Abstract
Soft Computing has become popular in Steel Industry for its applications in the areas of reduction in defects, prediction of properties, classification of the products and many others. In recent times, the prediction of properties of steel strip is an area of increased interest mainly because of its prospective benefits of reduction in testing cost, better control on properties, reduction of inventory, increase in yield, and improvement in delivery compliance. Prediction of mechanical properties is a complicated task, as it depends on the chemical composition of the steel, and a number of processing parameters. In general, a high degree of nonlinearity exists between the property and the factors influencing it. In the past only Artificial Neural Network (ANN) was used, sometimes along with the variable reduction technique such as principle components / factor analysis. However, Multivariate Adaptive Regression Splines (MARS) has never been used despite some of its known advantages over the ANN. In this work two predictive models have been developed - one based on ANN, and another, MARS. This paper discusses on the model development and the comparative performance analysis of these two. The analysis shows that the results from both the models are comparable. However, shorter training time and automatic selection of important predictor variables, give MARS an edge over ANN.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Döll, R., Sorgel, R., Daum, M., and Zouhar, G. (1999), “Control of mechanical properties,” Asia Steel, Crambeth Allen Publishing, Craven Arms, UK.
Duarte, B., Saraiva, P. M., and Pantelides, C. C. (2004), “Combined Mechanistic and Empirical Modelling,” International Journal of Chemical Reactor Engineering, vol. 2, pp. 1–19.
Dumortier, C., Lehert, P., Krupa, P., and Charlier, A. (1998), “Materials Science Forum,” vols. Trans. Tech Publications, Switzerland, pp. 284–393.
Dwinnell, W. (2000), “Exploring MARS: An Alternative to Neural Network,”PC AI Magazine
Elsilä, U., and Röning, J. (2002), “Knowledge Discovery in Steel Industry Measurements,”Proc of Starting Artificial Intelligence Researchers Symposium (STAIRS), Lyon, France, pp. 197–206.
Friedman, J. H. (1991), “Multivariate Adaptive Regression Splines,” The Annals of Statistics, vol. 19, pp. 1–141.
Guodong, W., Xianghua, L., Cheng, L., Xiumei, W., and Tong, W. (September 26–29,2000), “Application of AI in Rolling and Prediction of Properties of Hot Rolled Materials”, Asia Steel International Conference (Rolling), Beijing, China, pp. 38–47.
Hastie, T., Tibshirani, R., Friedman, J. (2001), “The Elements of Statistical Learning: Data Mining, Inference and Prediction,” Springer-Verlag, N.Y, USA.
Invention Intelligence: S&T Magazine, New Delhi, India, (May–June 2004), vol. 39, no. 3, pp. 125–126.
Korczak, P., Dyja, H., and Labuda, E. (1998), “Using Neural Network Models for predicting Mechanical Properties after Hot Plate Roll Process,” Journal of Materials Processing Technology, vol. 80–81, pp. 481–486.
Mukhopadhyay, A., and Iqbal, A. (2004), “Prediction of Mechanical Properties of Hot Rolled, Low-Carbon Steel Strips using Artificial Neural Network,”Materials and Manufacturing Processes, (2005) vol. 20,no. 5, pp. 739–746
Schlang, M., Feldkeller, B., Lang, B., Poppe, T., and Runkler, T. (2003), “Neural Computation in Steel Industry,” European Summer School on Multi-Agent Control, Hamilton Institute, National University of Ireland, Maynooth, Ireland.
STATISTICA™ DATA MINER ver 6.1: StatSoft, Inc., Tulsa, OK 74104, USA, (1984–2003).
Weiss, S. M., and Indurkhya, N. (1998), Predictive Data Mining – A Practical Guide, Morgan Kaufmann Publishers, Inc., San Francisco.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2006 Springer
About this paper
Cite this paper
Mukhopadhyay, A., Iqbal, A. (2006). Comparison of ANN and MARS in Prediction of Property of Steel Strips. In: Abraham, A., de Baets, B., Köppen, M., Nickolay, B. (eds) Applied Soft Computing Technologies: The Challenge of Complexity. Advances in Soft Computing, vol 34. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-31662-0_26
Download citation
DOI: https://doi.org/10.1007/3-540-31662-0_26
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-31649-7
Online ISBN: 978-3-540-31662-6
eBook Packages: EngineeringEngineering (R0)