基于EEMD和IHHO-LSSVM滚动轴承剩余寿命预测方法的研究

Research on Remaining Life Prediction of Rolling Bearing Based on EEMD and Improved HHO-LSSVM

针对滚动轴承剩余寿命预测准确度不高的问题,构建一种基于集合经验模态分解(EEMD)和考虑改进哈里斯鹰算法(IHHO)的最小二乘支持向量机(LSSVM)滚动轴承剩余寿命IHHO-LSSVM预测模型。首先,使用EEMD对原信号进行分解,根据峭度指标和相关系数选取合适的本征模态函数(IMF)进行重构。然后采用核主成分分析(KPCA)提取累计贡献率大于85%的主成分作为评估轴承退化性能指标。引入能量周期性递减调控机制,IHHO-LSSVM模型进行寿命预测,有效提高了HHO算法中寻找最优解的能力。通过轴承全寿命试验数据进行验证,其结果表明,该方法提取的轴承性能评估指标能够更为全面地表征轴承性能退化情况,建立的IHHO-LSSVM模型具有良好的预测效果。

Aiming at the problem that the remaining life of the rolling bearing is not accurate,a method based on ensemble empirical mode decomposition and improved Harris Eagle algorithm is proposed to optimize the model parameters of least squares support vector machine.Firstly,EEMD is used to decompose the original signal.According to the kurtosis value and correlation coefficient,it selects the appropriate Intrinsic Mode Function for reconstruction.Then,KPCA is used to extract the principal components whose cumulative contribution rate is more than 85%as the evaluation index of bearing degradation performance.IHHO-LSSVM model is used for life prediction by introducing the regulation mechanism of energy periodic decline,which effectively improves the ability to find the optimal solution in HHO algorithm.The results show that the bearing performance evaluation index extracted by this method can more comprehensively characterize the bearing performance degradation.The IHHO-LSSVM model has good prediction effect.