Rolling bearing fault diagnosis based on composite multiscale permutation entropy and reverse cognitive fruit fly optimization algorithm – Extreme learning machine

Abstract

Rolling bearings usually work in complex environments, which makes them more prone to mechanical failures. Aiming at the non-stationary and nonlinear characteristics of its vibration signals, a fault diagnosis model based on composite multiscale permutation entropy (CMPE) and reverse cognitive fruit fly optimization algorithm optimized extreme learning machine (RCFOA-ELM) is proposed. Firstly, the particle swarm optimization optimized variational mode decomposition (PSO-VMD) is used to decompose the bearing vibration signal. Then the composite multiscale permutation entropy (CMPE) is used to calculate and compose the fault feature vector. Finally, input the feature sets into the optimized extreme learning machine (ELM) model for training and testing. Different types and different degrees of rolling bearing fault diagnosis experiments have proved that this model has a higher fault diagnosis recognition rate than other models. Therefore, this model can effectively improve the accuracy of fault classification and provide a new solution for rolling bearing fault diagnosis.