Generating adaptive models of dynamic systems with recurrent neural networks

Author

Catfolis, Thierry

Author_Institution

Dept. of Chem. Eng., Katholieke Univ., Leuven, Belgium

Volume

5

fYear

1994

fDate

27 Jun-2 Jul 1994

Firstpage

3238

Abstract

Presents a method for building adaptive neural network models based on the real-time recurrent learning (RTRL) algorithm developed by Williams and Zipser (1989). The author introduces the error injection method as adaptation principle. This method consists of feeding back the model error as input to the network what causes the model to react to it. The main advantages of this method are a higher stability, and a better and faster model compared to networks using only the RTRL algorithm as adaptation rule. The author demonstrates the properties of this technique with a mathematical example and with an example based on a bioreactor model

Keywords

learning (artificial intelligence); modelling; recurrent neural nets; adaptive models; adaptive neural network models; bioreactor model; dynamic systems; error injection method; model error; real-time recurrent learning algorithm; recurrent neural networks; Adaptive systems; Chemical engineering; Control system synthesis; Expert systems; Mathematical model; Neural networks; Neurons; Nonlinear dynamical systems; Predictive models; Recurrent neural networks;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 1994. IEEE World Congress on Computational Intelligence., 1994 IEEE International Conference on

Conference_Location

Orlando, FL

Print_ISBN

0-7803-1901-X

Type

conf

DOI

10.1109/ICNN.1994.374754

Filename

374754