Direct MNN control of continuous stirred tank reactor based on input-output model

Author

Ge, S.S. ; Zhang, J. ; Lee, T.H.

Author_Institution

Dept. of Electr. & Comput. Eng., Nat. Univ. of Singapore, Singapore

Volume

5

fYear

2002

fDate

5-7 Aug. 2002

Firstpage

2770

Abstract

A direct multi-layer neural network control scheme is investigated for a class of continuous stirred tank reactors (CSTR). The CSTR plant under study is discretized to an input-output based τ-step ahead discrete-time model. By implicit function theorem, the existence of the implicit desired feedback control (IDFC) is proved. Multi-layer neural networks are used as the emulator of the desired feedback control. Projection algorithms are used to guarantee the boundness of the multi-layer neural network weights. Simulation results show the effectiveness of the proposed controller.

Keywords

chemical industry; chemical reactors; discrete time systems; multilayer perceptrons; neurocontrollers; CSTR plant; continuous stirred tank reactor; direct MNN control; direct multi-layer neural network control scheme; feedback control; implicit desired feedback control; implicit function theorem; input-output based T-step ahead discrete-time model; input-output model; multi-layer neural network weights; Adaptive control; Artificial neural networks; Chemical industry; Chemical processes; Continuous-stirred tank reactor; Control nonlinearities; Function approximation; Multi-layer neural network; Neural networks; Projection algorithms;

fLanguage

English

Publisher

ieee

Conference_Titel

SICE 2002. Proceedings of the 41st SICE Annual Conference

Print_ISBN

0-7803-7631-5

Type

conf

DOI

10.1109/SICE.2002.1195535

Filename

1195535