IMPROVED NEURAL-NETWORK MODEL FOR INDUCTION-MOTOR DESIGN

An improved model of the artificial neural network for analysis and de sign of induction motors is presented. Parameters of the machine equiv alent circuit are calculated using finite element method for a given m otor geometry. The training of the neural network model is based on a decoupled system between geometrical variables and circuit parameters. This method efficiently improved the training and performance of the neural network model which can be used to predict machine performance and solve design optimization problems.