Motor speed identification using multilayer feedforward neural networks

Abstract

This paper presents an artificial neural networks (ANNs) based high performance speed identified for a dc motor control system. The purpose is to achieve accurate trajectory control of the speed, specially when motor and load parameters are unknown. The unknown nonlinear dynamics of the motor and the load are captured by multilayer feedforward neural network contains three layers. The activation function of the hidden layers are logsigmoid function and the training technique is use the backpropagation technique.