Machine learning-based modeling of reactor physics problems has attracted increasing interest in recent years.Despite some progress in one-dimensional problems,there is still a paucity of benchmark studies that are ea...Machine learning-based modeling of reactor physics problems has attracted increasing interest in recent years.Despite some progress in one-dimensional problems,there is still a paucity of benchmark studies that are easy to solve using traditional numerical methods albeit still challenging using neural networks for a wide range of practical problems.We present two networks,namely the Generalized Inverse Power Method Neural Network(GIPMNN)and Physics-Constrained GIPMNN(PC-GIPIMNN)to solve K-eigenvalue problems in neutron diffusion theory.GIPMNN follows the main idea of the inverse power method and determines the lowest eigenvalue using an iterative method.The PC-GIPMNN additionally enforces conservative interface conditions for the neutron flux.Meanwhile,Deep Ritz Method(DRM)directly solves the smallest eigenvalue by minimizing the eigenvalue in Rayleigh quotient form.A comprehensive study was conducted using GIPMNN,PC-GIPMNN,and DRM to solve problems of complex spatial geometry with variant material domains from the fleld of nuclear reactor physics.The methods were compared with the standard flnite element method.The applicability and accuracy of the methods are reported and indicate that PC-GIPMNN outperforms GIPMNN and DRM.展开更多
This work illustrates the innovative results obtained by applying the recently developed the 2<sup>nd</sup>-order predictive modeling methodology called “2<sup>nd</sup>- BERRU-PM”, where the ...This work illustrates the innovative results obtained by applying the recently developed the 2<sup>nd</sup>-order predictive modeling methodology called “2<sup>nd</sup>- BERRU-PM”, where the acronym BERRU denotes “best-estimate results with reduced uncertainties” and “PM” denotes “predictive modeling.” The physical system selected for this illustrative application is a polyethylene-reflected plutonium (acronym: PERP) OECD/NEA reactor physics benchmark. This benchmark is modeled using the neutron transport Boltzmann equation (involving 21,976 uncertain parameters), the solution of which is representative of “large-scale computations.” The results obtained in this work confirm the fact that the 2<sup>nd</sup>-BERRU-PM methodology predicts best-estimate results that fall in between the corresponding computed and measured values, while reducing the predicted standard deviations of the predicted results to values smaller than either the experimentally measured or the computed values of the respective standard deviations. The obtained results also indicate that 2<sup>nd</sup>-order response sensitivities must always be included to quantify the need for including (or not) the 3<sup>rd</sup>- and/or 4<sup>th</sup>-order sensitivities. When the parameters are known with high precision, the contributions of the higher-order sensitivities diminish with increasing order, so that the inclusion of the 1<sup>st</sup>- and 2<sup>nd</sup>-order sensitivities may suffice for obtaining accurate predicted best- estimate response values and best-estimate standard deviations. On the other hand, when the parameters’ standard deviations are sufficiently large to approach (or be outside of) the radius of convergence of the multivariate Taylor-series which represents the response in the phase-space of model parameters, the contributions stemming from the 3<sup>rd</sup>- and even 4<sup>th</sup>-order sensitivities are necessary to ensure consistency between the computed and measured response. In such cases, the use of only the 1<sup>st</sup>-order sensitivities erroneously indicates that the computed results are inconsistent with the respective measured response. Ongoing research aims at extending the 2<sup>nd</sup>-BERRU-PM methodology to fourth-order, thus enabling the computation of third-order response correlations (skewness) and fourth-order response correlations (kurtosis).展开更多
The aging of operational reactors leads to increased mechanical vibrations in the reactor interior.The vibration of the incore sensors near their nominal locations is a new problem for neutronic field reconstruction.C...The aging of operational reactors leads to increased mechanical vibrations in the reactor interior.The vibration of the incore sensors near their nominal locations is a new problem for neutronic field reconstruction.Current field-reconstruction methods fail to handle spatially moving sensors.In this study,we propose a Voronoi tessellation technique in combination with convolutional neural networks to handle this challenge.Observations from movable in-core sensors were projected onto the same global field structure using Voronoi tessellation,holding the magnitude and location information of the sensors.General convolutional neural networks were used to learn maps from observations to the global field.The proposed method reconstructed multi-physics fields(including fast flux,thermal flux,and power rate)using observations from a single field(such as thermal flux).Numerical tests based on the IAEA benchmark demonstrated the potential of the proposed method in practical engineering applications,particularly within an amplitude of 5 cm around the nominal locations,which led to average relative errors below 5% and 10% in the L_(2) and L_(∞)norms,respectively.展开更多
In reactor neutrino experiments, the analysis of time correlations between different physical events is an important task. Such analysis can help to understand the physical mechanisms of the signal and background even...In reactor neutrino experiments, the analysis of time correlations between different physical events is an important task. Such analysis can help to understand the physical mechanisms of the signal and background events as well as the details of event selection and background estimation. This study investigates a ＂sampling and mixing＂ method used for producing large MC data samples for the Daya Bay reactor neutrino experiment. We designed a simple, generic mixing algorithm and generated large MC data samples for physics analysis from several samples according to their respective event rates. Basic plots based on the mixed data are shown.展开更多
基金partially supported by the National Natural Science Foundation of China(No.11971020)Natural Science Foundation of Shanghai(No.23ZR1429300)Innovation Funds of CNNC(Lingchuang Fund)。
文摘Machine learning-based modeling of reactor physics problems has attracted increasing interest in recent years.Despite some progress in one-dimensional problems,there is still a paucity of benchmark studies that are easy to solve using traditional numerical methods albeit still challenging using neural networks for a wide range of practical problems.We present two networks,namely the Generalized Inverse Power Method Neural Network(GIPMNN)and Physics-Constrained GIPMNN(PC-GIPIMNN)to solve K-eigenvalue problems in neutron diffusion theory.GIPMNN follows the main idea of the inverse power method and determines the lowest eigenvalue using an iterative method.The PC-GIPMNN additionally enforces conservative interface conditions for the neutron flux.Meanwhile,Deep Ritz Method(DRM)directly solves the smallest eigenvalue by minimizing the eigenvalue in Rayleigh quotient form.A comprehensive study was conducted using GIPMNN,PC-GIPMNN,and DRM to solve problems of complex spatial geometry with variant material domains from the fleld of nuclear reactor physics.The methods were compared with the standard flnite element method.The applicability and accuracy of the methods are reported and indicate that PC-GIPMNN outperforms GIPMNN and DRM.
文摘This work illustrates the innovative results obtained by applying the recently developed the 2<sup>nd</sup>-order predictive modeling methodology called “2<sup>nd</sup>- BERRU-PM”, where the acronym BERRU denotes “best-estimate results with reduced uncertainties” and “PM” denotes “predictive modeling.” The physical system selected for this illustrative application is a polyethylene-reflected plutonium (acronym: PERP) OECD/NEA reactor physics benchmark. This benchmark is modeled using the neutron transport Boltzmann equation (involving 21,976 uncertain parameters), the solution of which is representative of “large-scale computations.” The results obtained in this work confirm the fact that the 2<sup>nd</sup>-BERRU-PM methodology predicts best-estimate results that fall in between the corresponding computed and measured values, while reducing the predicted standard deviations of the predicted results to values smaller than either the experimentally measured or the computed values of the respective standard deviations. The obtained results also indicate that 2<sup>nd</sup>-order response sensitivities must always be included to quantify the need for including (or not) the 3<sup>rd</sup>- and/or 4<sup>th</sup>-order sensitivities. When the parameters are known with high precision, the contributions of the higher-order sensitivities diminish with increasing order, so that the inclusion of the 1<sup>st</sup>- and 2<sup>nd</sup>-order sensitivities may suffice for obtaining accurate predicted best- estimate response values and best-estimate standard deviations. On the other hand, when the parameters’ standard deviations are sufficiently large to approach (or be outside of) the radius of convergence of the multivariate Taylor-series which represents the response in the phase-space of model parameters, the contributions stemming from the 3<sup>rd</sup>- and even 4<sup>th</sup>-order sensitivities are necessary to ensure consistency between the computed and measured response. In such cases, the use of only the 1<sup>st</sup>-order sensitivities erroneously indicates that the computed results are inconsistent with the respective measured response. Ongoing research aims at extending the 2<sup>nd</sup>-BERRU-PM methodology to fourth-order, thus enabling the computation of third-order response correlations (skewness) and fourth-order response correlations (kurtosis).
基金partially supported by the Natural Science Foundation of Shanghai(No.23ZR1429300)the Innovation Fund of CNNC(Lingchuang Fund)+1 种基金EP/T000414/1 PREdictive Modeling with QuantIfication of UncERtainty for MultiphasE Systems(PREMIERE)the Leverhulme Centre for Wildfires,Environment,and Society through the Leverhulme Trust(No.RC-2018-023).
文摘The aging of operational reactors leads to increased mechanical vibrations in the reactor interior.The vibration of the incore sensors near their nominal locations is a new problem for neutronic field reconstruction.Current field-reconstruction methods fail to handle spatially moving sensors.In this study,we propose a Voronoi tessellation technique in combination with convolutional neural networks to handle this challenge.Observations from movable in-core sensors were projected onto the same global field structure using Voronoi tessellation,holding the magnitude and location information of the sensors.General convolutional neural networks were used to learn maps from observations to the global field.The proposed method reconstructed multi-physics fields(including fast flux,thermal flux,and power rate)using observations from a single field(such as thermal flux).Numerical tests based on the IAEA benchmark demonstrated the potential of the proposed method in practical engineering applications,particularly within an amplitude of 5 cm around the nominal locations,which led to average relative errors below 5% and 10% in the L_(2) and L_(∞)norms,respectively.
基金Supported by Chinese Academy of SciencesNational Natural Science Foundation of China(10225524, 10475086, 10535050, 10575056 and Y2118M005C)Ministry of Science and Technology of China
文摘In reactor neutrino experiments, the analysis of time correlations between different physical events is an important task. Such analysis can help to understand the physical mechanisms of the signal and background events as well as the details of event selection and background estimation. This study investigates a ＂sampling and mixing＂ method used for producing large MC data samples for the Daya Bay reactor neutrino experiment. We designed a simple, generic mixing algorithm and generated large MC data samples for physics analysis from several samples according to their respective event rates. Basic plots based on the mixed data are shown.
