NON-FINAL REJECTION, FIRST DETAILED ACTION
Status of Prosecution
The present application, 18/714,717 filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
The application was filed on June 23, 2024 in the Office.
Claims 1-20 are pending and all are rejected. Claims 1 and 13 are independent.
Status of the Claims
Claims 1-3 and 20 are rejected under 35 USC. § 103 as being unpatentable over
Johnson et al., (“Johnson”), US Patent 10,690,033 published June 23, 2020 in view of
Heichelbech et al. (“Heichelbech”), United States Patent Application Publication 2023/0326264 published on Oct. 12, 2023.
Claims 4-5 are rejected under 35 USC. § 103 as being unpatentable over Johnson in view of Heichelbech and in further view of Chen et al. (“Chen”), Chinese Patent Application Publication 115392437 published on Nov. 25, 2022.
Claims 6-8 are rejected under 35 USC. § 103 as being unpatentable over Johnson in view of Heichelbech and in further view of Yonekura et al. (“Yonekura”), United States Patent Application Publication 2022/0258101 published on Aug. 18, 2022.
Claims 9-10 are rejected under 35 USC. § 103 as being unpatentable over Johnson in view of Heichelbech and in further view of Yonekura in further view of Chen et al. (“Chen”),
Chinese Patent Application Publication 115392437 published on Nov. 25, 2022.
Claims 11-12 are rejected under 35 USC. § 103 as being unpatentable over Johnson in view of Heichelbech and in further view of Yonekura in further view of Chen and in further view of Halbe et al., (“Halbe”), United States Patent Application Publication 2024/0255940 published Aug. 1, 2024.
Claims 13-14 and 16-19 are rejected under 35 USC. § 103 as being unpatentable over Zhu et al. (“Zhu”), Chinese Patent Application Publication 111111430 published on May 8, 2020 in view of Vaughan et al., (“Vaughan”), United States Patent Application Publication
2016/0025028 published Jan. 8, 2016.
Claim 15 is rejected under 35 USC. § 103 as being unpatentable over Zhu in view of
Vaughan and in further view of Halbe.
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 of this title, 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.
A.
Claims 1-3 and 20 are rejected under 35 USC. § 103 as being unpatentable over
Johnson et al., (“Johnson”), US Patent 10,690,033 published June 23, 2020 in view of
Heichelbech et al. (“Heichelbech”), United States Patent Application Publication 2023/0326264 published on Oct. 12, 2023.
As to Claim 1, Johnson teaches: A method for selective catalytic reduction, comprising: obtaining, by a computing system, input data comprising one or more input values (Johnson: col. 8, lines 63 to 64, controller [30] receives information from various sensors for use as inputs to a control algorithm;); generating, based on the input data, output data indicative of an amount of a reactant (Johnson: col. 9, lines 12-22, based on determined flowrates per the received information from ssensors (i.e. the input data), the injection flowrates (i.e. amounts) of reactants is determined; and providing a signal, by the computing system, to cause the amount of the reactant to be provided to a selective catalytic reduction system (Johsnon: col. 9, lines 20-22, the signal lines [96, 98] receive data signals to control the amount of reactant).
Johnson may not explcitilyc teach: a computing system comprising a machine-learned model; generating, by the machine-learned model based on the input data, output data indicative of an amount of a reactant.
While Johnson does mention the possibility of machine learning for the aftertreatment control effects, it is is not specific as to the particulars (Johnson: col. 13, lines 58 to 65). Heichelbech teaches in general concepts related to determining appropriate timing or duratoin of an active regeneration event for an aftereatement system based on a corlleated control strategy (Heichelbech: Abstract). Specifically, Heichelbech teaches that machine learning models may be used to determine patterns for certain parameter values such as sulfur deposit amounts for vehciles along similar routes (Heichelbech: par. 0033).
It would have been obvious to a person having ordinary skill in the art at a time before the effective filing date of the invention to have modified the Johnson device by including computer instructions to utilize a machine learning model for parameter values involving chemical deposit amounts as taught and disclosed by Heichelbech. Such a person would have been motivated to do so with a reasonable expectation of success to reduce drain on a vehicle’s computing system by removing complicated models (Heicehlbech: par. 0015).
As to Claim 2, Johnson and Heichelbech teach the limitations of claim 1. Heichelbech further teaches: wherein generating the output data comprises:
retrieving, by the computing system from a data structure, two or more data examples indicative of prior reactant amounts; and generating, by the machine-learned model based on the two or more data examples, the output data (Heichelbech: par. 0042, “As such, the controller 26 is able to use this pool of information from previous runs in a feed-forward loop manner by utilizing the remote computing system's analysis of past performance parameters.”).
As to Claim 3, Johnson and Heichelbech teach the limitations of claim 2.
Heichelbech further teaches: wherein the two or more data examples are retrieved based on a metric of similarity between the input data and each of the two or more data examples (Heichelbech: par. 0033, “The determined and identified patterns may relate to repeated instances of similar parameter values (e.g., sulfur deposit amounts) for a vehicle(s) along similar routes.”).
As to Claim 20, it is rejected for similar reasons as claim 1. Johnson further teaches a computer readable medium and processor (Johnson: col. 10, lines 44-57, processor [212] and memory [214]).
B.
Claims 4-5 are rejected under 35 USC. § 103 as being unpatentable over Johnson et al.,(“Johnson”), US Patent 10,690,033 published June 23, 2020 in view of Heichelbech et al. (“Heichelbech”), United States Patent Application Publication 2023/0326264 published on Oct. 12, 2023 and in further view of Chen et al. (“Chen”), Chinese Patent Application Publication 115392437 published on Nov. 25, 2022.
As to Claim 4, Johnson and Heichelbech teach the limitations of claim 2.
Johnson and Heichelbech may not explicitly teach: wherein generating the output data based on the two or more data examples comprises at least one of:
interpolation; and regression.
Chen teaches in general concepts related to machine-learning techniques for smoke control (Chen: Title, p. 1). Specifically, Chen teaches a machine-learning-based flue gas control method using data from multiple sensors which then input the data into an oxide predivtion model to predict nitrogen oxides and resulting nitrogen oxide values after selective catalyitic reduction based on historical data (Chen: p. 1). A multiple linear regression model is used (Chen: p. 1, “The flow rate performs model training on the preset multiple linear regression model”).
It would have been obvious to a person having ordinary skill in the art at a time before the effective filing date of the invention to have modified the Johnson- Heichelbech device by including computer instructions to utilize linear regression techniques over the historical data for the machine learning model as taught and disclosed by Chen. Such a person would have been motivated to do so with a reasonable expectation of success to utilize a known-statistical method for using best data for model prediction functions.
As to Claim 5, Johnson and Heichelbech teach the limitations of claim 2.
Johnson and Heichelbech may not explicitly teach: wherein generating the output data based on the two or more data examples comprises at least one of:
linear interpolation; and linear regression.
Chen teaches in general concepts related to machine-learning techniques for smoke control (Chen: Title, p. 1). Specifically, Chen teaches a machine-learning-based flue gas control method using data from multiple sensors which then input the data into an oxide prediction model to predict nitrogen oxides and resulting nitrogen oxide values after selective catalytic reduction based on historical data (Chen: p. 1). A multiple linear regression model is used (Chen: p. 1, “The flow rate performs model training on the preset multiple linear regression model”).
It would have been obvious to a person having ordinary skill in the art at a time before the effective filing date of the invention to have modified the Johnson- Heichelbech device by including computer instructions to utilize linear regression techniques over the historical data for the machine learning model as taught and disclosed by Chen. Such a person would have been motivated to do so with a reasonable expectation of success to utilize a known-statistical method for using best data for model prediction functions.
C.
Claims 6-8 are rejected under 35 USC. § 103 as being unpatentable over Johnson et al., (“Johnson”), US Patent 10,690,033 published June 23, 2020 in view of Heichelbech et al. (“Heichelbech”), United States Patent Application Publication 2023/0326264 published on Oct. 12, 2023 and in further view of Yonekura et al. (“Yonekura”), United States Patent Application Publication 2022/0258101 published on Aug. 18, 2022.
As to Claim 6, Johnson and Heichelbech teach the limitations of claim 1.
Johnson and Heichelbech may not explicitly teach: wherein the input data comprises data indicative of a turbine load.
Yonekura teaches in general concepts related to controlling an injection amount of a reducing agent injected into exhaust gas flowing from a coal-fired boiler for a denitrification process (Yonekura: Abstract). Specifically Yonekura teaches that a steam turbine is used
(Yonekura: par. 0026).
It would have been obvious to a person having ordinary skill in the art at a time before the effective filing date of the invention to have modified the Johnson- Heichelbech device by including computer instructions to include a turbine in the system as taught and disclosed by Yonekura. Such a person would have been motivated to do so with a reasonable expectation of success to utilize a mechanical element that is conventional.
As to Claim 7, Johnson and Heichelbech teach the limitations of claim 1.
Heichelbech further teaches: wherein the output data indicative of the amount comprises a first reactant amount value, and further comprising:
determining, by the computing system based on a startup or shutdown process of an industrial system comprising the selective catalytic reduction system, a reactant amount adjustment value; adjusting, by the computing system based on the reactant amount adjustment value, the first reactant amount value to generate the amount of the reactant.
Yonekura teaches in general concepts related to controlling an injection amount of a reducing agent injected into exhaust gas flowing from a coal-fired boiler for a denitrification process (Yonekura: Abstract). Specifically Yonekura teaches that a steam turbine is used (Yonekura: par. 0026). Startup conditions involving the amount of exhaust gas increases is is a factor that varies the flow rate of the exhaust gas that in turn affects the NOx concentration (Yonekura: par. 0077). A prediction outputs the NOx concentration and adjusts the flow rate of the reducing agent o obtain the desired concentration (Yonekura: pars.0078-79).
It would have been obvious to a person having ordinary skill in the art at a time before the effective filing date of the invention to have modified the Johnson- Heichelbech device by including computer instructions to control the reactant as taught and disclosed by Yonekura. Such a person would have been motivated to do so with a reasonable expectation of success to utilize the machine learning efficiencies and optimization.
As to Claim 8, Johnson and Heichelbech teach the limitations of claim 1.
Heichelbech may not explicitly teach: providing, by the computing system, one or more signals to cause the amount of the reactant to be provided to the selective catalytic reduction system throughout a first time period associated with a latency of emissions data associated with the selective catalytic reduction system; adjusting, by a self-adjusting reactant flow control system after the first time period, a reactant flow provided to the selective catalytic reduction system.
Yonekura teaches in general concepts related to controlling an injection amount of a reducing agent injected into exhaust gas flowing from a coal-fired boiler for a denitrification process (Yonekura: Abstract). Specifically Yonekura teaches that a steam turbine is used (Yonekura: par. 0026). Startup conditions involving the amount of exhaust gas increases is is a factor that varies the flow rate of the exhaust gas that in turn affects the NOx concentration after a predetermined period of time (Yonekura: par. 0077). A prediction outputs the NOx concentration and adjusts the flow rate of the reducing agent to obtain the desired concentration (Yonekura: pars.0078-79).
It would have been obvious to a person having ordinary skill in the art at a time before the effective filing date of the invention to have modified the Johnson- Heichelbech device by including computer instructions to control the reactant per a predetermined period of time as taught and disclosed by Yonekura. Such a person would have been motivated to do so with a reasonable expectation of success to utilize the machine learning efficiencies and optimization.
D.
Claims 9-10 are rejected under 35 USC. § 103 as being unpatentable over Johnson et al., (“Johnson”), US Patent 10,690,033 published June 23, 2020 in view of Heichelbech et al. (“Heichelbech”), United States Patent Application Publication 2023/0326264 published on Oct. 12, 2023 and in further view of Yonekura et al. (“Yonekura”), United States Patent Application Publication 2022/0258101 published on Aug. 18, 2022 in further view of Chen et al. (“Chen”), Chinese Patent Application Publication 115392437 published on Nov. 25, 2022.
As to Claim 9, Johnson, Heichelbech and Yonekura teach the limitations of claim 8.
Johnson, Heichelbech and Yonekura may not explicitly teach: wherein the self-adjusting reactant flow control system comprises a proportional-integral-derivative controller.
Chen teaches in general concepts related to machine-learning techniques for smoke control (Chen: Title, p. 1). Specifically, Chen teaches a machine-learning-based flue gas control method using data from multiple sensors which then input the data into an oxide prediction model to predict nitrogen oxides and resulting nitrogen oxide values after selective catalytic reduction based on historical data (Chen: p. 1). A proportional-integral-derivative (PID) controller is used and PID parameters are used in the model (Chen: p. 2, “The historical ammonia water flow rate performs model training on the preset multiple linear regression model, and sets the PID parameters of the multiple linear regression model to obtain the ammonia water control amount calculation model, including: based on the first nitrogen oxide value”).
It would have been obvious to a person having ordinary skill in the art at a time before the effective filing date of the invention to have modified the Johnson- Heichelbech-Yonekura device by including computer instructions to utilize a PID controller with the machine learning model as taught and disclosed by Chen. Such a person would have been motivated to do so with a reasonable expectation of success to utilize a known controller for the system.
As to Claim 10, Johnson, Heichelbech, Yonekura and Chen teach the limitations of claim 8.
Chen further teaches: determining, by the computing system based on the adjusting, an adjusted reactant amount; and storing, by the computing system, data indicative of the adjusted reactant amount in a training data structure associated with the machine-learned model (Chen: p. 1 feature training vectors on the multiple linear regression model would include storing data of the adjusted reactant amount).
E.
Claims 11-12 are rejected under 35 USC. § 103 as being unpatentable over Johnson et al., (“Johnson”), US Patent 10,690,033 published June 23, 2020 in view of Heichelbech et al. (“Heichelbech”), United States Patent Application Publication 2023/0326264 published on Oct. 12, 2023 and in further view of Yonekura et al. (“Yonekura”), United States Patent Application
Publication 2022/0258101 published on Aug. 18, 2022 in further view of Chen et al. (“Chen”), Chinese Patent Application Publication 115392437 published on Nov. 25, 2022 and in further view of Halbe et al., (“Halbe”), United States Patent Application Publication 2024/0255940 published Aug. 1, 2024.
As to Claim 11, Johnson, Heichelbech, Yonekura and Chen teach the limitations of claim 10.
Johnson, Heichelbech, Yonekura and Chen may not explicitly teach: determining, by the computing system based on a comparison between the adjusted reactant amount and the amount of the reactant, whether to store the data indicative of the adjusted reactant amount in the training data structure associated with the machine-learned model; and wherein the storing is performed responsive to determining that the data should be stored.
Halbe teaches in general concepts related to determining a remaining useful life (RUL) of a component of an engine system (Halbe: Abstract). Specifically, Halbe teaches that certain data is preprocessed based on the status (Halbe: par. 0083, “pre-processing the ignitor data, by the RUL modeling circuit 212, may include cleaning and filtering operations, such as dropping empty rows, discarding zero load points and/or engine idle conditions”).
It would have been obvious to a person having ordinary skill in the art at a time before the effective filing date of the invention to have modified the Johnson- Heichelbech-YonekuraChen device by including computer instructions to store only certain data as taught and disclosed by Halbe. Such a person would have been motivated to do so with a reasonable expectation of success to reduce costs and storage space.
As to Claim 12, Johnson, Heichelbech, Yonekura, Chen and Halbe teach the limitations of claim 10.
Halbe further teaches: wherein determining the adjusted reactant amount comprises: monitoring, by the computing system, the adjusting; determining that the reactant flow has stabilized (Halbe: par. 0083, the stability of the engine is monitored); and
determining, by the computing system based on the stabilized reactant flow, the adjusted reactant amount (Examiner asserts that as combined, the adjusted reactant amount is determined and stored for the training and prediction).
Halbe teaches in general concepts related to determining a remaining useful life (RUL) of a component of an engine system (Halbe: Abstract). Specifically, Halbe teaches that certain data is preprocessed based on the status (Halbe: par. 0083, “pre-processing the ignitor data, by the RUL modeling circuit 212, may include cleaning and filtering operations, such as dropping empty rows, discarding zero load points and/or engine idle conditions”).
It would have been obvious to a person having ordinary skill in the art at a time before the effective filing date of the invention to have modified the Johnson- Heichelbech-YonekuraChen device by including computer instructions to store only certain data as taught and disclosed by Halbe. Such a person would have been motivated to do so with a reasonable expectation of success to reduce costs and storage space.
F.
Claims 13-14 and 16-19 are rejected under 35 USC. § 103 as being unpatentable over Zhu et al. (“Zhu”), Chinese Patent Application Publication 111111430 published on May 8, 2020 in view of Vaughan et al., (“Vaughan”), United States Patent Application Publication 2016/0025028 published Jan. 8, 2016.
As to Claim 13, Zhu teaches: A method for training a machine-learned model for outputting a reactant amount, comprising:
obtaining, by a self-adjusting reactant flow control system, emissions data indicative of one or more emissions amounts (Zhu: p. 2, “the NOx concentration at the SCR outlet is automatically adjusted and can be continuously input and the outlet NOx concentration value meets the standard emission”); adjusting, by the self-adjusting reactant flow control system based on the emissions data, a first amount of reactant provided to a selective catalytic reduction system (Zhu: p. 6,ffunctions to adjust the flow rate of the of the urea solution may be reduced or increased); monitoring, by a computing system comprising one or more computing devices, the adjusting (Zhu: p. 6, for each of the functions, the PID loop is adjusted based on the detected amounts and concentrations, which Examiner asserts is a monitoring); determining that the first amount of the reactant provided to the selective catalytic reduction system has stabilized (Zhu: p. 6, “After the optimization of the denitration adjustment control according to this scheme, the denitration and ammonia injection are automatically adjusted and stabilized, and the NOx emissions are stabilized to meet the standard”); and
Zhu may not explicitly teach: training, by the computing system using one or more data examples comprising data indicative of the stabilized first amount, the machine-learned model.
Vaughan teaches in general concepts related to controlling an internal combustion engine on a cycle-by-cycle basis and maintaining training data (Vaughan: Abstract). Specifically,
Vaughan teaches that training data is combined with adaptive data to form a combined data set
(Vaughan: par. 0012),
It would have been obvious to a person having ordinary skill in the art at a time before the effective filing date of the invention to have modified the Zhu device and techniques by including computer instructions to train the model with Zhu’s stabilized data paired with the training data as taught and disclosed by Vaughan. Such a person would have been motivated to do so with a reasonable expectation of success to allow for a useful training data set..
As to Claim 14, Zhu and Vaughan teach the elements of claim 13.
Vaughan further teaches: wherein the machine-learned model is configured to:
retrieve, responsive to receiving one or more inference inputs, data from a data structure comprising the one or more data examples based on the one or more inference inputs; and generate, based on the retrieved data, an output (Vaughan: cl. 4, the stored captured measurements are downloaded into a data store and used for determining a matrix of the mapping function for the engine).
As to Claim 16, Zhu and Vaughan teach the elements of claim 13.
Vaughan further teaches: deleting, by the computing system from a data structure comprising the one or more data examples, an earlier data example comprising data indicative of an earlier reactant amount (Vaughan: par. 0035, a ring buffer is implemented, allowing for forgetting of old data).
As to Claim 17, Zhu and Vaughan teach the elements of claim 13.
Vaughan further teaches: determining whether an industrial system comprising the selfadjusting reactant flow control system is in one or more predetermined conditions indicative of a lack of emissions data quality (Vaughan: par. 0064, outlier data may be reported and removed); and
responsive to determining that the industrial system is not in any of the one or more predetermined conditions, training the machine-learned model using the one or more data examples (Examiner asserts that the training will then take place without the outlier data).
As to Claim 18, Zhu and Vaughan teach the elements of claim 17.
Zhu further teaches: wherein the one or more predetermined conditions comprise at least one of:
a startup process of the industrial system; a shutdown process of the industrial system; a calibration mode of a component of the industrial system(Vaughan: par. 0064: a cycle misfired within a certain statistical criteria are part of a calibration mode); and a data signal having a current or voltage outside an expected current range or voltage range.
As to Claim 19, Zhu and Vaughan teach the elements of claim 13.
Zhu further teaches: wherein the self-adjusting reactant flow control system comprises a proportional-integral-derivative controller (Zhu: p. 1, a PID).
G.
Claim 15 is rejected under 35 USC. § 103 as being unpatentable over Zhu et al. (“Zhu”), Chinese Patent Application Publication 111111430 published on May 8, 2020 in view of Vaughan et al., (“Vaughan”), United States Patent Application Publication 2016/0025028 published Jan. 8, 2016 and in further view of Halbe et al., (“Halbe”), United States Patent Application Publication 2024/0255940 published Aug. 1, 2024.
As to Claim 15, Zhu and Vaughan teach the elements of claim 13.
Zhu and Vaughan may not explicitly teach: providing, by the computing system to the machine-learned model, input data associated with a system state of an industrial system comprising the selective catalytic reduction system; generating, by the machine-learned model based on the input data, output data indicative of a second amount of the reactant; determining, based on a comparison between the first amount and the second amount, whether to store the data indicative of the first amount in a data structure comprising the one or more data examples.
Halbe teaches in general concepts related to determining a remaining useful life (RUL) of a component of an engine system (Halbe: Abstract). Specifically, Halbe teaches that certain data is preprocessed based on the status (Halbe: par. 0083, “pre-processing the ignitor data, by the RUL modeling circuit 212, may include cleaning and filtering operations, such as dropping empty rows, discarding zero load points and/or engine idle conditions”).
It would have been obvious to a person having ordinary skill in the art at a time before the effective filing date of the invention to have modified the Zhu-Vaughan device by including computer instructions to store only certain data as taught and disclosed by Halbe. Such a person would have been motivated to do so with a reasonable expectation of success to reduce costs and storage space.
Conclusion
Prior art not relied upon but deemed relevant to the present application:
• Bowden, JR. et al., (“Bowden”), 2022/0399085 published in Dec. 15, 2022
(teaching SCR principles).
Any inquiry concerning this communication or earlier communications from the examiner should be directed to JAMES T TSAI whose telephone number is (571)270-3916. The examiner can normally be reached M-F 8-5 Eastern.
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, Viker Lamardo can be reached at 571-270-5871. 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.
/JAMES T TSAI/
Primary Examiner, Art Unit 2147
Prosecution Insights