DETAILED ACTION
This action is filed in response to the remarks filed on 12/23/2025.
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 .
Information Disclosure Statement
Acknowledgement is made of Applicant’s Information Disclosure Statements (IDS) form PTO-1149 filed on 3/30/2023. This IDS has been considered.
Response to Arguments
Applicant’s arguments, filed 12/23/2025 with respect to the rejections of Claims 1-20 have been fully considered and are persuasive. Therefore, the previous grounds of rejection has been withdrawn. However, amended grounds of rejection is made in view of Gooneratne (US112801772B2) and Affleck (US20220018241 A1).
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, 4-8, and 10-11 are rejected under 35 U.S.C. 103 as being unpatentable over Teodorescu (WO2016171650 A1) in view of Marx (US 20140116776 A1), and in further view of Gooneratne (US11280177B2).
Regarding Claim 1, Teodorescu teaches a method, comprising: obtaining surface drilling data for a drilling operation at a wellbore (e.g. see [0025] “Processing the drill cuttings data 214 may result in the determination of various characteristics of the drill cuttings 210, such as cuttings size distribution or density of the drill cuttings 210 traversing the shaker screens 222. As used herein, the "density" of the drill cuttings 210 refers to the amount of drill cuttings 210 flowing through the shaker 212 over a certain time period or, in other words, flow rate of the drill cuttings 210”);
generating, by a computer processor, predicted particle size data of cuttings in the drilling fluid using a machine-learning model, the surface drilling data, the drilling fluid data, the drilling fluid hydraulic data, and the geological data (e.g. see [0008] “Processed drill cuttings data may then be generated and may be indicative of at least one of a cuttings size distribution and a density of the drill cuttings traversing the shaker screens,” and [0039] “The processor 206 can be, for example, a general purpose microprocessor, a microcontroller, a digital signal processor, an application specific integrated circuit, a field programmable gate array, a programmable logic device, a controller, a state machine, a gated logic, discrete hardware components, an artificial neural network, or any like suitable entity that can perform calculations or other manipulations of data”).
determining, by the computer processor, a shaker screen type based on the predicted particle size data, wherein the shaker screen type corresponds to a predetermined cutting size (e.g. see [0034] and [0039]); and
transmitting, by the computer processor, a first command to a well control system, wherein the first command is configured to change a first shaker screen to a second shaker screen in a shale shaker device based on the shaker screen type (e.g. see [0039] “when the processed drill cuttings data indicate that the shaker 212 is not properly cleaning the drill cuttings 210 and instead passing undesired materials and drill cuttings 210 or otherwise clogging the shaker screens 222, this may be an indication that the drilling has entered a new substrate of a different material . The processed drill cuttings data may alert an operator (or trigger the automated system 230) that a change in mesh size of the shaker screens 222 may be required to return to efficient shaker 212 operation”).
While Teodorescu discloses the broad idea of obtaining drill cutting data, Teodorescu does not explicitly disclose obtaining drilling fluid data regarding a drilling fluid in the wellbore during the drilling operation; obtaining drilling fluid hydraulic data regarding a drilling fluid device that causes the drilling fluid to circulate in the wellbore; obtaining geological data regarding one or more formations being traversed by the drilling operation.
In the same field of endeavor, Marx teaches obtaining drilling fluid data regarding a drilling fluid in the wellbore during the drilling operation (e.g. see [0207-0210]) “In a dynamic circulating system 490, the factors affecting circulating pressure may include: length of the drill string; fluid density or mud weight; yield point and plastic viscosity of the fluid;”); and
obtaining drilling fluid hydraulic data regarding a drilling fluid device that causes the drilling fluid to circulate in the wellbore (e.g. see [0217] “Downhole hydraulics parameters, including equivalent circulating density (ECD) 2074, annular velocity, annular pressure loss 3243, jet nozzle pressure loss, hydraulics horsepower, jet velocity, pore pressure gradient, and jet impact force may be calculated using the equations below”).
It would have been obvious to one of ordinary skill in the art, before the effective filling date, to combine the data acquisition and generation of particle size data of Teodorescu with the more detailed data acquisition of Marx for the purpose of determining the correct shale shaker screen to use with the advantage of additional information to allow the machine learning model to make the most accurate determination.
Teodorescu as modified by Marx does not explicitly disclose obtaining geological data regarding one or more formations being traversed by the drilling operation. In the same field of endeavor, Gooneratne teaches obtaining geological data regarding one or more formations being traversed by the drilling operation (e.g. see [Col 18 Lines 5-9] “Alternatively or in addition, as shown in FIG. 5C, the shale shaker can be observed to monitor the magnitude of formation cuttings 516 as well as identify the type of cuttings and establish the specific downhole rock formations being drilled”);
It would have been obvious to one of ordinary skill in the art, before the effective filling date, to combine the data acquisition and generation of particle size data of Teodorescu with the more detailed data acquisition of Marx, and the method of obtaining geological data from Gooneratne for the purpose of determining the correct shale shaker screen to use with the advantage of additional information to allow the machine learning model to make the most accurate determination.
Regarding Claim 4, Teodorescu, Marx, and Gooneratne teach the limitations of Claim 1. Teodorescu does not explicitly disclose determining, in real-time during the drilling operation, a predetermined rate of penetration (ROP) value for a drill string coupled to a drilling system at the wellbore based on the predicted particle size data; and transmitting a second command to the drilling system that produces the predetermined ROP value using the drill string.
In the same field of endeavor, Marx teaches determining, in real-time during the drilling operation, a predetermined rate of penetration (ROP) value for a drill string coupled to a drilling system at the wellbore based on the predicted particle size data (e.g. see [0100] “As described further below, the trend fusion engine 308 may then generate expected analogous values for lithology 310, porosity 311, permeability 312, water saturation 313, bit wear 314, mud parameters 315, Bottom hole assembly (BHA) 331, pore pressure 316, Rate of Penetration (ROP)); and
transmitting a second command to the drilling system that produces the predetermined ROP value using the drill string (e.g. see [0280] “If there is a deviation from historical data, i.e. when all or some of the parameters are different from the historical database for the same bit, and there is a rate of penetration (ROP) decrease 4712, then it is determined whether the formation changed 4714, and if no, then it is determined whether there has been a change in the drilling parameters 4719. If yes, the parameters are reviewed and changed as required to maintain rate of penetration, if not the expert system engine prompts to trip for bit 4720”).
It would have been obvious to one of ordinary skill in the art before the effective filling date to combine the shale shaker selection method of Teodorescu with the rate of penetration of Marx for the purpose of determining the shale shaker size with the advantage of maintaining proper operation of the system.
Regarding Claim 5, Teodorescu, Marx, and Gooneratne teach the limitations of Claim 1. While Teodorescu teaches drilling fluid hydraulic data, Teodorescu does not explicitly disclose wherein the drilling fluid hydraulic data comprises bit mechanical horsepower data, jet impact force data, and jet velocity data. In the same field of endeavor, Marx teaches wherein the drilling fluid hydraulic data comprises bit mechanical horsepower data. jet impact force data, and jet velocity data (e.g. see [0217] “Downhole hydraulics parameters, including equivalent circulating density (ECD) 2074, annular velocity, annular pressure loss 3243, jet nozzle pressure loss, hydraulics horsepower, jet Velocity, pore pressure gradient, and jet impact force may be calculated using the equations below”).
It would have been obvious to one of ordinary skill in the art, before the effective filling date, to combine the drilling fluid hydraulic data of Teodorescu with the specific hydraulic data of Marx for the purpose of determining the correct shale shaker screen to use with the advantage of additional information to allow the machine learning model to make the most accurate determination.
Regarding Claim 6, Teodorescu, Marx, and Gooneratne teach the limitations of Claim 1.Teodorescu does not explicitly teach wherein the drilling fluid data comprises plastic viscosity and yield point data. In the same field of endeavor, Marx teaches wherein the drilling fluid data comprises plastic viscosity and yield point data (e.g. see [0207-0210]) “In a dynamic circulating system 490, the factors affecting circulating pressure may include: length of the drill string; fluid density or mud weight; yield point and plastic viscosity of the fluid;”).
It would have been obvious to one of ordinary skill in the art, before the effective filling date, to combine the data acquisition and generation of particle size data of Teodorescu with the more detailed data acquisition of Marx for the purpose of determining the correct shale shaker screen to use with the advantage of additional information to allow the machine learning model to make the most accurate determination.
Regarding Claim 7, Teodorescu, Marx, and Gooneratne teach the limitations of Claim 1.Teodorescu does not explicitly teach wherein the surface drilling data comprises flow rate data, rotary speed data, and weight-on-bit data. In the same field of endeavor, Marx teaches wherein the surface drilling data comprises flow rate data, rotary speed data, and weight-on-bit data (e.g. see [0104] “As discussed above, according to an embodiment, the database 202 may include pre-processed and mapped real-time drilling data 203 and logged data 204. The real-time drilling data 203 may include one or more data inputs relating to depth 2031, Rate of Penetration (ROP) 2032, Weight On Bit (WOB) 2033, rotary speed 2034, flow rate 2035, and torque 2036, as shown in Table 1, below, according to an embodiment”).
It would have been obvious to one of ordinary skill in the art, before the effective filling date, to combine the data acquisition and generation of particle size data of Teodorescu with the more detailed data acquisition of Marx for the purpose of determining the correct shale shaker screen to use with the advantage of additional information to allow the machine learning model to make the most accurate determination.
Regarding Claim 8, Teodorescu, Marx, and Gooneratne teach the limitations of Claim 1. Teodorescu does not explicitly teach wherein the geological data comprises formation type data. In the same field of endeavor, Gooneratne teaches wherein the geological data comprises formation type data (e.g. see [Col. 18 lines 5-9] “Alternatively or in addition, as shown in FIG. 5C, the shale shaker can be observed to monitor the magnitude of formation cuttings 516 as well as identify the type of cuttings and establish the specific downhole rock formations being drilled”).
It would have been obvious to one of ordinary skill in the art, before the effective filling date, to combine the data acquisition and generation of particle size data of Teodorescu with the more detailed data acquisition of Gooneratne for the purpose of determining the correct shale shaker screen to use with the advantage of additional information to allow the machine learning model to make the most accurate determination.
Regarding Claim 10, Teodorescu, Marx, and Gooneratne teach the limitations of Claim 1. Teodorescu further discloses wherein the shale shaker device comprises a hopper (e.g. see [0012] “ One or more chemicals, fluids, or additives may be added to the drilling fluid 122 via a mixing hopper 134 communicably coupled to or otherwise in fluid communication with the retention pit 132”), a feeder (e.g. see [0011] “A pump 120 (e.g., a mud pump) circulates drilling fluid 122 through a feed pipe 124 and to the kelly 110, which conveys the drilling fluid 122 downhole through the interior of the drill string 108 and through one or more orifices in the drill bit 114”) a screen basket (e.g. see [0032] “According to the method 300, spent drilling fluid 122 may be conveyed across one or more shaker screens 222 of a shaker 212, as at 302.,” and [0038] “In such embodiments, the shaker 212 may include a plurality of stacked shaker screens 222 and an operator or the automated control system 230 may selectively remove or change out one or more shaker screens 222 to remedy the problem”), and
an electric motor configured to generate vibrations ( e.g. see [0037] “The shaker 212 may include a motor that powers a cam system that provides vibration to the shaker screen 222”),
wherein the first shaker screen comprises a first mesh, and wherein the second shaker screen comprises a second mesh that is different from the first mesh (e.g. see [0038]).
Regarding Claim 11, Teodorescu, Marx, and Gooneratne teach the limitations of Claim 1. Teodorescu further discloses wherein the first command is transmitted to the well control system prior to the drilling operation being initiated at the wellbore (e.g. see [0038] “As will be appreciated, this may prove advantageous in optimizing the shaker 212 with suitable or proper shaker screens 222 for the drill cuttings 210 at any given moment in time, as detected via the imaging system 136”).
Claim 2 is rejected under 35 U.S.C. 103 as being unpatentable over Teodorescu (WO2016171650 A1) in view of Marx (US 20140116776 A1) and in further view of Gooneratne (US11280177 B2) and Jamison (WO2015065475) .
Regarding Claim 2, Teodorescu, Marx, and Gooneratne teach the limitations of Claim 1. While Teodorescu teaches the broader idea of analyzing the cutting size distribution (e.g. see [0025] “The live data can be analyzed in real-time by the software to determine the real-time cuttings size distribution and/or density of the drill cuttings 210 traversing the shaker screens 222”), Teodorescu does not explicitly disclose wherein the predicted particle size data describes a cutting size of a particle size distribution that splits a predetermined number of cuttings above the cutting size in the particle size distribution.
In the same field of endeavor, Jamison teaches wherein the predicted particle size data describes a cutting size of a particle size distribution that splits a predetermined number of cuttings above the cutting size in the particle size distribution (e.g. see [0015] “The drilling fluids described herein comprise a base fluid and a plurality of particles having a particle size distribution ("PSD") . As used herein the term, "particle size distribution" refers to a list of values or a mathematical function that defines the relative amount by volume of particles present within a fluid according to size. In some instances, the particles described herein may have a PSD characterized by a d10, a d25, a d50, a d75, and a d90. As used herein, the term "dn" (e.g., d10, d25, d50, d75, or d90) refers to a diameter for which n% by volume of the particles have a smaller diameter”).
It would have been obvious to one of ordinary skill in the art, before the effective filling date, to combine the particle size distribution of Teodorescu with the specific particle size distribution method of Jamison for the purpose of determining the correct shale shaker screen to use with the advantage of additional information to allow the machine learning model to make the most accurate determination.
Claim 3 is rejected under 35 U.S.C. 103 as being unpatentable over Teodorescu (WO2016171650 A1) in view of Marx (US 20140116776 A1) and in further view of Gooneratne (US11280177 B2) and Rowe (US20160370274 A1).
Regarding Claim 3, Teodorescu, Marx, and Gooneratne teach the limitations of Claim 1. Teodorescu does not explicitly disclose obtaining a selection of a plurality of training wells based on a predetermined criterion; obtaining first training data and second training data for a first well among the plurality of training wells, wherein the first training data correspond to a first plurality of cuttings at first well interval in the first well for a first formation, wherein the second training data corresponds to a first plurality of cuttings at a second well interval different from the first well interval in the first well for the first formation; and performing a training operation of the machine-learning model using the first training data and the second training data.
In the same field of endeavor, Rowe teaches obtaining a selection of a plurality of training wells based on a predetermined criterion; obtaining first training data and second training data for a first well among the plurality of training wells (e.g. see [0041] “When multiple wells are drilled in the same field and/or on the same drill rig, the database 120 may be populated with training data sets corresponding to known characteristics of sample drill cuttings derived from each well”),
wherein the first training data correspond to a first plurality of cuttings at first well interval in the first well for a first formation, wherein the second training data corresponds to a first plurality of cuttings at a second well interval different from the first well interval in the first well for the first formation (e.g. see [0041] “Various drilling parameters may also be stored in the database 120 and associated with each training data set. For instance, drilling parameters such as the configuration of the bottom-hole assembly used, the drilling fluid type, the weight-on-bit, and the true vertical depth may be stored in the database 120 for each training data set”);
and performing a training operation of the machine-learning model using the first training data and the second training data (e.g. see [0039-0040]).
It would have been obvious to one of ordinary skill in the art before the effective filling date to combine the machine learning model of Teodorescu with the training method of Rowe for the purpose of determining shale shaker selection with the advantage of multiple wells to allow for more datapoints in order to obtain an accurate determination.
Claim 9 is rejected under 35 U.S.C. 103 as being unpatentable over Teodorescu (WO2016171650 A1) in view of Marx (US 20140116776 A1) and in further view of Gooneratne (US11280177 B2) and Shrivastava (US20240084689).
Regarding Claim 9, Teodorescu, Marx, and Gooneratne teach the limitations of Claim 1. While Teodorescu teaches a neural network, Teodorescu does not explicitly teach wherein the machine learning model is a recurrent neural network. In the same field of endeavor Shrivastava teaches teach wherein the machine learning model is a recurrent neural network (e.g. see [0210] “a system can include one or more RNN-based ML models, which can include one or more LSTM components”).
It would have been obvious to one of ordinary skill in the art before the effective filling date to combine the neural network embodiment of Teodorescu with the recurrent neural network of Shrivastava for the purpose of determining shaker screen size with the advantage of a feedback loop to store data as memory when training and running the model.
Claims 12-13, and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Teodorescu (WO2016171650 A1) in view of Gooneratne (US11280177B2).
Regarding Claim 12, Teodorescu teaches a system, comprising: a drilling system comprising a drill string (e.g. see [0010] “As illustrated, the drilling system 100 may include a drilling platform 102 that supports a derrick 104 having a traveling block 106 for raising and lowering a drill string 108”) and a plurality of sensors (e.g. see [0026] “the device 202 may comprise one or more motion or proximity detectors, such as a capacitive displacement sensor, an inductive sensor, an electromagnetic field sensor, a photoelectric sensor, a through-beam sensor, laser, a retro-reflective sensor, a diffuse sensor, an ultrasonic sensor, and any combination thereof”), wherein the drilling system is coupled to a wellbore (e.g. see [0012] “The returning or spent drilling fluid 122 may contain cuttings and debris derived from the borehole 116 as the drill bit 114 grinds and scrapes the bottom and walls of the borehole 116”);
a mud pump system coupled to the wellbore, wherein the mud pump system is configured to supply a drilling fluid to the wellbore (e.g. see [0011] “A pump 120 (e.g., a mud pump) circulates drilling fluid 122 through a feed pipe 124 and to the kelly 110, which conveys the drilling fluid 122 downhole through the interior of the drill string 108 and through one or more orifices in the drill bit 114. The drilling fluid 122 is then circulated back to the surface via an annulus 126 defined between the drill string 108 and the walls of the borehole 116”); and
a control system coupled to the drilling system and the mud pump system, wherein the control system comprises a computer processor, the control system is configured to perform a method (e.g. see [0040] “referring again to FIG. 2, the data acquisition system 204 may be generally characterized as a computer or computer system and the computer hardware associated with the data acquisition system 204, such as the processor(s) 206, may be used to implement the various methods and algorithms described herein. More particularly, the processor(s) 206 may be configured to execute one or more sequences of instructions, programming stances, or code stored on a non-transitory, computer-readable medium, such as the memory 216”) comprising:
obtaining surface drilling data for a drilling operation at a wellbore (e.g. see [0008] “Drill cuttings data of the drill cuttings may then be generated and transmitted to a data acquisition system where the drill cuttings data is analyzed and processed using one or more processors included in the data acquisition system”);
generating predicted particle size data of cuttings in the drilling fluid using a machine-learning model, the surface drilling data, the drilling fluid data, the drilling fluid hydraulic data, and the geological data (e.g. see [0008] “Processed drill cuttings data may then be generated and may be indicative of at least one of a cuttings size distribution and a density of the drill cuttings traversing the shaker screens,” and [0039] “The processor 206 can be, for example, a general purpose microprocessor, a microcontroller, a digital signal processor, an application specific integrated circuit, a field programmable gate array, a programmable logic device, a controller, a state machine, a gated logic, discrete hardware components, an artificial neural network, or any like suitable entity that can perform calculations or other manipulations of data”).
determining a shaker screen type based on the predicted particle size data, wherein the shaker screen type corresponds to a predetermined cutting size (e.g. see [0034] and [0039]); and
changing a first shaker screen to a second shaker screen in a shale shaker device based on the shaker screen type (e.g. see [0039] “when the processed drill cuttings data indicate that the shaker 212 is not properly cleaning the drill cuttings 210 and instead passing undesired materials and drill cuttings 210 or otherwise clogging the shaker screens 222, this may be an indication that the drilling has entered a new substrate of a different material . The processed drill cuttings data may alert an operator (or trigger the automated system 230) that a change in mesh size of the shaker screens 222 may be required to return to efficient shaker 212 operation”).
While Teodorescu discloses the broad idea of obtaining drill cutting data, Teodorescu does not explicitly disclose obtaining drilling fluid data regarding a drilling fluid in the wellbore during the drilling operation; obtaining drilling fluid hydraulic data regarding a drilling fluid device that causes the drilling fluid to circulate in the wellbore; obtaining geological data regarding one or more formations being traversed by the drilling operation.
In the same field of endeavor, Gooneratne teaches obtaining drilling fluid data regarding a drilling fluid in the wellbore during the drilling operation (e.g. see [Col. 21 lines 54-61] “MP unit is placed in the MWD tool and the data from the instruments in MWD/LWD tools is passed onto the microprocessor/control system of the MP unit, where the data is compressed, modulated and encoded. MP telemetry is activated by a pre-programmed mechanism such as drilling fluid flow or drilling fluid pressure increase within the drill string assembly”);
obtaining drilling fluid hydraulic data regarding a drilling fluid device that causes the drilling fluid to circulate in the wellbore (e.g. see [ Col 17 lines 37-41] “Cameras can be installed at various points to monitor various aspects of operation. For example, cameras can be positioned to view the flow in/out lines 502 the settling pit 506, the suction tank 508, or a combination to monitor the level of drilling fluid flowing in and out of the wellbore,” and [Col 18 lines 43-49] “Alternatively or in addition, as shown in FIG. 5F, cameras can be located such that the cameras have a clear view of valves 514 that control flow through the various pipes that connect a drilling fluid hydraulic system. For example, the valves 514 can include a drivable device, such as a valve actuator, that can be controlled, driven, or both by the system 200”);
obtaining geological data regarding one or more formations being traversed by the drilling operation (e.g. see [Col 18 lines 5-9] “Alternatively or in addition, as shown in FIG. 5C, the shale shaker can be observed to monitor the magnitude of formation cuttings 516 as well as identify the type of cuttings and establish the specific downhole rock formations being drilled”);
It would have been obvious to one of ordinary skill in the art, before the effective filling date, to combine the data acquisition and generation of particle size data of Teodorescu with the more detailed data acquisition of Gooneratne for the purpose of determining the correct shale shaker screen to use with the advantage of additional information to allow the machine learning model to make the most accurate determination.
Regarding Claim 13, Teodorescu teaches a system, comprising: a drilling system comprising a drill string (e.g. see [0010] “As illustrated, the drilling system 100 may include a drilling platform 102 that supports a derrick 104 having a traveling block 106 for raising and lowering a drill string 108”) and a plurality of sensors (e.g. see [0026] “the device 202 may comprise one or more motion or proximity detectors, such as a capacitive displacement sensor, an inductive sensor, an electromagnetic field sensor, a photoelectric sensor, a through-beam sensor, laser, a retro-reflective sensor, a diffuse sensor, an ultrasonic sensor, and any combination thereof”), wherein the drilling system is coupled to a wellbore (e.g. see [0012] “The returning or spent drilling fluid 122 may contain cuttings and debris derived from the borehole 116 as the drill bit 114 grinds and scrapes the bottom and walls of the borehole 116”);
a mud pump system coupled to the wellbore, wherein the mud pump system is configured to supply a drilling fluid to the wellbore (e.g. see [0011] “A pump 120 (e.g., a mud pump) circulates drilling fluid 122 through a feed pipe 124 and to the kelly 110, which conveys the drilling fluid 122 downhole through the interior of the drill string 108 and through one or more orifices in the drill bit 114. The drilling fluid 122 is then circulated back to the surface via an annulus 126 defined between the drill string 108 and the walls of the borehole 116”);
a control system coupled to the drilling system and the mud pump system, wherein the control system comprises a computer processor, the control system is configured to perform a method (e.g. see [0040] “referring again to FIG. 2, the data acquisition system 204 may be generally characterized as a computer or computer system and the computer hardware associated with the data acquisition system 204, such as the processor(s) 206, may be used to implement the various methods and algorithms described herein. More particularly, the processor(s) 206 may be configured to execute one or more sequences of instructions, programming stances, or code stored on a non-transitory, computer-readable medium, such as the memory 216”) comprising:
obtaining surface drilling data for a drilling operation at a wellbore (e.g. see [0008] “Drill cuttings data of the drill cuttings may then be generated and transmitted to a data acquisition system where the drill cuttings data is analyzed and processed using one or more processors included in the data acquisition system”);
generating predicted particle size data of cuttings in the drilling fluid using a machine-learning model, the surface drilling data, the drilling fluid data, the drilling fluid hydraulic data, and the geological data (e.g. see [0008] “Processed drill cuttings data may then be generated and may be indicative of at least one of a cuttings size distribution and a density of the drill cuttings traversing the shaker screens,” and [0039] “The processor 206 can be, for example, a general purpose microprocessor, a microcontroller, a digital signal processor, an application specific integrated circuit, a field programmable gate array, a programmable logic device, a controller, a state machine, a gated logic, discrete hardware components, an artificial neural network, or any like suitable entity that can perform calculations or other manipulations of data”).
determining a shaker screen type based on the predicted particle size data, wherein the shaker screen type corresponds to a predetermined cutting size (e.g. see [0034] and [0039]); and
changing a first shaker screen to a second shaker screen in a shale shaker device based on the shaker screen type (e.g. see [0039] “when the processed drill cuttings data indicate that the shaker 212 is not properly cleaning the drill cuttings 210 and instead passing undesired materials and drill cuttings 210 or otherwise clogging the shaker screens 222, this may be an indication that the drilling has entered a new substrate of a different material . The processed drill cuttings data may alert an operator (or trigger the automated system 230) that a change in mesh size of the shaker screens 222 may be required to return to efficient shaker 212 operation”);
and a user device coupled to the control system, wherein the user device is configured to provide a graphical user interface for presenting a plurality of shale shaker screen types to a user and obtain one or more user selections in response to presenting the plurality of shale shaker screen types (e.g. see [0030-0031] “The data acquisition system 204 and/or the remote workstation 224 may include one or more peripheral devices 228, such as a computer screen, a graphical user interface, a hand-held device, a printer, or any combination thereof. The peripheral devices 228 may provide an operator with a graphical display of the results of processing the drill cuttings data 214. Accordingly, the operator may be apprised in real-time of the cuttings size distribution and/or density of the drill cuttings 210 traversing the shaker screens 222. Upon being apprised of cuttings size distribution and/or density of the drill cuttings 210 that fall outside of a predetermined operational threshold, the operator may then have the option of modifying and otherwise altering one or more operational parameters of the shaker 212 to thereby optimize its operation. More particularly, as mentioned above, one or more operating parameters of the shaker(s) 212 may be modified to ensure that the sol ids control equipment 128 is operating within a predetermined operating threshold,” and [0016] “As described herein, the imaging system 136 may be configured to provide an operator with a real-time indication of the efficiency of the solids control equipment 128, thereby allowing the operator to proactively adjust and otherwise alter one or more operating parameters of the solids control equipment 128 (e.g. , the shakers) to optimize its operation. Exemplary operating parameters of the solids control equipment 128 that may be adjusted may include, but are not limited to, increasing or decreasing an inclination angle {i. e. , slope) of a shaker screen, increasing or decreasing a vibration amplitude of a shaker, increasing or decreasing a vibration frequency of a shaker, altering the size {i.e. , mesh size) of a shaker screen, altering a configuration or mesh profile {e.g. , alternative hole shapes ) of a shaker screen, changing the operating speed {i.e. , RPM) of a centrifuge, altering the frequency on variable speed drive (VSD) equipment), and any combination thereof”).
While Teodorescu discloses the broad idea of obtaining drill cutting data, Teodorescu does not explicitly disclose obtaining drilling fluid data regarding a drilling fluid in the wellbore during the drilling operation; obtaining drilling fluid hydraulic data regarding a drilling fluid device that causes the drilling fluid to circulate in the wellbore; obtaining geological data regarding one or more formations being traversed by the drilling operation.
In the same field of endeavor, Gooneratne teaches obtaining drilling fluid data regarding a drilling fluid in the wellbore during the drilling operation (e.g. see [Col. 21 lines 54-61] “MP unit is placed in the MWD tool and the data from the instruments in MWD/LWD tools is passed onto the microprocessor/control system of the MP unit, where the data is compressed, modulated and encoded. MP telemetry is activated by a pre-programmed mechanism such as drilling fluid flow or drilling fluid pressure increase within the drill string assembly”);
obtaining drilling fluid hydraulic data regarding a drilling fluid device that causes the drilling fluid to circulate in the wellbore (e.g. see [ Col 17 lines 37-41] “Cameras can be installed at various points to monitor various aspects of operation. For example, cameras can be positioned to view the flow in/out lines 502 the settling pit 506, the suction tank 508, or a combination to monitor the level of drilling fluid flowing in and out of the wellbore,” and [Col 18 lines 43-49] “Alternatively or in addition, as shown in FIG. 5F, cameras can be located such that the cameras have a clear view of valves 514 that control flow through the various pipes that connect a drilling fluid hydraulic system. For example, the valves 514 can include a drivable device, such as a valve actuator, that can be controlled, driven, or both by the system 200”);
obtaining geological data regarding one or more formations being traversed by the drilling operation (e.g. see [Col 18 lines 5-9] “Alternatively or in addition, as shown in FIG. 5C, the shale shaker can be observed to monitor the magnitude of formation cuttings 516 as well as identify the type of cuttings and establish the specific downhole rock formations being drilled”);
It would have been obvious to one of ordinary skill in the art, before the effective filling date, to combine the data acquisition and generation of particle size data of Teodorescu with the more detailed data acquisition of Gooneratne for the purpose of determining the correct shale shaker screen to use with the advantage of additional information to allow the machine learning model to make the most accurate determination.
Regarding Claim 20, Teodorescu and Gooneratne teach the limitations of Claim 12. Teodorescu does not explicitly teach wherein the geological data comprises formation type data. In the same field of endeavor, Gooneratne teaches wherein the geological data comprises formation type data (e.g. see [Col 18 lines 5-9] “Alternatively or in addition, as shown in FIG. 5C, the shale shaker can be observed to monitor the magnitude of formation cuttings 516 as well as identify the type of cuttings and establish the specific downhole rock formations being drilled”).
It would have been obvious to one of ordinary skill in the art, before the effective filling date, to combine the data acquisition and generation of particle size data of Teodorescu with the more detailed data acquisition of Gooneratne for the purpose of determining the correct shale shaker screen to use with the advantage of additional information to allow the machine learning model to make the most accurate determination.
Claim 14 is rejected under 35 U.S.C. 103 as being unpatentable over Teodorescu (WO2016171650 A1) in view of Gooneratne (US11280177 B2) and in further view of and Jamison (WO2015065475) .
Regarding Claim 14, Teodorescu and Gooneratne teach the limitations of Claim 12. While Teodorescu teaches the broader idea of analyzing the cutting size distribution (e.g. see [0025] “The live data can be analyzed in real-time by the software to determine the real-time cuttings size distribution and/or density of the drill cuttings 210 traversing the shaker screens 222”), Teodorescu does not explicitly disclose wherein the predicted particle size data describes a cutting size of a particle size distribution that splits a predetermined number of cuttings above the cutting size in the particle size distribution.
In the same field of endeavor, Jamison teaches wherein the predicted particle size data describes a cutting size of a particle size distribution that splits a predetermined number of cuttings above the cutting size in the particle size distribution (e.g. see [0015] “The drilling fluids described herein comprise a base fluid and a plurality of particles having a particle size distribution ("PSD") . As used herein the term, "particle size distribution" refers to a list of values or a mathematical function that defines the relative amount by volume of particles present within a fluid according to size. In some instances, the particles described herein may have a PSD characterized by a d10, a d25, a d50, a d75, and a d90. As used herein, the term "dn" (e.g., d10, d25, d50, d75, or d90) refers to a diameter for which n% by volume of the particles have a smaller diameter”).
It would have been obvious to one of ordinary skill in the art, before the effective filling date, to combine the particle size distribution of Teodorescu with the specific particle size distribution method of Jamison for the purpose of determining the correct shale shaker screen to use with the advantage of additional information to allow the machine learning model to make the most accurate determination.
Claim 15 is rejected under 35 U.S.C. 103 as being unpatentable over Teodorescu (WO2016171650 A1) in view of Gooneratne (US11280177 B2) and in further view of Rowe (US20160370274 A1).
Regarding Claim 15, Teodorescu and Gooneratne teach the limitations of Claim 12. Teodorescu does not explicitly disclose obtaining a selection of a plurality of training wells based on a predetermined criterion; obtaining first training data and second training data for a first well among the plurality of training wells, wherein the first training data correspond to a first plurality of cuttings at first well interval in the first well for a first formation, wherein the second training data corresponds to a first plurality of cuttings at a second well interval different from the first well interval in the first well for the first formation; and performing a training operation of the machine-learning model using the first training data and the second training data.
In the same field of endeavor, Rowe teaches obtaining a selection of a plurality of training wells based on a predetermined criterion; obtaining first training data and second training data for a first well among the plurality of training wells (e.g. see [0041] “When multiple wells are drilled in the same field and/or on the same drill rig, the database 120 may be populated with training data sets corresponding to known characteristics of sample drill cuttings derived from each well”),
wherein the first training data correspond to a first plurality of cuttings at first well interval in the first well for a first formation, wherein the second training data corresponds to a first plurality of cuttings at a second well interval different from the first well interval in the first well for the first formation (e.g. see [0041] “Various drilling parameters may also be stored in the database 120 and associated with each training data set. For instance, drilling parameters such as the configuration of the bottom-hole assembly used, the drilling fluid type, the weight-on-bit, and the true vertical depth may be stored in the database 120 for each training data set”);
and performing a training operation of the machine-learning model using the first training data and the second training data (e.g. see [0039-0040]).
It would have been obvious to one of ordinary skill in the art before the effective filling date to combine the machine learning model of Teodorescu with the training method of Rowe for the purpose of determining shale shaker selection with the advantage of multiple wells to allow for more datapoints in order to obtain an accurate determination.
Claim 16 is rejected under 35 U.S.C. 103 as being unpatentable over Teodorescu (WO2016171650 A1) in view of Gooneratne (US11280177B2), and in further view of Affleck (US 20220018241 A1).
Regarding Claim 16, Teodorescu and Gooneratne teach the limitations of Claim 12. Teodorescu does not explicitly disclose determining, in real-time during the drilling operation, a predetermined rate of penetration (ROP) value for a drill string coupled to a drilling system at the wellbore based on the predicted particle size data; and transmitting a command to the drilling system that produces the predetermined ROP value using the drill string.
In the same field of endeavor, Affleck teaches determining, in real-time during the drilling operation, a predetermined rate of penetration (ROP) value for a drill string coupled to a drilling system at the wellbore based on the predicted particle size data (e.g. see [0063] “Considering that drilling parameters (for example, rate of penetration, weight on bit, slurry flow) and type of bit are dependent on the rock formation to be drilled, using the wrong setup and parameters may increase the bit wear while reducing the overall drilling performance. By implementing the techniques described here, the computer system 160 will develop an expected profile of solid objects characteristics associated with a specific bit type, formation, activity or depth of drilling…Moreover, different ML/DL models may be trained to identify the rock cuttings patterns (size, shape, concentration) for each rock formation type. For example, the output of executing an ML/DL model when drilling through limestone is expected to be fine grained cuttings. Otherwise, the computer system 160 can automatically raise an alarm); and
transmitting a command to the drilling system that produces the predetermined ROP value using the drill string (e.g. see [0059]).
It would have been obvious to one of ordinary skill in the art before the effective filling date to combine the shale shaker selection method of Teodorescu with the rate of penetration of Affleck for the purpose of determining the shale shaker size with the advantage of maintaining proper operation of the system.
Claims 17-19 are rejected under 35 U.S.C. 103 as being unpatentable over Teodorescu (WO2016171650 A1) in view of Gooneratne (US11280177B2), and in further view of Marx (US20140116776 A1).
Regarding Claim 17, Teodorescu and Gooneratne teach the limitations of Claim 12. While Teodorescu teaches drilling fluid hydraulic data, Teodorescu does not explicitly disclose wherein the drilling fluid hydraulic data comprises bit mechanical horsepower data, jet impact force data, and jet velocity data. In the same field of endeavor, Marx teaches wherein the drilling fluid hydraulic data comprises bit mechanical horsepower data. jet impact force data, and jet velocity data (e.g. see [0217] “Downhole hydraulics parameters, including equivalent circulating density (ECD) 2074, annular velocity, annular pressure loss 3243, jet nozzle pressure loss, hydraulics horsepower, jet Velocity, pore pressure gradient, and jet impact force may be calculated using the equations below”).
It would have been obvious to one of ordinary skill in the art, before the effective filling date, to combine the drilling fluid hydraulic data of Teodorescu with the specific hydraulic data of Marx for the purpose of determining the correct shale shaker screen to use with the advantage of additional information to allow the machine learning model to make the most accurate determination.
Regarding Claim 18, Teodorescu and Gooneratne teach the limitations of Claim 12.Teodorescu does not explicitly teach wherein the drilling fluid data comprises plastic viscosity and yield point data. In the same field of endeavor, Marx teaches wherein the drilling fluid data comprises plastic viscosity and yield point data (e.g. see [0207-0210]) “In a dynamic circulating system 490, the factors affecting circulating pressure may include: length of the drill string; fluid density or mud weight; yield point and plastic viscosity of the fluid;”).
It would have been obvious to one of ordinary skill in the art, before the effective filling date, to combine the data acquisition and generation of particle size data of Teodorescu with the more detailed data acquisition of Marx for the purpose of determining the correct shale shaker screen to use with the advantage of additional information to allow the machine learning model to make the most accurate determination.
Regarding Claim 19, Teodorescu and Gooneratne teach the limitations of Claim 12. Teodorescu does not explicitly teach wherein the surface drilling data comprises flow rate data, rotary speed data, and weight-on-bit data. In the same field of endeavor, Marx teaches wherein the surface drilling data comprises flow rate data, rotary speed data, and weight-on-bit data (e.g. see [0104] “As discussed above, according to an embodiment, the database 202 may include pre-processed and mapped real-time drilling data 203 and logged data 204. The real-time drilling data 203 may include one or more data inputs relating to depth 2031, Rate of Penetration (ROP) 2032, Weight On Bit (WOB) 2033, rotary speed 2034, flow rate 2035, and torque 2036, as shown in Table 1, below, according to an embodiment”).
It would have been obvious to one of ordinary skill in the art, before the effective filling date, to combine the data acquisition and generation of particle size data of Teodorescu with the more detailed data acquisition of Marx for the purpose of determining the correct shale shaker screen to use with the advantage of additional information to allow the machine learning model to make the most accurate determination.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to NYLA GAVIA whose telephone number is (703)756-1592. The examiner can normally be reached M-F 8:30-5:30pm.
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, Catherine Rastovski can be reached at 571-270-0349. 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.
/NYLA GAVIA/Examiner, Art Unit 2857
/Catherine T. Rastovski/Supervisory Primary Examiner, Art Unit 2857