Paper Title:
A Knowledge-Based System for Temperature Prediction in Hot Strip Mills
  Abstract

Rolling temperature is an important factor affecting mechanical properties of hot rolled strip significantly. Traditional techniques cannot meet higher precision control imperatives. In the present work, a novel knowledge-based system has been developed for the temperature prediction in hot strip mills. Neural network has been used for this purpose, which is an intelligent technique that can solve nonlinear problem of temperature control by learning from the samples. Furthermore, an annealing robust learning algorithm was presented to adjust the hidden node parameters as well as the weights of the adaptive neural networks. Simulations in a multi-object mode have been carried out to verify the effectivity of new neural optimization system. Calculation results confirm the feasibility of this approach and show a good agreement with experimental values obtained from a steel plant.

  Info
Periodical
Edited by
John Bell, Cheng Yan, Lin Ye and Liangchi Zhang
Pages
153-156
DOI
10.4028/www.scientific.net/AMR.32.153
Citation
H. B. Xie, Z. Y. Jiang, D. B. Wei, X. H. Liu, G. D. Wang, "A Knowledge-Based System for Temperature Prediction in Hot Strip Mills", Advanced Materials Research, Vol. 32, pp. 153-156, 2008
Online since
February 2008
Export
Price
$32.00
Share

In order to see related information, you need to Login.

In order to see related information, you need to Login.

Authors: Xiao Hong Zhang, Jiang Tao Zhang
Chapter 6: Materials Engineering
Abstract:According to two parameters combination of the material thickness and air-gap depth, from the angle of pure optimization, this paper obtained...
1187
  | Authors: Joachim Schöttler, Thorsten Maiwald, Gunnar Linke
Chapter 1: Technology of Rolling and Thermomechanical Processing
Abstract:The production of hot-rolled sheets of high-strength and wear-resistant special structural steels by direct quenching from the rolling heat...
29