基于数学形态学理论的旋转机械故障诊断方法研究

Research on the fault diagnosis method of rotating machinery based on mathematical morphology theory

在数学形态学理论的基础上运用局部特征长度域(LCD)算法和区间估计分形维数对传统诊断方法进行改进,利用LCD算法对信号进行处理,同时利用区间估计对形态谱进行故障分析。实验结果表明,基于LCD算法的故障诊断研究方法可以准确判断不同故障类型,区间估计分形维数方法的故障判断精度为95%,而且不同故障类型的形态谱特征与实际相符合。

On the basis of mathematical morphology theory,the traditional diagnosis method is improved by using local feature length domain(LCD)algorithm and interval estimation fractal dimension.LCD algorithm is used to process the signal,and interval estimation is used to analyze the morphological spectrum.The experimental results show that the fault diagnosis research method based on LCD algorithm can accurately judge different fault types,the fault diagnosis accuracy of interval estimation fractal dimension method is 95%,and the morphological spectrum characteristics of different fault types are consistent with the reality.