Anomaly Detection for Asynchronous Multivariate Time Series of Nuclear Power Plants Using a Temporal-Spatial Transformer
Sensors · 29.04.2024 · 24 (9) · 2845
DOI: 10.3390/s24092845 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 29.04.2024. Verfasst von Shuang Yi und 4 weiteren Autor:innen. Beteiligte Einrichtung: College of Electrical Engineering and New Energy, China Three Gorges University, Yichang 443002, China. Die Arbeit wurde bisher 19-mal zitiert (Crossref) und nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: The CNNC Key Laboratory of Nuclear Industry Simulation Technology External Open Fund Project., China Nuclear Industry Key Laboratory of Simulation Technology.
Abstract (Originalsprache)
Industrial process monitoring is a critical application of multivariate time-series (MTS) anomaly detection, especially crucial for safety-critical systems such as nuclear power plants (NPPs). However, some current data-driven process monitoring approaches may not fully capitalize on the temporal-spatial correlations inherent in operational MTS data. Particularly, asynchronous time-lagged correlations may exist among variables in actual NPPs, which further complicates this challenge. In this work, a reconstruction-based MTS anomaly detection approach based on a temporal-spatial transformer is proposed. It employs a two-stage temporal-spatial attention mechanism combined with a multi-scale strategy to learn the dependencies within normal operational data at various scales, thereby facilitating the extraction of temporal-spatial correlations from asynchronous MTS. Experiments on simulated datasets and real NPP datasets demonstrate that the proposed model possesses stronger feature learning capabilities, as evidenced by its improved performance in signal reconstruction and anomaly detection for asynchronous MTS data. Moreover, the proposed TS-Trans model enables earlier detection of anomalous events, which holds significant importance for enhancing operational safety and reducing potential losses in NPPs.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- College of Electrical Engineering and New Energy, China Three Gorges University, Yichang 443002, China.
- College of Science, China Three Gorges University, Yichang 443002, China.
- China Nuclear Power Operation Technology Corporation, Ltd., Wuhan 430074, China.
- China Nuclear Industry Key Laboratory of Simulation Technology, Wuhan 430074, China.
ORCID-Profile: Shuang Yi
Förderung
- The CNNC Key Laboratory of Nuclear Industry Simulation Technology External Open Fund Project.
- China Nuclear Industry Key Laboratory of Simulation Technology
Zitieren
APA
Yi, S., Zheng, S., Yang, S., Zhou, G., & Cai, J. (2024). Anomaly Detection for Asynchronous Multivariate Time Series of Nuclear Power Plants Using a Temporal-Spatial Transformer. Sensors, 24(9), 2845. https://doi.org/10.3390/s24092845
Vancouver
Yi S, Zheng S, Yang S, Zhou G, Cai J. Anomaly Detection for Asynchronous Multivariate Time Series of Nuclear Power Plants Using a Temporal-Spatial Transformer. Sensors. 2024;24(9):2845. doi:10.3390/s24092845
BibTeX
@article{Yi2024,
author = {Yi, Shuang and Zheng, Sheng and Yang, Senquan and Zhou, Guangrong and Cai, Jiajun},
title = {Anomaly Detection for Asynchronous Multivariate Time Series of Nuclear Power Plants Using a Temporal-Spatial Transformer},
journal = {Sensors},
year = {2024},
volume = {24},
number = {9},
pages = {2845},
doi = {10.3390/s24092845}
}
EUVIMED