Anomaly detection of cooling fan and fault classification of induction motor using Mahalanobis–Taguchi system

Abstract

A health index, Mahalanobis distance (MD), is proposed to indicate the health condition of cooling fan and induction motor based on vibration signal. Anomaly detection and fault classification are accomplished by comparing MDs, which are calculated based on the feature data set extracted from the vibration signals under normal and abnormal conditions. Since MD is a non-negative and non-Gaussian distributed variable, Box–Cox transformation is used to convert the MDs into normal distributed variables, such that the properties of normal distribution can be employed to determine the ranges of MDs corresponding to different health conditions. Experimental data of cooling fan and induction motor are used to validate the proposed approach. The results show that the early stage failure of cooling fan caused by bearing generalized-roughness faults can be detected successfully, and the different unbalanced electrical faults of induction motor can be classified with a higher accuracy by Mahalanobis–Taguchi system. Such works could aid in the reliable operation of the machines, the reduction of the unexpected failures, and the improvement of the maintenance plan.