【摘要】 针对复杂机械系统中经常出现的多种故障并存现象，讨论了基于主分量分析的机械故障信息分离的方法，然后利用最大熵谱处理短数据的优点对分离信号作频谱分析，达到对故障信号准确定位的目的，取得了较为满意的结果。更多还原

【Abstract】 Principal componenet analysis is taken to separate the faults information of complex machinery. The relationship between the separation of faults and principal component analysis is described. Maxmum entropy spectrum is used to estimate the frequency component in separated information. The practical examples are given. The results show that the principal component analysis successfully reduces dimension and complexity. A statisfactory result is acquired.更多还原