Online detection of bearing incipient fault with semi-supervised architecture and deep feature representation

• Published in: Journal of manufacturing systems Vol. 55; pp. 179 - 198
• Main Authors: Mao, Wentao, Tian, Siyu, Fan, Jingjing, Liang, Xihui, Safian, Ali
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 01.04.2020
• Subjects: Anomaly detection; Generalization error upper bound; Incipient fault detection; Semi-supervised learning; Stacked denoising auto-encoder; Generalization error upper bound; Semi-supervised learning; Stacked denoising auto-encoder; Anomaly detection; Incipient fault detection
• ISSN: 0278-6125; 1878-6642
• DOI: 10.1016/j.jmsy.2020.03.005

•We propose a new online anomaly recognition method for bearing incipient fault with semi-supervised architecture.•We propose a new fault alarm criterion for incipient fault without much human intervention.•The proposed approach does not need much offline data and has very low false alarm rate. Although researchers have made substantial progress in bearing fault detection and diagnosis recently, incipient fault detection, especially online detection, is still at an initial stage. Generally speaking, online detection of incipient faults is still subject to the following challenges: (1) improving discriminative ability of incipient fault features; (2) adaptive recognition of the distribution inconsistency that exists in online sequential data; (3) achieving automatic detections with avoiding manual adjustment of detection criterion; and (4) reducing false alarm rate. To address these challenges, this paper presents a new approach for bearing incipient fault online detection using semi-supervised architecture and deep feature representation. This approach is simple and effective. First, we extract deep features using stacked denoising auto-encoder from the target bearing's normal state data and an auxiliary bearing's fault state data. Second, we introduce safe semi-supervised support vector machine (S4VM), a kind of semi-supervised classifier, to identify the sequentially arrived data of the target bearing as normal or anomalous. To update the classifier effectively, we use the principal curve to generate synthetic fault data for keeping data classes balanced during online condition monitoring. Finally, we propose a new fault alarm criterion based on S4VM generalization error upper bound to adaptively recognize the occurrence of an incipient fault. The experimental results on three datasets (IEEE PHM Challenge 2012, IMS and XJTU-SY) demonstrate the effectiveness and high reliability of the proposed approach.