A Fault Diagnosis Method of Rolling Bearing through Wear Particle and Vibration Analyses

Abstract

Wear particle and vibration analysis are the two main condition monitoring techniques for machinery maintenance and fault diagnosis in industry. Due to the complex nature of machinery, these two techniques can only diagnose about 30% to 40% of faults when used independently. Therefore, it is critical to integrate vibration analysis and wear particle analysis to provide a more effective maintenance program. This paper presents a new fault diagnosis approach of rolling bearings via the combination of vibration analysis and wear particle analysis. Both the tribological and vibrant information of the rolling bearings with typical faults were collected by an experimental test rig. Wear particle analysis was applied to the oil samples to obtain the wear particle number and size distribution, the particle texture and the chemical compositions, etc. Vibration analysis was used to get the time and frequency characteristics of the vibration data. Then, an intelligent data fusion method based on the genetic algorithm based fuzzy neural network was employed to identify the rolling bearing conditions. The analysis results suggest that the proposed method is more feasible and effective for the rolling bearing fault diagnosis than separated use of the two techniques with respect to the classification rate, and thus has application importance.