Fault information extraction of mechanical equipment based on independent component analysis

作者：Xu Yong Gang^*; Li Qiang; Wang Zheng Ying; Wang Tai Yong

来源：Journal of Tianjin University, 2006, 39(9): 1066-1071.

• Cross correlation functions
• Fault diagnosis
• Vibration signals

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.

• 出版日期2006
• 单位天津大学