Title :
Motor speed identification using multilayer feedforward neural networks
Author :
Tipsuwanporn, V. ; Tarasantisuk, C. ; Numsumran, A. ; Sawaengsinkasikit, W.
Author_Institution :
Fac. of Eng., King Mongkut´´s Inst. of Technol., Bangkok, Thailand
Abstract :
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.
Keywords :
DC motor drives; angular velocity control; electric machine analysis computing; feedforward neural nets; machine control; multilayer perceptrons; parameter estimation; DC motor control system; DC motor drives; artificial neural networks; backpropagation technique; hidden layers activation function; high performance speed identification; load parameters; logsigmoid function; motor parameters; speed control; three layer feedforward neural network; training technique; trajectory control; unknown nonlinear dynamics; Artificial neural networks; Backpropagation algorithms; Control systems; DC motors; Electronic mail; Feedforward neural networks; Multi-layer neural network; Neural networks; Nonlinear dynamical systems; Shafts;
Conference_Titel :
Power Electronics and Drive Systems, 2001. Proceedings., 2001 4th IEEE International Conference on
Print_ISBN :
0-7803-7233-6
DOI :
10.1109/PEDS.2001.975285
