Conditional GAN and 2-D CNN for Bearing Fault Diagnosis With Small Samples

The rolling bearing is the key component of rotating machinery, and it is also a failure-prone component. The intelligent fault diagnosis method has been widely used to accurately diagnose bearing faults. However, in engineering practice, it is difficult to obtain sufficient sample data to train the intelligent diagnosis model. Therefore, in this paper, a fusion diagnosis model CGAN-2D-CNN that combines a conditional generative adversarial network (CGAN) and a two-dimensional convolutional neural network (2D-CNN) is proposed for bearing fault diagnosis with small samples. Considering the problem of insufficient sample data, CGAN is used to learn the data distribution of real samples to generate new samples with similar data distribution by the confrontation training of the generator and discriminator. Then, two-dimensional pre-processing is conducted to convert the generated one-dimensional data into two-dimensional grey gray images. Finally, these images are input into the 2D-CNN to extract the features and classify the bearing fault types. Two experimental cases are implemented to validate the effectiveness and feasibility of the proposed CGAN-2D-CNN. The experimental results illustrate that the diagnosis accuracy of the proposed method used on the small sample data is close to that of the 2D-CNN directly used on the enough original sample data whose size is equal to the expanded sample size. Additionally, compared with the 1D-CNN, SVM, and LSTM models, the 2D-CNN model after two-dimensional pre-processing has the higher fault classification accuracy.