IDENTIFICATION OF INDUCTION MACHINE PARAMETERS USING SUPPORT VECTOR MACHINES

Piotr Bilski

Abstract

The paper presents the application of the support vector machines (SVM) to identify the parameters of the induction machine. The task is related to the regression problem, solved using a separate SVM for each parameter of the analysed object. The purpose and significance of the research is explained. Then, rules of usage and advantages of SVM are introduced. The proposed approach is realised using the model of the induction motor. Importance of the correct SVM kernel and its parameters selection are explained in detail. The paper is concluded with results discussion, conclusions and future prospects.

Keywords

electrical machines, artificial intelligence, regression, fault identification

Download

IMEKO-WC-2012-TC10-O5.pdf

DOI

-

IMEKO TC

TC10 - Measurement for Diagnostics, Optimization and Control

Back to the proceedings