Artificial neural network reconstructs core power distribution
To effectively monitor the variety of distributions of neutron flux, fuel power or temperatures in the reactor core, usually the ex-core and in-core neutron detectors are employed. The thermocouples for temperature measurement are installed in the coolant inlet or outlet of the respective fuel assem...
Main Authors: | , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Elsevier
2022-02-01
|
Series: | Nuclear Engineering and Technology |
Subjects: | |
Online Access: | http://www.sciencedirect.com/science/article/pii/S1738573321005039 |
_version_ | 1798031308415303680 |
---|---|
author | Wenhuai Li Peng Ding Wenqing Xia Shu Chen Fengwan Yu Chengjie Duan Dawei Cui Chen Chen |
author_facet | Wenhuai Li Peng Ding Wenqing Xia Shu Chen Fengwan Yu Chengjie Duan Dawei Cui Chen Chen |
author_sort | Wenhuai Li |
collection | DOAJ |
description | To effectively monitor the variety of distributions of neutron flux, fuel power or temperatures in the reactor core, usually the ex-core and in-core neutron detectors are employed. The thermocouples for temperature measurement are installed in the coolant inlet or outlet of the respective fuel assemblies. It is necessary to reconstruct the measurement information of the whole reactor position. However, the reading of different types of detector in the core reflects different aspects of the 3D power distribution. The feasibility of reconstruction the core three-dimension power distribution by using different combinations of in-core, ex-core and thermocouples detectors is analyzed in this paper to synthesize the useful information of various detectors. A comparison of multilayer perceptron (MLP) network and radial basis function (RBF) network is performed. RBF results are more extreme precision but also more sensitivity to detector failure and uncertainty, compare to MLP networks. This is because that localized neural network could offer conservative regression in RBF. Adding random disturbance in training dataset is helpful to reduce the influence of detector failure and uncertainty. Some convolution neural networks seem to be helpful to get more accurate results by use more spatial layout information, though relative researches are still under way. |
first_indexed | 2024-04-11T19:54:19Z |
format | Article |
id | doaj.art-f7e82d3c7a43491691960935eaff2b40 |
institution | Directory Open Access Journal |
issn | 1738-5733 |
language | English |
last_indexed | 2024-04-11T19:54:19Z |
publishDate | 2022-02-01 |
publisher | Elsevier |
record_format | Article |
series | Nuclear Engineering and Technology |
spelling | doaj.art-f7e82d3c7a43491691960935eaff2b402022-12-22T04:06:12ZengElsevierNuclear Engineering and Technology1738-57332022-02-01542617626Artificial neural network reconstructs core power distributionWenhuai Li0Peng Ding1Wenqing Xia2Shu Chen3Fengwan Yu4Chengjie Duan5Dawei Cui6Chen Chen7China Nuclear Power Technology Research Institute Co., Ltd, Shenzhen, China; School of Electric Power, South China University of Technology, Guangzhou, China; Corresponding author. China Nuclear Power Technology Research Institute Co., Ltd, Shenzhen, China.China Nuclear Power Technology Research Institute Co., Ltd, Shenzhen, China; Corresponding author. China Nuclear Power Technology Research Institute Co., Ltd, Shenzhen, China.China Nuclear Power Technology Research Institute Co., Ltd, Shenzhen, ChinaChina Nuclear Power Technology Research Institute Co., Ltd, Shenzhen, ChinaChina Nuclear Power Technology Research Institute Co., Ltd, Shenzhen, ChinaChina Nuclear Power Technology Research Institute Co., Ltd, Shenzhen, ChinaChina Nuclear Power Technology Research Institute Co., Ltd, Shenzhen, ChinaChina Nuclear Power Technology Research Institute Co., Ltd, Shenzhen, ChinaTo effectively monitor the variety of distributions of neutron flux, fuel power or temperatures in the reactor core, usually the ex-core and in-core neutron detectors are employed. The thermocouples for temperature measurement are installed in the coolant inlet or outlet of the respective fuel assemblies. It is necessary to reconstruct the measurement information of the whole reactor position. However, the reading of different types of detector in the core reflects different aspects of the 3D power distribution. The feasibility of reconstruction the core three-dimension power distribution by using different combinations of in-core, ex-core and thermocouples detectors is analyzed in this paper to synthesize the useful information of various detectors. A comparison of multilayer perceptron (MLP) network and radial basis function (RBF) network is performed. RBF results are more extreme precision but also more sensitivity to detector failure and uncertainty, compare to MLP networks. This is because that localized neural network could offer conservative regression in RBF. Adding random disturbance in training dataset is helpful to reduce the influence of detector failure and uncertainty. Some convolution neural networks seem to be helpful to get more accurate results by use more spatial layout information, though relative researches are still under way.http://www.sciencedirect.com/science/article/pii/S1738573321005039Artificial neural networkIn-core power distributionRBFCNN |
spellingShingle | Wenhuai Li Peng Ding Wenqing Xia Shu Chen Fengwan Yu Chengjie Duan Dawei Cui Chen Chen Artificial neural network reconstructs core power distribution Nuclear Engineering and Technology Artificial neural network In-core power distribution RBF CNN |
title | Artificial neural network reconstructs core power distribution |
title_full | Artificial neural network reconstructs core power distribution |
title_fullStr | Artificial neural network reconstructs core power distribution |
title_full_unstemmed | Artificial neural network reconstructs core power distribution |
title_short | Artificial neural network reconstructs core power distribution |
title_sort | artificial neural network reconstructs core power distribution |
topic | Artificial neural network In-core power distribution RBF CNN |
url | http://www.sciencedirect.com/science/article/pii/S1738573321005039 |
work_keys_str_mv | AT wenhuaili artificialneuralnetworkreconstructscorepowerdistribution AT pengding artificialneuralnetworkreconstructscorepowerdistribution AT wenqingxia artificialneuralnetworkreconstructscorepowerdistribution AT shuchen artificialneuralnetworkreconstructscorepowerdistribution AT fengwanyu artificialneuralnetworkreconstructscorepowerdistribution AT chengjieduan artificialneuralnetworkreconstructscorepowerdistribution AT daweicui artificialneuralnetworkreconstructscorepowerdistribution AT chenchen artificialneuralnetworkreconstructscorepowerdistribution |