Modeling the Quality of Steel Production with an Adaptive Logic Network

Author

Timothy A. Stelljes
Kelvin T. Erickson, Missouri University of Science and TechnologyFollow

Abstract

An Adaptive Logic Network, a simplified, special case of the multilayer perceptron feedforward neural network, is used to model the off-line evaluation of the quality of a ball steel production line providing grinding media for the mining industry. The model developed in this project predicts the proportion of rejected bars in a cast based on significant information recorded during the process. The results of this application suggest that this method may be a faster way to develop a usable model for off-line analysis than conventional methods.

Recommended Citation

T. A. Stelljes and K. T. Erickson, "Modeling the Quality of Steel Production with an Adaptive Logic Network," Proceedings of the Artificial Neural Networks in Engineering Conference (1995, St. Louis, MO), vol. 5, pp. 943 - 948, American Society of Mechanical Engineers (ASME), Nov 1995.

Meeting Name

Artificial Neural Networks in Engineering Conference, ANNIE (1995: Nov. 12-15, St. Louis, MO)

Department(s)

Electrical and Computer Engineering

Keywords and Phrases

Bars (Metal); Computer Integrated Manufacturing; Iron and Steel Plants; Mathematical Models; Multilayer Neural Networks; Quality Control; Steelmaking; Adaptive Logic Networks; Feedforward Neural Networks

International Standard Book Number (ISBN)

0-7918-0048-2

Document Type

Article - Conference proceedings

Document Version

Citation

File Type

text

Language(s)

English

Rights

© 1995 American Society of Mechanical Engineers (ASME), All rights reserved.

Publication Date

01 Nov 1995