9 Parameters estimation of an extended induction machine model using genetic algorithms

Industries are innovating, developing and optimizing production line to improve productivity, quality and robustness of the production in order to be competitive. The different existing goals of optimization, such as the computation of closed-loop drive-fed motors, the reduction of energy consumption or the detection of motor faults, lead to the necessity to identify the induction machine parameters (resistance, inductances, ...). To these ends, researchers and companies are investigating efficient methods to identify these parameters. In this paper, we propose for the first time an effective identification of 9 parameters of the extended induction machine model based on the θ-NSGA III. In addition, a comparison between a classic genetic algorithm, the well-known NSGA II and the θ-NSGA III is performed. Results show that the θ-NSGA III provides a better estimation of parameters than the two other genetic algorithms.