Machinery fault diagnosis with imbalanced data using deep generative adversarial networks

• Published in: Measurement : journal of the International Measurement Confederation Vol. 152; p. 107377
• Main Authors: Zhang, Wei, Li, Xiang, Jia, Xiao-Dong, Ma, Hui, Luo, Zhong, Li, Xu
• Format: Journal Article
• Language: English
• Published: London Elsevier Ltd 01.02.2020; Elsevier Science Ltd
• Subjects: Bearings; Datasets; Deep learning; Fault diagnosis; Generative adversarial networks; Imbalanced data; Machine learning; Machinery; Mapping; Noise; Rotating machinery; Rotating machines; Rotation; Signal processing; Training; Vibration; Fault diagnosis; Deep learning; Imbalanced data; Generative adversarial networks; Rotating machines
• DOI: 10.1016/j.measurement.2019.107377
• ISSN: 0263-2241

•A deep learning method is proposed to address the data imbalance problem.•Deep generative adversarial networks are designed to generate fake samples.•Fake samples are similar with real machinery vibration data.•Experiments validate the proposed method on data augmentation in diagnosis. Despite the recent advances of intelligent data-driven fault diagnosis methods on rotating machines, balanced training data for different machine health conditions are assumed in most studies. However, the signals in machine faulty states are usually difficult and expensive to collect, resulting in imbalanced training dataset in most cases. That significantly deteriorates the effectiveness of the existing data-driven approaches. This paper proposes a deep learning-based fault diagnosis method to address the imbalanced data problem by explicitly creating additional training data. Generative adversarial networks are firstly used to learn the mapping between the distributions of noise and real machinery temporal vibration data, and additional realistic fake samples can be generated to balance and further expand the available dataset afterwards. Through experiments on two rotating machinery datasets, it is validated that the data-driven methods can significantly benefit from the data augmentation, and the proposed method offers a promising tool on fault diagnosis with imbalanced training data.