Neural networks application for modeling carbonizing process in fluidized bed

• Autorzy: Jasiński J. , Szota M. , Jeziorski L.
• Języki publikacji: EN

Abstrakty

EN

Purpose: This paper presents neural network model used for designing the assumed curve of hardness after carbonizing car drive cross in fluidized bed. This process is very complicated and difficult as multi-parameters changes are non linear and car drive cross structure is non homogeneous [1-2]. This fact and lack of mathematical algorithms describing this process makes modeling required curve of hardness by traditional numerical methods difficult or even impossible. In this case it is possible to try using artificial neural network [3-7]. Design/methodology/approach: The neural network structure is designed and prepared by choosing input and output parameters of process. The method of learning and testing neural network, the way of limiting nets structure and minimizing learning and testing error are discussed. Findings: Such prepared neural network model, after putting expected values of assumed hardness curve in output layer, can give answers to a lot of questions about running carbonizing process in fluidized bed. Practical implications: The neural network model can be used to build control system capable of on-line controlling running process and supporting engineering decision in real time. Originality/value: This paper presents different conception to obtain assumed material’s hardness after carbonizing in fluidized bed. The specially prepared neural networks model could be a help for engineering decisions and may be used in designing carbonizing process in fluidized bed as well as in controlling changes of this process.

Słowa kluczowe

EN

surface layer; neural network; process modeling; artificial intelligence

PL

warstwa wierzchnia; sieć neuronowa; modelowanie procesu; sztuczna inteligencja

• Wydawca: International OCSCO World Press
• Czasopismo: Archives of Materials Science and Engineering
• Rocznik: 2008
• Tom: Vol. 32, nr 2
• Strony: 103--108
• Opis fizyczny: Bibliogr. 15 poz.

Twórcy

autor

Jasiński J.

autor

Szota M.

autor

Jeziorski L.

• Faculty of Materials Processing Technology and Applied Physics, Materials Engineering Institute, Biomaterials and Surface Layer Research Institute, Czestochowa University of Technology, Al. Armii Krajowej 19, 42-200 Częstochowa, Poland,

Bibliografia

• [1] J. Jasinski, The influence fluidized bed for diffusion saturation of surface layer of steel, WIPMiFS Press, Czestochowa, 2003.
• [2] J. Jasinski, L. Jeziorski, M. Kubara, Carbonitriding of steel in fluidized beds, Heat Traetment of Metals 12/2 (1988).
• [3] S. Osowski, Neural Network for transformation informations, Politechnika Warszawska Publishing House, Warszawa, 2003.
• [4] L. Rutkowski, Neural networks and anurocomputers, Czestochowa University of Technology Press, Czestochowa, 1996.
• [5] J. Trzaska, L.A. Dobrzański, Application of neural networks for designing the chemical composition of steel with the assumed hardness after cooling from the austenitising temperature, Journal of Materials Processing Technology 164-165 (2005) 597-601.
• [6] W. Sitek, L.A. Dobrzański, Application of genetic method in materials' design, Journal of Materials Processing Technology 164-165 (2005) 605-609.
• [7] L.A. Dobrzański, M. Kowalski, J. Madejski, Methodology of the mechanical properties prediction for the metallurgical products from the engineering steels Rusing the Artificial Intelliegence methods, Journal of Materials Processing Technology 164-165 (2005) 610-613.
• [8] Z. Rogalski, Fluidized heat treatment, part 1, Surface Engineering 2 (2000) 3-20.
• [9] T. Babul, A. Nakonieczny, Z. Obuchowicz, D. Orzechowski, J. Jasinski, L. Jeziorski, T. Fraczek, R. Torbus, Industrial application visualization and computer control system of chamber for thermo and thermo-chemical treatment, Materials Engineering 5 (2002) 208-211.
• [10] J. Jasinski, L. Jeziorski, T. Fraczek, R. Torbus, P. Chrząstek, T. Babul, A. Nakonieczny, Z. Obuchowicz, Laboratory version of computer system for control and visualization F-A/O-D processes, Materials Engineering 5 (2002) 344-346
• [11] J. Jasinski, Laboratory version of system for visualization and control of thermo-chemical processes, ASTOR -Automatics Bulletin, Cracow, 2004.
• [12] S. Haykin, Neural networks, a comprehensive foundation, Macmillan College Publishing Company, New York, 1994.
• [13] J.-S. Son, D.-M. Lee, I.-S. Kim, S.-G. Choi, A study on on-line learning neural networks for prediction for rolling force in hot-rolling mill, Journal of Materials Processing Technology 164-165 (2005) 1612-1617.
• [14] D. Svietlicznyj, M. Pietzryk, On-line Model of Thermal Roll Profile during Hot Rolling, Metallurgy and Foundry Engineering 27 (2001) 73-95.
• [15] J. Kusiak, M. Pietrzyk, D. Svietlicznyj, Application of artificial neural network in on-line control of hot flat folling processes, International Journal Engineering Simulation 1/3 (2000) 17-23