Coupling Pairwise Support Vector Machines for Fault Classification

Abstract

Different coupling strategies to reconstruct a multi-class classifier from pairwise support vector machine (SVM) based classifiers are compared with application to fault diagnostics of a cage induction motor. Power spectrum density (PSD) estimates of circulating currents in parallel branches of the motor are calculated with Welch's method. and SVM's are trained to distinguish healthy spectrum from faulty spectra and faulty spectra from each other. Majority voting, a mixture matrix and neural network are compared in reconstruction the global classification decision from outputs of SVM's.