A multiclass SVM-based classifier for transformer fault diagnosis using a particle swarm optimizer with time-varying acceleration coefficients

摘要

A multiclass support vector machine (SVM) classifier based upon particle swarm optimization (PSO) withntime-varying acceleration coefficients for fault diagnosis of power transformers is proposed in this paper.nThe one-against-one combination scheme is adopted to extend SVM for settling the multiclass classificationnproblem. The algorithm of PSO with time-varying acceleration coefficients (PSO-TVAC) is employed tonoptimize the parameters for SVM. The results show that the convergence of the PSO-TVAC algorithm isnrelatively faster and much more precise than that of the classical PSO. Moreover, compared with othernreference diagnosis approaches, the results demonstrate the improved classification accuracy based uponnthe proposed approach and show it can be used as an effective tool for fault diagnosis of power transformers.nCopyright © 2011 John Wiley & Sons, Ltd.