Motor speed identification using multilayer feedforward neural networks
Vittaya Tipsuwanporn, Chanrit Tarasantisuk, A. Numsumran, Winyu Sawaengsinkasikit · 2005
This paper presents an artificial neural networks (ANNs) based high performance speed identifier for a DC motor control system. The purpose is to achieve accurate trajectory control of the speed, especially when motor and load parameters are unknown. The unknown nonlinear dynamics of the motor and the load are captured by multilayer feedforward neural network containing three layers. The activation function of the hidden layers are logsigmoid function and the training technique is use the backpropagation technique.