局域均值分解与矩阵分形的自动机故障诊断

Automaton Fault Diagnosis Based on LMD and Matrix Fractal Theory

针对自动机振动响应信号非线性、非平稳、高冲击的特性,提出基于局域均值分解(LMD)和矩阵分形相结合的自动机故障诊断方法。首先对采集到的自动机各工况信号采用LMD法对其进行分解,对分解得到的分量信号进行广义维数计算,通过广义维数相关系数判断方法选取分量信号,进而构建各工况的样本矩阵,用相关性判断方法计算待检测信号矩阵与样本矩阵之间的相关系数,最后通过对比相关系数的大小来判断故障模式。诊断结果与实际情况完全符合,表明该方法能有效的应用在自动机故障诊断中。

For the nonlinear, non-stationary, high impact properties of the automaton vibration response signal, a method which is proposed for the automaton fault diagnosis based on local mean decomposition （LMD） and fractal matrix. Firstly, LMD decomposition is used for various conditions automaton signal, calculated the generalized fractal dimension of the component signal, the component signal is selected by the method of generalized dimension correlation coefficient, then build the matrix sample of various conditions, calculated the correlation coefficient of signal matrix to be detected and sample matrix with correlation analysis, finally determined the fault types by comparing the correlation coefficient. The diagnosis result is in complete accordance with the actual situation, so it praves that the validity of this method for automaton fault diagnosis.