A Physics-Coupled Deep LSTM Autoencoder for Robust Sensor Fault Detection in Industrial Systems
Processes · 10.04.2026 · 14 (8) · 1213
DOI: 10.3390/pr14081213 ↗Kurz gefasst
Fachartikel in der Zeitschrift Processes, online erschienen am 10.04.2026. Verfasst von Weiwei Jia und 5 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Guangxi Key Technologies R&D Program, National Natural Science Foundation of China, Innovation Project of Guangxi Graduate Education.
Abstract (Originalsprache)
Reliable sensor fault detection is critical for the safe and efficient operation of complex industrial systems, such as thermal power plants. However, traditional data-driven methods and standard deep learning models often struggle to detect incipient gradual drift faults under severe environmental noise, primarily because they ignore the inherent physical correlations among multivariate sensor signals. To address this challenge, this paper proposes a novel Physics-Coupled Deep Long Short-Term Memory Autoencoder (PC-Deep-LSTM-AE). Specifically, we integrate a deep LSTM architecture with an explicit non-linear information compression bottleneck and layer normalization to enhance robust feature extraction in high-noise environments. Furthermore, we innovatively introduce a Physics-Coupling Loss (PCC Loss) that jointly optimizes the mean squared reconstruction error and the Pearson correlation coefficient, forcing the model to strictly preserve the dynamic physical relationships among multivariable signals. Extensive experiments were conducted on a real-world thermal power plant dataset with severe noise injection. The results demonstrate that the proposed PC-Deep-LSTM-AE achieves an outstanding F1-score of over 0.98, significantly outperforming mainstream baseline models, including Vanilla LSTM-AE, GRU-AE, Bi-LSTM-AE, and CNN-AE. The proposed method exhibits exceptional robustness and high interpretability for root-cause analysis, highlighting its immense potential for real-world industrial deployment.
Förderung
- Guangxi Key Technologies R&D Program
- National Natural Science Foundation of China
- Innovation Project of Guangxi Graduate Education
Zitieren
APA
Jia, W., Ding, Y., Ye, X., Huang, X., Wang, M., & Miao, C. (2026). A Physics-Coupled Deep LSTM Autoencoder for Robust Sensor Fault Detection in Industrial Systems. Processes, 14(8), 1213. https://doi.org/10.3390/pr14081213
Vancouver
Jia W, Ding Y, Ye X, Huang X, Wang M, Miao C. A Physics-Coupled Deep LSTM Autoencoder for Robust Sensor Fault Detection in Industrial Systems. Processes. 2026;14(8):1213. doi:10.3390/pr14081213
BibTeX
@article{Jia2026,
author = {Jia, Weiwei and Ding, Youcheng and Ye, Xilong and Huang, Xinyi and Wang, Maofa and Miao, Chenglong},
title = {A Physics-Coupled Deep LSTM Autoencoder for Robust Sensor Fault Detection in Industrial Systems},
journal = {Processes},
year = {2026},
volume = {14},
number = {8},
pages = {1213},
doi = {10.3390/pr14081213}
}
EUVIMED