Title :
Design of a multivariable neural-net based PID controller
Author :
Yamamoto, Toru ; Oki, Toshitslka ; Shah, Sirish L.
Author_Institution :
Fac. of Sch. Educ., Hiroshima Univ., Japan
Abstract :
It is well known that most industrial processes are multivariate in nature, and yet PID controllers are being widely used in a multiloop framework for the control of such interacting systems. In this paper, a design scheme for a neural net-based controller with a PID structure is proposed for the control of such multivariable systems. The proposed controller consists of a pre-compensator designed with a static gain matrix which compensates for the low-frequency interaction, and PID controllers placed diagonally, whose gains are tuned by a neural network
Keywords :
compensation; control system synthesis; gain control; multivariable control systems; neurocontrollers; three-term control; tuning; diagonally placed PID controllers; gain tuning; industrial processes; interacting systems; low-frequency interaction compensation; multiloop framework; multivariable neural-net based PID controller design; pre-compensator; static gain matrix; Biological neural networks; Chemical industry; Chemical processes; Chemical technology; Communication system control; Control engineering education; Control systems; Industrial control; Neural networks; Three-term control;
Conference_Titel :
Neural Information Processing, 1999. Proceedings. ICONIP '99. 6th International Conference on
Conference_Location :
Perth, WA
Print_ISBN :
0-7803-5871-6
DOI :
10.1109/ICONIP.1999.844681
