ADAPTIVE NEURO-FUZZY INFERENCE SYSTEM IDENTIFICATION OF AN INDUCTION MOTOR

Abstract

Modeling and simulation of the squirrel-cage induction motor (SCIM) is very complex and cannot represent the physical system exactly because the system is characterized by highly non-linear, complex and time-varying dynamics and inaccessibility of some of the states and outputs for measurements are depend on a lot of excited input parameters. This work demonstrated experimentally that ANFIS can be effectively used for identification of the system with highly accurate results. The accuracy of the identification results is demonstrated through validation tests including training, testing and validating data.