Semi-Supervised Multitask Learning Approach Boosted by Operation Strategy Expert System for Industrial Process Fault Diagnosis
IEEE Sensors Journal · 15.07.2025 · 25 (14) · 27250-27264
DOI: 10.1109/jsen.2025.3577708 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Sensors Journal, erschienen am 15.07.2025. Verfasst von Min Yin und 2 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 39 Literaturangaben. Gefördert von: National Key Research and Development Program of China, National Natural Science Foundation of China.
Abstract (Originalsprache)
Fault diagnosis (FD) is crucial for keeping industrial processes safe. Although there is a wealth of historical running data stored, labeled fault data is insufficient. Semi-supervised learning mechanisms can fully utilize unlabeled data to enhance model generalization and performance. Expert systems (ESs) store rich expert knowledge and experience, providing additional decision information and experiential label support for neural networks (NNs). This study proposes a semi-supervised learning approach that combines ESs with NNs for industrial process FD. This approach adopts a multitask learning framework, wherein classification and meta-feature learning are the main and auxiliary tasks, respectively. A rule-based ES is constructed using a mixed integer linear programming (MILP) method. ESs make decisions based on meta-feature learning results, and during the backpropagation process, these decisions are used alongside predictions of the main task for parameter updates. The research findings suggest that the proposed approach has several advantages, including: 1) it enhances the model’s diagnostic performance, interpretability, and interactability; 2) it lessens the demand for labeled samples in the NN; and 3) it provides visual explanations for decision results. This study was validated on a simulated three-tank water storage platform and a gasification process case in a certain factory, achieving satisfactory results.
Förderung
- National Key Research and Development Program of China
- National Natural Science Foundation of China
Zitieren
APA
Yin, M., Ma, X., & Wang, Y. (2025). Semi-Supervised Multitask Learning Approach Boosted by Operation Strategy Expert System for Industrial Process Fault Diagnosis. IEEE Sensors Journal, 25(14), 27250-27264. https://doi.org/10.1109/jsen.2025.3577708
Vancouver
Yin M, Ma X, Wang Y. Semi-Supervised Multitask Learning Approach Boosted by Operation Strategy Expert System for Industrial Process Fault Diagnosis. IEEE Sensors Journal. 2025;25(14):27250-27264. doi:10.1109/jsen.2025.3577708
BibTeX
@article{Yin2025,
author = {Yin, Min and Ma, Xin and Wang, Youqing},
title = {Semi-Supervised Multitask Learning Approach Boosted by Operation Strategy Expert System for Industrial Process Fault Diagnosis},
journal = {IEEE Sensors Journal},
year = {2025},
volume = {25},
number = {14},
pages = {27250--27264},
doi = {10.1109/jsen.2025.3577708}
}
EUVIMED