DETAILED ACTION
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Responsive to the communication dated 8/5/2026.
Claims 1, 8,15 are amended.
Claims 6, 13, 19 are cancelled.
Claims 21, 22, 23 are newly presented.
Claims 1 – 5, 7 – 12, 14 – 18, 20 - 23 are presented for examination.
Final Action
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.
Response to Arguments
Rejection under 35 USC 103
The Applicant has amended the independent claims. A new ground of rejection is presented below.
The Applicant has added new claims 21, 22, and 23. The claims are further rejected as shown in the body of the Office action.
End Response to Arguments
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.
Claims 1 – 5, 7 – 12, 14 – 18, 20, 21 are rejected under 35 U.S.C. 103 as being unpatentable over Kulkarni_2021 (US 2021/0404334 A1) in view of Jamison_2012 (US 2012/0094876 A1) in view of Chen_2022 (Optimization Design of Drilling Fluid Chemical Formula Based on Artificial Intelligence, Computational Intelligence and Neuroscience, October 4, 2022).
Claim 1. Kulkarni_2021 makes obvious “A system comprising: A processing device; and
A memory device that includes instructions executable by the processing device for causing the processing device to:” (par 19 - 21: “FIG. 2 is a block diagram of a drilling fluid analysis and control system according to at least one aspect of the disclosure… device 204 can include one or more processors 208 coupled to memory 216 through a bus 212. Memory 216 may be a non-transitory computer-readable medium… memory 216 stores instructions 220 and one or more interfaces 224 such as application programming interfaces and data interfaces that enable receiving or exporting data… can include one or more sets of instructions that execute using one or more processors 208…”; par 63: “in some aspects, systems and methods for analyzing and controlling drilling fluids are provided…”; par 87: “… embodiments may be implemented by hardware, software, scripting languages, firmware, middleware, microcode, hardware description languages, or any combination thereof, the program code or code segments to perform the necessary tasks may be stored in a machine readable medium…”; par 88: “… implementations in firmware, software, or combinations thereof, the methodologies may be implemented… any machine-readable medium tangibly embodying instructions may be used in implementing the methodologies described herein…”) Receive a set of target fluid properties for a downhole drilling fluid as input from a user (FIG. 5 block 520: “receiving a target property value corresponding to an optimal value of a property of the water-based drilling fluid”; par 12: “… the fluid analyzer receives a target property value that corresponds to an optimal value of a property of the water-based drilling fluid…”; par 31: “… drilling system 248 may receive an indication of the particular composition of drilling fluid that is to be used in drilling operations or a request to modify the drilling fluid that is currently in use from drilling system control 244…”; par 56: “… at block 520, a target property value is received. The target property value may be an optimal value for a property of the drill fluid…”; par 57: “… in some instances, the new target property value may be received automatically upon one or more sensors in the wellbore detecting a change in the drilling operations or subterranean environment. In other instances, the new target property value may be continuously derived by a field engineer…”; par 61: “… block 520, may include receiving a target value for multiple properties at once…”); Execute an iterative optimization process configured to determine an optimized composition of the downhole drilling fluid that satisfies at least one objective function and matches the set of target fluid properties, wherein the iterative optimization process is configured to iterate until a stopping condition is satisfied (FIG. 5 block 528: “property value = target value Yes or NO” if No iterate block 532: “modify water-based drilling fluid”; par 1: “… analysis and optimization of wellbore drilling fluids…”; par 10: “… optimization of the drilling fluid…”; par 12: “… receives a target property value that corresponds to an optimal value of a property… determine a composition of the drilling fluid and whether the value of the property of the drilling fluid is approximately equal to the target property value…”), each iteration of the iterative optimization process involving:
Selecting a mixture of fluid components for the downhole drilling fluid that includes a plurality of different mixtures of fluid components;
Providinginput to a trained machine-learning model, the trained machine-learning model being configured to determine a set of predicted fluid properties for the mixture of fluid components; Receiving the set of predicted fluid properties for the mixture of fluid components as output from the trained machine-learning model (par 24: “… properties of the drilling fluid may be obtained from one or more machine-learning models 232. One or more machine-learning models 232 may process sensor measurements to derive an output indicating or representing properties of the drilling fluid that may may not be directly measured using sensors 236…”; par 26: “the machine-learning models may be trained… the machine-learning models 232 may be trained… the feature set may indicate that drilling fluid with a particular volume of brine, low-gravity solids, and high-gravity solids is made up of a particular percentage of water. The machine learning model may use the feature set, as input, and the labels, as expected output, to define one or more functions that will output the expected additional one or more properties of the drilling fluid…”) ; and determining whether the set of predicted fluid properties matches the set of target fluid properties (FIG. 5; Page 58: “… to determine if the value of the property of the modified water-based drilling fluid now approximately equals the target property value…”); and transmit a control signal to a mixing subsystem for causing the mixing subsystem to produce the optimized composition of the downhole drilling fluid” (FIG. 2 block 244 drilling system control, block 248 drilling system; FIG. 5 block 536: “pump water-based drilling fluid into wellbore”; page 30: “… drilling system control 244 can control the operation of drilling system 248. In some instances, the output from fluid analysis device 204 may be used to reformulate the drilling fluid that is in operation. For instance, drilling system control 244 may receive the output and determine that the properties of the current drilling fluid may not be capable of producing an intended hydrostatic pressure on the formation surrounding the wellbore. Drilling system control 244 may generate a request to drilling system 248 to increase the density of the drilling fluid…”).
Kulkarni_2021 does not explicitly teach Selecting a mixture of fluid components for the downhole drilling fluid “from a search space” that includes a plurality of different mixtures of fluid components nor providing ”the selected mixture of fluid components as” nor “The selected mixture of fluid components being different from other mixtures of fluid components of the plurality of different mixtures of fluid components and comprising constituent fluid components and predetermined quantities of the constituent fluid components”
Jamison_2012, however, makes obvious selecting “from a search space” and providing “the selected mixture of fluid component” (abstract: “… determining a Design space comprising specified ranges for one or more drilling fluid properties…” FIG. 3 determine design space and fluid formulation sets; FIG. 4 design space and formulation set; Par 23: “in order to design a drilling fluid which accounts for many of the significant performance criterion, a complex mathematical model may be utilized… in some embodiments, artificial neural networks (“ANNs”) may utilize specified parameters as inputs in steps throughout the overall design process to result in an optimal drilling fluid…”)
Kulkarni_2021 and Jamison_2012 are analogous art because they are from the same field of endeavor called oil wells. Before the effective filing date, it would have been obvious to a person of ordinary skill in the art to combine Kulkarni_2021 and Jamison_2012. The rationale for doing so would have been that Kulkarni_2021 teaches to make a drilling fluid that has target properties. Jamison_2012 teaches to use a neural network (i.e., machine learning model) to design drilling fluids. Therefore, it would have been obvious to combine Kulkarni_2021 and Jamison_2012 for the benefit of deriving the target properties of the drilling fluid to obtain the invention as specified in the claims.
Chen_2022 makes obvious “The selected mixture of fluid components being different from other mixtures of fluid components of the plurality of different mixtures of fluid components and comprising constituent fluid components and predetermined quantities of the constituent fluid components” (Chen_2022 formalizes a multidimensional search space containing a plurality of distinct fluid formulations. It compares different mixtures by evaluating various component ratios. Optimal drilling fluid mixtures are selected by mapping the chemical formulas down to the specific constituent chemical treatment agents and their predetermined concentrations or quantities. The methodology uses a support vector machine and intelligent optimized search algorithms. Tables 4 and 5 illustrate calculated optimized recipes.).
Kulkarni_2021 and Chen_2022 are analogous art because they are from the same field of endeavor called drilling fluid. Before the effective filing date, it would have been obvious to a person of ordinary skill in the art to combine Kulkarni_2021 and Chen_2022. The rationale for doing so would have been Kulkarni_2021 teaches to use machine learning to explore and optimize drilling fluids. Chen_2022 teaches to create a search space and create drilling fluid recipes that achieve specific parameters using machine learning. Therefore, it would have been obvious to combine Kulkarni_2021 and Chen_2022 for the benefit of having a search space and creating recipes for a desired drilling fluid to obtain the invention as specified in the claims.
Claim 8. The limitations of claim 8 are substantially the same as those of claim 1 and are therefore rejected due to the same reasons as outlined above for claim 1. Kulkarni_2021 makes obvious the further limitations of “a method comprising:” and “by a processing device” and “by the processing device” (par 19 - 21: “FIG. 2 is a block diagram of a drilling fluid analysis and control system according to at least one aspect of the disclosure… device 204 can include one or more processors 208 coupled to memory 216 through a bus 212. Memory 216 may be a non-transitory computer-readable medium… memory 216 stores instructions 220 and one or more interfaces 224 such as application programming interfaces and data interfaces that enable receiving or exporting data… can include one or more sets of instructions that execute using one or more processors 208…”; par 63: “in some aspects, systems and methods for analyzing and controlling drilling fluids are provided…”; par 87: “… embodiments may be implemented by hardware, software, scripting languages, firmware, middleware, microcode, hardware description languages, or any combination thereof, the program code or code segments to perform the necessary tasks may be stored in a machine readable medium…”; par 88: “… implementations in firmware, software, or combinations thereof, the methodologies may be implemented… any machine-readable medium tangibly embodying instructions may be used in implementing the methodologies described herein…”).
Claim 15. The limitations of claim 15 are substantially the same as those of claim 1 and are therefore rejected due to the same reasons as outlined above for claim 1. Kulkarni_2021 makes obvious the further limitations of “a non-transitory computer-readable medium comprising instructions that are executable by a processor device for causing the processing device to perform operations comprising:” (par 19 - 21: “FIG. 2 is a block diagram of a drilling fluid analysis and control system according to at least one aspect of the disclosure… device 204 can include one or more processors 208 coupled to memory 216 through a bus 212. Memory 216 may be a non-transitory computer-readable medium… memory 216 stores instructions 220 and one or more interfaces 224 such as application programming interfaces and data interfaces that enable receiving or exporting data… can include one or more sets of instructions that execute using one or more processors 208…”; par 63: “in some aspects, systems and methods for analyzing and controlling drilling fluids are provided…”; par 87: “… embodiments may be implemented by hardware, software, scripting languages, firmware, middleware, microcode, hardware description languages, or any combination thereof, the program code or code segments to perform the necessary tasks may be stored in a machine readable medium…”; par 88: “… implementations in firmware, software, or combinations thereof, the methodologies may be implemented… any machine-readable medium tangibly embodying instructions may be used in implementing the methodologies described herein…”).
Claim 2, 9, 16. Kulkarni_2021 makes obvious “Wherein the memory device further includes instructions executable by the processing device for causing the processing device to execute the interative optimization process by, for a current iteration of the iterative optimization process: determining that the set of predicted fluid properties does not match the set of target fluid properties; determining a difference between the set of predicted fluid properties and the set of target fluid properties; and performing a subsequent iteration of the iterative optimization process based on the difference, such that the subsequent iteration is informed by the difference determined in the current iteration (FIG. 5).
Claim 3, 10, 17. Jamison_2012 makes obvious “Wherein the at least one objective function is configured to optimize for drilling speed downhole based on the optimized composition of the downhole drilling fluid” (Par 25: “… design space input parameters specifying potential ranges for drilling fluid properties may be determined to comply with a variety of parameters… to comply with given operational design parameters… operational design parameters may include, but are not limited to… rate of penetration…”).
Claim 4, 11, 18. Kulkarni_2021 makes obvious “Wherein the memory device further includes instructions executable by the processing device for causing the processing device to: generate the trained machine-learning model by training a machine-learning model using historical data, the historical data indicating fluid properties of candidate fluid components” (Par 23: “… historical records corresponding to one or more variations of drilling fluid… historical data associated each variation of drilling fluid that was in use at a particular time…”; par 26: “the machine-learning models may be trained using stored feature sets from contemporaneously collected sensor data, historical data, or generated data…”).
Claim 5, 12. Kulkarni_2021 makes obvious “Wherein the memory device further includes instructions executable by the processing device for causing the processing device to generate the trained machine-learning model by: identifying a subset of fluid components, from among the candidate fluid components listed in the historical data, that perform a same function in the downhole drilling fluid; modifying the historical data to replace the subset of fluid components with a single fluid component that is representative of the subset of fluid components; and training the machine-learning model using the modified historical data to generate the trained machine-learning model” (par 26: “… supervised or unsupervised learning…”; par 28: “… machine-learning models may be trained… until the machine-learning model reaches a predetermined accuracy value…”; par 29: “… training or re-training of machine-learning models 232…”; par 54: “… principle components can include training a machine-learning model based using historical drilling fluids or generated data… one or more sensor measurements…”).
Claim 20. Kulkarni_2021 makes obvious “Wherein the memory device further includes instructions executable by the processing device for causing the processing device to: receive a set of measured fluid properties for the mixture of fluid components output from the trained machine-learning model; modifying the historical data to include the set of measured fluid properties for the mixture of fluid components; and train the trained machine-learning model using the modified historical data” (par 29: “… training or re-training, machine-learning models 232 may continue to analyze drilling fluid… new machine-learning models may be instanced and trained using historical measurements, previously captured measurements stored in stored data 228…”).
Claim 7, 14. Kulkarni_2021 makes obvious “Wherein the iterative optimization process is implemented using an optimization algorithm, and wherein the optimization algorithm includes a Bayesian optimization algorithm, a genetic algorithm, or a Latin hypercube algorithm” (par 26 - 27: “… random forest, linear and non-linear; Bayesian statistics; neural networks; decision trees; Gaussian process regression, nearest neighbor, long short-term memory; deep learning algorithms; combinations thereof; and the like…”).
Claim 21. Chen_2022 makes obvious “Wherein, after a first execution of the iterative optimization process determine a first optimized composition, the processing device is further configured to:
Initiate a subsequent iteration of the iterative optimization process using the first optimized composition as the selected mixture of fluid components that is input to the trained machine-learning model; and Execute a plurality of further subsequent iterations of the iterative optimization process concurrently using an optimized composition from a prior iteration, wherein each further subsequent iteration of the plurality of further subsequent iterations employs a respective trained machine-learning model or a respective subset of trained machine-learning model to determine respective candidates optimized compositions” (Chen_2022 implements a support vector machine (SVM) utilizing a radial bias function kernel. The ML model acts as an analytical proxy to map out how different additives alter the drilling fluid’s structural performance. To escape local optima and accelerate finding the formula, the algorithm utilizes a matrix-descretized search. It systematically checks combinations of penalty factors © and kernel parameters (g) using n-fold cross-validation. This process evaluates trends across multiple points in the formulation space simultaneously rather than relying on slow, single-point loops.).
Claim 22 are rejected under 35 U.S.C. 103 as being unpatentable over Kulkarni_2021 in view of Jamison_2012 in view of Chen_2022 in view of Salem_2022 (Addressing Diverse Petroleum Industry Problems Using Machine Learning Techniques: Literary Methodology – Spotlight on Predicting Well Integrity Failures, ACS OMEGA, January 7, 2022) in view of Amin_2022 (Predicting the Rheological Properties of Super-Plasticized Concrete Using Modeling Techniques, Materials July 27, 2022).
Claim 22. Salem_2022 makes obvious “Wherein the trained machine-learning model comprises [ensemble model] and wherein the processing device is configured to use the selected one of the plurality of separately trained machine-learning models for the iterative optimization process based on a fluid sub-type of the downhole drilling fluid” (page 2506 “… key elements of machine learning… model ensembles…”; page 2507 Drilling Operations: “… ML algorithms to design drilling fluid… the developed tool predicts composition of drilling fluids and suggests composition of spacer fluid or concrete slurry by applying ML algorithms on the complied experimental data. This model can predict rheological properties… rheological properties of drilling fluids using mathematical model from the artificial neural network (ANNS)…” Figure 4:
PNG
media_image1.png
354
581
media_image1.png
Greyscale
Page 2507: “… used ML to develop ensemble for the prediction…”
EXAMINER NOTE: Salem_2022 teaches that machine learning models include ensemble models and outlines the use of machine learning models to iteratively predict and optimize fluid rheological properties.)
Kulkarni_2021 and Salem_2022 are analogous art because they are from the same field of endeavor called oil wells. Before the effective filing date, it would have been obvious to a person of ordinary skill in the art to combine Kulkarni_2021 and Salem_2022. The rationale for doing so would have been that Kulkarni_2021 teaches to use machine learning models during drilling operations and that the drilling fluid may be analyzed to identify and optimize the components of the drilling fluid. Kulkarni_2021 teaches that the machine learning models can include random forest, etc. See abstract, FIG. 2, par 26.
Salem_2022 also teaches to use machine learning models for fluid design during drilling operations and further teaches that machine learning models include ensemble models and teaches that ensemble models have been used for prediction during drilling operations. See page 2507. Therefore, it would have been obvious to combine Kulkarni_2021 and Salem_2022 for the benefit of fluid design during drilling operations to obtain the invention as specified in the claims.
Amin_2022 makes obvious “…selected one of a plurality of separately trained machine-learning models corresponding to different fluid types and fluid sub-types…” (page 2 – 3: “… ensemble ML algorithms normally use weak learners and split the mode into 29-sub models for high accuracy… both ensemble (R-R) and individual (ANN) PML methods to anticipate the rheological properties…”)
Kulkarni_2021 and Amin_2022 are analogous art because they are from the same field of endeavor called oil wells. Before the effective filing date, it would have been obvious to a person of ordinary skill in the art to combine Kulkarni_2021 and Amin_2022. The rationale for doing so would have been Kulkarni_2021 teaches to use machine learning that include random forest and Amin_2022 teaches that random forest include trained sub-models. Therefore, it would have been obvious to combine Kulkarni_2021 and Amin_2022 for the benefit of fluid design during drilling operations to obtain the invention as specified in the claims.
Claims 23 are rejected under 35 U.S.C. 103 as being unpatentable over Kulkarni_2021in view of Jamison_2012 in view of Chen_2022 in view of Takeuchi_2020 (On-the-fly closed-loop materials discovery via Bayesian active learning, Nature Communications, 2020).
Claim 23. Takeuchi_2020 makes obvious “Wherein, subsequent to a predetermined number of iterations of the iterative optimization process being performed, the processing device is further configured to: Select a corresponding mixture of fluid components associated with a most recent iteration of the iterative optimization process, the corresponding mixture of fluid components provided as input to the trained machine-learning model is the most recent iteration; Provide instructions to cause a real-world experiment to be conducted with the corresponding mixture of fluid components; Receive a set of measured fluid properties based on a result of the real-world experiment; and retrain the trained machine-learning model using historical data modified with the set of measured fluid properties” ( Takeuchi_2020 teaches a machine learning architecture built on physics-informed Bayesian machine learning which runs optimization algorithms to process existing datasets and output high-probability material candidate configuration. The system automatically controls high-throughput hardware, such as X-ray diffraction systems, to synthesize and test the selected candidate in a real-world experiment. The results from the real-world experiment are fed back into the database immediately to further train the machine learning model further refining the model in subsequent loops. See Figure 1.).
Kulkarni_2021 and Takeuchi_2020 are analogous art because they are from the same field of endeavor called material exploration and optimization/design. Before the effective filing date, it would have been obvious to a person of ordinary skill in the art to combine Kulkarni_2021 and Takeuchi_2020.
The rationale for doing so would have been that Kulkarni_2021 teaches to train and use machine learning models for the exploration/optimization/design of a material known as drilling fluid. Takeuchi_2020 teaches to incorporate real-world physical experiments that provide data to a machine learning model that improves the models training/prediction. Therefore, it would have been obvious to combine Kulkarni_2021 and Takeuchi_2020 for the benefit of training and improving machine learning models used for exploration and optimization of drilling fluids to obtain the invention as specified in the claims.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to BRIAN S COOK whose telephone number is (571)272-4276. The examiner can normally be reached 8:00 AM - 5:00 PM.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Emerson Puente can be reached at 571-272-3652. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/BRIAN S COOK/Primary Examiner, Art Unit 2187
Prosecution Insights