This study explores the use of neural network-based analytic continuation to extract spectra from Monte Carlo data.We apply this technique to both synthetic and Monte Carlo-generated data.The training sets for neural ...This study explores the use of neural network-based analytic continuation to extract spectra from Monte Carlo data.We apply this technique to both synthetic and Monte Carlo-generated data.The training sets for neural networks are carefully synthesized without“data leakage”.We find that the training set should match the input correlation functions in terms of statistical error properties,such as noise level,noise dependence on imaginary time,and imaginary time-displaced correlations.We have developed a systematic method to synthesize such training datasets.Our improved algorithm outperforms the widely used maximum entropy method in highly noisy situations.As an example,our method successfully extracted the dynamic structure factor of the spin-1/2 Heisenberg chain from quantum Monte Carlo simulations.展开更多
This paper proposes a novel method for solving the first-passage time probability problem of nonlinear stochastic dynamic systems.The safe domain boundary is exactly imposed into the radial basis function neural netwo...This paper proposes a novel method for solving the first-passage time probability problem of nonlinear stochastic dynamic systems.The safe domain boundary is exactly imposed into the radial basis function neural network(RBF-NN)architecture such that the solution is an admissible function of the boundary-value problem.In this way,the neural network solution can automatically satisfy the safe domain boundaries and no longer requires adding the corresponding loss terms,thus efficiently handling structure failure problems defined by various safe domain boundaries.The effectiveness of the proposed method is demonstrated through three nonlinear stochastic examples defined by different safe domains,and the results are validated against the extensive Monte Carlo simulations(MCSs).展开更多
This research work investigated comparative studies of expert system design and control of crude oil distillation column (CODC) using artificial neural networks based Monte Carlo (ANNBMC) simulation of random processe...This research work investigated comparative studies of expert system design and control of crude oil distillation column (CODC) using artificial neural networks based Monte Carlo (ANNBMC) simulation of random processes and artificial neural networks (ANN) model which were validated using experimental data obtained from functioning crude oil distillation column of Port-Harcourt Refinery, Nigeria by MATLAB computer program. Ninety percent (90%) of the experimental data sets were used for training while ten percent (10%) were used for testing the networks. The maximum relative errors between the experimental and calculated data obtained from the output variables of the neural network for CODC design were 1.98 error % and 0.57 error % when ANN only and ANNBMC were used respectively while their respective values for the maximum relative error were 0.346 error % and 0.124 error % when they were used for the controller prediction. Larger number of iteration steps of below 2500 and 5000 were required to achieve convergence of less than 10-7?for the training error using ANNBMC for both the design of the CODC and controller respectively while less than 400 and 700 iteration steps were needed to achieve convergence of 10-4?using ANN only. The linear regression analysis performed revealed the minimum and maximum prediction accuracies to be 80.65% and 98.79%;and 98.38% and 99.98% when ANN and ANNBMC were used for the CODC design respectively. Also, the minimum and maximum prediction accuracies were 92.83% and 99.34%;and 98.89% and 99.71% when ANN and ANNBMC were used for the CODC controller respectively as both methodologies have excellent predictions. Hence, artificial neural networks based Monte Carlo simulation is an effective and better tool for the design and control of crude oil distillation column.展开更多
Gamma ray shielding is essential to ensure the safety of personnel and equipment in facilities and environments where radiation exists.The Monte Carlo technique is vital for analyzing the gamma-ray shielding capabilit...Gamma ray shielding is essential to ensure the safety of personnel and equipment in facilities and environments where radiation exists.The Monte Carlo technique is vital for analyzing the gamma-ray shielding capabilities of materials.In this study,a simple Monte Carlo code,EJUSTCO,is developed to cd simulate gamma radiation transport in shielding materials for academic purposes.The code considers the photoelectric effect,Compton(incoherent)scattering,pair production,and photon annihilation as the dominant interaction mechanisms in the gamma radiation shielding problem.Variance reduction techniques,such as the Russian roulette,survival weighting,and exponential transformation,are incorporated into the code to improve computational efficiency.Predicting the exponential transformation parameter typically requires trial and error as well as expertise.Herein,a deep learning neural network is proposed as a viable method for predicting this parameter for the first time.The model achieves an MSE of 0.00076752 and an R-value of 0.99998.The exposure buildup factors and radiation dose rates due to the passage of gamma radiation with different source energies and varying thicknesses of lead,water,iron,concrete,and aluminum in single-,double-,and triple-layer material systems are validated by comparing the results with those of MCNP,ESG,ANS-6.4.3,MCBLD,MONTEREY MARK(M),PENELOPE,and experiments.Average errors of 5.6%,2.75%,and 10%are achieved for the exposure buildup factor in single-,double-,and triple-layer materials,respectively.A significant parameter that is not considered in similar studies is the gamma ray albedo.In the EJUSTCO code,the total number and energy albedos have been computed.The results are compared with those of MCNP,FOTELP,and PENELOPE.In general,the EJUSTCO-developed code can be employed to assess the performance of radiation shielding materials because the validation results are consistent with theoretical,experimental,and literary results.展开更多
This study proposes a source distribution inversion convolutional neural network (SDICNN), which is deep neural network model for the inversion of complex source distributions, to solve inversion problems involving fi...This study proposes a source distribution inversion convolutional neural network (SDICNN), which is deep neural network model for the inversion of complex source distributions, to solve inversion problems involving fixed-source distributions. A function is developed to obtain the distribution information of complex source terms from radiation parameters at individual sampling points in space. The SDICNN comprises two components:a fully connected network and a convolutional neural network. The fully connected network mainly extracts the parameter measurement information from the sampling points,whereas the convolutional neural network mainly completes the fine inversion of the source-term distribution. Finally, the SDICNN obtains a high-resolution source-term distribution image. In this study, the proposed source-term inversion method is evaluated based on typical geometric scenarios. The results show that, unlike the conventional fully connected neural network, the SDICNN model can extract the two-dimensional distribution features of the source terms, and its inversion results are better. In addition, the effects of the shielding mechanism and number of sampling points on the inversion process are examined. In summary, the result of this study can facilitate the accurate assessment of dose distributions in nuclear facilities.展开更多
A novel variational wave function defined as a Jastrow factor multiplying a backflow transformed Slater determinant was developed for A=3 nuclei.The Jastrow factor and backflow transformation were represented by artif...A novel variational wave function defined as a Jastrow factor multiplying a backflow transformed Slater determinant was developed for A=3 nuclei.The Jastrow factor and backflow transformation were represented by artificial neural networks.With this newly developed wave function,variational Monte Carlo calculations were carried out for3H and3He nuclei starting from a nuclear Hamiltonian based on the leadingorder pionless effective field theory.The obtained ground-state energy and charge radii were successfully benchmarked against the results of the highly-accurate hypersphericalharmonics method.The backflow transformation plays a crucial role in improving the nodal surface of the Slater determinant and,thus,providing accurate ground-state energy.展开更多
Monte Carlo Simulations(MCS),commonly used for reliability analysis,require a large amount of data points to obtain acceptable accuracy,even if the Subset Simulation with Importance Sampling(SS/IS)methods are used.The...Monte Carlo Simulations(MCS),commonly used for reliability analysis,require a large amount of data points to obtain acceptable accuracy,even if the Subset Simulation with Importance Sampling(SS/IS)methods are used.The Second Order Reliability Method(SORM)has proved to be an excellent rapid tool in the stochastic analysis of laminated composite structures,when compared to the slower MCS techniques.However,SORM requires differentiating the performance function with respect to each of the random variables involved in the simulation.The most suitable approach to do this is to use a symbolic solver,which renders the simulations very slow,although still faster than MCS.Moreover,the inability to obtain the derivative of the performance function with respect to some parameters,such as ply thickness,limits the capabilities of the classical SORM.In this work,a Neural Network-Based Second Order Reliability Method(NNBSORM)is developed to replace the finite element algorithm in the stochastic analysis of laminated composite plates in free vibration.Because of the ability to obtain expressions for the first and second derivatives of the NN system outputs with respect to any of its inputs,such as material properties,ply thicknesses and orientation angles,the need for using a symbolic solver to calculate the derivatives of the performance function no longer exists.The proposed approach is accordingly much faster,and easily allows for the consideration of ply thickness uncertainty.The present analysis showed that dealing with ply thicknesses as random variables results in 37%increase in the laminate’s probability of failure.展开更多
Deregulation policy has caused some changes in the concepts of power systems reliability assessment and enhancement. In the present research, generation reliability is considered, and a method for its assessment is pr...Deregulation policy has caused some changes in the concepts of power systems reliability assessment and enhancement. In the present research, generation reliability is considered, and a method for its assessment is proposed using Game Theory (GT) and Neural Networks (NN). Also, due to the stochastic behavior of power markets and generators’ forced outages, Monte Carlo Simulation (MCS) is used for reliability evaluation. Generation reliability focuses merely on the interaction between generation complex and load. Therefore, in the research, based on the behavior of players in the market and using GT, two outcomes are considered: cooperation and non-cooperation. The proposed method is assessed on IEEE-Reliability Test System with satisfactory results. Loss of Load Expectation (LOLE) is used as the reliability index and the results show generation reliability in cooperation market is better than non-cooperation outcome.展开更多
The physical quantities calculated by nuclear reactor Monte Carlo simulations are typically recorded on a grid of two or three spatial dimensions and one dimension of neutron energy.Because of this,increasing the reso...The physical quantities calculated by nuclear reactor Monte Carlo simulations are typically recorded on a grid of two or three spatial dimensions and one dimension of neutron energy.Because of this,increasing the resolution of the calculated quantities can have a significant impact on the memory and CPU time required to run a simulation.Convolutional neural networks have been shown to accurately upsample coarse-resolution photo-graphic images to resolutions multiple times finer than the originals.Here we show that a convolutional neural network can accurately upsample flux tallies in a Monte Carlo neutron transport simulation by a factor of two along the spatial and energy dimensions.Neutron flux tallies in pressurized water reactor assemblies were calculated using OpenMC at a 64×64 pixel spatial resolution and 8 neutron energy groups for input to the neural network.The network upsamples the low-resolution neutron flux to 128×128 pixel spatial resolution and 16 neutron energy groups.High-resolution neutron flux tallies and their uncertainties were also calculated with OpenMC and compared with the network’s predictions.The upsampled data and the high-resolution tally results agree to within the statistical uncertainty calculated by OpenMC.展开更多
基金support from the National Natural Science Foundation of China (Grant Nos. 12274004 and 11888101)
文摘This study explores the use of neural network-based analytic continuation to extract spectra from Monte Carlo data.We apply this technique to both synthetic and Monte Carlo-generated data.The training sets for neural networks are carefully synthesized without“data leakage”.We find that the training set should match the input correlation functions in terms of statistical error properties,such as noise level,noise dependence on imaginary time,and imaginary time-displaced correlations.We have developed a systematic method to synthesize such training datasets.Our improved algorithm outperforms the widely used maximum entropy method in highly noisy situations.As an example,our method successfully extracted the dynamic structure factor of the spin-1/2 Heisenberg chain from quantum Monte Carlo simulations.
基金Project supported by the National Natural Science Foundation of China(Nos.11972070,12072118,and 12372029)the Natural Science Funds for Distinguished Young Scholars of the Fujian Province of China(No.2021J06024)。
文摘This paper proposes a novel method for solving the first-passage time probability problem of nonlinear stochastic dynamic systems.The safe domain boundary is exactly imposed into the radial basis function neural network(RBF-NN)architecture such that the solution is an admissible function of the boundary-value problem.In this way,the neural network solution can automatically satisfy the safe domain boundaries and no longer requires adding the corresponding loss terms,thus efficiently handling structure failure problems defined by various safe domain boundaries.The effectiveness of the proposed method is demonstrated through three nonlinear stochastic examples defined by different safe domains,and the results are validated against the extensive Monte Carlo simulations(MCSs).
文摘This research work investigated comparative studies of expert system design and control of crude oil distillation column (CODC) using artificial neural networks based Monte Carlo (ANNBMC) simulation of random processes and artificial neural networks (ANN) model which were validated using experimental data obtained from functioning crude oil distillation column of Port-Harcourt Refinery, Nigeria by MATLAB computer program. Ninety percent (90%) of the experimental data sets were used for training while ten percent (10%) were used for testing the networks. The maximum relative errors between the experimental and calculated data obtained from the output variables of the neural network for CODC design were 1.98 error % and 0.57 error % when ANN only and ANNBMC were used respectively while their respective values for the maximum relative error were 0.346 error % and 0.124 error % when they were used for the controller prediction. Larger number of iteration steps of below 2500 and 5000 were required to achieve convergence of less than 10-7?for the training error using ANNBMC for both the design of the CODC and controller respectively while less than 400 and 700 iteration steps were needed to achieve convergence of 10-4?using ANN only. The linear regression analysis performed revealed the minimum and maximum prediction accuracies to be 80.65% and 98.79%;and 98.38% and 99.98% when ANN and ANNBMC were used for the CODC design respectively. Also, the minimum and maximum prediction accuracies were 92.83% and 99.34%;and 98.89% and 99.71% when ANN and ANNBMC were used for the CODC controller respectively as both methodologies have excellent predictions. Hence, artificial neural networks based Monte Carlo simulation is an effective and better tool for the design and control of crude oil distillation column.
基金Our profound gratitude and appreciation go to the Egyptian and Japanese governments for supporting and financing this research work at the Egypt-Japan University of Science and TechnologyFurther appreciation goes to the Science and Technology Development Fund for the additional financial support(project ID:STDF-33397).
文摘Gamma ray shielding is essential to ensure the safety of personnel and equipment in facilities and environments where radiation exists.The Monte Carlo technique is vital for analyzing the gamma-ray shielding capabilities of materials.In this study,a simple Monte Carlo code,EJUSTCO,is developed to cd simulate gamma radiation transport in shielding materials for academic purposes.The code considers the photoelectric effect,Compton(incoherent)scattering,pair production,and photon annihilation as the dominant interaction mechanisms in the gamma radiation shielding problem.Variance reduction techniques,such as the Russian roulette,survival weighting,and exponential transformation,are incorporated into the code to improve computational efficiency.Predicting the exponential transformation parameter typically requires trial and error as well as expertise.Herein,a deep learning neural network is proposed as a viable method for predicting this parameter for the first time.The model achieves an MSE of 0.00076752 and an R-value of 0.99998.The exposure buildup factors and radiation dose rates due to the passage of gamma radiation with different source energies and varying thicknesses of lead,water,iron,concrete,and aluminum in single-,double-,and triple-layer material systems are validated by comparing the results with those of MCNP,ESG,ANS-6.4.3,MCBLD,MONTEREY MARK(M),PENELOPE,and experiments.Average errors of 5.6%,2.75%,and 10%are achieved for the exposure buildup factor in single-,double-,and triple-layer materials,respectively.A significant parameter that is not considered in similar studies is the gamma ray albedo.In the EJUSTCO code,the total number and energy albedos have been computed.The results are compared with those of MCNP,FOTELP,and PENELOPE.In general,the EJUSTCO-developed code can be employed to assess the performance of radiation shielding materials because the validation results are consistent with theoretical,experimental,and literary results.
基金supported by the Platform Development Foundation of the China Institute for Radiation Protection (No. YP21030101)the National Natural Science Foundation of China (General Program)(Nos. 12175114, U2167209)+1 种基金the National Key R&D Program of China (No. 2021YFF0603600)the Tsinghua University Initiative Scientific Research Program (No. 20211080081)。
文摘This study proposes a source distribution inversion convolutional neural network (SDICNN), which is deep neural network model for the inversion of complex source distributions, to solve inversion problems involving fixed-source distributions. A function is developed to obtain the distribution information of complex source terms from radiation parameters at individual sampling points in space. The SDICNN comprises two components:a fully connected network and a convolutional neural network. The fully connected network mainly extracts the parameter measurement information from the sampling points,whereas the convolutional neural network mainly completes the fine inversion of the source-term distribution. Finally, the SDICNN obtains a high-resolution source-term distribution image. In this study, the proposed source-term inversion method is evaluated based on typical geometric scenarios. The results show that, unlike the conventional fully connected neural network, the SDICNN model can extract the two-dimensional distribution features of the source terms, and its inversion results are better. In addition, the effects of the shielding mechanism and number of sampling points on the inversion process are examined. In summary, the result of this study can facilitate the accurate assessment of dose distributions in nuclear facilities.
基金Supported by National Key R&D Program of China (018YFA0404400)National Natural Science Foundation of China (12070131001,11875075,11935003,11975031,12141501)。
文摘A novel variational wave function defined as a Jastrow factor multiplying a backflow transformed Slater determinant was developed for A=3 nuclei.The Jastrow factor and backflow transformation were represented by artificial neural networks.With this newly developed wave function,variational Monte Carlo calculations were carried out for3H and3He nuclei starting from a nuclear Hamiltonian based on the leadingorder pionless effective field theory.The obtained ground-state energy and charge radii were successfully benchmarked against the results of the highly-accurate hypersphericalharmonics method.The backflow transformation plays a crucial role in improving the nodal surface of the Slater determinant and,thus,providing accurate ground-state energy.
文摘Monte Carlo Simulations(MCS),commonly used for reliability analysis,require a large amount of data points to obtain acceptable accuracy,even if the Subset Simulation with Importance Sampling(SS/IS)methods are used.The Second Order Reliability Method(SORM)has proved to be an excellent rapid tool in the stochastic analysis of laminated composite structures,when compared to the slower MCS techniques.However,SORM requires differentiating the performance function with respect to each of the random variables involved in the simulation.The most suitable approach to do this is to use a symbolic solver,which renders the simulations very slow,although still faster than MCS.Moreover,the inability to obtain the derivative of the performance function with respect to some parameters,such as ply thickness,limits the capabilities of the classical SORM.In this work,a Neural Network-Based Second Order Reliability Method(NNBSORM)is developed to replace the finite element algorithm in the stochastic analysis of laminated composite plates in free vibration.Because of the ability to obtain expressions for the first and second derivatives of the NN system outputs with respect to any of its inputs,such as material properties,ply thicknesses and orientation angles,the need for using a symbolic solver to calculate the derivatives of the performance function no longer exists.The proposed approach is accordingly much faster,and easily allows for the consideration of ply thickness uncertainty.The present analysis showed that dealing with ply thicknesses as random variables results in 37%increase in the laminate’s probability of failure.
文摘Deregulation policy has caused some changes in the concepts of power systems reliability assessment and enhancement. In the present research, generation reliability is considered, and a method for its assessment is proposed using Game Theory (GT) and Neural Networks (NN). Also, due to the stochastic behavior of power markets and generators’ forced outages, Monte Carlo Simulation (MCS) is used for reliability evaluation. Generation reliability focuses merely on the interaction between generation complex and load. Therefore, in the research, based on the behavior of players in the market and using GT, two outcomes are considered: cooperation and non-cooperation. The proposed method is assessed on IEEE-Reliability Test System with satisfactory results. Loss of Load Expectation (LOLE) is used as the reliability index and the results show generation reliability in cooperation market is better than non-cooperation outcome.
基金This research was supported by the Exascale Computing Project(17-SC-20-SC),a collaborative effort of the U.S.
文摘The physical quantities calculated by nuclear reactor Monte Carlo simulations are typically recorded on a grid of two or three spatial dimensions and one dimension of neutron energy.Because of this,increasing the resolution of the calculated quantities can have a significant impact on the memory and CPU time required to run a simulation.Convolutional neural networks have been shown to accurately upsample coarse-resolution photo-graphic images to resolutions multiple times finer than the originals.Here we show that a convolutional neural network can accurately upsample flux tallies in a Monte Carlo neutron transport simulation by a factor of two along the spatial and energy dimensions.Neutron flux tallies in pressurized water reactor assemblies were calculated using OpenMC at a 64×64 pixel spatial resolution and 8 neutron energy groups for input to the neural network.The network upsamples the low-resolution neutron flux to 128×128 pixel spatial resolution and 16 neutron energy groups.High-resolution neutron flux tallies and their uncertainties were also calculated with OpenMC and compared with the network’s predictions.The upsampled data and the high-resolution tally results agree to within the statistical uncertainty calculated by OpenMC.
