Application of Artificial Neural Networks in The On-Line
Control of Hot-Flat Rolling Processes

Jan Kusiak1, Dmitry Svietlichnyj2, Maciej Pietrzyk1

1Akademia Górniczo-Hutnicza, al. Mickiewicza 30, 30-059 Krakow, Poland

2National Metallurgical Academy of Ukraine, Gagarina 4, 49600 Dniepropetrovsk, Ukraine


FREE ABSTRACT (to read the full article, please log in below).

The objective of this paper is to apply artificial neural networks models (ANN), to control the hot plate rolling process. These models use iterative procedures and take advantage of the capabilities of modern computers. Two ANN models are described. The first predicts roll bending and the second calculates the thermal profile of a roll. The training and testing data comes from the FEM simulation of the hot rolling process.



To read the full article,
please log in:
If you haven't registered already,
you can do so for free:

(c) Copyright 2001 Professor F.R. Hall - University of Wolverhampton.