A Novel GAN-based Fault Diagnosis Approach for Imbalanced Industrial Time Series
This addresses fault diagnosis for industrial systems with imbalanced data, but it is incremental as it builds on existing GAN methods with specific modifications.
The paper tackles fault diagnosis in imbalanced industrial time series where normal samples dominate failure cases, proposing a GAN-based approach that achieves excellent performance in detecting faults by outputting significantly larger evaluation scores on rolling bearing data.
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.