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.
Allowable Subject Matter
Claims 6-8 and 16-18 are objected to as being dependent upon a rejected base claim, but would be allowable if rewritten in independent form including all of the limitations of the base claim and any intervening claims.
Claim Rejections - 35 USC § 102
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claims 1-4 and 11-14 are rejected under 35 U.S.C. 102(a)(1) as being unpatentable by
U.S. Patent Application Publication No. 2024/0019204 (Qurashi).
Claim 1:
The cited prior art describes a method, comprising: (Qurashi: “The present disclosure generally relates to operating compressors such as compressors in natural gas liquids (NGL) plants.” Paragraph 0001; “This specification describes systems and methods for managing operational strategies for efficiently running compression trains in industrial facilities (e.g., NGL plants). These systems and methods use supervised machine learning algorithms (e.g., regression and decision tree models) to develop the operational strategies. These systems and methods have been used to develop a prototype system predicting incoming feed gas volumes, identifying optimum number of running trains required, and estimating the optimal recycle rates. The developed prototype also advises plant operators whether to shut down compressor trains, maintain existing operations, or start-up new compressor trains.” Paragraph 0003)
obtaining an input flow rate for each input material within a set of input materials received by a processing plant, (Qurashi: “The monitoring process includes obtaining upstream flow volumes, input flows, and operating conditions for a first time period and a second time period (step 372).” Paragraph 0055; “The upstream flow volumes, input flows, and operating conditions stored in the data store 150 are provided to the feed gas prediction module 144.” Paragraph 0033)
wherein the processing plant: (Qurashi: “FIG. 1 is a schematic of a NGL plant 100. Atypical NGL Plant 100 includes one or more compression trains 110, stripping fractionation 112, and a de-ethanization section 114.” Paragraph 0029)
comprises one or more material processors connected according to a process flow, and (Qurashi: see the compressors in NGL Plant 120, 122 as illustrated in figure 2)
outputs a set of output materials; (Qurashi: see the NGL to refinery and the off-gas to gas plants as illustrated in figure 1)
determining, using an artificial intelligence (AI) model, a set of process variables, based on the process flow and the input flow rate for each input material within the set of input materials, wherein the set of process variables comprises a first output flow rate for a first output material within the set of output materials; (Qurashi: “The machine learning system 350 extracts feature values from the input data of the training set, the features being variables deemed potentially relevant to whether or not the input data items have the associated property or properties.” Paragraph 0042; “The machine learning models of the feed gas prediction module 144 determine one or more features to extract from the upstream flow volumes, input flows, and operating conditions (step 374). These features represent physical features of a refinery complex for each of the first time period and the second time period.” Paragraph 0055; “The system 140 can be implemented in computer processors located in a control center of a NGL plant. The system 140 includes a compressor control engine 142 which includes feed gas prediction module 144 and a n optional compressor operation module 148.” Paragraph 0032)
determining a performance of the processing plant, based on the set of process variables; and (Qurashi: “The capacity of the running compression trains is compared to the predicted feed gas volumes (step 412). If the capacity of the running compression trains matches the predicted feed gas volume, no changes required in normal operations are continued (step 414). The compression operation module 148 then checks if operations are continuing (step 416).” Paragraph 0058)
optimizing the performance of the processing plant, wherein optimizing the performance comprises increasing the first output flow rate by adjusting the input flow rate for one or more input materials within the set of input materials. (Qurashi: see the start a train 428 to increase volume as illustrated in figure 5 and as described in paragraphs 0003, 0061)
Claim 2:
The cited prior art describes the method of claim 1, wherein:
the set of input materials comprises natural gas; and (Qurashi: see the feed gas header 116 with the feed gas of natural gas as illustrated in figure 1 and as described in paragraph 0029)
the set of output materials comprises one or more of:
sales gas, the sales gas comprising methane,
ethane, (Qurashi: “The bottom product is routed to a refinery under the system pressure. Remaining of propane and almost all of ethane and lighter components (including H.sup.2S and CO.sup.2) are separated as overhead gases. The overhead gases are routed to the de-ethanizer feed system and then to gas plants for further processing.” Paragraph 0029)
sulfur, and
a natural gas liquid (NGL). (Qurashi: see the NGL to refinery as illustrated in figure 1)
Claim 3:
The cited prior art describes the method of claim 2,
wherein the one or more material processors comprise one or more of:
a gas feeder; (Qurashi: see the gas header 116 as illustrated in figure 1)
a gas sweetener;
a gas condensate stripper; (Qurashi: see the stripper 126 as illustrated in figure 1)
a fractionation column; (Qurashi: see the stripping fractionation 112 as illustrated in figure 1)
a cooler; (Qurashi: see the coolers as described in paragraph 0029)
a compressor; (Qurashi: see the compressors in NGL Plant 120, 122 as illustrated in figure 2)
a dehydrator;
a triethylene glycol (TEG) gas dehydrator;
a heat recovery steam generator; and
a boiler.
Claim 4:
The cited prior art describes the method of claim 1:
wherein the one or more material processors comprises a first material processor that receives, at least, a first input material of the set of input materials; (Qurashi: see the compression train 110 as illustrated in figure 1; “The compression trains 110 take suction from a common network of feed gas header 116.” Paragraph 0029)
wherein the set of process variables further comprises a first input flow rate for the first input material; (Qurashi: “The monitoring process includes obtaining upstream flow volumes, input flows, and operating conditions for a first time period and a second time period (step 372).” Paragraph 0055; “The upstream flow volumes, input flows, and operating conditions stored in the data store 150 are provided to the feed gas prediction module 144.” Paragraph 0033)
wherein the method further comprises:
obtaining a first maximum input flow rate for the first input material, and (Qurashi: see the feed gas prediction 410 as illustrated in figure 5 and as described in paragraph 0058)
making a determination whether the first input flow rate is greater than the first maximum input flow rate; and (Qurashi: see the compare capacity of running trains (i.e., first input flow rate) to the predicted volume trains (i.e., maximum input flow rate) 422, 426 as illustrated in figure 5 and as described in paragraphs 0059, 0060)
wherein optimizing the performance further comprises, in response to the determination that the first input flow rate is greater than the first maximum input flow rate, diverting some of the first input material to another material processor within the one or more material processors. (Qurashi: see the shutdown of a train 420, 424 thereby diverting input away from the shutdown train as illustrated in figure 5 and as described in paragraphs 0059, 0060)
Claim 11:
Claim 11 is substantially similar to claim 1 and is rejected based on the same reasons and rationale.
11. A system, comprising:
a process flow;
a processing plant, comprising one or more material processors connected by the process flow,
wherein the processing plant:
receives a set of input materials, and
outputs a set of output materials;
a computer, configured to:
receive an input flow rate for each input material within a set of input materials;
determine, using an artificial intelligence (AI) model, a set of process variables, based on the process flow and the input flow rate for each input material within the set of input materials, wherein the set of process variables comprises a first output flow rate for a first output material within the set of output materials;
determine a performance of the processing plant, based on the set of process variables; and
optimize the performance of the processing plant, wherein optimizing the performance comprises increasing the first output flow rate by adjusting the input flow rate for one or more input materials within the set of input materials.
Claim 12:
Claim 12 is substantially similar to claim 2 and is rejected based on the same reasons and rationale.
12. The system of claim 11, wherein:
the set of input materials comprises natural gas; and
the set of output materials comprises one or more of: sales gas, the sales gas comprising methane, ethane, sulfur, and a natural gas liquid (NGL).
Claim 13:
Claim 13 is substantially similar to claim 3 and is rejected based on the same reasons and rationale.
13. The system of claim 12, wherein the one or more material processors comprise one or more of: a gas feeder; a gas sweetener; a gas condensate stripper; a fractionation column; a cooler; a compressor; a dehydrator; a triethylene glycol (TEG) gas dehydrator; a heat recovery steam generator; and a boiler.
Claim 14:
Claim 14 is substantially similar to claim 4 and is rejected based on the same reasons and rationale.
14. The system of claim 11:
wherein the one or more material processors comprises a first material processor that receives, at least, a first input material of the set of input materials;
wherein the set of process variables further comprises a first input flow rate for the first input material;
wherein the computer is further configured to: obtain a first maximum input flow rate for the first input material, and make a determination whether the first input flow rate is greater than the first maximum input flow rate; and
wherein optimizing the performance further comprises, in response to the determination that the first input flow rate is greater than the first maximum input flow rate, diverting some of the first input material to another material processor within the one or more material processors.
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 5 and 15 are rejected under 35 U.S.C. 103 as being unpatentable over
U.S. Patent Application Publication No. 2024/0019204 (Qurashi) in view of
U.S. Patent Application Publication No. 2018/0356151 (Suraganda).
Claim 5:
Qurashi does not explicitly describe energy consumption as described below. However, Suraganda teaches the energy consumption as described below.
The cited prior art describes the method of claim 1:
wherein the one or more material processors comprises a first material processor that receives, at least, a first input material of the set of input materials; (Qurashi: see the compression train 110 as illustrated in figure 1; “The compression trains 110 take suction from a common network of feed gas header 116.” Paragraph 0029)
wherein the performance is further based on an energy consumption of the one or more material processors; (Suraganda: “The system according to claim 17, wherein the optimizer of the optimization system is selected from a group consisting of: linear programming, quadratic programming, mixed integer non-linear programming, stochastic programming, global non-linear programming, genetic algorithms, and particle/swarm techniques; and wherein the optimization process further comprising the steps of: receiving a cost function that defines costs associated with each of the one or more operating goals and the one or more operating constraints, wherein the optimizer of the optimization system is configured to determine the optimal operating mode by accessing the system model to minimize the cost function; wherein the cost function comprises a mathematical representation for evaluating the operation of the LNG production train relative to the one or more operating goals and the one or more operating constraints; and wherein the cost function includes a term related to a minimization of a specific energy consumption per unit of LNG produced.” Claim 19)
wherein optimizing the performance further comprises inactivating the first material processor to prevent the prevent material processor from consuming energy; and (Qurashi: see the shutdown of a train 420, 424 thereby saving energy as illustrated in figure 5 and as described in paragraphs 0059, 0060)
wherein the method further comprises re-routing the first input material to another material processor within the one or more material processors. (Qurashi: see the shutdown of a train 420, 424 thereby diverting input away from the shutdown train as illustrated in figure 5 and as described in paragraphs 0059, 0060)
One of ordinary skill in the art would have recognized that applying the known technique of Qurashi, namely, operating compressors in a NGL plant, with the known techniques of Suraganda, namely, enhancing production in a LNG production train, would have yielded predictable results and resulted in an improved system. Accordingly, applying the teachings of Qurashi to control operation in a NGL plant based on various data with the teachings of Suraganda to control operation in a LNG production train based on various data would have been recognized by those of ordinary skill in the art as resulting in an improved gas plant control system (i.e., the combination of the references provides for a gas plant control system based on various data based on the teachings of a gas plant control system using an AI model of Qurashi and the teachings of gas plant control system using energy consumption data in Suraganda).
Claim 15:
Claim 15 is substantially similar to claim 5 and is rejected based on the same reasons and rationale.
15. The system of claim 11:
wherein the one or more material processors comprises a first material processor that receives, at least, a first input material of the set of input materials;
wherein the performance is further based on an energy consumption of the one or more material processors;
wherein optimizing the performance further comprises inactivating the first material processor to prevent the prevent material processor from consuming energy; and
wherein the computer is futher configured to re-route the first input material to another material processor within the one or more material processors.
Claims 9-10 and 19-20 are rejected under 35 U.S.C. 103 as being unpatentable over
U.S. Patent Application Publication No. 2024/0019204 (Qurashi) in view of
U.S. Patent Application Publication No. 2020/0040272 (Cavness).
Claim 9:
Qurashi does not explicitly describe a polynomial as described below. However, Cavness teaches the polynomial as described below.
The cited prior art describes the method of claim 1, wherein the AI model comprises a polynomial fit. (Cavness: “Additionally or alternatively, the DCUs may be adapted to execute mathematical operations in relation to training computationally intensive machine learning, artificial intelligence, statistical or deep learning models, such as neural networks, recurrent neural networks, convolutional neural networks, generative adversarial networks, gradient boosting machines, random forests, classification and regression trees, linear, polynomial, exponential and generalized linear regressions, logistic regression, reinforcement learning, deep reinforcement learning, hyperparameter optimization, cross validation, support vector machines, principal component analysis, singular value decomposition, convex optimization, and/or independent component analysis.” Paragraph 0030)
One of ordinary skill in the art would have recognized that applying the known technique of Qurashi, namely, operating compressors in a NGL plant, with the known techniques of Cavness, namely, natural gas processing system, would have yielded predictable results and resulted in an improved system. Accordingly, applying the teachings of Qurashi to control operation in a NGL plant based on various data with the teachings of Cavness to control operation in a natural gas processing system using various mechanisms would have been recognized by those of ordinary skill in the art as resulting in an improved gas plant control system (i.e., the combination of the references provides for a gas plant control system based on various data and based on various mechanisms based on the teachings of a gas plant control system using an AI model of Qurashi and the teachings of natural gas plant control system using a polynomial operations in Cavness).
Claim 10:
The cited prior art describes the method of claim 9, further comprising:
conducting a plurality of training operations for the processing plant, each training operation comprising: inputting the set of input materials to the processing plant, each material within the set of input materials input with a distinct input flow rate; recording, for each training operation, an output flow rate for the first output material; (Qurashi: “The machine learning system 350 is capable of applying machine learning techniques to train the machine learning model 320.” Paragraph 0041; “The machine learning system 350 extracts feature values from the input data of the training set, the features being variables deemed potentially relevant to whether or not the input data items have the associated property or properties. An ordered list of the features for the input data is herein referred to as the feature vector for the input data.” Paragraph 0042)
constructing a training dataset of training examples, wherein each training example comprises: for a training operation, the flow rate for each input material within the set of input materials, and the first output flow rate recorded for the training operation; and (Qurashi: “As part of the training of the machine learning model 320, the machine learning system 350 forms a training set of input data by identifying a positive training set of input data items that have been determined to have the property in question, and, in some embodiments, forms a negative training set of input data items that lack the property in question.” Paragraph 0041; “FIG. 6 shows the regression model output using the training data set. This chart 500 compares actual and predicted incoming feed gas volumes of generated by the feed gas prediction module of a prototype system using the training data set.” Paragraph 0065)
training the AI model using the training dataset, the AI model configured to receive, as input, the input flow rate for each input material within the set of input materials, and return, as output, the first output flow rate for the first output material. (Qurashi: “The machine learning system 350 extracts feature values from the input data of the training set, the features being variables deemed potentially relevant to whether or not the input data items have the associated property or properties. An ordered list of the features for the input data is herein referred to as the feature vector for the input data. In one embodiment, the machine learning system 350 applies dimensionality reduction (e.g., via linear discriminant analysis (LDA), principle component analysis (PCA), or the like) to reduce the amount of data in the feature vectors for the input data to a smaller, more representative set of data.” Paragraph 0042; “In one embodiment, the machine learning module iteratively re-trains the machine learning model until the occurrence of a stopping condition, such as the accuracy measurement indication that the model is sufficiently accurate, or a number of training rounds having taken place.” Paragraph 0044; “In some implementations, the machine learning system 350 uses supervised machine learning to train the machine learning models 320 with the feature vectors of the positive training set and the negative training set serving as the inputs.” Paragraph 0043)
Claim 19:
Claim 19 is substantially similar to claim 9 and is rejected based on the same reasons and rationale.
19. The system of claim 11, wherein the AI model comprises a polynomial fit.
Claim 20:
Claim 20 is substantially similar to claim 10 and is rejected based on the same reasons and rationale.
20. The system of claim 19, wherein the computer is further configured to:
receive results of a plurality of training operations for the processing plant, each training operation comprising:
inputting the set of input materials to the processing plant, each material within the set of input materials input with a distinct input flow rate;
recording, for each training operation, an output flow rate for the first output material;
construct a training dataset of training examples, wherein each training example comprises:
for a training operation, the flow rate for each input material within the set of input materials, and
the first output flow rate recorded for the training operation; and
train the AI model using the training dataset, the AI model configured to receive, as input, the input flow rate for each input material within the set of input materials, and return, as output, the first output flow rate for the first output material.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
U.S. Patent Application Publication No. 2021/0123431 describes a synthetic data generation system.
U.S. Patent Application Publication No. 2022/0333857 describes a system for determining operating conditions for liquefied natural gas plant.
U.S. Patent Application Publication No. 2008/0202159 describes optimizing a liquefied natural gas facility.
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