基于独立分量分析的机械故障信息提取

Fault Information Extraction of Mechanical Equipment Based on Independent Component Analysis

独立分量分析是盲源分离的一种新方法,其处理的时象是相互统计独立的信号源经线性组合而产生的一组混合信号,最终目的是从混合信号中分离出各独立的信号分量．为此,论证了机械振动信号盲源分离的可行性,并对盲源分离中的“源”赋予了新的含义,利用互相关函数估计不同通道之间的时延参数,适当截取后组成混合信号再进行盲源分离,可以保证振动信号分离的有效性．盲源分离技术在涡流传感器失效故障诊断和早期碰摩故障诊断的成功应用,表明该技术在机械设备状态监测和故障诊断中有着广阔的应用前景．

As a new approach of blind source separation （BSS）, independent component analysis （ICA） is a method recently developed in which the processed objects are mixed signals from linear combination of the original data. At last the source is separated from the mixtures and the components separated are statistically independent, or as independent as possible. The feasibility of applying BSS to vibration signals is demonstrated, and the ＂source＂ in BSS is endued with new meaning. The time delay parameters between different channels are estimated by using cross-correlation functions, and appropriate parts of original signals are chosen to reconstruct new mixtures for BSS, These preprocessing methods will ensure the validity of vibration signals separation, Successful applications of BSS are achieved in the detection of eddy-current sensor failure and the diagnosis of incipient impact-rub fault. The results show that BSS has wide application prospect in the condition monitoring and fault diagnosis of mechanical equipment.