Investigation of vibration signatures for multiple fault diagnosis in variable frequency drives using complex wavelets

Abstract

Embedded variable frequency induction motor drives are now an integral part of any industry due to their improved speed regulation and fast dynamic response. Hence, their diagnosis becomes vital to avoid downtimes and economic losses. In this paper, a technique based on a recent enhancement on wavelets, known as complex wavelets, is proposed for identifying multiple faults in vector controlled induction motor drives (VCIMDs). Radial, axial, and tangential vibrations are analyzed for diagnostic purpose. Initially, a relatively simple thresholding based method is investigated for feasibility of diagnosis under variable frequency and load conditions. In the second part, the feature extraction and classifier modeling are discussed, in which the nearly shift-invariant complex wavelet based model is compared with the discrete wavelet transform (DWT) for its applicability in detecting multiple faults. The fault conditions considered here are the most prominent ones such as interturn fault, interturn fault under progression, and bearing damage. Comparable performances of support vector machine (SVM) based models and simple technique based on k-nearest neighbor (k-NN) show the importance of efficient representation of input space by analytical wavelet based feature extraction. The performance indexes show the applicability of the scheme for industrial drives under variable frequencies and load conditions.