Title :
A design method of feed-forward control based on inverse system
Author :
Masuda, Maklo ; Fujiwara, Toshitaka
Author_Institution :
Mitsubishi Heavy Ind. Ltd., Hyogo, Japan
Abstract :
The authors propose a high-speed learning method and high speed learning neural networks by backpropagation. A method of feedforward control using an inverse system is proposed. The effects of these methods are confirmed by simulation. The inverse system is shown to be an effective measure for process control
Keywords :
identification; learning systems; neural nets; process computer control; backpropagation; design; feedforward control; inverse system; learning method; neural networks; process control; Control systems; Design methodology; Error correction; Feedforward systems; Feeds; Integral equations; Learning systems; Neural networks; Power generation; Thermal variables control;
Conference_Titel :
Neural Networks, 1991. 1991 IEEE International Joint Conference on
Print_ISBN :
0-7803-0227-3
DOI :
10.1109/IJCNN.1991.170583
