Metamodel driven optimization of thermomechanical industrial processes

by

Metamodel driven optimization of thermomechanical industrial processes

Jan Kusiak, Łukasz Sztangret, Łukasz Rauch, Maciej Pietrzyk

AGH University of Science and Technology, al. Mickiewicza 30, 30-059 Kraków, Poland.

DOI:

https://doi.org/10.7494/cmms.2014.1.0472

Abstract:

The main objective of the paper is presentation of the metamodel driven optimization (MDO) strategy of thermomechanical industrial processes. In this approach, the model of considered industrial process is replaced by a metamodel, which allows obtaining a significant reduction of the simulation time. Low simulation time of the analyzed process gives the ability to use heuristic optimization methods, which increase the probability of finding the global optimum. The paper discusses the idea of metamodelling and presents results of metamodelling and optimization of a selected metal forming process.

Cite as:

Kusiak, J., Sztangret, Ł., Rauch, Ł., & Pietrzyk, M. (2014). Metamodel driven optimization of thermomechanical industrial processes. Computer Methods in Materials Science, 14(1), 20 – 26. https://doi.org/10.7494/cmms.2014.1.0472

Article (PDF):

Keywords:

Metamodel driven optimization, Artificial neural networks, Cooling of rails

Publication dates:

Received: 29.12.2013, accepted: 05.01.2014, published:

Publication type:

Original scientific paper

References:

Bishop, C.M., 1995, Neural Networks for Pattern Recognition, Oxford University Press, Oxford.

Haykin, S., 1999, Neural Networks: A Comprehensive Foundation, Prentice Hall, New York.

Kusiak, J., Szeliga, D., Sztangret, Ł., 2012, Modelling techniques for optimizing metal forming processes, in: Microstructure evolution in metal forming processes,eds. Lin J., Balint D., Pietrzyk M., Woodhead Publishing Limited,
35-66.

Kuziak, R., Zygmunt, T., 2013, A new method of rail head hardening of standard gauge rails for improved wear and
damage resistance, Steel Research International, 84, 13-19.

Kuziak, R., Molenda, R., Wrożyna, A., Kusiak, J., Pietrzyk, M., 2014, Experimental verification and validation of the
phase transformation model used for optimization of heat treatment of rails, Computer Methods in Materials
Science, 14, (1), 53-63.

Pietrzyk, M., Kuziak, R., 2012, Numerical simulation of controlled cooling of rails as a tool for optimal design of
this process, Computer Methods in Materials Science, 12, 233-243.

Rauch, Ł., Skiba, M., Kusiak, J., 2014, Computer system dedicated to optimization of production processes and cycles
in metal forming industry, Computer Methods in Materials Science, 14, (1), 3-12.

Sztangret, Ł., Rauch, Ł., Kusiak, J., Jarosz, P., Małecki, S., 2011, Modeling of the oxidizing roasting process of zinc
sulphide concentrates using artificial neural networks, Computer Methods in Materials Science, 11, 122-127

Sztangret, Ł., Szeliga, D., Kusiak, J., Pietrzyk, M., 2012, Application of inverse analysis with metamodelling for identification of metal flowstress, Canadian Metallurgical Quarterly, 51, 440-446.

Tadeusiewicz, R., 1993, Sieci neuronowe, Akademicka Oficyna Wydawnicza, Warszawa, (in Polish).