Fault detection and diagnosis of a motor bearing shield

Recent years have seen increased attention to the Preventive Maintenance (PM) where corrective actions are promptly taken before small faults manifest themselves to be serious failures. Also, these undetected incipient faults present in an unhealthy machine can result in unnecessary waste of energy. Therefore, fault detection and diagnosis at the very early stage have become important. This paper presents an application of an Adaptive-Network-based Fuzzy Inference System (ANFIS) for diagnosing faults in the bearing shield of an induction motor. The experimental results show that the vibration parameters can efficiently indicate the occurrence of the faults which can be detected by the system.