An educational tool for neural network control of brushless DC motors

Abstract

This paper presents an educational tool developed for neural network (NN) control of brushless DC (BLDC) motors. Neural networks courses are widely offered at the graduate and undergraduate level due to the successful applications of neural networks to the nonlinear and unmodelled systems control. However, teaching of neural network control in a laboratory may be time consuming and an expensive task. The developed software helps students learn the application of neural network control to the electric machinery. It provides flexible structure and graphical interface which permits the design of the neural networks and its training with various learning algorithms. Using the proposed tool, neural network control performance of BLDC motors cat? be monitored graphically for different NN control structure under different load conditions and parameter variations.