基于DE-ELM的刮板输送机用减速器故障诊断

Fault Diagnosis of Reducer for Scraper Conveyor Based on DE-ELM

提出一种基于差分进化-极限学习器(DE-ELM)的刮板输送机用减速器故障诊断方法。首先将减速器中齿轮不同故障类型的一维时域振动信号通过Hankel矩阵转化为二维矩阵,然后利用奇异值分解方法求取信号所对应的矩阵奇异值;同时,利用DE算法对ELM中的输入权值与隐含层节点阈值进行优化,提高ELM的稳定性与精度;最后,将奇异值特征作为DE-ELM的输入,实现减速器的故障诊断。实验结果表明,该方法具有更高的齿轮故障诊断精度及效率。

A fault diagnosis method of reducer for scraper conveyor based on differential evolution-extreme learning machine(DE-ELM)was proposed.Firstly,the one-dimensional time-domain vibration signal of different fault types of gears is transformed into a two-dimensional matrix by Hankel matrix,and then the singular value of the matrix corresponding to the signal is obtained by singular value decomposition method.At the same time,in order to improve the stability and accuracy of ELM.the DE algorithm is used to optimize the input weights and hidden layer node thresholds in ELM.Finally,the singular value feature is used as the input of DE-ELM to realize the fault diagnosis of gear.The experimental results show that this method has higher gear fault diagnosis accuracy and efficiency.