Adaptive controller design using just-in-time learning algorithm

Author

Cheng, Cheng ; Hashimoto, Yoshihiro ; Chiu, Min-Sen

Author_Institution

Dept. of Chem. & Biomolecular Eng., Nat. Univ. of Singapore, Singapore

Volume

2

fYear

2004

fDate

2-4 Sept. 2004

Firstpage

1106

Abstract

An adaptive PID controller design based on just-in-time learning (JITL) algorithm is developed. Inspired by the learning strategy of neural network, a gradient descent algorithm is used to tune the controller parameters on-line based on the information provided by JITL. In addition, a predictive feedforward control scheme is devised to enhance the disturbance rejection capability of the proposed design. The proposed method is illustrated and evaluated by a case study of a polymerization reactor.

Keywords

adaptive control; chemical reactors; control system synthesis; feedforward; gradient methods; learning systems; predictive control; process control; three-term control; PID control; adaptive control design; disturbance rejection capability; gradient descent algorithm; just-in-time learning algorithm; neural network; polymerization reactor; predictive feedforward control; Adaptive control; Algorithm design and analysis; Chemical processes; Chemical technology; Electrical equipment industry; Inductors; Neural networks; Polymers; Programmable control; Three-term control;

fLanguage

English

Publisher

ieee

Conference_Titel

Control Applications, 2004. Proceedings of the 2004 IEEE International Conference on

Print_ISBN

0-7803-8633-7

Type

conf

DOI

10.1109/CCA.2004.1387520

Filename

1387520