DETAILED ACTION
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
Claim Objections
Claims 1-2, 7, and 10-11 are objected to because the term “the reactor input condition” lacks antecedent basis. For examination purposes, Examiner assumes that “the reactor input condition” should be “the optimal reactor input condition”. Appropriate correction is required.
Claim 3 is objected to because of the following informalities: the metes and bounds of the limitations are unclear because the limitations state “and” and “or” within the list after includes. Is the list after includes supposed to “and” (i.e., all list elements are required), “or” (i.e., only one list element is required), or something else? For examination purposes, Examiner assumes that the elements are delineated by the “or” and only one list element is required. Appropriate correction is required.
Claim Interpretation
The following is a quotation of 35 U.S.C. 112(f):
(f) Element in Claim for a Combination. – An element in a claim for a combination may be expressed as a means or step for performing a specified function without the recital of structure, material, or acts in support thereof, and such claim shall be construed to cover the corresponding structure, material, or acts described in the specification and equivalents thereof.
The following is a quotation of pre-AIA 35 U.S.C. 112, sixth paragraph:
An element in a claim for a combination may be expressed as a means or step for performing a specified function without the recital of structure, material, or acts in support thereof, and such claim shall be construed to cover the corresponding structure, material, or acts described in the specification and equivalents thereof.
The claims in this application are given their broadest reasonable interpretation using the plain meaning of the claim language in light of the specification as it would be understood by one of ordinary skill in the art. The broadest reasonable interpretation of a claim element (also commonly referred to as a claim limitation) is limited by the description in the specification when 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is invoked.
As explained in MPEP § 2181, subsection I, claim limitations that meet the following three-prong test will be interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph:
(A) the claim limitation uses the term “means” or “step” or a term used as a substitute for “means” that is a generic placeholder (also called a nonce term or a non-structural term having no specific structural meaning) for performing the claimed function;
(B) the term “means” or “step” or the generic placeholder is modified by functional language, typically, but not always linked by the transition word “for” (e.g., “means for”) or another linking word or phrase, such as “configured to” or “so that”; and
(C) the term “means” or “step” or the generic placeholder is not modified by sufficient structure, material, or acts for performing the claimed function.
Use of the word “means” (or “step”) in a claim with functional language creates a rebuttable presumption that the claim limitation is to be treated in accordance with 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph. The presumption that the claim limitation is interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is rebutted when the claim limitation recites sufficient structure, material, or acts to entirely perform the recited function.
Absence of the word “means” (or “step”) in a claim creates a rebuttable presumption that the claim limitation is not to be treated in accordance with 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph. The presumption that the claim limitation is not interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is rebutted when the claim limitation recites function without reciting sufficient structure, material or acts to entirely perform the recited function.
Claim limitations in this application that use the word “means” (or “step”) are being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, except as otherwise indicated in an Office action. Conversely, claim limitations in this application that do not use the word “means” (or “step”) are not being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, except as otherwise indicated in an Office action.
This application includes one or more claim limitations that do not use the word “means,” but are nonetheless being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, because the claim limitation(s) uses a generic placeholder that is coupled with functional language without reciting sufficient structure to perform the recited function and the generic placeholder is not preceded by a structural modifier. Such claim limitation(s) is/are:
Limitation
Claims
Support/Interpretation
“a data correction unit generating . . .”
1, 7
See the data correction unit 120 as illustrated in figure 2 and as described in paragraph 0060
“a data derivation unit learning . . .”
1, 4, 5, 7
See the data derivation unit 130 as illustrated in figure 2 and as described in paragraph 0061
“an input unit obtaining . . .”
1, 7
See the input unit 200 as illustrated in figure 2 and as described in paragraphs 0066, 0079
“an output unit receiving . . .”
1, 7
See the output unit 300 as illustrated in figure 2 and as described in paragraphs 0065, 0080
“a data analysis unit comparing . . .”
4
See the data analysis unit 140 as illustrated in figure 3 and as described in paragraph 0071
“a data re-training unit re-training . . .”
4
See the data re-training unit 150 as illustrated in figure 3 and as described in paragraph 0073
Because this/these claim limitation(s) is/are being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, it/they is/are being interpreted to cover the corresponding structure described in the specification as performing the claimed function, and equivalents thereof.
If applicant does not intend to have this/these limitation(s) interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, applicant may: (1) amend the claim limitation(s) to avoid it/them being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph (e.g., by reciting sufficient structure to perform the claimed function); or (2) present a sufficient showing that the claim limitation(s) recite(s) sufficient structure to perform the claimed function so as to avoid it/them being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 10-13 are rejected under 35 U.S.C. 101 because the claimed invention is directed to non-statutory subject matter. The claims do not fall within at least one of the four categories of patent eligible subject matter because the claimed invention is directed to an abstract idea without significantly more.
The claims recite storing data, generating training data, and generating an AI model (see claims 10, 11, 13). The claims further recite updating parameters (see claim 12). The storing, generating, generating, and updating, as briefly described above and as recited in claims 10-13, are mental processes (e.g., generating an AI model as recited in claim 10). Accordingly, claims 10-13 recite an abstract idea because the particular limitations, as briefly outlined above, fall into at least one of the groupings of abstract ideas (see MPEP 2106.04(a)).
This judicial exception is not integrated into a practical application because the claim limitations are directed to the generality of generating an AI model (e.g., see claim 10). In other words, the claim limitations are generally generating an AI model based on information and these generally applicable claim limitations are not particularly tied to a system. Furthermore, the claim limitations are not directed to an application for any particular system and the application is only nominally directed to an application for various systems (e.g., see paragraph 0001 of the specification as filed). In other words, the claim limitations are not providing meaningful limitations to the method. Finally, the method, as recited in independent claim 10, is merely the field of use of the AI model generation as the elements are not integrated into the claim limitations. In other words, the method is no more than a general link to the technology environment and do not provide any meaningful limitations to the claims.
The claims do not include additional elements, individually or in combination, that are sufficient to amount to significantly more than the judicial exception because the reactor, as recited in claim 10, is a generic element. Furthermore, the claim limitations are implemented on these generic elements. In other words, the claim limitations are being implemented on these units and are not specifically liked to these elements.
Accordingly, these claims are rejected under 35 U.S.C. 101.
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 1-13 are rejected under 35 U.S.C. 103 as being unpatentable over
U.S. Patent Application Publication No. 2020/0379442 (Chan) in view of
U.S. Patent Application Publication No. 2022/0143569 (Holzmeister).
Claim 1:
The cited prior art describes an artificial intelligence (AI) model-based process control system comprising: (Chan: “The present invention is directed at a new paradigm for modeling and simulation of industrial chemical processes by combining first principles knowledge with machine learning techniques. The new paradigm is a specific application of a more general framework of using artificial intelligence to improve asset optimization in the process industry” paragraph 0041)
an AI control model unit including (Chan: see the process modeling system 130 as illustrated in figure 1A)
a data storage unit storing a plurality of pieces of preset reactor process data, (Chan: see the plant data 102 as illustrated in figures 1A, 1B; “Plant data 102 represents inputs (feed amounts, values of certain variables, etc.) and outputs (products, residuals, physical operating characteristics/conditions, etc.) of the chemical process 124.” Paragraph 0047; “In one embodiment, system 100 at libraries 110, 112, 114 store key variables, relationships, and equations (or calculations) in a database(s) for different process phenomena and equipment.” Paragraph 0064)
Chan does not explicitly describe data processing as described below. However, Holzmeister teaches the data processing as described below.
a data correction unit generating training data by removing absolute values from the stored reactor process data, and (Holzmeister: “For instance the procedure includes, applying viable absolute thresholds based on catalyst domain knowledge, like a minimum reactor temperature, a maximum steam/oil-ratio and a maximum pressure after the reactors; identifying outliers by comparing each value or set of values to the distribution of all other values of the same parameter or set of parameters available from the respective production plant, e.g. using absolute thresholds based on distribution metrics like 6 times the interquartile range (a conservative threshold used in the example application) or alternatively based on the estimated likelihood of the data point originating from the overall distribution and/or identifying irregularities based on big jumps of parameters compared to the monthly coefficient of variation for this parameter.” Paragraph 0155)
a data derivation unit learning from the generated training data and deriving an optimal reactor input condition for satisfying a reactor operation condition and a physical property value of a product be a reactor; (Chan: see the train and develop machine learning model for Y from X and XA 108 as illustrated in figure 1B; “Plant data 102 represents inputs (feed amounts, values of certain variables, etc.) and outputs (products, residuals, physical operating characteristics/conditions, etc.) of the chemical process 124.” Paragraph 0047; “The measured inputs (X) and the measured outputs (Y) can be used to train machine learning model 108.” Paragraph 0065; “Embodiments 700 train a machine learning model 706 such as an artificial neural network (ANN) using data 104 to predict reaction rate constants and/or reaction rates used in the reactor simulation model 707.” Paragraph 0081)
an input unit obtaining data including a reactor target operation condition and a target physical property value of the product and providing the obtained data to the AI control model unit; and (Chan: see the input data 104 being provided to the neural network 122 as illustrated in figure 8; see the target reaction result as illustrated in figure 8 and as described in paragraph 0083; see the input data 104 with the production rate and mass flow rates as illustrated in figure 8 and as described in paragraphs 0084-0088)
an output unit (Chan: see the settings 132 to the reactor 180 as illustrated in figure 8)
receiving the optimal reactor input condition for satisfying the reactor target operation condition and the target physical property value of the product from the AI control model unit and (Chan: see the input data 104 being provided to the neural network 122 as illustrated in figure 8; see the target reaction result as illustrated in figure 8 and as described in paragraph 0083; see the input data 104 with the production rate and mass flow rates as illustrated in figure 8 and as described in paragraphs 0084-0088)
controlling input of the reactor under the optimal reactor input condition, (Chan: see the settings 132 sent from the controller 122 to the reactor 180 for controlling the reactor 180 as illustrated in figure 8; “A controller 122 employs model process control to configure and maintain settings 132 (i.e., parameter values, temperature selection, pressure settings, flow rate, other values of variables representing physical characteristics) operating the plant equipment in carrying out the subject chemical process 124.” Paragraph 0047)
wherein the reactor input condition includes (a) below: (a): one or more of a composition, temperature, flow rate, and pressure of a raw material introduced into the reactor or combinations thereof. (Chan: “A controller 122 employs model process control to configure and maintain settings 132 (i.e., parameter values, temperature selection, pressure settings, flow rate, other values of variables representing physical characteristics) operating the plant equipment in carrying out the subject chemical process 124.” Paragraph 0047)
One of ordinary skill in the art would have recognized that applying the known technique of Chan, namely, modeling process industries, with the known techniques of Holzmeister, namely, determining operation conditions in chemical production plants, would have yielded predictable results and resulted in an improved system. Accordingly, applying the teachings of Chan model and determine operating parameters in process industries with the teachings of Holzmeister to process data for determining operation conditions in chemical production plants would have been recognized by those of ordinary skill in the art as resulting in an improved a process control system (i.e., the combination of references provides for a process control system to determine and control a process control system based on the teachings of processing data for process control in Chan and the teachings of processing data for process control in Holzmeister).
Claim 2:
The cited prior art describes the AI model-based process control system of claim 1, wherein the reactor input condition further includes (b) below: (b) a composition, temperature, flow rate, and pressure of a catalyst introduced into the reactor or combinations thereof. (Chan: “A controller 122 employs model process control to configure and maintain settings 132 (i.e., parameter values, temperature selection, pressure settings, flow rate, other values of variables representing physical characteristics) operating the plant equipment in carrying out the subject chemical process 124.” Paragraph 0047)
Claim 3:
The cited prior art describes the AI model-based process control system of claim 1,
wherein the plurality of pieces of preset reactor process data includes
an actual input condition of the reactor, (Chan: see the plant data 102 as illustrated in figures 1A, 1B; “Plant data 102 represents inputs (feed amounts, values of certain variables, etc.) and outputs (products, residuals, physical operating characteristics/conditions, etc.) of the chemical process 124.” Paragraph 0047; “In one embodiment, system 100 at libraries 110, 112, 114 store key variables, relationships, and equations (or calculations) in a database(s) for different process phenomena and equipment.” Paragraph 0064)
an actual operation condition of the reactor, and (Chan: see the plant data 102 as illustrated in figures 1A, 1B; “Plant data 102 represents inputs (feed amounts, values of certain variables, etc.) and outputs (products, residuals, physical operating characteristics/conditions, etc.) of the chemical process 124.” Paragraph 0047; “In one embodiment, system 100 at libraries 110, 112, 114 store key variables, relationships, and equations (or calculations) in a database(s) for different process phenomena and equipment.” Paragraph 0064)
an actual physical property value of the product by the reactor or (Chan: see the plant data 102 as illustrated in figures 1A, 1B; “Plant data 102 represents inputs (feed amounts, values of certain variables, etc.) and outputs (products, residuals, physical operating characteristics/conditions, etc.) of the chemical process 124.” Paragraph 0047; “In one embodiment, system 100 at libraries 110, 112, 114 store key variables, relationships, and equations (or calculations) in a database(s) for different process phenomena and equipment.” Paragraph 0064)
a computation result by simulation. (Chan: see the simulation 707 as illustrated in figure 8)
Claim 4:
The cited prior art describes the AI model-based process control system of claim 3, wherein
the data derivation unit derives a predicted operation condition of the reactor and a predicted physical property value of the product by the reactor based on the input conditions of the reactor provided from the input unit, and (Chan: see the predicted operation conditions as described in paragraphs 0117-0120; “In turn, process modeling system 130 produces improved output, namely increased in accuracy predictions of physical conditions (e.g., reaction rate) of the subject chemical process 800.” Paragraph 0099; “Instead, error calculation module 708 calculates the error between the overall simulation model prediction of 707 and measured data 102, such as reactor yield, and uses the calculated error to train the ANN model 706. Step 709 is illustrative propagating the calculated error of module 708 back to the machine learning/ANN model 706 for model training. Ultimately the resulting hybrid model 716 for process modeling system 130 is generated when the calculated error of module 708 is acceptable, i.e., meets a predefined threshold.” Paragraph 0082)
the artificial intelligence control model unit further includes:
a data analysis unit comparing the predicted operation condition of the reactor and the predicted physical property value of the product derived by the data derivation unit with the actual operation condition of the reactor and the actual physical property value of the product in the data storage unit or the data correction unit; and (Chan: “Instead, error calculation module or step 708 calculates the errors of the output prediction (YS) of combined machine learning and first principles models 706, 707 relative to the field measurement outputs (Y).” paragraph 0080; “Instead, error calculation module 708 calculates the error between the overall simulation model prediction of 707 and measured data 102, such as reactor yield, and uses the calculated error to train the ANN model 706. Step 709 is illustrative propagating the calculated error of module 708 back to the machine learning/ANN model 706 for model training. Ultimately the resulting hybrid model 716 for process modeling system 130 is generated when the calculated error of module 708 is acceptable, i.e., meets a predefined threshold.” Paragraph 0082)
a data re-training unit re-training the data derivation unit when a comparison result provided from the data analysis unit satisfies with condition (1) or condition (2) below: (Chan: “If the calculated error (/(YS)−(Y)/) does not satisfy a threshold acceptability level, then error calculation module 708 propagates at 709 the calculated errors into the machine learning model 706 for training.” Paragraph 0080)
(1) when an error rate between the actual operation conditions of the reactor and the predicted operation conditions of the reactor exceeds a preset tolerance, (Chan: “Instead, error calculation module or step 708 calculates the errors of the output prediction (YS) of combined machine learning and first principles models 706, 707 relative to the field measurement outputs (Y). If the calculated error (/(YS)−(Y)/) does not satisfy a threshold acceptability level, then error calculation module 708 propagates at 709 the calculated errors into the machine learning model 706 for training.” Paragraph 0080)
(2) when the error rate between the actual physical property value of the product and the predicted physical property value of the product exceeds a preset tolerance. (Chan: “Instead, error calculation module 708 calculates the error between the overall simulation model prediction of 707 and measured data 102, such as reactor yield, and uses the calculated error to train the ANN model 706. Step 709 is illustrative propagating the calculated error of module 708 back to the machine learning/ANN model 706 for model training. Ultimately the resulting hybrid model 716 for process modeling system 130 is generated when the calculated error of module 708 is acceptable, i.e., meets a predefined threshold.” Paragraph 0082)
Claim 5:
Chan does not explicitly describe new optimal conditions as described below. However, Holzmeister teaches the new optimal conditions as described below.
The cited prior art describes the AI model-based process control system of claim 1, wherein, when the target physical property value provided from the input unit is changed during an operation of the reactor, the data derivation unit derives a new optimal input condition of the reactor by analyzing dynamic characteristics of the reactor input condition for reaching a changed target physical property value from a time point at which the target physical property value is changed. (Holzmeister: “receive, via the communication interface, operating data indicative of a pre-defined operating condition for the scheduled production run, or measured operating data indicative of a current operating condition for the current production run, wherein at least one operating data point includes a desired operating value indicative of the change in the current operating condition,” paragraph 0013; “determine, via the processing device, at least one target operating parameter for the operating condition of the scheduled production run or the change in the current production run based on the operating data and the catalyst age indicator using a data-driven model, preferably a data-driven machine learning model, wherein the data-driven model is parameterized according to a training dataset, wherein the training dataset is based on sets of historical data comprising operating data, catalyst age indicator, and the at least one target operating parameter,” paragraph 0015)
Chan and Holzmeister are combinable for the same rationale as set forth above with respect to claim 1.
Claim 6:
The cited prior art describes the AI model-based process control system of claim 1, wherein the AI control model unit is trained by one or more of linear regression, logistic regression, a decision tree, a random forest, a support vector machine, gradient boosting, a convolution neural network, a recurrent neural network, long-short term memory, an attention model, a transformer, a generative adversarial network, reinforcement learning, or combinations (ensemble) thereof. (Chan: “In this embodiment of FIG. 1B, the system 100 or module 108 has a library of different machine learning models that can be used such as random forest regression, neural networks, or support vector machines. For example, FIG. 4 shows an augmented hybrid model 116 for pipe flow using a random forest regressor. In this case, the random forest regression does a better job on the complete data set that includes the different flow regimes graphed in FIG. 4. This is because random forest regression is an ensemble technique that aggregates multiple models. It therefore combines different models for the different flow regimes.” Paragraph 0063; see the train and develop machine learning model for Y from X and XA 108 as illustrated in figure 1B; “Plant data 102 represents inputs (feed amounts, values of certain variables, etc.) and outputs (products, residuals, physical operating characteristics/conditions, etc.) of the chemical process 124.” Paragraph 0047; “The measured inputs (X) and the measured outputs (Y) can be used to train machine learning model 108.” Paragraph 0065; “Embodiments 700 train a machine learning model 706 such as an artificial neural network (ANN) using data 104 to predict reaction rate constants and/or reaction rates used in the reactor simulation model 707.” Paragraph 0081)
Claim 7:
The cited prior art describes a reactor including an artificial intelligence (AI)-based process control system, The artificial intelligence (AI)-based process control system comprising: (Chan: “The present invention is directed at a new paradigm for modeling and simulation of industrial chemical processes by combining first principles knowledge with machine learning techniques. The new paradigm is a specific application of a more general framework of using artificial intelligence to improve asset optimization in the process industry” paragraph 0041)
an AI control model unit including (Chan: see the process modeling system 130 as illustrated in figure 1A)
a data storage unit storing a plurality of pieces of preset reactor process data, (Chan: see the plant data 102 as illustrated in figures 1A, 1B; “Plant data 102 represents inputs (feed amounts, values of certain variables, etc.) and outputs (products, residuals, physical operating characteristics/conditions, etc.) of the chemical process 124.” Paragraph 0047; “In one embodiment, system 100 at libraries 110, 112, 114 store key variables, relationships, and equations (or calculations) in a database(s) for different process phenomena and equipment.” Paragraph 0064)
Chan does not explicitly describe data processing as described below. However, Holzmeister teaches the data processing as described below.
a data correction unit generating training data by removing absolute values from the stored reactor process data, and (Holzmeister: “For instance the procedure includes, applying viable absolute thresholds based on catalyst domain knowledge, like a minimum reactor temperature, a maximum steam/oil-ratio and a maximum pressure after the reactors; identifying outliers by comparing each value or set of values to the distribution of all other values of the same parameter or set of parameters available from the respective production plant, e.g. using absolute thresholds based on distribution metrics like 6 times the interquartile range (a conservative threshold used in the example application) or alternatively based on the estimated likelihood of the data point originating from the overall distribution and/or identifying irregularities based on big jumps of parameters compared to the monthly coefficient of variation for this parameter.” Paragraph 0155)
a data derivation unit learning from the generated training data and deriving an optimal reactor input condition for satisfying a reactor operation condition and a physical property value of a product be a reactor; (Chan: see the train and develop machine learning model for Y from X and XA 108 as illustrated in figure 1B; “Plant data 102 represents inputs (feed amounts, values of certain variables, etc.) and outputs (products, residuals, physical operating characteristics/conditions, etc.) of the chemical process 124.” Paragraph 0047; “The measured inputs (X) and the measured outputs (Y) can be used to train machine learning model 108.” Paragraph 0065; “Embodiments 700 train a machine learning model 706 such as an artificial neural network (ANN) using data 104 to predict reaction rate constants and/or reaction rates used in the reactor simulation model 707.” Paragraph 0081)
an input unit obtaining data including a reactor target operation condition and a target physical property value of the product and providing the obtained data to the AI control model unit; and (Chan: see the input data 104 being provided to the neural network 122 as illustrated in figure 8; see the target reaction result as illustrated in figure 8 and as described in paragraph 0083; see the input data 104 with the production rate and mass flow rates as illustrated in figure 8 and as described in paragraphs 0084-0088)
an output unit (Chan: see the settings 132 to the reactor 180 as illustrated in figure 8)
receiving the optimal reactor input condition for satisfying the reactor target operation condition and the target physical property value of the product from the AI control model unit and (Chan: see the input data 104 being provided to the neural network 122 as illustrated in figure 8; see the target reaction result as illustrated in figure 8 and as described in paragraph 0083; see the input data 104 with the production rate and mass flow rates as illustrated in figure 8 and as described in paragraphs 0084-0088)
controlling input of the reactor under the optimal reactor input condition, (Chan: see the settings 132 sent from the controller 122 to the reactor 180 for controlling the reactor 180 as illustrated in figure 8; “A controller 122 employs model process control to configure and maintain settings 132 (i.e., parameter values, temperature selection, pressure settings, flow rate, other values of variables representing physical characteristics) operating the plant equipment in carrying out the subject chemical process 124.” Paragraph 0047)
wherein the reactor input condition includes (a) below: (a): one or more of a composition, temperature, flow rate, and pressure of a raw material introduced into the reactor or combinations thereof. (Chan: “A controller 122 employs model process control to configure and maintain settings 132 (i.e., parameter values, temperature selection, pressure settings, flow rate, other values of variables representing physical characteristics) operating the plant equipment in carrying out the subject chemical process 124.” Paragraph 0047)
Chan and Holzmeister are combinable for the same rationale as set forth above with respect to claim 1.
Claim 8:
The cited prior art describes the reactor of claim 7, wherein the reactor is one of a tubular reactor, a tower reactor, a stirred tank reactor, a fluidized-bed type reactor, and a loop reactor. (Chan: “FIG. 8 illustrates a hypothetical scenario for an esterification reaction 800 in a continuous stirred tank reactor (CSTR) 180 where the reaction taking place is” paragraph 0083)
Claim 9:
Chan does not explicitly describe a plurality of reactors as described below. However, Holzmeister teaches the plurality of reactors as described below.
The cited prior art describes the reactor of claim 7, wherein the reactor is provided in plurality, and the plurality of reactors is one of a tubular reactor, a tower reactor, a stirred tank reactor, a fluidized-bed type reactor, and a loop reactor, independently. (Holzmeister: “In case of a chemical production plant derived parameters may include averaged inlet temperature over multiple catalytic reactors” paragraph 0081; “Plant metadata for instance includes a number of reactors the reactant mixture subsequently passes through, e.g. 2 or 3 reactors, a total catalyst volume, a catalyst volume by reactor, dimensions (length, diameter, height . . . ) of each reactor, catalyst type used in the plant or combinations thereof.” Paragraph 0082; “The methods, systems, computer programs and computer program products disclosed herein are applicable to other production plants with at least one catalytic reactor, particularly with fixed bed reactors.” Paragraph 0135) (Chan: “FIG. 8 illustrates a hypothetical scenario for an esterification reaction 800 in a continuous stirred tank reactor (CSTR) 180 where the reaction taking place is” paragraph 0083)
Chan and Holzmeister are combinable for the same rationale as set forth above with respect to claim 1.
Claim 10:
The cited prior art describes a method for generating an artificial intelligence (AI) model for process control, the method comprising: (Chan: “The present invention is directed at a new paradigm for modeling and simulation of industrial chemical processes by combining first principles knowledge with machine learning techniques. The new paradigm is a specific application of a more general framework of using artificial intelligence to improve asset optimization in the process industry” paragraph 0041)
storing a plurality of pieces of reactor process data including an actual input condition of a reactor, an actual operation condition of the reactor, and an actual physical property value of a product by the reactor or a computation result based on a simulation; (Chan: see the plant data 102 as illustrated in figures 1A, 1B; “Plant data 102 represents inputs (feed amounts, values of certain variables, etc.) and outputs (products, residuals, physical operating characteristics/conditions, etc.) of the chemical process 124.” Paragraph 0047; “In one embodiment, system 100 at libraries 110, 112, 114 store key variables, relationships, and equations (or calculations) in a database(s) for different process phenomena and equipment.” Paragraph 0064; “In another embodiment of the present invention, a system 500 generates a process simulation model 516 with the workflow described in FIG. 5.” Paragraph 0071; “Next, module 104 feeds the input values (X) into a simulation model 506 to predict the output (YS).” Paragraph 0072; “A reactor model 707 with the appropriate feed and product streams is configured within a simulator like Aspen Plus (by Assignee-Applicant Aspen Technology, Inc.).” paragraph 0098)
Chan does not explicitly describe data processing as described below. However, Holzmeister teaches the data processing as described below.
generating training data by removing absolute values from the stored reactor process data; and (Holzmeister: “For instance the procedure includes, applying viable absolute thresholds based on catalyst domain knowledge, like a minimum reactor temperature, a maximum steam/oil-ratio and a maximum pressure after the reactors; identifying outliers by comparing each value or set of values to the distribution of all other values of the same parameter or set of parameters available from the respective production plant, e.g. using absolute thresholds based on distribution metrics like 6 times the interquartile range (a conservative threshold used in the example application) or alternatively based on the estimated likelihood of the data point originating from the overall distribution and/or identifying irregularities based on big jumps of parameters compared to the monthly coefficient of variation for this parameter.” Paragraph 0155)
generating an AI model using an AI algorithm that learns the generated training data to derive an optimal reactor input condition to satisfy an operation condition of a reactor and a physical property value of a product by a reactor, (Chan: see the train and develop machine learning model for Y from X and XA 108 as illustrated in figure 1B; “Plant data 102 represents inputs (feed amounts, values of certain variables, etc.) and outputs (products, residuals, physical operating characteristics/conditions, etc.) of the chemical process 124.” Paragraph 0047; “The measured inputs (X) and the measured outputs (Y) can be used to train machine learning model 108.” Paragraph 0065; “Embodiments 700 train a machine learning model 706 such as an artificial neural network (ANN) using data 104 to predict reaction rate constants and/or reaction rates used in the reactor simulation model 707.” Paragraph 0081)
wherein the reactor input condition includes (a) below: one or more of a composition, flow rate, and pressure of a raw material introduced into the reactor, or combinations thereof. (Chan: “A controller 122 employs model process control to configure and maintain settings 132 (i.e., parameter values, temperature selection, pressure settings, flow rate, other values of variables representing physical characteristics) operating the plant equipment in carrying out the subject chemical process 124.” Paragraph 0047)
Chan and Holzmeister are combinable for the same rationale as set forth above with respect to claim 1.
Claim 11:
The cited prior art describes the method of claim 10, wherein the reactor input condition further includes (b) below: (b) one or more of a composition, temperature, flow rate, and pressure of a catalyst introduced into the reactor or combinations thereof. (Chan: “A controller 122 employs model process control to configure and maintain settings 132 (i.e., parameter values, temperature selection, pressure settings, flow rate, other values of variables representing physical characteristics) operating the plant equipment in carrying out the subject chemical process 124.” Paragraph 0047)
Claim 12:
Chan does not explicitly describe new optimal conditions as described below. However, Holzmeister teaches the new optimal conditions as described below.
The cited prior art describes the method of claim 10, wherein, in the artificial intelligence algorithm, when the physical property value of the product is changed during an operation of the reactor, dynamic characteristics of the reactor input condition to reach a changed physical property value from a time point at which the physical property value is changed are analyzed to derive a new optimal reactor input condition. (Holzmeister: “receive, via the communication interface, operating data indicative of a pre-defined operating condition for the scheduled production run, or measured operating data indicative of a current operating condition for the current production run, wherein at least one operating data point includes a desired operating value indicative of the change in the current operating condition,” paragraph 0013; “determine, via the processing device, at least one target operating parameter for the operating condition of the scheduled production run or the change in the current production run based on the operating data and the catalyst age indicator using a data-driven model, preferably a data-driven machine learning model, wherein the data-driven model is parameterized according to a training dataset, wherein the training dataset is based on sets of historical data comprising operating data, catalyst age indicator, and the at least one target operating parameter,” paragraph 0015)
Chan and Holzmeister are combinable for the same rationale as set forth above with respect to claim 1
Claim 13:
The cited prior art describes the method of claim 10, wherein, in the generating of the AI model, the AI model is generated by one or more of linear regression, logistic regression, a decision tree, a random forest, a support vector machine, gradient boosting, a convolution neural network, a recurrent neural network, long-short term memory, an attention model, a transformer, a generative adversarial network, reinforcement learning, or combinations (ensemble) thereof. (Chan: “In this embodiment of FIG. 1B, the system 100 or module 108 has a library of different machine learning models that can be used such as random forest regression, neural networks, or support vector machines. For example, FIG. 4 shows an augmented hybrid model 116 for pipe flow using a random forest regressor. In this case, the random forest regression does a better job on the complete data set that includes the different flow regimes graphed in FIG. 4. This is because random forest regression is an ensemble technique that aggregates multiple models. It therefore combines different models for the different flow regimes.” Paragraph 0063; see the train and develop machine learning model for Y from X and XA 108 as illustrated in figure 1B; “Plant data 102 represents inputs (feed amounts, values of certain variables, etc.) and outputs (products, residuals, physical operating characteristics/conditions, etc.) of the chemical process 124.” Paragraph 0047; “The measured inputs (X) and the measured outputs (Y) can be used to train machine learning model 108.” Paragraph 0065; “Embodiments 700 train a machine learning model 706 such as an artificial neural network (ANN) using data 104 to predict reaction rate constants and/or reaction rates used in the reactor simulation model 707.” Paragraph 0081)
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
U.S. Patent No. 10,990,067 describes a process model for predictive analytics.
U.S. Patent No. 11,520,310 describes generating control settings for a chemical reactor.
U.S. Patent No. 11,782,401 describes a deep learning controller.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to CHRISTOPHER E EVERETT whose telephone number is (571)272-2851. The examiner can normally be reached Monday-Friday 8:00 am to 5:00 pm (Pacific).
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Robert Fennema can be reached at 571-272-2748. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/Christopher E. Everett/Primary Examiner, Art Unit 2117