A Generative Adversarial Network Based a Rolling Bearing Data Generation Method Towards Fault Diagnosis

As a new generative model, the generative adversarial network (GAN) has great potential in the accuracy and efficiency of generating pseudoreal data. Nowadays, bearing fault diagnosis based on machine learning usually needs sufficient data. If enough near-real data can be generated in the case of insufficient samples in the actual operating condition, the effect of fault diagnosis will be greatly improved. In this study, a new rolling bearing data generation method based on the generative adversarial network (GAN) is proposed, which can be trained adversarially and jointly via a learned embedding, and applied to solve fault diagnosis problems with insufficient data. By analyzing the time-domain characteristics of rolling bearing life cycle monitoring data in actual working conditions, the operation data are divided into three periods, and the construction and training of the generative adversarial network model are carried out. Data generated by adversarial are compared with the real data in the time domain and frequency domain, respectively, and the similarity between the generated data and the real data is verified.