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
The amendment filed August 4, 2025 has been entered. Claims 1, 3-4, 7-11, 14-18 remain pending in the application.
Response to Arguments
Applicant’s arguments, see Remarks on Page 7, filed August 4, 2025, with respect to Figure 3 have been fully considered and are persuasive. The Drawing Objection of Figure 3 having incorrect labels has been withdrawn.
Applicant’s arguments, see Remarks on Page 7-9, filed August 4, 2025, with respect to claims 1-20 have been fully considered and are persuasive. The U.S.C. 101 rejection of reciting an abstract idea of “mental process” and “mathematical calculation” of claims 1-20, has been withdrawn.
Applicant’s arguments with respect to 35 U.S.C. 102, claims 1-3, 7, 8-10, and 14-17 have been considered but are moot because the new ground of rejection does not rely on any reference applied in the prior rejection of record for any teaching or matter specifically challenged in the argument. Specifically, the amended language is considered to be taught by Goual, Sun, and Johnston. See 35 U.S.C. 103 Rejections below for further explanation on how the Bryant-Goual-Sun-Johnston combination are considered to render the claim obvious.
Applicant’s arguments with respect to 35 U.S.C. 103, claims 4, 11, and 18 have been considered but are moot because the new ground of rejection does not rely on any reference applied in the prior rejection of record for any teaching or matter specifically challenged in the argument. Specifically, the amended language is considered to be taught by Goual, Sun, and Johnston. See 35 U.S.C. 103 Rejections below for further explanation on how the Bryant-Goual-Sun-Johnston combination and the Bryant-Goual-Sun-Johnston-Kirsner combination are considered to render the claim obvious.
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.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claims 1, 3, 7-10, and 14-17 are rejected under 35 U.S.C 103 as being unpatentable over in view of Bryant (U.S. Patent 10,943,182 B2, hereinafter referred to as “Bryant”) in further view of Goual et al. (U.S. Publication No. 2021/0363408 A1, hereinafter referred to as “Goual”) and in further view of Sun (U.S. Publication No. 2021/0017846 A1, hereinafter referred to as “Sun”) and in further view of Johnston et al. (U.S. Patent 9,983,327 B2, hereinafter referred to as “Johnston”).
Regarding claim 1, Bryant teaches A method comprising: (The present invention may be a system, a method, and/or a computer program product at any possible technical detail level of integration.” Bryant – [Page 13, Column 9, Lines 64-66])
establishing a database (“Concerning the EOR DB 200, there are a number of ways this database could be built. FIG. 3 is a logic flow diagram illustrating one embodiment for building an EOR database.” Bryant – [Page 12, Column 7, Lines 18-20]) comprising one or more characteristics of reactants (“Once the material for any one or more of polymer flooding, gel flooding, surfactant flooding, nanoparticle flooding, or alkaline flooding is found, the computational tool access is database 360 with the material properties for these EOR materials 70. The computational tool then assigns (block 365) properties to a selected material, e.g., stored in a vector of material properties.” Bryant – [Page 12, Column 7, Lines 51-57]), including a nanoparticle, a surfactant, and a stabilizer (“For a specific EOR strategy that employs materials (polymer flooding, hydrogels, surfactants, alkaline, and nanoparticles), the cognitive platform will enable us to select a material or a set of materials suitable for a specific oil reservoir and at same time learn what kinds of material properties are important to the effectiveness of oil/gas recovery.” Bryant – [Page 10, Column 3, Lines 62-67]), and a historical data subset; (“Once the material for any one or more of polymer flooding, gel flooding, surfactant flooding, nanoparticle flooding, or alkaline flooding is found, the computational tool access is database 360 with the material properties for these EOR materials 70. The computational tool then assigns (block 365) properties to a selected material, e.g., stored in a vector of material properties.” Bryant – [Page 12, Column 7, Lines 51-57])
determining, utilizing a machine learning algorithm (“The EOR reservoir advisor may also use an EOR materials database together with Artificial Intelligence (AI) techniques, such as machine learning, neural network models, principal component analyses, and the like, to produce an indication (e.g., output over a GUI) to an operator selecting EOR materials.” Bryant – [Page 10, Column 4, Lines 19-24])
trained with data stored in the database (“The EOR reservoir advisor may also use an EOR materials database together with Artificial Intelligence (AI) techniques, such as machine learning, neural network models, principal component analyses, and the like, to produce an indication (e.g., output over a GUI) to an operator selecting EOR materials.” Bryant – [Page 10, Column 4, Lines 19-24]), a combination of the reactants and a reaction condition to be used for synthesis of a nanofluid (“initial definition may include initially defining concentrations for one or more of the following: polymer (block 415); gel (block 420); surfactant (block 425); nanoparticle (block 430); and/or alkaline (block 435). In principle, the blocks 445, 450, and 455 are typically performed for a single EOR material, but it is also possible consider as a combination of these materials, such as a combination of alkaline, polymer and surfactant (e.g., ASP flooding) for these blocks.” Bryant – [Page 12, Column 8, Lines 50-59]),
synthesizing the nanofluid based on the combination of reactants and the reaction condition (“Once the Machine Learning technique ranks the short-listed EOR materials (and the user modifies the scores in block 155), one or more signals may be sent (block 160) to a set of actuators or mixers (e.g., valves) to provide the EOR material with the highest score (e.g., the highest enhanced oil recovery effectiveness for the reservoir condition at that moment) to the reservoir or to mix the EOR additives 70 together.” Bryant – [Page 11, Column 6, Lines 10-17]),
wherein at least one of the plurality of hidden layers is configured to generate (“The EOR reservoir advisor may also use an EOR materials database together with Artificial Intelligence (AI) techniques, such as machine learning, neural network models, principal component analyses, and the like, to produce an indication (e.g., output over a GUI) to an operator selecting EOR materials.” Bryant – [Page 10, Column 4, Lines 19-24]) the combination of the reactants and the reaction condition based on stability (“initial definition may include initially defining concentrations for one or more of the following: polymer (block 415); gel (block 420); surfactant (block 425); nanoparticle (block 430); and/or alkaline (block 435). In principle, the blocks 445, 450, and 455 are typically performed for a single EOR material, but it is also possible consider as a combination of these materials, such as a combination of alkaline, polymer and surfactant (e.g., ASP flooding) for these blocks.” Bryant – [Page 12, Column 8, Lines 50-59]), such that the nanofluid synthesized based on the combination and the reaction condition (“Once the Machine Learning technique ranks the short-listed EOR materials (and the user modifies the scores in block 155), one or more signals may be sent (block 160) to a set of actuators or mixers (e.g., valves) to provide the EOR material with the highest score (e.g., the highest enhanced oil recovery effectiveness for the reservoir condition at that moment) to the reservoir or to mix the EOR additives 70 together.” Bryant – [Page 11, Column 6, Lines 10-17]).
Bryant does not appear to specifically teach having a deep belief network comprising a plurality of hidden layers, composed of the nanoparticle encapsulated in the surfactant and stabilized with the stabilizer and is configured to reduce an interfacial tension between crude oil and water; and, is colloidal stable in a brine for a period of time.
However, Goual, which relates to nanofluids used for recovery and cleanup of crude oil from subsurface geological formations (“Quantum Dot Nanofluids”), does teach composed of the nanoparticle encapsulated in the surfactant and stabilized with the stabilizer (“The presence of oxygenated functional groups and abundant active edge sites allow quantum dots to be thermally reduced or chemically functionalized to increase their interfacial activity. The surface-modified particles have amphiphilic structures that can effectively lower the IFT and stabilize oil-in-water Pickering emulsions.” Goual – Paragraph – [0007]; “The“QDs of the present disclosure, as a new class of nanoparticles, can help to stabilize the lamella by absorption at the interface. The stability of such foams may be improved via inclusion of quantum dot nanoparticles.” Goual – Paragraph [0033]) and is configured to reduce an interfacial tension between crude oil and water; and (Interfacial tension measurements were conducted using a Kruss spinning drop tensiometer to observe the impact of these mixtures on IFT between crude oil and water…FIG. 6 shows that the highly hydrophilic QDs were able to lower the IFT between water and oil from 19.6 mN/m to about 7 mN/m, whereas the EQDs reduced it to about 4.9 mN/m.” Goual – Paragraph [0128])
Goual does not appear to specifically teach having a deep belief network comprising a plurality of hidden layers, is colloidal stable in a brine for a period of time.
However, Sun, which relates to improved fluid processing in oil and gas wellbores (“Control Scheme For Surface Steerable Drilling System”), does teach having a deep belief network comprising a plurality of hidden layers (“The system 200 may include the use of a deep learning model. This may include the use of training samples to train the model, use the corresponding method (such as a supervised learning method) to perform iterative training, update the algorithm parameters, and obtain the corresponding parameters such as the connection weight of the neural network model until achieving optimal control results.” Sun – Paragraph [0101])
Sun does not appear to specifically teach is colloidal stable in a brine for a period of time.
However, Johnston, which also relates to polymer grafted nanoparticles for use in subsurface reservoir imaging under high salinity and/or high temperature conditions (“Polymer Coated Nanoparticles”), does teach is colloidal stable in a brine for a period of time (“In this disclosure, standard American Petroleum Institute brine (“standard API brine”) is composed of 8% wt. NaCl + 2% wt. CaCl2.” Johnston – [Page 39, Column 2, Lines 25-27], “The magnetic nanoparticle dispersion is suitable for maintaining a colloidal stability in an environment comprising a standard API brine. The colloidal stability may be for about 3 weeks, 4 weeks, 5 weeks, 6 weeks, 7 weeks, 9 weeks, 10 weeks, 11 weeks, 12 weeks, 13 weeks, 14 weeks, 15 weeks, 4 months, 5 months, 6 months, 7 months, 8 months, 9 months, 10 months, 11 months, 1 year, 2 years, 3 years, 4 years, or more.” Johnston – [Page 39, Column 2, Lines 46-53], “Based on these results, a select class of sulfonic acid copolymers was determined to provide nanoparticle stability in standard API brine for at least 3 weeks at 90°C.” Johnston – [Page 45, Column 13, Lines 57-60], “Therefore, the sulfonic acid polymer-coated particles, particularly PAMPS-PAA IO nanoclusters in this study, remained stable in standard API brine.” Johnston – [Page 50, Colum 23, Lines 55-58]).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine Bryant with Goual because a teaching suggestion or motivation in the prior art would have led one of ordinary skill in the art to combine prior art teaching to arrive at the claimed invention. Bryant discloses a system and method that teaches all of the claimed features except for the use of a deep belief network to determine a nanofluid composition composed of nanoparticles in a surfactant that is stabilized to reduce an interfacial tension between crude oil and water and a nanofluid that is colloidal stable in a brine. Bryant specifically references a system and method (Bryant – [Page 13, Column 9, Lines 64-66]) for determining an material for polymer flooding, gel flooding, surfactant flooding, nanoparticle flooding, or alkaline flooding (Bryant – [Page 12, Column 7, Lines 51-57]) that are stored in a vector of material properties (Bryant – [Page 12, Column 7, Lines 51-57]) using an EOR reservoir advisor that uses an EOR materials database together with Artificial Intelligence (AI) techniques (Bryant – [Page 10, Column 4, Lines 19-24]) to generate materials that are a combination of alkaline, polymer and surfactant (Bryant – [Page 12, Column 8, Lines 50-59]) and send the materials list to actuators or mixers to create the EOR material that has the highest enhanced oil recovery effectiveness for the reservoir condition (Bryant – [Page 11, Column 6, Lines 10-17]), and Goual explains a method for combining oxygenated functional groups with quantum dots, which have amphiphilic structures (Goual – Paragraph – [0007]), that stabilize the lamella foam (Goual – Paragraph [0033]) and lower the IFT between crude oil and water (Goual – Paragraph [0128]), which can be useful for improving the recovery or cleanup of crude oil from subsurface geological formations and/or for the remediation of oil-contaminated aquifers (Goual – Paragraph [0009]). Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine Bryant with Goual to improve the recovery or cleanup of crude oil from subsurface geological formations.
However, the Bryant-Goual combination does not appear to specifically disclosing the use of a deep belief network. On the other hand, Sun does teach a system that uses a deep learning model (Sun – Paragraph [0101]). Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the use of a deep learning model disclosed in Sun to the Bryant-Goual combination to improve control and automation to increase efficiency and save operational time and save operational costs (Sun – Paragraph [0021]).
However, the Bryant-Goual-Sun combination does not appear to specifically disclose a nanofluid combination that is colloidal stable in a brine for a period of time. On the other hand, Johnston does teach a magnetic nanoparticle dispersion suitable for maintaining a colloidal stability in an environment comprising a standard API brine (Johnston – [Page 39, Column 2, Lines 46-53]) for 3 weeks at 90°C (Johnston – [Page 45, Column 13, Lines 57-60]). Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the magnetic nanoparticle dispersion suitable for maintaining a colloidal stability in a standard API brine for 3 weeks at 90°C disclosed in Johnston to the Bryant-Goual-Sun combination to improve electromagnetic imaging with a composition capable of providing sufficient electrostatic repulsion and/or an effective polymer stabilizer under high salinity or high temperature conditions (Johnston [Page 39, Column 1, Lines 52-55]).
Regarding claim 3, Bryant in view of Goual in further view of Sun and in further view of Johnston teaches the method of claim 1. Bryant further teaches wherein the historical data subset comprises stability data of known combinations (“For example for polymers 70-1, one needs to decide which kinds of polymers are suitable among an enormous combination of physical, chemical and topological characteristics, such as chemical composition, glass transition temperature, melting point, degradability, polymer chain characteristics: linear/non-linear, homopolymer/copolymer, organic/inorganic, and the like.” Bryant – [Page 10, Column 3, Lines 45-52]).
Regarding claim 7, Bryant in view of Goual in further view of Sun and in further view of Johnston teaches the method of claim 1. Bryant further teaches wherein the reaction condition (“Then the machine learning (e.g., artificial intelligence technique(s)) in block 140 will screen possible EOR additives that are suitable for such reservoir conditions.” Bryant – [Page 11, Column 5, Lines 18-20]) defines concentration of each reactant in the combination (“The output for the actuators may be the EOR material(s) shortlisted with a specific concentration. More specifically, the EOR materials/concentrations can be converted into some output that would cause the actuators/mixers/both at or near the injection well to provide and use the EOR materials at their corresponding concentrations at the oil reservoir.” Bryant – [Page 11, Column 6, Lines 17-23]).
Regarding claim 8, Bryant teaches A system comprising: (The present invention may be a system, a method, and/or a computer program product at any possible technical detail level of integration.” Bryant – [Page 13, Column 9, Lines 64-66])
a memory comprising a database (“The computer system 205 includes one or more memories 245” Bryant – [Page 11, Column 6, Lines 40-41]) configured to store (“The one or more memories 245 comprise computer readable code 285 comprising the EOR reservoir advisor 50, and also comprise the EOR database 200.” Bryant – [Page 11, Column 6, Lines 48-51]) one or more characteristics of reactants (“Once the material for any one or more of polymer flooding, gel flooding, surfactant flooding, nanoparticle flooding, or alkaline flooding is found, the computational tool access is database 360 with the material properties for these EOR materials 70. The computational tool then assigns (block 365) properties to a selected material, e.g., stored in a vector of material properties.” Bryant – [Page 12, Column 7, Lines 51-57]), including a nanoparticle, a surfactant, and a stabilizer (“For a specific EOR strategy that employs materials (polymer flooding, hydrogels, surfactants, alkaline, and nanoparticles), the cognitive platform will enable us to select a material or a set of materials suitable for a specific oil reservoir and at same time learn what kinds of material properties are important to the effectiveness of oil/gas recovery.” Bryant – [Page 10, Column 3, Lines 62-67]), and a historical data subset; and (“Once the material for any one or more of polymer flooding, gel flooding, surfactant flooding, nanoparticle flooding, or alkaline flooding is found, the computational tool access is database 360 with the material properties for these EOR materials 70. The computational tool then assigns (block 365) properties to a selected material, e.g., stored in a vector of material properties.” Bryant – [Page 12, Column 7, Lines 51-57])
a processor (“The computer system 205 includes one or more memories 245, one or more processors 210” Bryant – [Page 11, Column 6, Lines 40-41]) configured to determine, utilizing a machine learning algorithm (“The EOR reservoir advisor may also use an EOR materials database together with Artificial Intelligence (AI) techniques, such as machine learning, neural network models, principal component analyses, and the like, to produce an indication (e.g., output over a GUI) to an operator selecting EOR materials.” Bryant – [Page 10, Column 4, Lines 19-24])
trained on the database (“The EOR reservoir advisor may also use an EOR materials database together with Artificial Intelligence (AI) techniques, such as machine learning, neural network models, principal component analyses, and the like, to produce an indication (e.g., output over a GUI) to an operator selecting EOR materials.” Bryant – [Page 10, Column 4, Lines 19-24]), a combination of the reactants and a reaction condition to be used for synthesis of a nanofluid (“initial definition may include initially defining concentrations for one or more of the following: polymer (block 415); gel (block 420); surfactant (block 425); nanoparticle (block 430); and/or alkaline (block 435). In principle, the blocks 445, 450, and 455 are typically performed for a single EOR material, but it is also possible consider as a combination of these materials, such as a combination of alkaline, polymer and surfactant (e.g., ASP flooding) for these blocks.” Bryant – [Page 12, Column 8, Lines 50-59])
wherein the processor (“The computer system 205 includes one or more memories 245, one or more processors 210” Bryant – [Page 11, Column 6, Lines 40-41])
to output (“The EOR reservoir advisor may also use an EOR materials database together with Artificial Intelligence (AI) techniques, such as machine learning, neural network models, principal component analyses, and the like, to produce an indication (e.g., output over a GUI) to an operator selecting EOR materials.” Bryant – [Page 10, Column 4, Lines 19-24]) the combination of the reactants and the reaction (“initial definition may include initially defining concentrations for one or more of the following: polymer (block 415); gel (block 420); surfactant (block 425); nanoparticle (block 430); and/or alkaline (block 435). In principle, the blocks 445, 450, and 455 are typically performed for a single EOR material, but it is also possible consider as a combination of these materials, such as a combination of alkaline, polymer and surfactant (e.g., ASP flooding) for these blocks.” Bryant – [Page 12, Column 8, Lines 50-59]) condition such that the nanofluid synthesized based on the combination and the reaction condition (“Once the Machine Learning technique ranks the short-listed EOR materials (and the user modifies the scores in block 155), one or more signals may be sent (block 160) to a set of actuators or mixers (e.g., valves) to provide the EOR material with the highest score (e.g., the highest enhanced oil recovery effectiveness for the reservoir condition at that moment) to the reservoir or to mix the EOR additives 70 together.” Bryant – [Page 11, Column 6, Lines 10-17]).
Bryant does not appear to specifically teach ]) having a deep belief network comprising a plurality of hidden layers, composed of the nanoparticle encapsulated in the surfactant and stabilized with the stabilizer and is configured to reduce an interfacial tension between crude oil and water, is configured to utilize the deep belief network, is colloidal stable in a brine for a period of time.
However, Goual, which relates to nanofluids used for recovery and cleanup of crude oil from subsurface geological formations (“Quantum Dot Nanofluids”), does teach composed of the nanoparticle encapsulated in the surfactant and stabilized with the stabilizer (“The presence of oxygenated functional groups and abundant active edge sites allow quantum dots to be thermally reduced or chemically functionalized to increase their interfacial activity. The surface-modified particles have amphiphilic structures that can effectively lower the IFT and stabilize oil-in-water Pickering emulsions.” Goual – Paragraph – [0007]; “The“QDs of the present disclosure, as a new class of nanoparticles, can help to stabilize the lamella by absorption at the interface. The stability of such foams may be improved via inclusion of quantum dot nanoparticles.” Goual – Paragraph [0033]) and is configured to reduce an interfacial tension between crude oil and water (Interfacial tension measurements were conducted using a Kruss spinning drop tensiometer to observe the impact of these mixtures on IFT between crude oil and water…FIG. 6 shows that the highly hydrophilic QDs were able to lower the IFT between water and oil from 19.6 mN/m to about 7 mN/m, whereas the EQDs reduced it to about 4.9 mN/m.” Goual – Paragraph [0128]).
Goual does not appear to specifically teach having a deep belief network comprising a plurality of hidden layers, is configured to utilize the deep belief network, is colloidal stable in a brine for a period of time.
However, Sun, which relates to improved fluid processing in oil and gas wellbores (“Control Scheme For Surface Steerable Drilling System”), does teach having a deep belief network comprising a plurality of hidden layers (“The system 200 may include the use of a deep learning model. This may include the use of training samples to train the model, use the corresponding method (such as a supervised learning method) to perform iterative training, update the algorithm parameters, and obtain the corresponding parameters such as the connection weight of the neural network model until achieving optimal control results.” Sun – Paragraph [0101])
is configured to utilize the deep belief network (“The system 200 may include the use of a deep learning model. This may include the use of training samples to train the model, use the corresponding method (such as a supervised learning method) to perform iterative training, update the algorithm parameters, and obtain the corresponding parameters such as the connection weight of the neural network model until achieving optimal control results.” Sun – Paragraph [0101])
Sun does not appear to specifically teach is colloidal stable in a brine for a period of time.
However, Johnston, which also relates to polymer grafted nanoparticles for use in subsurface reservoir imaging under high salinity and/or high temperature conditions (“Polymer Coated Nanoparticles”), does teach is colloidal stable in a brine for a period of time (“In this disclosure, standard American Petroleum Institute brine (“standard API brine”) is composed of 8% wt. NaCl + 2% wt. CaCl2.” Johnston – [Page 39, Column 2, Lines 25-27], “The magnetic nanoparticle dispersion is suitable for maintaining a colloidal stability in an environment comprising a standard API brine. The colloidal stability may be for about 3 weeks, 4 weeks, 5 weeks, 6 weeks, 7 weeks, 9 weeks, 10 weeks, 11 weeks, 12 weeks, 13 weeks, 14 weeks, 15 weeks, 4 months, 5 months, 6 months, 7 months, 8 months, 9 months, 10 months, 11 months, 1 year, 2 years, 3 years, 4 years, or more.” Johnston – [Page 39, Column 2, Lines 46-53], “Based on these results, a select class of sulfonic acid copolymers was determined to provide nanoparticle stability in standard API brine for at least 3 weeks at 90°C.” Johnston – [Page 45, Column 13, Lines 57-60], “Therefore, the sulfonic acid polymer-coated particles, particularly PAMPS-PAA IO nanoclusters in this study, remained stable in standard API brine.” Johnston – [Page 50, Colum 23, Lines 55-58]).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine Bryant with Goual and the Bryant-Goual combination with Sun and the Bryant-Goual-Sun combination with Johnston for the same reasons as provided in claim 1.
Regarding claim 9, Bryant in view of Goual in further view of Sun and in further view of Johnston teaches the system of claim 8. Bryant further teaches wherein the reactants include one or more of a nanoparticle, a surfactant, and a stabilizer (“For a specific EOR strategy that employs materials (polymer flooding, hydrogels, surfactants, alkaline, and nanoparticles), the cognitive platform will enable us to select a material or a set of materials suitable for a specific oil reservoir and at same time learn what kinds of material properties are important to the effectiveness of oil/gas recovery.” Bryant – [Page 10, Column 3, Lines 62-67]).
Regarding claim 10, Bryant in view of Goual in further view of Sun and in further view of Johnston teaches the system of claim 8. Bryant further teaches wherein the memory comprises the historical data subset including stability of known combinations (“For example for polymers 70-1, one needs to decide which kinds of polymers are suitable among an enormous combination of physical, chemical and topological characteristics, such as chemical composition, glass transition temperature, melting point, degradability, polymer chain characteristics: linear/non-linear, homopolymer/copolymer, organic/inorganic, and the like.” Bryant – [Page 10, Column 3, Lines 45-52]).
Regarding claim 14, Bryant in view of Goual in further view of Sun and in further view of Johnston teaches the system of claim 8. Bryant further teaches wherein the reaction condition (“Then the machine learning (e.g., artificial intelligence technique(s)) in block 140 will screen possible EOR additives that are suitable for such reservoir conditions.” Bryant – [Page 11, Column 5, Lines 18-20]) defines concentrations of each reactant in the combination (“The output for the actuators may be the EOR material(s) shortlisted with a specific concentration. More specifically, the EOR materials/concentrations can be converted into some output that would cause the actuators/mixers/both at or near the injection well to provide and use the EOR materials at their corresponding concentrations at the oil reservoir.” Bryant – [Page 11, Column 6, Lines 17-23]).
Regarding claim 15, Bryant teaches A non-transitory computer readable medium storing instructions executable by a computer processor, the instructions comprising functionality for: (“The computer program product may include a computer readable storage medium (or media) having computer readable program instructions thereon for causing a processor to carry out aspects of the present invention. The computer readable storage medium can be a tangible device that can retain and store instructions for use by an instruction execution device.” Bryant – [Page 13, Columns 9-10, Lines 66-67 and 1-6], “A computer readable storage medium, as used herein, is not to be construed as being transitory signals per se” Bryant – [Page 13, Column 10, Lines 22-23])
obtaining a database (“Concerning the EOR DB 200, there are a number of ways this database cold be built. FIG. 3 is a logic flow diagram illustrating one embodiment for building an EOR database.” Bryant – [Page 12, Column 7, Lines 18-20]) comprising one or more characteristics of reactants (“Once the material for any one or more of polymer flooding, gel flooding, surfactant flooding, nanoparticle flooding, or alkaline flooding is found, the computational tool access is database 360 with the material properties for these EOR materials 70. The computational tool then assigns (block 365) properties to a selected material, e.g., stored in a vector of material properties.” Bryant – [Page 12, Column 7, Lines 51-57]), including a nanoparticle, a surfactant, and a stabilizer (“For a specific EOR strategy that employs materials (polymer flooding, hydrogels, surfactants, alkaline, and nanoparticles), the cognitive platform will enable us to select a material or a set of materials suitable for a specific oil reservoir and at same time learn what kinds of material properties are important to the effectiveness of oil/gas recovery.” Bryant – [Page 10, Column 3, Lines 62-67]), and a historical data subset; and (“Once the material for any one or more of polymer flooding, gel flooding, surfactant flooding, nanoparticle flooding, or alkaline flooding is found, the computational tool access is database 360 with the material properties for these EOR materials 70. The computational tool then assigns (block 365) properties to a selected material, e.g., stored in a vector of material properties.” Bryant – [Page 12, Column 7, Lines 51-57])
determining, utilizing a machine learning algorithm (“The EOR reservoir advisor may also use an EOR materials database together with Artificial Intelligence (AI) techniques, such as machine learning, neural network models, principal component analyses, and the like, to produce an indication (e.g., output over a GUI) to an operator selecting EOR materials.” Bryant – [Page 10, Column 4, Lines 19-24])
trained with the database (“The EOR reservoir advisor may also use an EOR materials database together with Artificial Intelligence (AI) techniques, such as machine learning, neural network models, principal component analyses, and the like, to produce an indication (e.g., output over a GUI) to an operator selecting EOR materials.” Bryant – [Page 10, Column 4, Lines 19-24]), a combination of reactants and a reaction condition for synthesis (“initial definition may include initially defining concentrations for one or more of the following: polymer (block 415); gel (block 420); surfactant (block 425); nanoparticle (block 430); and/or alkaline (block 435). In principle, the blocks 445, 450, and 455 are typically performed for a single EOR material, but it is also possible consider as a combination of these materials, such as a combination of alkaline, polymer and surfactant (e.g., ASP flooding) for these blocks.” Bryant – [Page 12, Column 8, Lines 50-59]),
wherein the combination and the reaction condition are subsequently used in the synthesis of a nanofluid (“Once the Machine Learning technique ranks the short-listed EOR materials (and the user modifies the scores in block 155), one or more signals may be sent (block 160) to a set of actuators or mixers (e.g., valves) to provide the EOR material with the highest score (e.g., the highest enhanced oil recovery effectiveness for the reservoir condition at that moment) to the reservoir or to mix the EOR additives 70 together.” Bryant – [Page 11, Column 6, Lines 10-17])
wherein the determining (“The EOR reservoir advisor may also use an EOR materials database together with Artificial Intelligence (AI) techniques, such as machine learning, neural network models, principal component analyses, and the like, to produce an indication (e.g., output over a GUI) to an operator selecting EOR materials.” Bryant – [Page 10, Column 4, Lines 19-24])
to output the combination of the reactants and the reaction condition (“initial definition may include initially defining concentrations for one or more of the following: polymer (block 415); gel (block 420); surfactant (block 425); nanoparticle (block 430); and/or alkaline (block 435). In principle, the blocks 445, 450, and 455 are typically performed for a single EOR material, but it is also possible consider as a combination of these materials, such as a combination of alkaline, polymer and surfactant (e.g., ASP flooding) for these blocks.” Bryant – [Page 12, Column 8, Lines 50-59]) such that the nanofluid synthesized based on the combination and the reaction condition (“Once the Machine Learning technique ranks the short-listed EOR materials (and the user modifies the scores in block 155), one or more signals may be sent (block 160) to a set of actuators or mixers (e.g., valves) to provide the EOR material with the highest score (e.g., the highest enhanced oil recovery effectiveness for the reservoir condition at that moment) to the reservoir or to mix the EOR additives 70 together.” Bryant – [Page 11, Column 6, Lines 10-17]).
Bryant does not appear to specifically teach having a deep belief network comprising a plurality of hidden layers, composed of the nanoparticle encapsulated in the surfactant and stabilized with the stabilizer and is configured to reduce an interfacial tension between crude oil and water, utilizes the deep belief network, is colloidal stable in a brine for a period of time.
However, Goual, which relates to nanofluids used for recovery and cleanup of crude oil from subsurface geological formations (“Quantum Dot Nanofluids”), does teach composed of the nanoparticle encapsulated in the surfactant and stabilized with the stabilizer (“The presence of oxygenated functional groups and abundant active edge sites allow quantum dots to be thermally reduced or chemically functionalized to increase their interfacial activity. The surface-modified particles have amphiphilic structures that can effectively lower the IFT and stabilize oil-in-water Pickering emulsions.” Goual – Paragraph – [0007]; “The“QDs of the present disclosure, as a new class of nanoparticles, can help to stabilize the lamella by absorption at the interface. The stability of such foams may be improved via inclusion of quantum dot nanoparticles.” Goual – Paragraph [0033]) and is configured to reduce an interfacial tension between crude oil and water, (Interfacial tension measurements were conducted using a Kruss spinning drop tensiometer to observe the impact of these mixtures on IFT between crude oil and water…FIG. 6 shows that the highly hydrophilic QDs were able to lower the IFT between water and oil from 19.6 mN/m to about 7 mN/m, whereas the EQDs reduced it to about 4.9 mN/m.” Goual – Paragraph [0128])
Goual does not appear to specifically teach having a deep belief network comprising a plurality of hidden layers, utilizes the deep belief network, is colloidal stable in a brine for a period of time.
However, Sun, which relates to improved fluid processing in oil and gas wellbores (“Control Scheme For Surface Steerable Drilling System”), does teach having a deep belief network comprising a plurality of hidden layers (“The system 200 may include the use of a deep learning model. This may include the use of training samples to train the model, use the corresponding method (such as a supervised learning method) to perform iterative training, update the algorithm parameters, and obtain the corresponding parameters such as the connection weight of the neural network model until achieving optimal control results.” Sun – Paragraph [0101])
utilizes the deep belief network (“The system 200 may include the use of a deep learning model. This may include the use of training samples to train the model, use the corresponding method (such as a supervised learning method) to perform iterative training, update the algorithm parameters, and obtain the corresponding parameters such as the connection weight of the neural network model until achieving optimal control results.” Sun – Paragraph [0101])
Sun does not appear to specifically teach is colloidal stable in a brine for a period of time.
However, Johnston, which also relates to polymer grafted nanoparticles for use in subsurface reservoir imaging under high salinity and/or high temperature conditions (“Polymer Coated Nanoparticles”), does teach is colloidal stable in a brine for a period of time (“In this disclosure, standard American Petroleum Institute brine (“standard API brine”) is composed of 8% wt. NaCl + 2% wt. CaCl2.” Johnston – [Page 39, Column 2, Lines 25-27], “The magnetic nanoparticle dispersion is suitable for maintaining a colloidal stability in an environment comprising a standard API brine. The colloidal stability may be for about 3 weeks, 4 weeks, 5 weeks, 6 weeks, 7 weeks, 9 weeks, 10 weeks, 11 weeks, 12 weeks, 13 weeks, 14 weeks, 15 weeks, 4 months, 5 months, 6 months, 7 months, 8 months, 9 months, 10 months, 11 months, 1 year, 2 years, 3 years, 4 years, or more.” Johnston – [Page 39, Column 2, Lines 46-53], “Based on these results, a select class of sulfonic acid copolymers was determined to provide nanoparticle stability in standard API brine for at least 3 weeks at 90°C.” Johnston – [Page 45, Column 13, Lines 57-60], “Therefore, the sulfonic acid polymer-coated particles, particularly PAMPS-PAA IO nanoclusters in this study, remained stable in standard API brine.” Johnston – [Page 50, Colum 23, Lines 55-58]).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine Bryant with Goual and the Bryant-Goual combination with Sun and the Bryant-Goual-Sun combination with Johnston for the same reasons as provided in claim 1.
Regarding claim 16, Bryant in view of Goual in further view of Sun and in further view of Johnston teaches the non-transitory computer readable medium of claim 15. Bryant further teaches wherein the reactants include one or more of a nanoparticle, a surfactant, and a stabilizer (“For a specific EOR strategy that employs materials (polymer flooding, hydrogels, surfactants, alkaline, and nanoparticles), the cognitive platform will enable us to select a material or a set of materials suitable for a specific oil reservoir and at same time learn what kinds of material properties are important to the effectiveness of oil/gas recovery.” Bryant – [Page 10, Column 3, Lines 62-67]).
Regarding claim 17, Bryant in view of Goual in further view of Sun and in further view of Johnston teaches the non-transitory computer readable medium of claim 15. Bryant further teaches wherein the historical data subset includes stability data of known combinations (“For example for polymers 70-1, one needs to decide which kinds of polymers are suitable among an enormous combination of physical, chemical and topological characteristics, such as chemical composition, glass transition temperature, melting point, degradability, polymer chain characteristics: linear/non-linear, homopolymer/copolymer, organic/inorganic, and the like.” Bryant – [Page 10, Column 3, Lines 45-52]).
Claims 4, 11, and 18 are rejected under 35 U.S.C 103 as being unpatentable over in view of Bryant (U.S. Patent 10,943,182 B2, hereinafter referred to as “Bryant”) in further view of Goual et al. (U.S. Publication No. 2021/0363408 A1, hereinafter referred to as “Goual”) and in further view of Sun (U.S. Publication No. 2021/0017846 A1, hereinafter referred to as “Sun”) and in further view of Johnston et al. (U.S. Patent 9,983,327 B2, hereinafter referred to as “Johnston”) and in further view of Kirsner et al. (U.S. Patent 7,645,723 B2, hereinafter referred to as “Kirsner”).
Regarding claim 4, Bryant in view of Goual in further view of Sun and in further view of Johnston teaches the method of claim 1. Bryant further teaches wherein the historical data subset (“Once the material for any one or more of polymer flooding, gel flooding, surfactant flooding, nanoparticle flooding, or alkaline flooding is found, the computational tool access a database 360 with the material properties for those EOR materials 70. The computational tool then assigns (block 365) properties to a selected material, e.g., stored in a vector of material properties.” Bryant – [Page 12, Column 7, Lines 51-57]).
Although Bryant teaches wherein the historical data subset.
Bryant does not appear to specifically teach comprises cost data of the reactants.
However, Kirsner, which also relates to oil or synthetic fluid based drilling fluids (“Method Of Drilling Using Invert Emulsion Drilling Fluids”), does teach comprises cost data of the reactants (“The exact proportions of the components comprising an ester blend (or other blend or base for an invert emulsion) for use in the present invention will vary depending on drilling requirements (and characteristics needed for the blend or base to meet those requirements), supply and availability of the components, cost of the components, and characteristics of the blend or base necessary to meet environmental regulations or environmental acceptance.” (Kirsner – [Page 22, Column 13, Lines 55-62]).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine Bryant with Goual and the Bryant-Goual combination with Sun and the Bryant-Goual-Sun combination with Johnston for the same reasons as provided in claim 1. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the Bryant-Goual-Sun-Johnston combination with Kirsner because a teaching, suggestion or motivation in the prior art would have led one of ordinary skill in the art to combine prior art teaching to arrive at the claimed invention. The Bryant-Goual-Sun-Johnston combination discloses a system that teaches all of the claimed features except for cost data of the reactants being a part of the historical data subset. The Bryant-Goual-Sun-Johnston combination specifically references a computational tool accessing a database with material properties for EOR materials in order to assign properties to a selected material (Bryant – [Page 12, Column 7, Lines 51-57]), and Kirsner explains using various characteristics, including cost of the components, for determining the exact proportions of components comprising an ester blend (Kirsner – [Page 22, Column 13, Lines 55-62]). A person having ordinary skill in the art would have a reasonable expectation of successfully combining the accessing of a database with material properties of EOR materials of Bryant (Bryant – [Page 12, Column 7, Lines 51-57]), with the specific functions of Kirsner such as considering cost of the components when determining the exact proportions of components comprising an ester blend (Kirsner – [Page 22, Column 13, Lines 55-62]), which can be useful to determine new drilling fluid compositions that provide improved performance while meeting environmental restrictions and cost demands (Kirsner – Page 16, Column 2, Lines 4-8). Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the Bryant-Goual-Sun-Johnston combination with Kirsner to improve the development of new drilling fluid compositions that provide improved performance while meeting environmental restrictions and cost demands.
Regarding claim 11, Bryant in view of Goual in further view of Sun and in further view of Johnston teaches the system of claim 8. Bryant further teaches wherein the memory comprises the historical data subset (“Once the material for any one or more of polymer flooding, gel flooding, surfactant flooding, nanoparticle flooding, or alkaline flooding is found, the computational tool access a database 360 with the material properties for those EOR materials 70. The computational tool then assigns (block 365) properties to a selected material, e.g., stored in a vector of material properties.” Bryant – [Page 12, Column 7, Lines 51-57]).
Although Bryant teaches wherein the memory comprises the historical data subset.
Bryant does not appear to specifically teach including cost data of the reactants.
However, Kirsner, which also relates to oil or synthetic fluid based drilling fluids (“Method Of Drilling Using Invert Emulsion Drilling Fluids”), does teach including cost data of the reactants (“The exact proportions of the components comprising an ester blend (or other blend or base for an invert emulsion) for use in the present invention will vary depending on drilling requirements (and characteristics needed for the blend or base to meet those requirements), supply and availability of the components, cost of the components, and characteristics of the blend or base necessary to meet environmental regulations or environmental acceptance.” (Kirsner – [Page 22, Column 13, Lines 55-62]).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the Bryant-Goual-Sun-Johnston combination and Kirsner for the same reason as provided in claim 4.
Regarding claim 18, Bryant in view of Goual in further view of Sun and in further view of Johnston teaches the non-transitory computer readable medium of claim 15. Bryant further teaches wherein the historical data subset (“Once the material for any one or more of polymer flooding, gel flooding, surfactant flooding, nanoparticle flooding, or alkaline flooding is found, the computational tool access a database 360 with the material properties for those EOR materials 70. The computational tool then assigns (block 365) properties to a selected material, e.g., stored in a vector of material properties.” Bryant – [Page 12, Column 7, Lines 51-57]).
Although Bryant teaches wherein the historical data subset.
Bryant does not appear to specifically teach includes cost data of the reactants.
However, Kirsner, which also relates to oil or synthetic fluid based drilling fluids (“Method Of Drilling Using Invert Emulsion Drilling Fluids”), does teach includes cost data of the reactants (“The exact proportions of the components comprising an ester blend (or other blend or base for an invert emulsion) for use in the present invention will vary depending on drilling requirements (and characteristics needed for the blend or base to meet those requirements), supply and availability of the components, cost of the components, and characteristics of the blend or base necessary to meet environmental regulations or environmental acceptance.” (Kirsner – [Page 22, Column 13, Lines 55-62]).
It would have been obvious to one of ordinary skill in the art before the eff