A fuzzy expert system, Bearing -Expert, has been developed. This expert system is PC-based. It is menu driven and it is very user-friendly. This expert system offers specific knowledge of various aspects about bearing monitoring, such as diagnostic methods, defect frequencies, feature selection, fuzzy bearing classification etc. By responding to different questions successively, the user can obtain very specific knowledge via the shortest path.
In order to demonstrate the effectiveness of Bearing -Expert, experiments have been conducted. Radial accelerations have been measured and analysed. Feature selection has been performed effectively by the integration of Bearing -Expert and a computer program. The average of the top five values of frequency response in the high frequency region (5-22 kHz) has been found to be the best feature for the detection of roller bearing defects. Fuzzy reasoning has also been used via Bearing -Expert. Piecewise linear membership functions have been developed. A 100% reliability has been achieved for the detection of roller bearing defects via fuzzy reasoning. Bearing -Expert is very beneficial for factory automation and preventive maintenance.