Title :
Reducing the computational demands of continually online-trained artificial neural networks for system identification and control of fast processes
Author :
Burton, Bruce ; Harley, Ronald G.
Author_Institution :
Dept. of Electr. Eng., Natal Univ., Durban, South Africa
Abstract :
This paper describes many of the generic factors which influence the computational demands of continually online-trained backpropagation artificial neural networks (ANNs) used to identify and control fast processes. The limitations of even parallel hardware in meeting these demands is discussed. An adaptive online-trained ANN induction motor stator current controller is considered as a typical fast process. Various modifications are made to the ANN structure to lower computational demands and increase ANN parallelism. The effects of these modifications on the overall controller stability and performance are illustrated by means of simulation results
Keywords :
adaptive control; backpropagation; electric current control; feedforward neural nets; identification; induction motors; machine control; neurocontrollers; parallel processing; power engineering computing; stability; stators; transputer systems; adaptive online-trained ANN; computational demands reduction; continually online-trained artificial neural networks; controller performance; controller stability; fast processes control; induction motor; online-trained backpropagation artificial neural networks; parallel hardware; parallel processing; sigmoidal feedforward neural net; single-transputer based platform; stator current controller; system identification; Adaptive control; Artificial neural networks; Backpropagation; Computer networks; Concurrent computing; Hardware; Induction motors; Process control; Programmable control; Stators;
Journal_Title :
Industry Applications, IEEE Transactions on
