Wind turbine anomaly detection based on SCADA: A deep autoencoder enhanced by fault instances
ISA Transactions · 2023-08 · 139 · 586-605
DOI: 10.1016/j.isatra.2023.03.045 ↗Kurz gefasst
Fachartikel in der Zeitschrift ISA Transactions, 2023-08. Verfasst von Jiarui Liu und 5 weiteren Autor:innen. Beteiligte Einrichtung: School of Control and Computer Engineering, North China Electric Power University, Beijing, 102206, PR China. Electronic address: ruijialiu@ncepu.edu…. Die Arbeit wurde bisher 48-mal zitiert (Crossref) und nennt 60 Literaturangaben. Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
An increasing number of deep autoencoder-based algorithms for intelligent condition monitoring and anomaly detection have been reported in recent years to improve wind turbine reliability. However, most existing studies have only focused on the precise modeling of normal data in an unsupervised manner; few studies have utilized the information of fault instances in the learning process, which results in suboptimal detection performance and low robustness. To this end, we first developed a deep autoencoder enhanced by fault instances, that is, a triplet-convolutional deep autoencoder (triplet-Conv DAE), jointly integrating a convolutional autoencoder and deep metric learning. Aided by fault instances, triplet-Conv DAE can not only capture normal operation data patterns but also acquire discriminative deep embedding features. Moreover, to overcome the difficulty of scarce fault instances, we adopted an improved generative adversarial network-based data augmentation method to generate high-quality synthetic fault instances. Finally, we validated the performance of the proposed anomaly detection method using a multitude of performance measures. The experimental results show that our method is superior to three other state-of-the-art methods. In addition, the proposed augmentation method can efficiently improve the performance of the triplet-Conv DAE when fault instances are insufficient.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Control and Computer Engineering, North China Electric Power University, Beijing, 102206, PR China. Electronic address: ruijialiu@ncepu.edu.cn.
- School of Control and Computer Engineering, North China Electric Power University, Beijing, 102206, PR China. Electronic address: ygt@ncepu.edu.cn.
- School of Control and Computer Engineering, North China Electric Power University, Beijing, 102206, PR China. Electronic address: lixinli@ncepu.edu.cn.
- School of Control and Computer Engineering, North China Electric Power University, Beijing, 102206, PR China. Electronic address: wqm@ncepu.edu.cn.
- School of Control and Computer Engineering, North China Electric Power University, Beijing, 102206, PR China. Electronic address: hyc@ncepu.edu.cn.
- School of Control and Computer Engineering, North China Electric Power University, Beijing, 102206, PR China. Electronic address: yangxiyun916@ncepu.edu.cn.
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Liu, J., Yang, G., Li, X., Wang, Q., He, Y., & Yang, X. (2023). Wind turbine anomaly detection based on SCADA: A deep autoencoder enhanced by fault instances. ISA Transactions, 139, 586-605. https://doi.org/10.1016/j.isatra.2023.03.045
Vancouver
Liu J, Yang G, Li X, Wang Q, He Y, Yang X. Wind turbine anomaly detection based on SCADA: A deep autoencoder enhanced by fault instances. ISA Transactions. 2023;139:586-605. doi:10.1016/j.isatra.2023.03.045
BibTeX
@article{Liu2023,
author = {Liu, Jiarui and Yang, Guotian and Li, Xinli and Wang, Qianming and He, Yuchen and Yang, Xiyun},
title = {Wind turbine anomaly detection based on SCADA: A deep autoencoder enhanced by fault instances},
journal = {ISA Transactions},
year = {2023},
volume = {139},
pages = {586--605},
doi = {10.1016/j.isatra.2023.03.045}
}
EUVIMED