关键词: 滚动轴承, 变分模态分解, 小波核极限学习机, 灰狼优化算法

Abstract: According to the parameter-dependent characteristics of the wavelet kernel extreme learning machine, which make the effect of the rolling bearing fault classifier model poor, a fault classification method based on improved grey wolf optimizer algorithm for optimizing wavelet kernel extreme learning machine was proposed. The method combined the variational mode decomposition and singular value decomposition to extract fault signal characteristics. The opposition-based-learning and the levy flight strategy were introduced to improve the grey wolf optimizer algorithm, which enriched the population diversity of the grey wolf optimizer algorithm, improved the convergence speed of the algorithm and the ability to get out of the local optimum. The improved grey wolf optimizer algorithm was applied to optimize the parameters of wavelet kernel extreme learning machine, and the best parameter combination was obtained to build the classifier model. The comparative experimental results show that the method has better fault recognition effect, faster training speed and stronger stability.

Key words: rolling bearing, variational mode decomposition, wavelet kernel extreme learning machine, grey wolf optimizer