Abnormal Event Detection in Nuclear Power Plants via Attention Networks
Ensuring the safety of nuclear energy necessitates proactive measures to prevent the escalation of severe operational conditions. This article presents an efficient and interpretable framework for the swift identification of abnormal events in nuclear power plants (NPPs), equipping operators with ti...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-09-01
|
Series: | Energies |
Subjects: | |
Online Access: | https://www.mdpi.com/1996-1073/16/18/6745 |
_version_ | 1797580331493097472 |
---|---|
author | Tianhao Zhang Qianqian Jia Chao Guo Xiaojin Huang |
author_facet | Tianhao Zhang Qianqian Jia Chao Guo Xiaojin Huang |
author_sort | Tianhao Zhang |
collection | DOAJ |
description | Ensuring the safety of nuclear energy necessitates proactive measures to prevent the escalation of severe operational conditions. This article presents an efficient and interpretable framework for the swift identification of abnormal events in nuclear power plants (NPPs), equipping operators with timely insights for effective decision-making. A novel neural network architecture, combining Long Short-Term Memory (LSTM) and attention mechanisms, is proposed to address the challenge of signal coupling. The derivative dynamic time warping (DDTW) method enhances interpretability by comparing time series operating parameters during abnormal and normal states. Experimental validation demonstrates high real-time accuracy, underscoring the broader applicability of the approach across NPPs. |
first_indexed | 2024-03-10T22:49:29Z |
format | Article |
id | doaj.art-a4f69851d2d140bbbec3d9e1b7e42f2a |
institution | Directory Open Access Journal |
issn | 1996-1073 |
language | English |
last_indexed | 2024-03-10T22:49:29Z |
publishDate | 2023-09-01 |
publisher | MDPI AG |
record_format | Article |
series | Energies |
spelling | doaj.art-a4f69851d2d140bbbec3d9e1b7e42f2a2023-11-19T10:29:28ZengMDPI AGEnergies1996-10732023-09-011618674510.3390/en16186745Abnormal Event Detection in Nuclear Power Plants via Attention NetworksTianhao Zhang0Qianqian Jia1Chao Guo2Xiaojin Huang3Collaborative Innovation Center of Advanced Nuclear Energy Technology of China, Key Laboratory of Advanced Reactor Engineering and Safety of Ministry of Education, Institute of Nuclear and New Energy Technology, Tsinghua University, Beijing 100084, ChinaCollaborative Innovation Center of Advanced Nuclear Energy Technology of China, Key Laboratory of Advanced Reactor Engineering and Safety of Ministry of Education, Institute of Nuclear and New Energy Technology, Tsinghua University, Beijing 100084, ChinaCollaborative Innovation Center of Advanced Nuclear Energy Technology of China, Key Laboratory of Advanced Reactor Engineering and Safety of Ministry of Education, Institute of Nuclear and New Energy Technology, Tsinghua University, Beijing 100084, ChinaCollaborative Innovation Center of Advanced Nuclear Energy Technology of China, Key Laboratory of Advanced Reactor Engineering and Safety of Ministry of Education, Institute of Nuclear and New Energy Technology, Tsinghua University, Beijing 100084, ChinaEnsuring the safety of nuclear energy necessitates proactive measures to prevent the escalation of severe operational conditions. This article presents an efficient and interpretable framework for the swift identification of abnormal events in nuclear power plants (NPPs), equipping operators with timely insights for effective decision-making. A novel neural network architecture, combining Long Short-Term Memory (LSTM) and attention mechanisms, is proposed to address the challenge of signal coupling. The derivative dynamic time warping (DDTW) method enhances interpretability by comparing time series operating parameters during abnormal and normal states. Experimental validation demonstrates high real-time accuracy, underscoring the broader applicability of the approach across NPPs.https://www.mdpi.com/1996-1073/16/18/6745nuclear energyabnormal event detectionneural networkattention mechanisminterpretation |
spellingShingle | Tianhao Zhang Qianqian Jia Chao Guo Xiaojin Huang Abnormal Event Detection in Nuclear Power Plants via Attention Networks Energies nuclear energy abnormal event detection neural network attention mechanism interpretation |
title | Abnormal Event Detection in Nuclear Power Plants via Attention Networks |
title_full | Abnormal Event Detection in Nuclear Power Plants via Attention Networks |
title_fullStr | Abnormal Event Detection in Nuclear Power Plants via Attention Networks |
title_full_unstemmed | Abnormal Event Detection in Nuclear Power Plants via Attention Networks |
title_short | Abnormal Event Detection in Nuclear Power Plants via Attention Networks |
title_sort | abnormal event detection in nuclear power plants via attention networks |
topic | nuclear energy abnormal event detection neural network attention mechanism interpretation |
url | https://www.mdpi.com/1996-1073/16/18/6745 |
work_keys_str_mv | AT tianhaozhang abnormaleventdetectioninnuclearpowerplantsviaattentionnetworks AT qianqianjia abnormaleventdetectioninnuclearpowerplantsviaattentionnetworks AT chaoguo abnormaleventdetectioninnuclearpowerplantsviaattentionnetworks AT xiaojinhuang abnormaleventdetectioninnuclearpowerplantsviaattentionnetworks |