Fine-tuning of the rolling mill using an Internet-based on-line application-processing interface

Abstract

In order to meet the challenge of steady growing pressure to improve product quality, rolling mills employ extensive automation and sophisticated on-line data sampling techniques. However, the steel sheet quality is influenced by the entire ‘life history’ of the rolled strip.

Application of the self-organizing maps helps to discover hidden dependencies influencing the quality parameters, such as flatness, profile, wedge, thickness and width deviations and surface quality, as well as mechanical and magnetic properties. A dataset collected from the measured parameters in a strip location corresponds to a proper process state, described by a point in the state space. Time series of points corresponding to each sampled data set show how the system ‘moves’ in the state space and how the predicted product quality is changing within the strip.

Keywords

rolling data mining self-organizing maps OLAP on-line control

References

Lenard

J. G.

Pietrzyk

Cser

Mathematical and Physical Modelling of Hot Rolling, 1999 (Elsevier, Oxford).

Korhonen

A. S.

Larkiola

Application of neural networks in rolling of steel. In Proceedings of Australasia-Pacific Forum on Intelligent Processing and Manufacturing of Materials (IPMM 1997), Gold Coast, Australia, 14–17 July 1997, pp. 324–329.

Montesi

Trivella

Brambilla

Estimation of crude fraction cut-point using hybrid ANN. In Proceedings of EANN 1996, London, 17–19 June 1996, pp. 99–102.

Cser

Korhonen

A. S.

Simula

Larkiola

Myllykoski

Ahola

Knowledge based methods in modelling of hot rolling of steel strip. In Proceedings of Conference on Intelligent Computation in Manufacturing Engineering (ICME 1998), Capri, Italy, 1998, pp. 265–270.

Kohonen

Self-Organizing Maps, 1995 (Springer-Verlag, Berlin and Heidelberg, Germany).

Girardin

Mapping the virtual geography of the world wide web. In Fifth International World Wide Web Conference, Paris, France, 6–10 May 1996.

Ultsch

Self organizing neural networks perform different from statistical k-means clustering. In Gesellschaft für Klassification, Basel, Switzerland, 8–10 March 1995.

Cser

Korhonen

A. S.

GulyÃs

Mäntylä

Simula

Reiss

Gy.

Ruha

Data mining and state monitoring in hot rolling (Keynote paper). In Proceedings of the 2nd International Conference on Intelligent Processing and Manufacturing of Materials (IPMM 1999), Honolulu, Hawaii, 10–15 July 1999, pp. 529–536 (IEEE, Piscataway, New Jersey).

Larkiola

Myllykoski

Korhonen

A. S.

Cser

The role of neural networks in the optimisation of rolling processes. J. Mater. Processing Technol., 1998, 80-81, 16–23.

10.

Frenzel

C. W.

Management of Information Technology, 3rd edition, 2000 (Thompson Learning, USA).

11.

Post

G. V.

Anderson

D. L.

Management Information Systems–Solving Business Problems with Information Technology, 3rd edition, 2003 (McGraw-Hill, New York).