盲源分离技术在齿轮故障诊断中的应用

Application of Blind Source Separation Method to Gear Fault Diagnosis

随着齿轮故障诊断学的发展,一种新的多通道信号处理技术随之产生—盲源分离技术。采用一种基于稳健的二阶统计量的盲源分离算法,此算法优越性在于不必估计复杂的源信号概率密度函数且计算量少。实验结果表明,盲源分离技术能有效地诊断出齿轮的故障,实现对多输入多输出系统的源信号恢复。

A new multi - channel signal processing technology- Blind Source Separation （BSS） is resulting with the development of gear fault diagnosis. Uses a Blind Source Separation algorithm based on the robust second - order statistics of the algorithm needn＇ t estimate the source signal complex probability density function and has low computing cost. Experimental results show that Blind Source Separation technology can diagnose the gear failure very good and complete the source signal recovery of the multi - input multi - output system possible.