Conditional feature disentanglement learning for anomaly detection in machines operating under time-varying conditions

Haoxuan Zhou, Zihao Lei, Enrico Zio (), Guangrui Wen, Zimin Liu, Yu Su and Xuefeng Chen
Additional contact information
Haoxuan Zhou: Xjtu - Xi'an Jiaotong University, POLIMI - Politecnico di Milano [Milan]
Zihao Lei: Xjtu - Xi'an Jiaotong University
Enrico Zio: CRC - Centre de recherche sur les Risques et les Crises - Mines Paris - PSL (École nationale supérieure des mines de Paris) - PSL - Université Paris Sciences et Lettres, POLIMI - Politecnico di Milano [Milan]
Guangrui Wen: Xjtu - Xi'an Jiaotong University
Zimin Liu: Xjtu - Xi'an Jiaotong University
Yu Su: Xjtu - Xi'an Jiaotong University
Xuefeng Chen: Xjtu - Xi'an Jiaotong University, POLIMI - Politecnico di Milano [Milan]

Post-Print from HAL

Abstract: Anomaly detection(AD) is an important task of machines' condition monitoring(CM). Data-driven policies can be used in a more intelligent way to achieve anomaly detection and effectively avoid the introduction of expert experience, thus having a broader scope of application. However, Machines like wind turbines often work under time-varying operating conditions(TVOCs), and the performance of traditional data-driven AD methods is significantly degraded because TVOCs can lead to "false alarms" and "missed alarms" in the implementation due to the monitoring data shifting caused by variation of operating conditions(OCs). To address this problem, this paper proposes a novel conditional feature disentanglement learning framework to solve the disturbance in AD on account of entanglement between OCs and health states. The proposed approach performs conditional self-supervised AD by utilizing the variational autoencoder(VAE) and OCs information. Then, a feature disentanglement conditional VAE(FDCVAE) network is developed to realize the disentanglement of OCs and health states. Subsequently, An anomaly indicator(ANI) is constructed by the dimension reduction of the disentangled health state-related feature and combined with the statistics anomaly threshold for AD. Experiments on accelerated fatigue degradation of bearings under TVOCs validate the effectiveness of the proposed method and further demonstrate the superiority of the constructed ANI in eliminating TVOC interference, compared with common fault mechanisms-based and data-driven ANI. The proposed method not only achieves anomaly detection under TVOCs but also provides a new way for representation learning under variable working conditions in machine health management applications in the foreseeable future.

Keywords: Anomaly detection; Bearing; Feature disentanglement learning; Machines; Time-varying operating conditions; Variational autoencoder; Condition monitoring; Feature extraction; Learning systems (search for similar items in EconPapers)
Date: 2023-05
References: Add references at CitEc
Citations: View citations in EconPapers (1)

Published in Mechanical Systems and Signal Processing, 2023, 191, pp.110139. ⟨10.1016/j.ymssp.2023.110139⟩

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:hal:journl:hal-04103555

DOI: 10.1016/j.ymssp.2023.110139

Access Statistics for this paper

More papers in Post-Print from HAL
Bibliographic data for series maintained by CCSD ().