Title :
Neural emulation applied to chemical reactors
Author :
Atig, Asma ; Druaux, Fabrice ; Lefebvre, Dimitri ; Abderrahim, Kamel ; Abdennour, R.B.
Author_Institution :
GREAH, Univ. du Havre, Le Havre, France
Abstract :
In this paper, a real time recurrent learning-based emulator is presented for nonlinear plants with unknown dynamics. This emulator is based on fully connected recurrent neural networks. Starting from zero values, updating rate, time parameter and weights of the instantaneous neural emulator adapt themselves in order to estimate the process output. The contribution of this paper is to validate the emulator with experimental data from the batch reactor of National Engineering School of Gabes, Tunisia.
Keywords :
chemical engineering computing; chemical reactors; production engineering computing; recurrent neural nets; batch reactor; chemical reactor; instantaneous neural emulator; neural emulation; nonlinear plant; recurrent learning-based emulator; recurrent neural network; Neural emulation; RTRL algorithm; chemical reactor; fully connected recurrent neural networks;
Conference_Titel :
Systems Signals and Devices (SSD), 2010 7th International Multi-Conference on
Conference_Location :
Amman
Print_ISBN :
978-1-4244-7532-2
DOI :
10.1109/SSD.2010.5585587
