Auxiliary generative mutual adversarial networks for class-imbalanced fault diagnosis under small samples

Abstract

The effect of intelligent fault diagnosis of mechanical equipment based on data-driven is often premised on big data and class-balance. However, due to the limitation of working environment, operating conditions and equipment status, the fault data collected by mechanical equipment are often small and imbalanced with normal samples. Therefore, in order to solve the above-mentioned dilemma faced by the fault diagnosis of practical mechanical equipment, an auxiliary generative mutual adversarial network (AGMAN) is proposed. Firstly, the generator combined with the auto-encoder (AE) constructs the decoder reconstruction feature loss to assist it to complete the accurate mapping between noise distribution and real data distribution, generate high-quality fake samples, supplement the imbalanced dataset to improve the accuracy of small sample class-imbalanced fault diagnosis. Secondly, the discriminator introduces a structure with unshared dual discriminators. Realize the mutual adversarial between the dual discriminator by setting the scoring criteria that the dual discriminator are completely opposite to the real and fake samples, thus improving the quality and diversity of generated samples to avoid mode collapse. Finally, the auxiliary generator and the dual discriminator are updated alternately. The auxiliary generator can generate fake samples that deceive both discriminators at the same time. Meanwhile, the dual discriminator cannot give correct scores to the real and fake samples according to their respective scoring criteria, so as to achieve Nash equilibrium. Using three different test-bed datasets for verification, the experimental results show that the proposed method can explicitly generate high-quality fake samples, which greatly improves the accuracy of class-unbalanced fault diagnosis under small sample, especially when it is extremely imbalanced, after using this method to supplement fake samples, the fault diagnosis accuracy of DCNN and SAE are relatively big improvements. So, the proposed method provides an effective solution for small sample class-unbalanced fault diagnosis.