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 .
Response to Amendment
This Office Action has been issued in response to amendment filed 04/24/2026. Applicant's arguments have been carefully and fully considered; and they are persuasive. Therefore, the rejection has been withdrawn. However, upon further consideration, a new ground(s) of rejection is made. Accordingly, this action has been made FINAL.
Claim Status
Claims 1-2, 9-10, and 17-18 have been amended. Claims 1-20 remain pending and are ready for examination.
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, 9, and 17 is/are rejected under 35 U.S.C. 103 as being unpatentable over Beck et al. (US20210071508A1 -hereinafter Beck) in view of Ahmari (US20220003071A1 -hereinafter Ahmari) in view of Kwon et al. (KR101706245B1 -hereinafter Kwon -Note: As the machine translation attached).
Regarding Claim 1, Beck teaches a method for controlling an electric submersible pump (ESP) installed in a wellbore (see [0001]; Beck: “controlling operation of electric submersible pumps (ESP) using deep learning models.”), the method comprising:
providing… the target production rate as input to a neural network (see [0018]; Beck: “In centralized control, a deep learning model associated with a motor controller of an ESP receives various inputs. The various inputs include one or more of operating conditions, application input, supervisory input, model inputs, and a goal set associated with fluid production from the geologic formation.” See [0029]: “The deep learning model 134, 136 is a neural network…”) that provides as output ESP operating parameters to achieve the target production rate (see [0039]; Beck: “The goal set 212 would be input into the deep learning model so that the deep learning model 202 can generate outputs for controlling the ESP to meet the desired operating conditions in the goal set.”), the ESP operating parameters comprising …a motor speed (see [0042]; Beck: “The operating parameters may impact how long an ESP should pump fluid, at which rate, motor speed etc. to meet fluid production objectives.”), and the neural network modeling an ESP- equipped wellbore; and (see [0017]; Beck: “The deep learning model allows for intelligent control of the ESP to meet fluid production goals of the wellbore and well system”).
controlling the ESP to operate according to the ESP operating parameters. (see [0049]; Beck: “At 306, operation of the ESP may be adjusted based on the output.” See [0050]: “The operating parameters output may produce not only a desired change in fluid production of a given ESP but also a desired change in fluid production by the reservoir.”)
However, Beck does not explicitly teach:
determining, during a production phase of the wellbore, a target production rate for the wellbore, the target production rate being different from a current production rate;
providing the current production rate …as input to a neural network…
…comprising a choke size percentage…
Ahmari from the same or similar field of endeavor teaches:
determining, during a production phase of the wellbore (see [0028]; Ahmari: “the production system 124 includes devices that facilitate that extraction of production from the reservoir 102 by way of the wellbore 120.” See [0004]: “during production operations,”), a target production rate for the wellbore (see Abstract; Ahmari: “receive (from a well control system) a target production rate”), the target production rate being different from a current production rate; (see [0029]; Ahmari: “The flowrate of production may be referred to as the “production rate” (or “flowrate”) of the well 106.” See [0046]: “if the production rate of the well 106 has averaged 3,500 STB/day from 1:00 pm-2:00 pm, and the production data 160 indicates a current production rate of the well 106 of 4,000 STB/day at 2:00 pm, it may be determined that there has been a deviation in the production rate of the well 106.” See [0049]: “method 400 includes determining a target operating parameter for the well (block 410). This may include determining a desired operating parameter, such as a target production rate for the well. For example, determining a target operating parameter for the well may include the choke valve control system 152 receiving, from the well control system 122, a target production rate (e.g., 3,500 STB/day).”)
…comprising a choke size percentage… (see [0041]; Ahmari: “the ANN may output a well profile 162 for the well 106 includes a well rate-pressure profile 180 and a well pressure-choke profile 182 for each of some or all of the possible sets/combinations of well conditions.” See [0035]: “For example, the choke valve 150 may have eleven positions (or “states” or “settings”), 0-10, with position 0 being a 0% open position (or a “fully-closed” position), each of positions 1-9 providing sequentially increasing degrees of opening of the flow area of the choke valve 150, and state 10 being a 100% open position (or a “fully-opened” position).”)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to modify the teaching of Beck to include Ahmari’s features of determining, during a production phase of the wellbore, a target production rate for the wellbore, the target production rate being different from a current production rate; and comprising a choke size percentage. Doing so would optimize the overall production of hydrocarbons from the reservoir. (Ahmari, [0004])
However, it does not explicitly teach: providing the current production rate …as input to a neural network…
Kwon from the same or similar field of endeavor teaches: providing the current production rate …as input to a neural network… (see page 3, paragraphs 5-6; Kwon: “The data collecting step is configured to acquire various data generated during the production and operation of the oil or the gas by real-time monitoring through the Internet or the wireless Internet provided in the digital oil field. Also, in the artificial neural network model building step, the artificial neural network model includes, as the input data, the oil flow rate, the gas flow rate, and the water flow rate at the dongle, and the output data includes the head temperature, the head pressure, and a choke size.”)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to modify the teachings of Beck and Ahmari to include Kwon’s features of providing the current production rate as input to a neural network. Doing so would using an artificial neural network in a digital oil field to reduce time and cost for choke size control. (Kwon, page 3, second paragraph)
Regarding Claim 9, the limitations in this claim is taught by the combination of Beck, Ahmari, and Kwon as discussed connection with claim 1.
Regarding Claim 17, the limitations in this claim is taught by the combination of Beck, Ahmari, and Kwon as discussed connection with claim 1.
Claim(s) 2, 10, and 18 is/are rejected under 35 U.S.C. 103 as being unpatentable over Beck in view of Ahmari in view of Kwon view of Dufour et al. (US20210285605A1 -hereinafter Dufour).
Regarding Claim 2, the combination of Beck, Ahmari, and Kwon teaches all the limitations of claim 1 above, Beck further teaches wherein the input to the neural network further comprises a real- time data comprising: an intake pressure (see [0027]; Beck: “the downhole sensors 108 may provide measurement data related to operating conditions downhole in and around the ESP 150 such as … pump intake pressure.”), an ESP motor load, (see [0019]: Beck: the computational loads on each motor controller”)
Ahmari further teaches …a water cut, (see [0006]; Ahmari: “a control system of a smart choke valve system of a hydrocarbon well may collect production data directly from productions sensors (e.g., flowrate, pressure, temperature, water cut and gas-oil-ratio (GOR) data for production fluid of the well obtained from respective flowrate, pressure, temperature, water cut and GOR sensors of the well)”)
The same motivation to combine Beck and Ahmari a set forth for Claim 1 equally applies to Claim 2.
However, it does not explicitly teach: …and an upstream-downstream (US/DS) differential pressure (DP).
Dufour from the same or similar field of endeavor teaches …and an upstream-downstream (US/DS) differential pressure (DP). (see [0203]; Dufour: “All the flow rate calculation methods are based on the upstream pressure (and/or the downstream pressure) and the upstream/downstream pressure differential of the element on which the flow rate will be modeled.”)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to modify the teaching of Beck, Ahmari, and Kwon to include Dufour’s features of an upstream-downstream (US/DS) differential pressure (DP). Doing so would optimize an energy and/or economic cost factor. Dufour, [0244])
Regarding Claim 10, the limitations in this claim is taught by the combination of Beck, Ahmari, Kwon, and Dufour as discussed connection with claim 2.
Regarding Claim 18, the limitations in this claim is taught by the combination of Beck, Ahmari, Kwon, and Dufour as discussed connection with claim 2.
Claim(s) 3-6, 11-14, and 19-20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Beck in view of Ahmari in view of Kwon in view of AlAjmi et al. (US20170293835A1 -hereinafter AlAjmi).
Regarding Claim 3, the combination of Beck, Ahmari, and Kwon teaches all the limitations of claim 1 above; however, it does not explicitly teach wherein the neural network is trained based on historical production data.
AlAjmi from the same or similar field of endeavor teaches wherein the neural network is trained based on historical production data. (see [0004]; AlAjmi: “building a feed-forward back propagation neural network; calibrating the simulation model utilizing actual production history from the training data set;”)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to modify the teaching of Beck, Ahmari, and Kwon to include AlAjmi’s features of the neural network is trained based on historical production data. Doing so would produce the most accurate output and improve the network prediction performance. (AlAjmi, [0069] and [0075])
Regarding Claim 4, the combination of Beck, Ahmari, and Kwon teaches all the limitations of claim 1 above; however, it does not explicitly teach: wherein generating the neural network comprises: obtaining historical production data comprising data points associated with respective wells, each data point comprising at least one of oil production rate, a water cut, an intake pressure, an ESP motor load, or an upstream-downstream (US/DS) differential pressure (DP); splitting the historical production into training data and testing data; and iteratively training the neural network using the training data to generate the neural network.
AlAjmi from the same or similar field of endeavor teaches wherein generating the neural network comprises:
obtaining historical production data comprising data points associated with respective wells (see [0088]; AlAjmi: “At 504, the oil production rate test data are collected, uploaded, and divided into subsets by a downstream-to-upstream pressure ratio.”), each data point comprising at least one of oil production rate, a water cut, an intake pressure, an ESP motor load, or an upstream-downstream (US/DS) differential pressure (DP); (see Abstract; AlAjmi: “The oil production rate test data are collected, uploaded, and divided into subsets by a downstream-to-upstream pressure ratio.”)
splitting the historical production into training data and testing data; and (see [0092]; AlAjmi: “At 512, the simulation model is calibrated utilizing actual production history from the training data set.” See [0093]: “At 514, the model performance is tested utilizing actual production history from the testing data set.” See [0089]: “At 508, for each subset-split, the data is split randomly into training data sets and testing data sets.”)
iteratively training the neural network using the training data to generate the neural network. (see [0072]; AiAjmi: “An iterative process, that is indicated by FIG. 2 for example, can minimize any resulting error. Once the network is trained, a testing dataset can be introduced to the ANN model to predict the outputs and to validate the ANN model's performance.”)
The same motivation to combine Beck, Ahmari, Kwon, and AiAjmi a set forth for Claim 3 equally applies to Claim 4.
Regarding Claim 5, the combination of Beck, Ahmari, Kwon, and AiAjmi teaches all the limitations of claim 4 above, Beck further teaches wherein iteratively training the neural network comprises:
creating the neural network; (see [0081]; Beck: “At 902, an initial deep learning model may be defined.”)
defining initial hyperparameters for the neural network; (see [0081]; Beck: “The initial deep learning model may be a neural network with more than two hidden layers.”) the hidden layers reads on ‘initial hyperparameters’]
training the neural network based on the training data; (see [0081]; Beck: “at 904, the training dataset may be input into the initial deep learning model.”)
determining, based on at least one performance indicator, whether the training of the neural network is complete; (see [0081]; Beck: “At 908, the output is compared to the goal set.”)
if the training the neural network is complete, deploying the neural network; and (see [0081]; Beck: “The training data may be input into the deep learning model and steps 904 to 910 iteratively carried out until the output matches the goal data.” See [0080]: “the submodel and/or ESP/well specific deep learning model may be trained on the centralized computer system and then sent to the respective motor controller to control the ESP.”)
if the training the neural network is incomplete, returning to training the neural network using the training data to generate new hyperparameter values for the neural network. (see [0081]; Beck: “The training data may be input into the deep learning model and steps 904 to 910 iteratively carried out until the output matches the goal data.” See [0082]: “The more than two layers of the deep learning model allow for modeling the changing conditions in the wellbore over time.”)
Regarding Claim 6, the combination of Beck, Ahmari, Kwon, and AiAjmi teaches all the limitations of claim 5 above, Beck further teaches wherein determining, based on at least one performance indicator, whether the training of the neural network is complete comprises: determining whether the at least one performance indicator satisfies a respective threshold. (see [0081]; Beck: “At 908, the output is compared to the goal set. At 910, revisions of deep learning model may be made, e.g. by adaptation of the neural network associated with the deep learning model, in an iterative process to refine the deep learning model by the comparison of the output to the goal data. For example, the comparison may be classified in terms of a level of match such as correlation. If the correlation is less than a threshold amount, further analysis may be undertaken, e.g. the deep learning model may be adapted by adjusting the weights of the neural network, either by the model itself or by another process or by human intervention until the output matches the goal data.”)
Regarding Claim 11, the limitations in this claim is taught by the combination of Beck, Ahmari, Kwon, and AiAjmi as discussed connection with claim 3.
Regarding Claim 12, the limitations in this claim is taught by the combination of Beck, Ahmari, Kwon, and AiAjmi as discussed connection with claim 4.
Regarding Claim 13, the limitations in this claim is taught by the combination of Beck, Ahmari, Kwon, and AiAjmi as discussed connection with claim 5.
Regarding Claim 14, the limitations in this claim is taught by the combination of Beck, Ahmari, Kwon, and AiAjmi as discussed connection with claim 6.
Regarding Claim 19, the limitations in this claim is taught by the combination of Beck, Ahmari, Kwon, and AiAjmi as discussed connection with claim 3.
Regarding Claim 20, the limitations in this claim is taught by the combination of Beck, Ahmari, Kwon, and AiAjmi as discussed connection with claim 4.
Claim(s) 7-8 and 15-16 is/are rejected under 35 U.S.C. 103 as being unpatentable over Beck in view of Ahmari in view of Kwon in view of AiAjmi in view of Koch et al. (US20180240041A1 -hereinafter Koch).
Regarding Claim 7, the combination of Beck, Ahmari, Kwon, and AiAjmi teaches all the limitations of claim 5 above, Beck further teaches wherein the at least one performance indicator comprises at least one of a correlation coefficient (CC) (see [0081]; Beck: “the comparison may be classified in terms of a level of match such as correlation.”),
However, it does not explicitly teach: a root mean squared error (RMSE), or an average absolute percentage error (AAPE).
Koch from the same or similar field of endeavor teaches a root mean squared error (RMSE) (see [0080]; Koch: “The FACTMAC procedure computes the biases and factors by using a stochastic gradient descent (SGD) algorithm that minimizes a root mean square error (RMSE) criterion.”), or an average absolute percentage error (AAPE).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to modify the teaching of Beck, Ahmari, Kwon, and AiAjmi to include Koch’s features of a root mean squared error (RMSE). Doing so would determine the best model configuration and govern the quality of the resulting predictive models. (Koch, [0002]-[0003])
Regarding Claim 8, the combination of Beck, Ahmari, Kwon, and AiAjmi teaches all the limitations of claim 4 above, Beck further teaches wherein the initial hyperparameters comprise a number of neuron layers (see [0109]; Beck: “the first deep learning model is a neural network with more than two hidden layers.”),
However, it does not explicitly teach a number of neurons per layer, and a seed number for the neural network.
Koch from the same or similar field of endeavor teaches a number of neurons per layer (see [0003]; Koch: “a number of hidden layers and neurons in each layer in a neural network model type”), and a seed number for the neural network. (see [0131]; Koch: “a random seed value may be specified”)
The same motivation to combine Beck, Ahmari, Kwon, AiAjmi, and Koch a set forth for Claim 7 equally applies to Claim 8.
Regarding Claim 15, the limitations in this claim is taught by the combination of Beck, Ahmari, Kwon, AiAjmi, and Koch as discussed connection with claim 7.
Regarding Claim 16, the limitations in this claim is taught by the combination of Beck, Ahmari, Kwon, AiAjmi, and Koch as discussed connection with claim 8.
Response to Arguments
Applicant’s arguments with respect to the claim rejection(s) of the independent claim(s) have been fully considered and are persuasive because of the amendments. Therefore, the rejection has been withdrawn. However, upon further consideration, a new ground(s) of rejection is made.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Jamison et al. (US20130318019A1) discloses once the artificial neural network is trained, a formation characteristic of the target formation and fluid characteristic of target drilling fluid may be input.
AI-Harbi (US11087221B2) discloses the proposed well performance parameters include target well production rates and a proposed configuration and location of the well in the reservoir.
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to VI N TRAN whose telephone number is (571)272-1108. The examiner can normally be reached Mon-Fri 9:00-5:00.
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, ROBERT FENNEMA can be reached at (571) 272-2748. 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.
/V.N.T./Examiner, Art Unit 2117
/ROBERT E FENNEMA/Supervisory Patent Examiner, Art Unit 2117
Prosecution Insights