Parameter identification of an induction machine using genetic algorithms

This paper applies genetic algorithms to the problem of parameter identification of induction machines. For the purpose of variable speed application, the motor´s general mathematical model based upon Kron´s voltage equations has been employed to estimate the parameters, and the motor´s start-up performance has been used as the measurement during the identification process. Results with different measurement noises and different measured performances are presented. For comparison, the results of a simple random search (SRS) method under the same condition are also given. The results show that the performance of the GA is much better than that of the SRS technique. It is concluded that the GA is a powerful tool for parameter identification