The application of artificial neural networks in optimization of heat treatment processes of steel

• Autorzy: Wołowiec E. , Kula P.
• Języki publikacji: EN

Abstrakty

EN

This article is dedicated to processes of vacuum carburization, which constitute an alternative method to industrial multi-segment carburization. Special attention has been paid to the possibility of using artificial neural networks to design processes of such type. The following subchapters deal with the essence and purposes of vacuum carburization, the course of research on processes and the possibility of using neural networks to design such processes, and the architecture of a sample neural network which achieves this goal.

Słowa kluczowe

EN

neural networks; heat treatment; vacuum carburizing

PL

sieci neuronowe; obróbka cieplna; nawęglanie próżniowe

• Wydawca: Wydawnictwo Politechniki Łódzkiej
• Czasopismo: Journal of Applied Computer Science
• Rocznik: 2011
• Tom: Vol. 19, nr 1
• Strony: 161--169
• Opis fizyczny: Bibliogr. 7 poz.

Twórcy

autor

Wołowiec E.

autor

Kula P.

• Technical University of Łódź, Institute of Materials Science and Engineering, Stefanowskiego 1/15, 90-924 Łódź, Poland,

Bibliografia

• [1] Sitek, W. and Dobrzański, L., Computer aiding of material selection on machines parts, 3rd Scientific Conference on Materials, Mechanical and Manufacturing Engineering. Gliwice, 2005, (in Polish).
• [2] Kula, P., Progress in carburizing technology, Material Engineering 3 (116). Lodz. 2000.
• [3] Kula, P., Olejnik, J., Some technological aspects of vacuum carburizing, IProc. XIIth IFMT & SE Congress Vol.3, pp. 195-220. Melbourne, 2000.
• [4] Szczepaniak, P., Intelligent computations, fast transforms and classifiers, EXIT Academic Publishing House. Warsaw, 2004, (in Polish).
• [5] Korbicz, J., Obuchowicz, A., Uciński D., Artificial neural network. Basis and applications, PLJ Academic Publishing House. Warsaw, 1994, (in Polish).
• [6] Hornik, K., Stinchcombe, M., White, H., Multi-layer feed forward networks are universal approximations, Neural Networks, Vol.2. pp 359-366, 1989.
• [7] Cybenko, G., Continuous valued neural networks with two hidden layers are sufficient, Technical Report. Tufts University, Medford, MA: Dept of Computer Science, 1988.