The state estimation of the CSTR system based on a recurrent neural network trained by HGAs

Author

Lei, Jia ; He, Guangdong ; Jiang, Jing Ping

Author_Institution

Dept. of Electr. Eng., Zhejiang Univ., Hangzhou, China

Volume

2

fYear

1997

fDate

9-12 Jun 1997

Firstpage

779

Abstract

The CSTR system (continuous stirred tank reactor system) is a typical nonlinear system. At present, one of its states, reaction consistence, can not be measured. In this paper, a recurrent neural network is used to estimate the value of the state. Nevertheless, due to the strong nonlinearity of the system, traditional training method such as BP algorithm usually converges in local optimum. Genetic algorithms (GAs), as a global optimization search method, can solve the problem, but the conventional GAs converge very slowly. To improve the learning speed of the neural network, a hybrid genetic algorithm (HGA) is employed. The results demonstrate the proposed HGA can get a very good effect

Keywords

backpropagation; chemical technology; genetic algorithms; learning (artificial intelligence); multilayer perceptrons; nonlinear systems; recurrent neural nets; state estimation; CSTR system; continuous stirred tank reactor system; hybrid genetic algorithm; learning speed; nonlinear system; nonlinearity; reaction consistence; recurrent neural network; state estimation; Continuous-stirred tank reactor; Genetic algorithms; Gradient methods; Helium; Inductors; Neural networks; Nonlinear systems; Optimization methods; Recurrent neural networks; State estimation;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks,1997., International Conference on

Conference_Location

Houston, TX

Print_ISBN

0-7803-4122-8

Type

conf

DOI

10.1109/ICNN.1997.616121

Filename

616121