A Novel GAN-based Fault Diagnosis Approach for Imbalanced Industrial Time Series

Abstract

This paper proposes a novel fault diagnosis approach based on generative adversarial networks (GAN) for imbalanced industrial time series where normal samples are much larger than failure cases. We combine a well-designed feature extractor with GAN to help train the whole network. Aimed at obtaining data distribution and hidden pattern in both original distinguishing features and latent space, the encoder-decoder-encoder three-sub-network is employed in GAN, based on Deep Convolution Generative Adversarial Networks (DCGAN) but without Tanh activation layer and only trained on normal samples. In order to verify the validity and feasibility of our approach, we test it on rolling bearing data from Case Western Reserve University and further verify it on data collected from our laboratory. The results show that our proposed approach can achieve excellent performance in detecting faulty by outputting much larger evaluation scores.

Cited by in corpus (8)

• Data Augmentation techniques in time series domain: A survey and taxonomy
• A Comprehensive Survey of Deep Transfer Learning for Anomaly Detection in Industrial Time Series: Methods, Applications, and Directions
• Real-World Anomaly Detection by using Digital Twin Systems and Weakly-Supervised Learning
• Data-driven Machinery Fault Diagnosis: A Comprehensive Review
• A Survey of Predictive Maintenance: Systems, Purposes and Approaches
• GRD-Net: Generative-Reconstructive-Discriminative Anomaly Detection with Region of Interest Attention Module
• Intelligent Icing Detection Model of Wind Turbine Blades Based on SCADA data
• DTWSSE: Data Augmentation with a Siamese Encoder for Time Series