Improving tuning capability of the adjusting neural network

Author

Sugita, Yoichi ; Kayama, Masahiro ; Morooka, Yasuo

Author_Institution

Power & Ind. Syst. R&D Div., Hitachi Ltd., Japan

Volume

2

fYear

1997

fDate

9-12 Jun 1997

Firstpage

761

Abstract

The adjusting neural network (AJNN) we (1995) proposed previously has the capability for parameter tuning of a control model, namely it can perform parameter tuning accurately with small tuning numbers. However, when parameter errors are relatively large, its tuning capability may occasionally deteriorate, which leads to an increase of tuning numbers. In this paper, we discuss two ways of overcoming this weakness of the AJNN. We propose a new learning algorithm for the AJNN and develop the AJNN architecture. We simulate the effectiveness of both approaches and compare these results with results from our previous AJNN using the problem of temperature control for a reheating furnace plant

Keywords

feedforward neural nets; furnaces; learning (artificial intelligence); neural net architecture; neurocontrollers; temperature control; tuning; adjusting neural network; architecture; control model; learning algorithm; multilayer neural nets; parameter tuning; reheating furnace plant; temperature control; Cellular neural networks; Control system synthesis; Error correction; Furnaces; Multi-layer neural network; Neural networks; Predictive models; Slabs; Temperature control; Tuners;

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.1997.616118

Filename

616118