基于改进极限学习机的滚动轴承故障诊断

Fault Diagnosis of Rolling Bearing Based on Improved Extreme Learning Machine

鉴于小波核极限学习机对参数依赖的特性,致使滚动轴承故障分类器模型效果差,提出了一种基于改进灰狼优化算法优化小波核极限学习机的故障分类方法。该方法综合变分模态分解和奇异值分解方法提取故障信号特征。引入反向学习及levy飞行策略对灰狼优化算法(Grey Wolf Optimizer,GWO)进行改进,从而丰富了GWO算法种群多样性,提高了算法的收敛速度以及跳出局部最优的能力。将改进后的GWO算法用于小波核极限学习机参数优化,获取最佳参数组合构建分类器模型。对比实验结果表明,该方法的故障识别效果更好,训练速度更快,稳定性更强。

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.