Bearing fault diagnosis method based on Gramian angular field and ensemble deep learning

Inspired by the successful experience of convolutional neural networks (CNN) in image classification, encoding vibration signals to images and then using deep learning for image analysis to obtain better performance in bearing fault diagnosis has become a highly promising approach. Based on this, we propose a novel approach to identify bearing faults in this study, which includes image-interpreted signals and integrating machine learning. In our method, each vibration signal is first encoded into two Gramian angular fields (GAF) matrices. Next, the encoded results are used to train a CNN to obtain the initial decision results. Finally, we introduce the random forest regression method to learn the distribution of the initial decision results to make the final decisions for bearing faults. To verify the effectiveness of the proposed method, we designed two case analyses using Case Western Reserve University (CWRU) bearing data. One is to verify the effectiveness of mapping the vibration signal to the GAFs, and the other is to demonstrate that integrated deep learning can improve the performance of bearing fault detection. The experimental results show that our method can effectively identify different faults and significantly outperform the comparative approach.