Fault Feature Extraction of Wind Turbine Rolling Bearing Based on PSO-VMD

Abstract

Taking the rolling bearing of wind turbine as the research object, and aiming at the problem that its fault feature is difficult to be extracted under the background of strong noise. A method based on variational mode decomposition and particle swarm optimization was proposed. Firstly, the PSO was used to search for the optimal parameters of the VMD algorithm, the wind turbine rolling bearing fault signal was decomposed according to the searching results. The fault signal can be decomposed into a series of intrinsic mode functions (IMFs) adaptively. The best signal component was selected and processed by envelope demodulation algorithm, bearing fault type was judged by analyzing the signal’s envelope spectrum. The experimental results show that the PSO-VMD algorithm can effectively eliminate noise impact and extract the wind turbine rolling bearing fault feature, and the accuracy can reach 99.57%.