A Multihead Attention Self-Supervised Representation Model for Industrial Sensors Anomaly Detection
IEEE Transactions on Industrial Informatics · 2024-02 · 20 (2) · 2190-2199
DOI: 10.1109/tii.2023.3280337 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Industrial Informatics, 2024-02. Verfasst von Yiqun Qiao und 5 weiteren Autor:innen. Die Arbeit wurde bisher 127-mal zitiert (Crossref) und nennt 43 Literaturangaben. Gefördert von: National Key R&D Program of China, National Natural Science Foundation of China, Beijing Nova Program.
Abstract (Originalsprache)
Industrial sensors capture critical information for intelligent manufacturing maintenance. To promote equipment upgrading and manufacturing processes, intelligent decisions, and information learning play an important role. Although deep learning methods historically obtain excellent results, there is always a tradeoff between fine-tuning existing networks or designing models from scratch for sensor data processing. In this article, we propose the multihead attention self-supervised (MAS) representation model, which is a self-supervised learning-based sensor feature extraction network. To the best of our knowledge, this is the first time a self-supervised contrastive learning method using positive samples that represent multidimensional industry sensor data is being used for anomaly detection. We review alternative data augmentation methods proposed for better-representing sensor sequence data. We use this insight to design a new structure that adapts to the temporal characteristics of the application. We apply our method to a real-world water circulation system that uses a variety of industrial sensors. The effectiveness of the proposed MAS methods is demonstrated.
Förderung
- National Key R&D Program of China
- National Natural Science Foundation of China
- Beijing Nova Program
Zitieren
APA
Qiao, Y., Lü, J., Wang, T., Liu, K., Zhang, B., & Snoussi, H. (2024). A Multihead Attention Self-Supervised Representation Model for Industrial Sensors Anomaly Detection. IEEE Transactions on Industrial Informatics, 20(2), 2190-2199. https://doi.org/10.1109/tii.2023.3280337
Vancouver
Qiao Y, Lü J, Wang T, Liu K, Zhang B, Snoussi H. A Multihead Attention Self-Supervised Representation Model for Industrial Sensors Anomaly Detection. IEEE Transactions on Industrial Informatics. 2024;20(2):2190-2199. doi:10.1109/tii.2023.3280337
BibTeX
@article{Qiao2024,
author = {Qiao, Yiqun and Lü, Jinhu and Wang, Tian and Liu, Kexin and Zhang, Baochang and Snoussi, Hichem},
title = {A Multihead Attention Self-Supervised Representation Model for Industrial Sensors Anomaly Detection},
journal = {IEEE Transactions on Industrial Informatics},
year = {2024},
volume = {20},
number = {2},
pages = {2190--2199},
doi = {10.1109/tii.2023.3280337}
}
EUVIMED