Fault Diagnosis Method of Rolling Bearing Based on Feature Mode Decomposition and Convolution Neural Network

Rolling bearing failure will affect the normal operation of the mechanical equipment. Effective early failure diagnosis can avoid unnecessary losses caused by bearing fault. A fault diagnostic method of rolling bearing relying on Feature Mode Decomposition (FMD) and Convolutional Neural Network (CNN) is proposed in this article. Firstly, the effective fault feature information in rolling bearing vibration signal will be extracted by FMD method, and then the collected feature information is introduced into the CNN framework to effectively classify different types of faults of rolling bearing. This method is of practical significance for the fault classification of rolling bearing under the strong background noise.