A new model for bearing fault diagnosis based on mutual mapping of signals and images and sparse representation

For the issue of significant noise in the collected bearing fault signals, a new bearing fault diagnosis model based on mutual mapping of signals and images (MMSI) and sparse representation (SR) denoising is proposed. Firstly, the fault signal is divided into several segments with the same number of sampling points, and then arrange these segments in ascending order of rows. Secondly, convert the arranged signals into grayscale image and use dictionary learning for block denoising. Then, the de-noised grayscale image is restored to a signal in line order. Finally, k-nearest neighbor (KNN) is used for fault classification. To verify the performance of the proposed model, experiments are tested on 12 single working conditions and 30 multi working conditions on the Case Western Reserve University (CWRU) dataset and the Paderborn dataset. The experimental results indicate that compared with some existing models, the MMSI-SR-KNN model can not only accurately diagnose bearing faults in artificial damage experiments, but also performs better in real damage faults. This indicates that the model has good generalization ability between different datasets and working conditions.