Study and application on recurrent neural network controller

SUN Feng ;ZHU Qun-xiong

Journal of Beijing University of Chemical Technology ›› 2000, Vol. 27 ›› Issue (3) : 88-90.

PDF(195 KB)
Welcome to Journal of Beijing University of Chemical Technology, Today is July 24, 2025
Email Alert  RSS
PDF(195 KB)
Journal of Beijing University of Chemical Technology ›› 2000, Vol. 27 ›› Issue (3) : 88-90.
研究论文

Study and application on recurrent neural network controller

  • SUN Feng ;ZHU Qun-xiong
Author information +
History +

Abstract

The direct neural network control is introduced and the dynamic feedback recurrent neural network (RNN) with multi-layers as a controller is analyzed. A new type of RNN control system is proposed with applications to a continuous stirred tank reactor (CSTR) control and a plant wide industrial process control (Benchmark) problems. The control results show that the RNN controller with multi layers leads to simplification of control structure and good effect, especially for multi input/multi-output cascade control systems, exhibiting that the RNN controller is adaptable and applicable to complex industrial problems.

Cite this article

Download Citations
SUN Feng ;ZHU Qun-xiong . Study and application on recurrent neural network controller [J]. Journal of Beijing University of Chemical Technology, 2000, 27(3): 88-90

References

[1 ]  朱群雄,孙锋. RNN 神经网络的应用研究. 北京化工大学学报,1998 , 25 (1) : 86~90
[2 ]  Michael Nikolaou , Vijaykumar Hanagandi. Control of nonlinear dynamical systems modeled by recurrent neural networks. AIChE Journal , 1993 , 39 :1890~1894
[3 ]  Henson M A , Sebory D E. Input2output linearization of general nonlinear process. AIChE Journal , 1990 , 36 :1753~1757
[4 ]  Ricker N L , Lee J H. Nonlinear model predictive control of the tennessee eastman plant2wide control problem.Computers Chem Eng , 1995 , 19 (4) : 453~480
[5 ]  McAvoy T J , Ye N. Base control for the tennessee eastman problem. Computers Chem Eng , 1994 , 18 (5) : 383~413
PDF(195 KB)

4189

Accesses

0

Citation

Detail

Sections
Recommended

/