Abstract
A new concept on the degree of credibility of parameter value variations (DCPV factor) is proposed in this paper to solve the problem that on-line monitoring and failure diagnosis of rolling element bearings are affected by monitoring parameter value variations caused by the intrusive vibration signals. Using the factor of the degree of credibility and the basic principle of the expert system, an on-line monitoring and diagnostic method of rolling element bearings with AI is developed. The technique enhances traditional vibration analysis and provides a means of automating the monitoring and diagnosis of vibrating device.
