Artificial neural network based induction motor design

Abstract

This paper presents an artificial neural network based designing for induction motors. Based on the actual design data for various types of induction motors, three-layered artificial neural networks have been trained to give better solutions for the fundamental quantities and parameters of individual induction motor. After training, selected quantities have been estimated quite accurately from the input data which is the specification of an individual induction motor. The proposed neural network based designing system is efficient to reduce the designing process and also to have the near optimal design in a restricted time period without expert designer's knowledge.