A Fuzzy Expert System for Predicting the Performance of Switched Reluctance Motor

Abstract

In this paper a fuzzy expert system for predicting the performance of a switched reluctance motor has been developed. The design vector consists of design parameters, and output performance variables are efficiency and torque ripple. An accurate analysis program based on Improved Magnetic Equivalent Circuit (IMEC) method has been used to generate the input-output data. These input-output data is used to produce the initial fuzzy rules for predicting the performance of Switched Reluctance Motor (SRM). The initial set of fuzzy rules with triangular membership functions has been devised using a table look-up scheme. The initial fuzzy rules have been optimized to a set of fuzzy rules with Gaussian membership functions using gradient descent training scheme. The performance prediction results for a 6/8, 4kw, SR motor shows good agreement with the results obtained from IMEC method or Finite Element (FE) analysis. The developed fuzzy expert system can be used for fast prediction of motor performance in the optimal design process or on-line control schemes of SR motor.