Title :
Learning by a neural net aimed at minimisation of torque fluctuations of a reluctance machine
Author :
Herbert, B.J. ; Dessaint, Louis-A. ; Olivier, Guy
Author_Institution :
Montreal Higher Technol. Sch., Que., Canada
Abstract :
A radial basis function network is proposed for modelling the inverse transfer function of a variable-reluctance machine. It requires fewer neurons and is faster than the multilayer perceptron. A method of learning is presented and results of simulation using experimental data are included
Keywords :
control system analysis; feedforward neural nets; learning (artificial intelligence); machine control; machine theory; neurocontrollers; optimal control; reluctance machines; torque control; transfer functions; control simulation; inverse transfer function; modelling; neural net learning; neurons; radial basis function network; torque fluctuations minimisation; variable-reluctance machine; Commutation; Construction industry; Content addressable storage; Digital TV; Information analysis; Robustness; Rotors; Stators;
Conference_Titel :
Electrical and Computer Engineering, 1995. Canadian Conference on
Conference_Location :
Montreal, Que.
Print_ISBN :
0-7803-2766-7
DOI :
10.1109/CCECE.1995.528132
