Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
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 1-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to a judicial exception without significantly more.
Step 1 (The Statutory Categories): Is the claim to a process, machine, manufacture, or composition of matter? MPEP 2106.03.
Per Step 1, claims 1- 8 is to an apparatus (system) (i.e., a machine), claim 9-16 to a method (i.e., a process), Claim 17-20 to a computer -readable medium (i.e., a manufacture). Thus, the claims are directed to statutory categories of invention. However, the claims are rejected under 35 U.S.C. 101 because they are directed to an abstract idea, a judicial exception, without reciting additional elements that integrate the judicial exception into a practical application.
The analysis proceeds to Step 2A Prong One.
Step 2A Prong One: Does the claim recite an abstract idea, law of nature, or natural phenomenon? MPEP 2106.04.
The abstract idea of claim 1 and 9 (claim 1 being representative):
An apparatus for diagnosis and prediction of a severe accident in a nuclear power plant, comprising: a classification unit configured to derive a plurality of scenarios for diagnosis and prediction of the severe accident in the nuclear power plant;
a storage medium storing instructions for executing a method for diagnosis and prediction of the severe accident in the nuclear power plant using a learning model trained by a training database including training input variables for the plurality of scenarios and severe accident diagnosis and prediction information corresponding to the training input variables;
and a processor executing the one or more instructions stored in the storage medium, wherein the instructions, when executed by the processor, cause the processor to obtain diagnostic input variables for the diagnosis and prediction of the severe accident in the nuclear power plant, input the diagnostic input variables into the learning model to check the severe accident diagnosis and prediction information, and output the checked severe accident diagnosis and prediction information.
The abstract idea of claim 17:
A non-transitory computer-readable storage medium storing computer executable instructions, wherein the instructions, when executed by a processor, cause the processor to perform a method for training a learning model for diagnosis and prediction of a severe accident in a nuclear power plant, the method comprising: preparing the learning model including a severe accident prediction learning model and a source term prediction learning model;
selecting training input variables for the diagnosis and prediction of the severe accident in the nuclear power plant; deriving a plurality of scenarios for the diagnosis and prediction of the severe accident in the nuclear power plant;
constructing a training database for each scenario;
inputting the training input variables into the severe accident prediction learning model and training the severe accident prediction learning model to predict changes in the training input variables and output a severe accident prediction result; and inputting the training input variables into the source term prediction learning model and training the source term prediction learning model to predict radioactive material release information and output a source term prediction result.
The abstract idea steps italicized above are those which could be performed mentally, including with pen and paper. The steps describe, at a high level, diagnosing, predicting, classifying, storing, obtaining and executing accident scenarios. If a claim limitation, under its broadest reasonable interpretation, covers performance of the limitation in the mind, including observations, evaluations, judgements, and/or opinions, then it falls within the Mental Processes – Concepts Performed in the Human Mind grouping of abstract ideas. Accordingly, the claim recites an abstract idea.
Additionally and alternatively, the abstract idea steps italicized above relate to determining/predicting accident at a power plant, which constitutes a process that, under its broadest reasonable interpretation, covers managing personal behavior relationships, interactions between people. This is further supported by [0018] of applicant’s specification as filed. If a claim limitation, under its broadest reasonable interpretation, covers managing personal behavior relationships, interactions between people, including social activities, teaching, and/or following rules or instructions, then it falls within the Certain Methods of Organizing Human Activity – Managing Personal Behavior Relationships, Interactions Between People grouping of abstract ideas. Accordingly, the claim recites an abstract idea.
Step 2A Prong Two: Does the claim recite additional elements that integrate the judicial exception into a practical application? MPEP 2106.04.
This judicial exception is not integrated into a practical application because the additional elements are merely instructions to apply the abstract idea to a computer, as described in MPEP 2106.05(f).
Claim 1 and 9 recite the following additional elements: a classification unit, a storage medium, learning model trained, database, a processor
Claim 17 recite the following additional elements: A non-transitory computer-readable storage medium, a processor, a learning model, a source term prediction learning model, training database, the severe accident prediction learning model, source term prediction learning model.
These elements are merely instructions to apply the abstract idea to a computer, per MPEP 2106.05(f). Applicant has only described generic computing elements in their specification, as seen in [0025] of applicant’s specification as filed, for example.
Further, the combination of these elements is nothing more than a generic computing system applied to the tasks of the abstract idea. Because the additional elements are merely instructions to apply the abstract idea to a generic computing system, they do not integrate the abstract idea into a practical application, when viewed in combination. See MPEP 2106.05(f).
Therefore, per Step 2A Prong Two, the additional elements, alone and in combination, do not integrate the judicial exception into a practical application. The claim is directed to an abstract idea.
Step 2B (The Inventive Concept): Does the claim recite additional elements that amount to significantly more than the judicial exception? MPEP 2106.05.
Step 2B involves evaluating the additional elements to determine whether they amount to significantly more than the judicial exception itself.
The examination process involves carrying over identification of the additional element(s) in the claim from Step 2A Prong Two and carrying over conclusions from Step 2A Prong Two pertaining to MPEP 2106.05(f).
The additional elements and their analysis are therefore carried over: applicant has merely recited elements that facilitate the tasks of the abstract idea, as described in MPEP 2106.05(f).
Further, the combination of these elements is nothing more than a generic computing system. When the claim elements above are considered, alone and in combination, they do not amount to significantly more.
Therefore, per Step 2B, the additional elements, alone and in combination, are not significantly more. The claims are not patent eligible.
The analysis takes into consideration all dependent claims as well:
Dependent claims 2-8, 10-16 and 18-20 contain additional steps that further narrow the abstract idea above.
Claim 2, 3, 10, 11, 18 recites the following additional elements: a severe accident prediction learning model, a source term prediction learning model, computer-readable recording medium. Applicant has only described generic computing elements in their specification, as seen in {[0019]} of applicant’s specification as filed. This does not integrate the abstract idea into practical application and/or add significantly more. The claim is ineligible. Refer to MPEP 2106.05(f).
Claim 7 recites the following additional elements: processor, database, analysis code. Applicant has only described generic computing elements in their specification, as seen in {[0015]} of applicant’s specification as filed. This does not integrate the abstract idea into practical application and/or add significantly more. The claim is ineligible. Refer to MPEP 2106.05(f).
Claim 12, 13, 14, 15, 19 and 20 recites the following additional elements: time series data, training database, analysis code, computer-readable recording medium. Applicant has only described generic computing elements in their specification, as seen in {[0060-0062]} of applicant’s specification as filed. This does not integrate the abstract idea into practical application and/or add significantly more. The claim is ineligible. Refer to MPEP 2106.05(f).
Dependent claim 8 and 16, further describes the abstract idea. Claim 8and 16 are based on the claims describing a mental process of training and determining using phenomenon analysis code. See applicants’ specification {[0062]} for further details. The phenomenon analysis codes are merely generic technology to store vehicle information. The apparatus is not a technical improvement and merely implementing the abstract idea using generic technology. As such additional elements are not significantly more or transformative into a practical application. MPEP 2106.05(f). Therefore, the claims are covered under certain methods of mental process groupings of abstract ideas.
In conclusion the claims do not provide an inventive concept, because the claims do not recite additional elements or a combination of elements that amount to significantly more than the judicial exception of the claims. Therefore, whether taken individually or as an order combination, the claims are nonetheless rejected under 35 U.S.C. 101 as being directed to non-statutory subject matter.
Accordingly, claims 1-20 are rejected under 35 USC § 101 as being directed to non-statutory subject matter.
Claim Rejections - 35 USC § 103
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.
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.
Claim(s) 1-20 are rejected under 35 U.S.C. 103 as being unpatentable over Yilmaz et al [US 2022/0027731 A1] hereafter Yilmaz, in view of Banyay et al [US 2022/0270772 A1] hereafter Banyay.
As per claim 1 and 9 (Claim 1 being representative):
Yilmaz discloses the nuclear power plant and generating plurality scenarios, and event tree, [0040-0041]; classification of the plurality of scenarios [0054]
An apparatus for diagnosis and prediction of a severe accident in a nuclear power plant, comprising: a classification unit configured to derive a plurality of scenarios for diagnosis and prediction of the severe accident in the nuclear power plant;
{[0040] The tool 102 may include a processing unit 106 (e.g., a Central Processing Unit (CPU), a Graphical Processing Unit (GPU) or similar) that may be configured to access the memory 104 and execute the machine-readable instructions stored in the memory 104… The processing unit 106 may be configured to receive scenario data 108. The scenario data 108 may be generated based on a DET (dynamic event trees) evaluation associated with an emergency causing event… The scenario test data 108 may be representative of a plurality of different test scenarios for a system at a nuclear facility.
[0041] The ADAPT system may be programmed to determine an evolution of possible scenarios for a system model (e.g., the three-loop PWR) based on branching and stopping rules, which may be user-defined.
[0054] The neural network engine 112 may be programmed to provide the scenario test data to the CNN 502 for classification of the plurality of different scenarios.}
Yilmaz discloses the actual prediction and classification output; see [0052-0054]
{[0052] the CNN 502 may be programmed to receive input data 504 (e.g., scenarios test data from a nuclear power plant) and process the input data to produce a plurality of output labels 506.
[0054] The neural network engine 112 may be programmed to train the CNN 502 based on scenario training data comprising a plurality of training scenarios…..The CNN 502 may be programmed to classify each of the plurality of different scenarios as having a TEDE less than or equal to 10 rem or having a TEDE greater than 10 rem.}
Yilmaz does not explicitly disclose the following, however; Banyay discloses storage medium [0085]; training the model and nuclear power plant [0034];
a storage medium storing instructions for executing a method for diagnosis and prediction of the severe accident in the nuclear power plant using a learning model trained by a training database including training input variables for the plurality of scenarios and severe accident diagnosis and prediction information corresponding to the training input variables;
{[0003] a system configured to monitor the structural health of reactor vessel internals of a nuclear reactor is disclosed
[0085] Software may be embodied as a software package, code, instructions, instruction sets and/or data recorded on non-transitory computer readable storage medium.
[0031] configured to perform a sensitivity analysis of characteristics and conditions—or candidate degradation scenarios
[0034] any artificial intelligence, machine learning, deep learning, and/or neural network techniques can be implemented to train and/or verify the mechanical diagnostic subsystem 112 and improve the model 113. Accordingly, the computation of parameter sensitivities and subsequent sensitivity analysis of candidate degradation scenarios can continually improve in time.
[0035] continuously and efficiently assess the credibility of the analysis performed by the anomaly detection subsystem 110 and can further generate diagnostic conclusions that illustrate likely sources of degradation within the RVI and inform future inspections and/or maintenance}
Banyay discloses inputting diagnostic variables into a learning model [0034] [0037]; diagnostic output/ prediction [0033] [0053]
and a processor executing the one or more instructions stored in the storage medium, wherein the instructions, when executed by the processor, cause the processor to obtain diagnostic input variables for the diagnosis and prediction of the severe accident in the nuclear power plant, input the diagnostic input variables into the learning model to check the severe accident diagnosis and prediction information, and output the checked severe accident diagnosis and prediction information.
{[0040] the anomaly detection subsystem 110 can include a control circuit 107 configured to process information received from the sensor 103 and/or memory 104 via covariance matrix calculations 209, wavenumber decompositions 210, data normalizations 211, direct current voltage shifts 213, mode identification 214 and ultimately, feature extraction 215.
[0033] The assessed likelihood of each candidate degradation scenario can be included in a diagnostic conclusion generated by the mechanical diagnostic subsystem 110, which can further include historical remedial information accessed from the memory 104, which correlates to the most likely candidate degradation scenarios.
[0034] the mechanical diagnostic subsystem 112 can be further configured to implement artificial intelligence, machine learning, deep learning, and/or neural network techniques based to improve its assessment of candidate degradation scenarios received from the anomaly detection subsystem 110.
[0037] The asset management platform 116 can be further configured to receive the diagnostic conclusion directly from the mechanical diagnostic subsystem 112 and/or the digital twin 114 as well as any aggregate inputs 106. The asset management platform 116 can be further configured to generate diagnostic conclusions, alerts, and/or other useful information associated with the RVI based on inputs it receives from the mechanical diagnostic subsystem 112, anomaly detection subsystem 110, and/or digital twin 114 to generate diagnostic conclusions.
[0053] wherein the generation of the diagnostic conclusion includes machine learning.}
Motivation: It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify an Apparatus and Method for Diganosis and Prediction of Severe Accidents in Nuclear Power Plant using Artificial Intelligence as disclosed by Yilmaz with an addition of a storage medium and inputting diagnostic variables into a learning model as taught by Banyay, to store instructions and verify the prediction or outcome.
As per claim 2 and 10 (Similar scope);
Yilmaz discloses training the input variable [0045]; severe accident prediction or progression [0006] [0036-0038]
The apparatus of claim 1, wherein the learning model includes: a severe accident prediction learning model trained to receive the training input variables, predict changes in the training input variables, and output a severe accident prediction result; and
{[0045] the observable parameters for each scenario may be obtained from the severe accident analysis code for a given number of time divisions over multiple simulations of the system. Each scenario may be represented by a matrix, n×m, wherein n is a number of the observable parameters and m is the given number of time divisions.
[0006] The computer-implemented method may include providing a sub-set of test scenarios to a trained neural network to identify one or more sub-set of test scenarios. The one or more identified sub-set of test scenarios may correspond to one or more anomaly test scenarios from the sub-set of test scenarios that is most likely to lead to an undesirable outcome associated with an emergency causing event.
[0036] The systems described herein can process data and assist personnel in assessing an event sequence probabilistically as an Unusual Event (UE), an Alert, a Site Area Emergency (SAE) or a General Emergency (GE) as the accident evolves
[0038] the systems described herein may assist personnel in predicting the likelihood of future states of the nuclear facility to support the declaration of a site emergency and to assist in the emergency response.}
Yilmaz discloses the Radioactive source term and release output [0037-0038] [0040] [0044];
a source term prediction learning model trained to receive the training input variables and output a source term prediction result for predicting radioactive material release information.
[0037] the systems described herein may be configured to construct a real-time SAMGs based on dynamic event trees (DETs) to support a declaration of a site emergency and to guide off-site response. In DET analysis, the systems described herein may be configured to characterize alternative scenarios or pathways by branching points in a tree as the accident progresses in time for which branching probabilities may be assigned in a similar manner to ETs…. DETs may be used to estimate a likelihood of different levels of offsite release of radionuclides based on deep learning methodologies described herein based on the training data set.
[0040] The scenario data 108 may be generated based on a DET (dynamic event trees) evaluation associated with an emergency causing event.
[0044] For each scenario dataset, the severe accident analysis code (or the ADAPT system) may be programmed to calculate probabilities of radionuclide release fractions. Each scenario may be characterized by a set of observable parameters of the system in response to the emergency causing event. For each scenario dataset, the severe accident analysis code (or the ADAPT system) may be programmed to calculate probabilities of radionuclide release fractions.}
As per claim 3;
Yilmaz discloses the sources term radio-active Material release [0037]; training of the input variable [0045], severe accident prediction [0038]; classification of different scenarios and the undesirable outcome See [0054];
The apparatus of claim 2, wherein the learning model further includes a severe accident diagnosis learning model trained to classify the training input variables corresponding to the scenarios and outputs a severe accident diagnosis result, wherein the severe accident prediction learning model is trained to output results of prediction of changes in the training input variables on the basis of the severe accident diagnosis result provided from the severe accident diagnosis learning model, and wherein the source term prediction learning model is trained to output the source term prediction result for predicting radioactive material release information on the basis of the training input variables for the scenarios with respect to the severe accident diagnosis result provided from the severe accident diagnosis learning model.
[0037] DETs may be used to estimate a likelihood of different levels of offsite release of radionuclides based on deep learning methodologies described herein based on the training data set.
[0038] the systems described herein may assist personnel in predicting the likelihood of future states of the nuclear facility to support the declaration of a site emergency and to assist in the emergency response.
[0044] For each scenario dataset, the severe accident analysis code (or the ADAPT system) may be programmed to calculate probabilities of radionuclide release fractions.
[0045] the observable parameters for each scenario may be obtained from the severe accident analysis code for a given number of time divisions over multiple simulations of the system. Each scenario may be represented by a matrix, n×m, wherein n is a number of the observable parameters and m is the given number of time divisions.
[0054] The neural network engine 112 may be programmed to provide the scenario test data to the CNN 502 for classification of the plurality of different scenarios. The CNN 502 may be programmed to classify each of the plurality of different scenarios as having a TEDE less than or equal to 10 rem or having a TEDE greater than 10 rem…. Each scenario of the plurality of different scenarios classified as having the TEDE greater than 10 rem may correspond to one or more scenarios that is most likely to lead to the undesirable outcome associated with the emergency causing event…. the undesirable outcome may correspond to a release of ionizing radiation.
As per claim 4, 12 and 19 (Similar scope);
Yilmaz discloses the time series/ time divided observation of the nuclear facility. See [0036-0040] [0045].
The apparatus of claim 1, wherein the diagnostic input variables include time series data related to status information of the nuclear power plant.
[0036] observable parameters from personnel and environmental devices (e.g., instrumentation) at a nuclear facility.
[0040] The scenario test data 108 may be representative of a plurality of different test scenarios for a system at a nuclear facility.
[0045] the observable parameters for each scenario may be obtained from the severe accident analysis code for a given number of time divisions over multiple simulations of the system. Each scenario may be represented by a matrix, n×m, wherein n is a number of the observable parameters and m is the given number of time divisions.
As per claim 5, 13 and 20 (Similar scope);
Yilmaz discloses the scenario generation and accident analysis, probabilistic aspect; [0034] [0036] [0040]
The apparatus of claim 1, wherein the scenarios are derived based on probabilistic safety assessment (PSA).
{[0040] The scenario data 108 may be generated based on a DET (dynamic event trees) evaluation associated with an emergency causing event… the scenario data 108 may be generated based on a DET study performed for a station blackout (SBO) in a three-loop pressurized water reactor (PWR).
[0034] An event tree (ET)/fault tree (FT) methodology may be traditionally used for PRA to account for uncertainties in accident progression.
[0036] The systems described herein can process data and assist personnel in assessing an event sequence probabilistically as an Unusual Event (UE), an Alert, a Site Area Emergency (SAE) or a General Emergency (GE) as the accident evolves and may reduce the level of exposure of the population, as well as the negative impacts of possible evacuation.}
As per claim 6 and 14 (Similar scope);
Yilmaz does not explicitly disclose the following, however, Banyay discloses;
The apparatus of claim 5, wherein the scenarios are classified into detailed scenario of initiating events according to the probabilistic safety assessment on the basis of a plant damage state event tree (PDS ET) technique.
{[0031] The mechanical diagnostic subsystem 112 of FIG. 1 can be configured to perform a sensitivity analysis of characteristics and conditions—or candidate degradation scenarios—it receives from either the anomaly detection subsystem 110 and/or digital twin 114. As is true for most sensitivity analyses, the mechanical diagnostic subsystem 112 can determine how different values of an independent variable can affect a particular dependent variable under a given set of assumptions. In other words, the sensitivity analysis can assess the level of mathematical uncertainty associated with a particular candidate degradation scenario, as determined by the anomaly detection subsystem 110.
[0033] The assessed likelihood of each candidate degradation scenario can be included in a diagnostic conclusion generated by the mechanical diagnostic subsystem 110, which can further include historical remedial information accessed from the memory 104, which correlates to the most likely candidate degradation scenarios.}
Motivation: It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify an Apparatus and Method for Diagnosis and Prediction of Severe Accidents in Nuclear Power Plant using Artificial Intelligence as disclosed by Yilmaz with an addition of a training input variable as taught by Banyay, to access degradation scenarios.
Yilmaz discloses the event tree, scenarios
a plant damage state event tree (PDS ET) technique.
{[0034] An event tree (ET)/fault tree (FT) methodology may be traditionally used for PRA to account for uncertainties in accident progression. The ET may be used to model the sequence of events to possible end states.
[0037] the systems described herein may be configured to characterize alternative scenarios or pathways by branching points in a tree as the accident progresses in time for which branching probabilities may be assigned in a similar manner to ETs.
[0040] The scenario data 108 may be generated based on a DET (dynamic event trees) evaluation associated with an emergency causing event… the scenario data 108 may be generated based on a DET study performed for a station blackout (SBO) in a three-loop pressurized water reactor (PWR).}
As per claim 7 and 15 (Similar scope);
Banyay discloses;
The apparatus of claim 1, wherein the processor is configured to construct the training database in which uncertainty is analyzed for each of the scenarios and stores the training database in a database unit.
{[0031] The mechanical diagnostic subsystem 112 of FIG. 1 can be configured to perform a sensitivity analysis of characteristics and conditions—or candidate degradation scenarios—it receives from either the anomaly detection subsystem 110 and/or digital twin 114. As is true for most sensitivity analyses, the mechanical diagnostic subsystem 112 can determine how different values of an independent variable can affect a particular dependent variable under a given set of assumptions. In other words, the sensitivity analysis can assess the level of mathematical uncertainty associated with a particular candidate degradation scenario, as determined by the anomaly detection subsystem 110.
[0033] The assessed likelihood of each candidate degradation scenario can be included in a diagnostic conclusion generated by the mechanical diagnostic subsystem 110, which can further include historical remedial information accessed from the memory 104, which correlates to the most likely candidate degradation scenarios.}
Banyay discloses stores the training database in a database unit.
{[0085] Software may be embodied as a software package, code, instructions, instruction sets and/or data recorded on non-transitory computer readable storage medium.
[0031] configured to perform a sensitivity analysis of characteristics and conditions.}
Motivation: It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify an Apparatus and Method for Diagnosis and Prediction of Severe Accidents in Nuclear Power Plant using Artificial Intelligence as disclosed by Yilmaz with an addition of a storage medium and inputting diagnostic variables into a learning model as taught by Banyay, to store instructions and verify the prediction or outcome.
As per claim 8 and 16 (Similar scope);
Yilmaz discloses the codes;
The apparatus of claim 7, wherein the uncertainty includes phenomenon analysis code uncertainty and analysis scenario uncertainty.
{[0034] An event tree (ET)/fault tree (FT) methodology may be traditionally used for PRA to account for uncertainties in accident progression.
[0042] A severe accident analysis code may include a simulation data generator… MELCOR may be used to model a behavior of a system associated with an emergency causing initiating event.}
As per claim 11;
Banyay discloses performing a sensitivity analysis,
The method of claim 9, wherein the learning model further includes a severe accident diagnosis learning model trained to classify the training input variables corresponding the scenarios and output a severe accident diagnosis result, and wherein the performing processing includes: outputting results of prediction of changes in the diagnostic input variables on the basis of the severe accident diagnosis result provided from the severe accident diagnosis learning model using the severe accident prediction learning model; and outputting a source term prediction result for predicting radioactive material release information on the basis of the diagnostic input variables for the scenarios with respect to the severe accident diagnosis result provided from the severe accident diagnosis learning model using the source term prediction learning model.
{[0031] The mechanical diagnostic subsystem 112 of FIG. 1 can be configured to perform a sensitivity analysis of characteristics and conditions—or candidate degradation scenarios—it receives from either the anomaly detection subsystem 110 and/or digital twin 114. As is true for most sensitivity analyses, the mechanical diagnostic subsystem 112 can determine how different values of an independent variable can affect a particular dependent variable under a given set of assumptions. In other words, the sensitivity analysis can assess the level of mathematical uncertainty associated with a particular candidate degradation scenario, as determined by the anomaly detection subsystem 110.
[0034] the mechanical diagnostic subsystem 112 can be further configured to implement artificial intelligence, machine learning, deep learning, and/or neural network techniques based to improve its assessment of candidate degradation scenarios received from the anomaly detection subsystem 110……. the mechanical diagnostic subsystem 112 can be algorithmically configured to improve its assessment of candidate degradation scenarios via Gaussian Process Regression (GPR), machine learning (e.g., k-NN, correlation grouping, etc.), and/or neural network techniques.}
Motivation: It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify an Apparatus and Method for Diagnosis and Prediction of Severe Accidents in Nuclear Power Plant using Artificial Intelligence as disclosed by Yilmaz with an addition of a training input variable as taught by Banyay, to access degradation scenarios.
Yilmaz discloses source term prediction learning model, Radioactive-material release;
{[0037] the systems described herein may be configured to construct a real-time SAMGs based on dynamic event trees (DETs) to support a declaration of a site emergency and to guide off-site response. In DET analysis, the systems described herein may be configured to characterize alternative scenarios or pathways by branching points in a tree as the accident progresses in time for which branching probabilities may be assigned in a similar manner to ETs…. DETs may be used to estimate a likelihood of different levels of offsite release of radionuclides based on deep learning methodologies described herein based on the training data set.
[0040] The scenario data 108 may be generated based on a DET (dynamic event trees) evaluation associated with an emergency causing event.
[0044] For each scenario dataset, the severe accident analysis code (or the ADAPT system) may be programmed to calculate probabilities of radionuclide release fractions. Each scenario may be characterized by a set of observable parameters of the system in response to the emergency causing event. For each scenario dataset, the severe accident analysis code (or the ADAPT system) may be programmed to calculate probabilities of radionuclide release fractions.}
Yilmaz discloses the classification of the training input variables;
{[0054] The neural network engine 112 may be programmed to provide the scenario test data to the CNN 502 for classification of the plurality of different scenarios.}
As per claim 17;
Yilmaz discloses the nuclear power plant and generating plurality scenarios, and event tree, [0040-0041]; classification of the plurality of scenarios [0054]; source term prediction learning model [0037]
A non-transitory computer-readable storage medium storing computer executable instructions, wherein the instructions, when executed by a processor, cause the processor to perform a method for training a learning model for diagnosis and prediction of a severe accident in a nuclear power plant, the method comprising: preparing the learning model including a severe accident prediction learning model and a source term prediction learning model;
{[0037] DETs may be used to estimate a likelihood of different levels of offsite release of radionuclides based on deep learning methodologies described herein based on the training data set.
[0040] The tool 102 may include a processing unit 106 (e.g., a Central Processing Unit (CPU), a Graphical Processing Unit (GPU) or similar) that may be configured to access the memory 104 and execute the machine-readable instructions stored in the memory 104… The processing unit 106 may be configured to receive scenario data 108. The scenario data 108 may be generated based on a DET (dynamic event trees) evaluation associated with an emergency causing event… The scenario test data 108 may be representative of a plurality of different test scenarios for a system at a nuclear facility.
[0041] The ADAPT system may be programmed to determine an evolution of possible scenarios for a system model (e.g., the three-loop PWR) based on branching and stopping rules, which may be user-defined.
[0054] The neural network engine 112 may be programmed to provide the scenario test data to the CNN 502 for classification of the plurality of different scenarios.}
Yilmaz discloses the actual prediction and classification output; see [0052-0054]
{[0052] the CNN 502 may be programmed to receive input data 504 (e.g., scenarios test data from a nuclear power plant) and process the input data to produce a plurality of output labels 506.
[0054] The neural network engine 112 may be programmed to train the CNN 502 based on scenario training data comprising a plurality of training scenarios…..The CNN 502 may be programmed to classify each of the plurality of different scenarios as having a TEDE less than or equal to 10 rem or having a TEDE greater than 10 rem.}
Yilmaz discloses;
source term prediction learning model to predict radioactive material release information and output a source term prediction result.
[0037] the systems described herein may be configured to construct a real-time SAMGs based on dynamic event trees (DETs) to support a declaration of a site emergency and to guide off-site response. In DET analysis, the systems described herein may be configured to characterize alternative scenarios or pathways by branching points in a tree as the accident progresses in time for which branching probabilities may be assigned in a similar manner to ETs…. DETs may be used to estimate a likelihood of different levels of offsite release of radionuclides based on deep learning methodologies described herein based on the training data set.
[0040] The scenario data 108 may be generated based on a DET (dynamic event trees) evaluation associated with an emergency causing event.
[0044] For each scenario dataset, the severe accident analysis code (or the ADAPT system) may be programmed to calculate probabilities of radionuclide release fractions. Each scenario may be characterized by a set of observable parameters of the system in response to the emergency causing event. For each scenario dataset, the severe accident analysis code (or the ADAPT system) may be programmed to calculate probabilities of radionuclide release fractions.
Yilmaz does not explicitly disclose the following, however; Banyay discloses;
selecting training input variables for the diagnosis and prediction of the severe accident in the nuclear power plant; deriving a plurality of scenarios for the diagnosis and prediction of the severe accident in the nuclear power plant;
{[0031] configured to perform a sensitivity analysis of characteristics and conditions—or candidate degradation scenarios
[0003] a system configured to monitor the structural health of reactor vessel internals of a nuclear reactor is disclosed
[0034] any artificial intelligence, machine learning, deep learning, and/or neural network techniques can be implemented to train and/or verify the mechanical diagnostic subsystem 112 and improve the model 113. Accordingly, the computation of parameter sensitivities and subsequent sensitivity analysis of candidate degradation scenarios can continually improve in time.
[0035] continuously and efficiently assess the credibility of the analysis performed by the anomaly detection subsystem 110 and can further generate diagnostic conclusions that illustrate likely sources of degradation within the RVI and inform future inspections and/or maintenance}
Banyay discloses inputting diagnostic variables into a learning model [0034] [0037]; diagnostic output/ prediction [0033] [0053]
constructing a training database for each scenario; inputting the training input variables into the severe accident prediction learning model and training the severe accident prediction learning model to predict changes in the training input variables and output a severe accident prediction result; and inputting the training input variables into the source term prediction learning model and training the source term prediction learning model to predict radioactive material release information and output a source term prediction result.
{[0040] the anomaly detection subsystem 110 can include a control circuit 107 configured to process information received from the sensor 103 and/or memory 104 via covariance matrix calculations 209, wavenumber decompositions 210, data normalizations 211, direct current voltage shifts 213, mode identification 214 and ultimately, feature extraction 215.
[0033] The assessed likelihood of each candidate degradation scenario can be included in a diagnostic conclusion generated by the mechanical diagnostic subsystem 110, which can further include historical remedial information accessed from the memory 104, which correlates to the most likely candidate degradation scenarios.
[0034] the mechanical diagnostic subsystem 112 can be further configured to implement artificial intelligence, machine learning, deep learning, and/or neural network techniques based to improve its assessment of candidate degradation scenarios received from the anomaly detection subsystem 110.
[0037] The asset management platform 116 can be further configured to receive the diagnostic conclusion directly from the mechanical diagnostic subsystem 112 and/or the digital twin 114 as well as any aggregate inputs 106. The asset management platform 116 can be further configured to generate diagnostic conclusions, alerts, and/or other useful information associated with the RVI based on inputs it receives from the mechanical diagnostic subsystem 112, anomaly detection subsystem 110, and/or digital twin 114 to generate diagnostic conclusions.
[0053] wherein the generation of the diagnostic conclusion includes machine learning.}
Motivation: It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify an Apparatus and Method for Diagnosis and Prediction of Severe Accidents in Nuclear Power Plant using Artificial Intelligence as disclosed by Yilmaz with an addition of a training input variable as taught by Banyay, to access degradation scenarios.
As per claim 18;
Yilmaz does not explicitly disclose the following; however, Banyay discloses;
The computer-readable recording medium of claim 17, wherein the learning model further includes a severe accident diagnosis learning model trained to classify the training input variables corresponding to the scenarios and outputs a severe accident diagnosis result,
{[0031] The mechanical diagnostic subsystem 112 of FIG. 1 can be configured to perform a sensitivity analysis of characteristics and conditions—or candidate degradation scenarios—it receives from either the anomaly detection subsystem 110 and/or digital twin 114. As is true for most sensitivity analyses, the mechanical diagnostic subsystem 112 can determine how different values of an independent variable can affect a particular dependent variable under a given set of assumptions. In other words, the sensitivity analysis can assess the level of mathematical uncertainty associated with a particular candidate degradation scenario, as determined by the anomaly detection subsystem 110.}
Banyay discloses;
wherein the training of the severe accident prediction learning model includes training the severe accident prediction learning model to output results of prediction of changes in the training input variables using the severe accident diagnosis result provided from the severe accident diagnosis learning model, and wherein the training of the source term prediction learning model includes training the source term prediction learning model to output radioactive material release information using the training input variables for the scenarios of the severe accident diagnosis result provided from the severe accident diagnosis learning model.
{[0034] the mechanical diagnostic subsystem 112 can be further configured to implement artificial intelligence, machine learning, deep learning, and/or neural network techniques based to improve its assessment of candidate degradation scenarios received from the anomaly detection subsystem 110……. the mechanical diagnostic subsystem 112 can be algorithmically configured to improve its assessment of candidate degradation scenarios via Gaussian Process Regression (GPR), machine learning (e.g., k-NN, correlation grouping, etc.), and/or neural network techniques.}
Motivation: It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify an Apparatus and Method for Diagnosis and Prediction of Severe Accidents in Nuclear Power Plant using Artificial Intelligence as disclosed by Yilmaz with an addition of a training input variable as taught by Banyay, to access degradation scenarios.
Yilmaz discloses;
source term prediction learning model to output radioactive material release information
{[0037] the systems described herein may be configured to construct a real-time SAMGs based on dynamic event trees (DETs) to support a declaration of a site emergency and to guide off-site response. In DET analysis, the systems described herein may be configured to characterize alternative scenarios or pathways by branching points in a tree as the accident progresses in time for which branching probabilities may be assigned in a similar manner to ETs…. DETs may be used to estimate a likelihood of different levels of offsite release of radionuclides based on deep learning methodologies described herein based on the training data set.
[0040] The scenario data 108 may be generated based on a DET (dynamic event trees) evaluation associated with an emergency causing event.
[0044] For each scenario dataset, the severe accident analysis code (or the ADAPT system) may be programmed to calculate probabilities of radionuclide release fractions. Each scenario may be characterized by a set of observable parameters of the system in response to the emergency causing event. For each scenario dataset, the severe accident analysis code (or the ADAPT system) may be programmed to calculate probabilities of radionuclide release fractions.}
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure:
Tsai et al [US 2012/010,9618 A1] discloses an accident parameter identification method, combining optimization algorithm and severe accident analysis software, for severe accidents. The optimization algorithm and severe accident analysis software are compiled into individual applications. The process for parameter identification is decided by the optimization algorithm. The actual accident parameter can be obtained by minimizing the difference between the calculations and the actual signals in the nuclear power plant.
M. Mamoon and A. Jain, "Estimation of Energy Demand and Sustainable Source for India & Study of Renewable Energy though Machine Learning," 2022 International Conference on Smart and Sustainable Technologies in Energy and Power Sectors (SSTEPS), Mahendragarh, India, 2022, pp. 198-203.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to VICTOR ESONU whose telephone number is (571)272-4883. The examiner can normally be reached Monday - Friday 9:00 am - 5pm.
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, SARAH MONFELDT can be reached on (571) 270-1833. 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, vis it: 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.
/VICTOR ESONU/
Examiner, Art Unit 3629
/SARAH M MONFELDT/Supervisory Patent Examiner, Art Unit 3629
Prosecution Insights