Application of Self-Tuning Pid Control Based on Diagonal Recurrent Neural Network in Crystallization Process

Author

Song, Zhe-ying ; Liu, Chao-ying ; Song, Xue-ling

Author_Institution

Coll. of Electr. Eng. & Inf. Sci., Hebei Univ. of Sci. & Technol.

fYear

2006

fDate

13-16 Aug. 2006

Firstpage

365

Lastpage

369

Abstract

In crystallization process there are strong coupling between the temperature control and the level control in the tank, and the parameter is time-varying, so it is difficult to apply general PID control. The self-adjusting PID control method based on diagonal recurrent neural network (DRNN) is introduced in this paper. According to the influence of object´s parameter to system output performance, the DRNN can auto-adjust its weights to vary k_P, k_I and k_D. The Simulation results show that the presented control system has quick response speed and strong adaptive capability

Keywords

control engineering computing; crystallisation; level control; process control; recurrent neural nets; self-adjusting systems; temperature control; time-varying systems; DRNN; crystallization process; diagonal recurrent neural network; level control; self-tuning PID control; temperature control; time-varying parameter; Chaos; Crystallization; Cybernetics; Educational institutions; Electronic mail; Intelligent networks; Machine learning; Neural networks; Recurrent neural networks; Temperature control; Three-term control; Time varying systems; Crystallization process; DRNN; Decoupling Control; Simulation;

fLanguage

English

Publisher

ieee

Conference_Titel

Machine Learning and Cybernetics, 2006 International Conference on

Conference_Location

Dalian, China

Print_ISBN

1-4244-0061-9

Type

conf

DOI

10.1109/ICMLC.2006.259040

Filename

4028090