International Federation of Automatic Control
3rd IFAC SYMPOSIUM on SYSTEM, STRUCTURE and CONTROL

Foz do Iguassu, Brazil October 17th - 19th, 2007


Wednesday Morning

Session WM3: Control Strategies and Applications


Chair: Luc Dugard - France
Co-chair: Alexandre Trofino - Brazil
Room: Santiago
2007-10-17
From 10:00 to 12:00
Automatic Startup of Nuclear Reactors Using Differential Neural Networks
J. Humberto Pérez-Cruz; Alexander Poznyak
Contact: J. Humberto Pérez-Cruz - Mexico
11:40-12:00
Abstract:
In this paper, the automatic startup of a nuclear reactor subjected to period scram constraint is considered. To achieve this operation in a minimum time avoiding the difficulties associated with the application on-line of maximum principle or dynamic programming, first the optimal trajectory is calculated off-line. Next, the nuclear plant considered as a black box is identified by a differential neural network. The structure provided by this neural identifier is feedback to follow the optimal trajectory. The modeling error is compensated by the usage of the power derivative. So, the asymptotic stability of the tracking error can be guaranteed. Copyright © 2007 IFAC.