Research on Rolling Bearing Fault Diagnosis based on MVMD Energy Entropy and ELM

Motor rolling bearing fault vibration signal as the object of diagnosis analysis to provide a feasible basis for diagnosis. However, in some cases, the collected vibration signals in the time domain cannot directly allow us to give the diagnosis results, so we need to further measure and quantify the collected vibration signals. In this paper, a fault diagnosis scheme of motor rolling bearing based on multivariate variational mode decomposition (MVMD) energy entropy is proposed, and the extreme learning machine (ELM) is used for classification recognition. Through the simulation analysis of the collected vibration signals, the feasibility of the proposed method is verified.