DWT-based fault diagnosis in induction motors by using CVA

Abstract

In this paper, faults in induction motors were diagnosed by using the Common Vector Approach (CVA). CVA is a well-known subspace-based pattern recognition method that is widely used in speech recognition, speaker recognition, and image recognition problems. In order to analyze the performance of CVA, a database including the current signals of six identical induction motors were used. One of these induction motors was healthy motor whereas the remaining five induction motors were exposed to different synthetic faults. The multi-step One-Dimensional Discrete Wavelet Transform (1D-DWT) is applied on the current signals in order to construct feature vectors of each faulty class in the database. While performing CVA, the leave-20-out strategy was followed in order to test all feature vectors in the database. Highly satisfactory classification results were obtained.