035, 0037, 0048).
Claim(s) 10:
Claim(s) 10 correspond to Claim 3, and thus, An and Nistala teach or suggest the limitations of claim(s) 10 as well.
Claim 4:
An further teaches or suggests determining a realtime choke opening curve comprises applying an ... sub-model to acquired real-time well dynamic data including flowrate, choke upstream pressure (U/S) and temperature and choke downstream (D/S) pressure and temperature as input (see Fig. 5, 10-12; para. 0040 - FIG. 5 shows a graph 595 of a performance curve 563 for a choke valve (e.g., choke valve 370); para. 0045 - provide for real time evaluation of the performance of a choke valve; para. 0042 - a choke valve 670, one or more sensor devices 660-1 located upstream of the choke valve 670, and one or more sensor devices 660-2 located downstream of the choke valve 670; para. 0044 - parameters that can be used for differential measurement include, but are not limited to, pressure; para. 0056 - sensor measurements to evaluate the performance of the choke valve 670 during a subterranean field operation in real time; configured to determine and communicate, in real time, an adjustment that can be made to the choke valve 670 to improve the performance of the choke valve 670 and extend the useful life of the choke valve 670. The controller can further be configured to adjust a performance curve of the choke valve 670. based on an estimated flow area of the choke valve 670 (using measurements made by the sensor devices 660) and a previously-established performance curve corresponding to a predicted flow area of the choke valve 670; para. 0056 - model that estimates, in real time, a flow area through the choke valve 670 in real time using parameters (e.g., pressure, temperature, flow rate, flow properties) measured by at least some of the sensor devices 660; para. 0063 - Such data can be any type of data, including but not limited to historical data, current data, and forecasts; para. 0070 - estimate, in real time, a flow area through the choke valve 670 in real time using parameters (e.g., pressure, temperature, flow rate) measured by at least some of the sensor devices 660; para. 0112 - measurements can be differential measurements of parameters (e.g., pressure, temperature, flow rate) made by the sensor devices 660-1 (downstream of the choke valve 670) and the sensor devices 660-2 (upstream of the choke valve 670). three of the sensor devices 660-1 can measure pressure, temperature, flow rate upstream of the choke valve 670 at a point in time, and three of the sensor devices 660-2 can measure pressure, temperature, flow rate downstream of the choke valve 670; para. 0134 - provide for real time evaluation of the performance of a choke valve; Claims 4, 5.).
Nistala further teaches or suggests applying the second ML sub-model to acquired real-time well dynamic data (see para. 0007 - the plurality of parameters comprises: a flow rate of oil, gas and brine produced from each well in the connected oil and gas wells, a pressure, a temperature distribution and a velocity distribution in multiphase flow from each well of the connected oil and gas wells; para. 0031 - parameters comprises: a mass flow rate of oil, gas and brine coming out from each well of the connected oil and gas wells, a pressure and temperature, and velocity distribution in the multiphase flow from each well of the connected oil and gas wells; para. 0032 - well and wellhead assets include such as choke control valves; para. 0035 – Real time diagnostics of performance drift is performed using data-driven diagnostic models built using one or more of the statistical and machine learning techniques; para. 0037 - configured to monitor performance of all well surveillance models in real-time using actual measurements, whenever available, to detect drifts/drop in accuracy. Self-learning is performed using the historical as well as the latest available data from all the data sources. re-training the well surveillance models by tuning the weights and hyperparameters in the models, modifying the machine learning technique used in the models and changing the features used in the models; para. 0048 – Models for forecasting the well performance are physics-guided artificial neural network (ANN) models that incorporate the physics-based model equations corresponding to multiphase flow in the wells. Models for estimating the health of well and wellhead assets are built using one or more of the statistical and machine learning techniques including ... artificial neural networks and its variants. Models for estimating the health of well and wellhead assets are built using one or more of the statistical and machine learning techniques; para. 0053 - initially the plurality of physics-guided well surveillance model generation is a one-time process, but later plurality of physics-guided well surveillance model can be retrained or retuned whenever there is a performance drop. The plurality of parameters comprises: a flow rate of oil, gas and brine coming out of each well in the connected oil and gas wells, a pressure, temperature distribution and velocity distribution in the multiphase flow from each well of the connected oil and gas wells.).
Accordingly, it would have been obvious to one having ordinary skill before the effective filing date of the claimed invention to modify the system and method, taught in An, to include applying the second ML sub-model to acquired real-time well dynamic data for the purpose of efficiently training and retraining models for well asset including choke valves based on large amounts of pertinent data, improving model performance to provide diagnostics and prediction, as taught by Nistala (0035, 0037, 0048).
Claim(s) 11:
Claim(s) 11 correspond to Claim 4, and thus, An and Nistala teach or suggest the limitations of claim(s) 11 as well.
Claim 5:
An further teaches or suggests wherein the ... sub-model is constructed by algorithms ... configured to receive the real-time well dynamic data (see Fig. 5, 10-12; para. 0040 - FIG. 5 shows a graph 595 of a performance curve 563 for a choke valve (e.g., choke valve 370); para. 0045 - provide for real time evaluation of the performance of a choke valve; para. 0042 - a choke valve 670, one or more sensor devices 660-1 located upstream of the choke valve 670, and one or more sensor devices 660-2 located downstream of the choke valve 670; para. 0044 - parameters that can be used for differential measurement include, but are not limited to, pressure; para. 0056 - sensor measurements to evaluate the performance of the choke valve 670 during a subterranean field operation in real time; configured to determine and communicate, in real time. model that estimates, in real time, a flow area through the choke valve 670 in real time using parameters (e.g., pressure, temperature, flow rate, flow properties) measured by at least some of the sensor devices 660; para. 0061 - algorithms 733 of the storage repository 730 can be any formulas, mathematical models, forecasts, simulations, and/or other similar tools that the control engine 706 of the controller 704 uses to reach a computational conclusion. model that estimates, in real time, a flow area through the choke valve 670 in real time using parameters (e.g., pressure, temperature, flow rate, flow properties) measured by at least some of the sensor devices 660; para. 0062 - one or more algorithms 733 can be or include a model that determines an amount of adjustment of the position of the plug of the choke valve 670 that should be made to extend the useful life of the choke valve 670 by reducing the amount of erosion or obstruction that the choke valve 670 experiences; para. 0063 - Such data can be any type of data, including but not limited to historical data, current data, and forecasts; para. 0070 - estimate, in real time, a flow area through the choke valve 670 in real time using parameters (e.g., pressure, temperature, flow rate) measured by at least some of the sensor devices 660; para. 0112 - measurements can be differential measurements of parameters (e.g., pressure, temperature, flow rate) made by the sensor devices 660-1 (downstream of the choke valve 670) and the sensor devices 660-2 (upstream of the choke valve 670). three of the sensor devices 660-1 can measure pressure, temperature, flow rate upstream of the choke valve 670 at a point in time, and three of the sensor devices 660-2 can measure pressure, temperature, flow rate downstream of the choke valve 670; para. 0134 - provide for real time evaluation of the performance of a choke valve; Claims 4, 5.).
Nistala further teaches or suggests wherein the ML sub-model is constructed by training algorithms configured to receive real-time well dynamic data (see para. 0007 - the plurality of parameters comprises: a flow rate of oil, gas and brine produced from each well in the connected oil and gas wells, a pressure, a temperature distribution and a velocity distribution in multiphase flow from each well of the connected oil and gas wells; para. 0031 - parameters comprises: a mass flow rate of oil, gas and brine coming out from each well of the connected oil and gas wells, a pressure and temperature, and velocity distribution in the multiphase flow from each well of the connected oil and gas wells; para. 0032 - well and wellhead assets include such as choke control valves; para. 0035 – Real time diagnostics of performance drift is performed using data-driven diagnostic models built using one or more of the statistical and machine learning techniques; para. 0037 - configured to monitor performance of all well surveillance models in real-time using actual measurements, whenever available, to detect drifts/drop in accuracy. Self-learning is performed using the historical as well as the latest available data from all the data sources. re-training the well surveillance models by tuning the weights and hyperparameters in the models, modifying the machine learning technique used in the models and changing the features used in the models; para. 0048 – Models for forecasting the well performance are physics-guided artificial neural network (ANN) models that incorporate the physics-based model equations corresponding to multiphase flow in the wells. Models for estimating the health of well and wellhead assets are built using one or more of the statistical and machine learning techniques including ... artificial neural networks and its variants; para. 0053 - initially the plurality of physics-guided well surveillance model generation is a one-time process, but later plurality of physics-guided well surveillance model can be retrained or retuned whenever there is a performance drop. The plurality of parameters comprises: a flow rate of oil, gas and brine coming out of each well in the connected oil and gas wells, a pressure, temperature distribution and velocity distribution in the multiphase flow from each well of the connected oil and gas wells.).
Accordingly, it would have been obvious to one having ordinary skill before the effective filing date of the claimed invention to modify the system and method, taught in An, to include wherein the ML sub-model is constructed by training algorithms configured to receive real-time well dynamic data for the purpose of efficiently training and retraining models for well assets including choke valves based on large amounts of pertinent data, improving model performance, as taught by Nistala (0035, 0037, 0048).
Claim(s) 12:
Claim(s) 12 correspond to Claim 5, and thus, An and Nistala teach or suggest the limitations of claim(s) 12 as well.
Claim 6:
Nistala further teaches or suggests wherein the training algorithms are selected from XGboost, artificial neural networks (ANN), and recurrent neural networks (see para. 0032 - well and wellhead assets include such as choke control valves; para. 0035 – Real time diagnostics of performance drift is performed using data-driven diagnostic models built using one or more of the statistical and machine learning techniques; para. 0037 - configured to monitor performance of all well surveillance models in real-time using actual measurements, whenever available, to detect drifts/drop in accuracy. Self-learning is performed using the historical as well as the latest available data from all the data sources. re-training the well surveillance models by tuning the weights and hyperparameters in the models, modifying the machine learning technique used in the models and changing the features used in the models; para. 0048 – Models for forecasting the well performance are physics-guided artificial neural network (ANN) models that incorporate the physics-based model equations corresponding to multiphase flow in the wells. TheANNs used in the well surveillance models include multilayer perceptron and recurrent neural network and its variants. Models for estimating the health of well and wellhead assets are built using one or more of the statistical and machine learning techniques including ... artificial neural networks and its variants.).
Accordingly, it would have been obvious to one having ordinary skill before the effective filing date of the claimed invention to modify the system and method, taught in An, to include wherein the training algorithms are selected from XGboost, artificial neural networks (ANN), and recurrent neural networks for the purpose of efficiently training and retraining models for well assets including choke valves based on large amounts of pertinent data, improving model performance, as taught by Nistala (0035, 0037, 0048).
Claim(s) 13:
Claim(s) 13 correspond to Claim 6, and thus, An and Nistala teach or suggest the limitations of claim(s) 13 as well.
Claim 7:
Nistala further teaches or suggests wherein the training algorithms are selected from XGboost, artificial neural networks (ANN), recurrent neural networks (see para. 0032 - well and wellhead assets include such as choke control valves; para. 0035 – Real time diagnostics of performance drift is performed using data-driven diagnostic models built using one or more of the statistical and machine learning techniques; para. 0037 - configured to monitor performance of all well surveillance models in real-time using actual measurements, whenever available, to detect drifts/drop in accuracy. Self-learning is performed using the historical as well as the latest available data from all the data sources. re-training the well surveillance models by tuning the weights and hyperparameters in the models, modifying the machine learning technique used in the models and changing the features used in the models; para. 0048 – Models for forecasting the well performance are physics-guided artificial neural network (ANN) models that incorporate the physics-based model equations corresponding to multiphase flow in the wells. TheANNs used in the well surveillance models include multilayer perceptron and recurrent neural network and its variants. Models for estimating the health of well and wellhead assets are built using one or more of the statistical and machine learning techniques including ... artificial neural networks and its variants.).
Accordingly, it would have been obvious to one having ordinary skill before the effective filing date of the claimed invention to modify the system and method, taught in An, to include wherein the training algorithms are selected from XGboost, artificial neural networks (ANN), recurrent neural networks for the purpose of efficiently training and retraining models for well assets including choke valves based on large amounts of pertinent data, improving model performance, as taught by Nistala (0035, 0037, 0048).
Claim(s) 14:
Claim(s) 14 correspond to Claim 7, and thus, An and Nistala teach or suggest the limitations of claim(s) 14 as well.
Response to Arguments
Rejections under 35 USC 101:
Applicant argues the claims do not recite a mental process.
The Examiner respectfully disagrees. As indicated above, claim 1 recites the following judicial exceptions: determining a choke opening baseline (mental process –can be performed in the human mind, or by a human using a pen and paper (e.g. a person may use data to determine valve opening baseline information.); determining a ... choke opening curve (mental process –can be performed in the human mind, or by a human using a pen and paper (e.g. a person may use data to determine and plot a choke valve opening curve.); comparing the choke opening baseline to the ... choke opening curve (mental process –can be performed in the human mind, or by a human using a pen and paper (e.g. a person may use data to determine valve opening baseline information, use data to determine and plot a choke valve opening curve, and then compare); providing an assessment of choke lifetime as a function of said comparing (see mental process –can be performed in the human mind, or by a human using a pen and paper (e.g. a person may use data to determine valve opening baseline information, use data to determine and plot a choke valve opening curve, compare, and then produce an evaluation of choke lifespan based on the comparison.). The Examiner notes the claims do recite limitations amounting to a mental process.
Applicant argues the claims are such that the judicial exception is integrated into a practical application. The Examiner respectfully disagrees. Claim 1 includes additional elements including by applying a first machine learning (ML) model to acquired real-time well dynamic data including flowrate, choke upstream pressure (U/S) and temperature and choke downstream (D/S) pressure and temperature as input and by applying a second ML sub-model to the acquired real-time well dynamic data. The Examiner notes these elements appear to be mere instructions to apply the exception or implement the exception on a computer (e.g. – a computer with a generic machine learning algorithm may be used to carry out the judicial exception at the time the data is recieved; see MPEP §2106.05(f).), and merely generally link the use of a judicial exception to a particular technological environment or field of use (e.g. using machine learning algorithm; see MPEP §2106.05(h).). These additional elements do not effectively integrate the abstract idea into a practical application. 2B: revisiting the additional elements, the additional elements do not amount to significantly more than the judicial exception – recited high level of generality and corresponds to storing and retrieving information and performing calculations. Further, claim 1 includes the additional elements of a realtime ... realtime. The Examiner notes these elements appear to correspond to mere instructions to apply the exception or implement the exception on a computer (e.g. – a computer may be used to carry out the judicial exception at the time the data is recieved; see MPEP §2106.05(f).). The additional elements do not effectively integrate the abstract idea into a practical application. 2B: revisiting the additional elements, the additional elements do not amount to significantly more than the judicial exception – recited high level of generality and corresponds to storing and retrieving information in memory and performing calculations.).
The Applicant argues the ordered combination amounts to significantly more. The Examiner respectfully disagrees. Claim 1 appears to merely correspond to data collection and data analytics and the integration of generic machine learning concepts, and thus, not amounting to significantly more than the judicial exception.
Rejections under 35 USC 103:
Applicant argues the combined teachings of An and Nistala to not disclose, teach, or suggest: (1) a first ML model trained on historical well-specific data – including well completion size and type, produced gas properties, and choke type and size – and applied to real-time well dynamic data to generate choke opening percentage baseline; (2) a second ML sub-model applied to real-time well dynamic data to generate a realtime choke opening percentage curve; and (3) an assessment of choke lifetime as a function of the comparison between those two choke opening percentage curves.
The Examiner respectfully disagrees.
An teaches pressure and/or other factors that can lead to a pressure, a flow rate, a temperature, and flow properties. Para. 0043. Further, Stored data 734 of the storage repository 730 can be any data (e.g., nameplate data, manufacturing information) associated with a component (e.g., each sensor device 660, the choke valve 670) of the system 600 used during a subterranean field operation, any measurements made by the sensor devices 660, threshold values, PVT tables for one or more subterranean fields, results of previously run or calculated algorithms 733, data (e.g., sensor measurements, results of algorithms, predicted flow area through a choke valve, estimated flow area through a choke valve) associated with other field operations having subterranean characteristics and/or choke valves similar to those of the present subterranean field operation. Para. 0064. Such data can be any type of data, including but not limited to historical data, current data, and forecasts. Id. Further, measurements of parameters (e.g., flow rate, temperature, pressure) made by the sensor devices 660, the position of the choke valve 670, nameplate data for the choke valve 670, manufacturing performance curves for the choke valve 670, historical data associated with other choke valves having the same make and manufacturer as the choke valve 670 used in the present subterranean field operation, and data associated with other subterranean field operations. Para. 0108. Further, used to provide for real time evaluation of the performance of a choke valve used in subterranean field operations, particularly when the choke valve is part of a Christmas tree. Para. 0134. The Examiner notes An teaches well related models for performing analytics that are generated based on the data types cited in these sections, data indicative of well sizes and types, gas properties, and choke sizes and types. Nistala teaches parameters comprises: a mass flow rate of oil, gas and brine coming out from each well of the connected oil and gas wells, a pressure and temperature, and velocity distribution in the multiphase flow from each well of the connected oil and gas wells. Para. 0031. Further, Real time diagnostics of performance drift is performed using data-driven diagnostic models built using one or more of the statistical and machine learning techniques. Para. 0035. Further, Models for forecasting the well performance are physics-guided artificial neural network (ANN) models that incorporate the physics-based model equations corresponding to multiphase flow in the wells. Para. 0048. Models for estimating the health of well and wellhead assets are built using one or more of the statistical and machine learning techniques including ... artificial neural networks and its variants. Id. Models for estimating the health of well and wellhead assets are built using one or more of the statistical and machine learning techniques. Id. The Examiner notes Nistala teaches the generation of multiple machine learning models based on well related data for well monitoring and analytics purposes. One of ordinary skill in the art would find it obvious to combine the machine learning aspects of Nistala to the specific well monitoring and analytics models of An. Accordingly, the combination of An and Nistala teaches or suggests (1) a first ML model trained on historical well-specific data – including well completion size and type, produced gas properties, and choke type and size – and applied to real-time well dynamic data.
Further, An teaches a previously-established performance curve corresponding to a predicted flow area of the choke valve 670. Para. 0042. Further, one or more algorithms 733 can be or include a model that determines an amount of adjustment of the position of the plug of the choke valve 670 that should be made to extend the useful life. Para. 0062. Further, Such data can be any type of data, including but not limited to historical data, current data, and forecasts. Para. 0063. Further, baseline performance data of a choke valve 670 during a first time period is collected. Para. 0107. Further, collecting baseline performance data for the choke valve during a first time period during the field operation, wherein the choke valve has a fluid flowing therethrough during the first time period. Claim 1. These sections describe collecting and analyzing baseline data or data from a first time period related to choke opening and other well related collected data in order to make determinations related to the usefule life of the choke valve. Further, Fig. 5 and 10 describe choke valve openness percentage. Accordingly, An teaches or suggests to generate choke opening percentage baseline.
Further, An teaches provide for real time evaluation of the performance of a choke valve. Para. 0045. Further, sensor measurements to evaluate the performance of the choke valve 670 during a subterranean field operation in real time. Para. 0056. Further, configured to determine and communicate, in real time, an adjustment that can be made to the choke valve 670 to improve the performance of the choke valve 670 and extend the useful life of the choke valve 670. Id. The controller can further be configured to adjust a performance curve of the choke valve 670. Id. Further, based on an estimated flow area of the choke valve 670 (using measurements made by the sensor devices 660) and a previously-established performance curve corresponding to a predicted flow area of the choke valve 670. Id. Further, model that estimates, in real time, a flow area through the choke valve 670 in real time using parameters. Para. 0061. Further, provide for real time evaluation of the performance of a choke valve. Para. 0134. Further, Fig. 5 and 10 describe choke valve openness percentage. The Examiner notes these sections describe models applied to real-time well data and choke opening percentage plots related to the data. Accordingly, An teaches or suggests sub-model applied to real-time well dynamic data to generate a realtime choke opening percentage curve. Nistala teaches parameters comprises: a mass flow rate of oil, gas and brine coming out from each well of the connected oil and gas wells, a pressure and temperature, and velocity distribution in the multiphase flow from each well of the connected oil and gas wells. Para. 0031. Further, Real time diagnostics of performance drift is performed using data-driven diagnostic models built using one or more of the statistical and machine learning techniques. Para. 0035. Further, Models for forecasting the well performance are physics-guided artificial neural network (ANN) models that incorporate the physics-based model equations corresponding to multiphase flow in the wells. Para. 0048. Models for estimating the health of well and wellhead assets are built using one or more of the statistical and machine learning techniques including ... artificial neural networks and its variants. Id. Models for estimating the health of well and wellhead assets are built using one or more of the statistical and machine learning techniques. Id. The Examiner notes Nistala teaches the generation of multiple machine learning models based on well related data for well monitoring and analytics purposes. Accordingly, Nistala teaches or suggests (2) a second ML sub-model applied to real-time well dynamic data. One of ordinary skill in the art would find it obvious to combine the machine learning aspects of Nistala to the specific well monitoring and analytics models of An. Accordingly, the combination of An and Nistala teaches or suggests (2) a second ML sub-model applied to real-time well dynamic data to generate a realtime choke opening percentage curve.
An further teaches provide for real time evaluation of the performance of a choke valve. Para. 0045. Further, sensor measurements to evaluate the performance of the choke valve 670 during a subterranean field operation in real time. Para. 0056. Further, configured to determine and communicate, in real time, an adjustment that can be made to the choke valve 670 to improve the performance of the choke valve 670 and extend the useful life of the choke valve 670. Id. The controller can further be configured to adjust a performance curve of the choke valve 670. Id. Further, based on an estimated flow area of the choke valve 670 (using measurements made by the sensor devices 660) and a previously-established performance curve corresponding to a predicted flow area of the choke valve 670. Id. Further, communication can be generated by the controller 704 and sent to one or more users 750 to communicate that the performance of the choke valve 670 is no longer within a range of acceptable performance values. Para. 0116. This communication can include any of a number of different types of information, including but not limited to a basic statement that the choke valve 670 is failing or operating sub-optimally, whether the choke valve 670 is experiencing erosion or congestion, the severity of the erosion or congestion of the choke valve 670, and specific actions. Id. The Examiner notes An collects and analyzes baseline data, collects and analyzes real-time data, and uses models to perform analytics using the baseline and real-time data of the choke and make determinations based on the analytics. Accordingly, An teaches or suggests (3) an assessment of choke lifetime as a function of the comparison between those two choke opening percentage curves.
Applicant argues the Examiner’s motivation to combine is insufficient. The Examiner respectfully disagrees. As indicated above, An teaches or suggests collecting well data and generating and using models for management of a well. Nistala teaches Real time diagnostics of performance drift is performed using data-driven diagnostic models built using one or more of the statistical and machine learning techniques. Para. 0035. Further, model performance monitoring and self-learning module 132 is configured to monitor performance of all well surveillance models in real-time using actual measurements. Para. 0037. Further, Models for forecasting the well performance are physics-guided artificial neural network (ANN) models that incorporate the physics-based model equations corresponding to multiphase flow in the wells. Para. 0048. Models for estimating the health of well and wellhead assets are built using one or more of the statistical and machine learning techniques including ... artificial neural networks and its variants. Id. Models for estimating the health of well and wellhead assets are built using one or more of the statistical and machine learning techniques. Id. The Examiner notes these sections describe training multiple machine learning models using well asset data to provide well related diagnostics and prediction. The Office Action recites, as motivation to combine, “for the purpose of efficiently training and retraining models for well asset including choke valves based on large amounts of pertinent data, improving model performance to provide diagnostics and prediction, as taught by Nistala (0035, 0037, 0048).” The stated motivation is sufficient and one of ordinary skill in the art would have found it obvious at the time of the invention to combine the teachings, as Nistala specifically uses multiple machine learning models for well related management that would improve the well analysis and management models of An.
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 Andrew T McIntosh whose telephone number is (571)270-7790. The examiner can normally be reached M-Th 8:00am-5:30pm.
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, Tamara Kyle can be reached at 571-272-4241. 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.
/ANDREW T MCINTOSH/Primary Examiner, Art Unit 2144
Prosecution Insights