Abnormal Event Detection in Nuclear Power Plants via Attention Networks

• Published in: Energies (Basel) Vol. 16; no. 18; p. 6745
• Main Authors: Zhang, Tianhao, Jia, Qianqian, Guo, Chao, Huang, Xiaojin
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01-09-2023
• Subjects: abnormal event detection; attention mechanism; Genetic algorithms; Identification; interpretation; Machine learning; Methods; neural network; Neural networks; Nuclear energy; Nuclear power plants; Nuclear reactors; Parameter estimation; Pattern recognition
• ISSN: 1996-1073; 1996-1073
• DOI: 10.3390/en16186745

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.