Title :
Implementation of a neural network to adaptively identify and control VSI fed induction motor stator currents
Author :
Burton, Bruce ; Harley, Ronald G. ; Diana, Gregory ; Rodgerson, James L.
Author_Institution :
Dept. of Electr. Eng., Natal Univ., Durban, South Africa
Abstract :
This paper presents a prototype hardware implementation of a continually online trained artificial neural network to adaptively identify the electrical dynamics of an induction machine and control its stator currents from a pulse width modulated voltage source inverter. A single transputer based hardware platform is described and the effects of computational speed limitations on the controller bandwidth are discussed. Captured results are compared with simulation results to practically verify the success of the adaptive neural network identification and control scheme
Keywords :
PWM invertors; adaptive control; digital control; electric current control; feedforward neural nets; induction motors; learning (artificial intelligence); machine control; machine testing; machine theory; parameter estimation; power engineering computing; stators; transputers; PWM VSI; adaptive control; computational speed; controller bandwidth; hardware platform; induction motor; neural network; simulation; stator currents; transputer; Artificial neural networks; Bandwidth; Induction machines; Neural network hardware; Neural networks; Prototypes; Pulse inverters; Pulse width modulation inverters; Stators; Voltage control;
Conference_Titel :
Industry Applications Society Annual Meeting, 1994., Conference Record of the 1994 IEEE
Conference_Location :
Denver, CO
Print_ISBN :
0-7803-1993-1
DOI :
10.1109/IAS.1994.377662
