A Modified Generative Adversarial Network for Fault Diagnosis in High-Speed Train Components with Imbalanced and Heterogeneous Monitoring Data

Abstract

Data-driven methods are widely considered for fault diagnosis in complex systems. However, in practice the between-class imbalance due to limited faulty samples may deteriorate their classification performance. To address this issue, synthetic minority methods for enhancing data have been proved to be effective in many applications. Generative Adversarial Networks (GANs), capable of automatic features extraction, can also be adopted for augmenting the faulty samples. However, the monitoring data of a complex system may include not only continuous signals, but also discrete/categorical signals. Since the current GAN methods still have some challenges in handling such heterogeneous monitoring data, a Mixed Dual Discriminator GAN (noted as M-D2GAN) is proposed in this work. In order to render the expanded fault samples more aligned with the real situation, and improve the accuracy and robustness of the fault diagnosis model, different types of variables are generated in different ways, including: floating-point, integer, categorical, and hierarchical. For effectively considering the class imbalance problem, proper modifications are made to the GAN model, where a normal class discriminator is added. A practical case study concerning the braking system of a high-speed train is carried out to verify the effectiveness of the proposed framework. Compared to the classic GAN, the proposed framework achieves better results with respect to F-measure and G-mean metrics.

Data Augmentation and Intelligent Fault Diagnosis of Planetary Gearbox Using ILoFGAN Under Extremely Limited Samples

“…However, the success of deep learning largely depends on the sufficiency of training samples. Unfortunately, with the increasing improvement of reliability and quality, the machinery works under healthy states most of time in the real industrial scenarios, which means that acquiring sufficient fault samples is difficult [8][9][10].…”

Non-negative wavelet matrix factorization-based bearing fault intelligent classification method

“…However, external noise interference and * Author to whom any correspondence should be addressed. internal structural complexity present significant challenges for diagnosing faults in actual working conditions [3,4], and effective fault diagnosis and identification methods need to be developed [5].…”

A new meta-transfer learning method with freezing operation for few-shot bearing fault diagnosis

“…Meta-learning must typically learn a large number of tasks which demonstrate unknown relevance and are difficult to determine. Therefore, avoiding catastrophic forgetting during learning is also important because information from old tasks should not be forgotten when accepting new ones [16][17][18].…”