Toward Self-Supervised Feature Learning for Online Diagnosis of Multiple Faults in Electric Powertrains

• Published in: IEEE transactions on industrial informatics Vol. 17; no. 6; pp. 3772 - 3781
• Main Authors: Senanayaka, Jagath Sri Lal, Van Khang, Huynh, Robbersmyr, Kjell G.
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 01.06.2021; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Anomalies; Artificial neural networks; Classification algorithms; Convolutional neural network (CNN); electric powertrains; Fault detection; Fault diagnosis; Machine learning; Mechanical power transmission; one-class support vector machine (SVM); Powertrain; self-supervised learning; Signal processing algorithms; Support vector machines; Training; Training data; Vibrations
• ISSN: 1551-3203; 1941-0050
• DOI: 10.1109/TII.2020.3014422

This article proposes a novel online fault diagnosis scheme for industrial powertrains without using historical faulty or labeled training data. The proposed method combines a one-class support vector machine (SVM) based anomaly detection and supervised convolutional neural network (CNN) algorithms to online detect multiple faults and fault severities under variable speeds and loads. The one-class SVM algorithm is to derive a score for defining faults or health classes in the first stage, and the resulting health classes are used as the training data for the CNN-based classifier in the second stage. Within this framework, the self-supervised learning of the proposed CNN algorithm allows the online diagnosis scheme to learn features based on the latest data. The effectiveness of the scheme is validated via a comparison study using experimental data from an in-house test setup. Finally, the online implementation of the proposed scheme on the test setup is briefly introduced.