Application a neural networks in crystallization process of Mg-Al-Zn alloys

• Autorzy: Dobrzański L.A. , Król M. , Tański T.
• Języki publikacji: EN

Abstrakty

EN

Purpose: The purpose of this paper is presents a methodology to predict crystallization temperatures during solidify of metal obtained during crystallization process using an UMSA platform, based on cooling rate and chemical composition. Design/methodology/approach: The experimental magnesium alloy used for training of neural network was prepared in cooperation with the Faculty of Metallurgy and Materials Engineering of the Technical University of Ostrava and the CKD Motory plant, Hradec Kralove in the Czech Republic. The alloy was cooled with three different cooling rates in UMSA Technology Platform. Temperatures were registered by supersensitive K-thermocouples. Findings: Research limitations/implications: The results of this investigation show that there is a high correlation between experimental and predicted dates and the neural networks have a great potential in crystallization process behaviour modelling of Mg-Al-Zn alloys. Practical implications: The presented model can be applied in computer system of Mg-Al-Zn casting alloys, selection and designing for Mg-Al-Zn casting parts and makes possibility to determine a crystallization temperatures based on chemical composition. Originality/value: Original value of the work is applied the artificial intelligence as a tools for designing the required mechanical properties for Mg-Al-Zn castings.

Słowa kluczowe

EN

numerical techniques; neural networks; mechanical properties; magnesium alloys

PL

techniki numeryczne; sieci neuronowe; właściwości mechaniczne; stopy magnezowe

• Wydawca: International OCSCO World Press
• Czasopismo: Archives of Computational Materials Science and Surface Engineering
• Rocznik: 2010
• Tom: Vol. 2, nr 3
• Strony: 149--156
• Opis fizyczny: Bibliogr. 18 poz., tab., rys., wykr.

Twórcy

autor

Dobrzański L.A.

autor

Król M.

autor

Tański T.

• Division of Material Processing Technology, Management and Computer Techniques in Materials Science, Institute of Engineering Materials and Biomaterials, Silesian University of Technology, ul. Konarskiego 18a, 44-100 Gliwice, Poland,

Bibliografia

• [1] P. Korczak, H. Dyja, E. Łabuda, Using neural network models for predicting mechanical properties after hot plate rolling processes, Journal of Materials Processing Technology 80-81 (1998) 481-486.
• [2] V.K. Potemkin, O.S. Khlybov, V.A. Peshkov, Complex Mathematical Model for Predicting Mechanical Properties and Structure of Steel Sheets, Journal Metal Science and Heat Treatment 42/11-12 (2000) 489-492.
• [3] L.A. Dobrzański, J. Trzaska, Application of artificial neural networks in mechanical properties modelling of constructional steels, Proceedings of the Scientific Conference “Materials, Mechanical and Manufacturing Engineering” M3E’2000, Gliwice, 2000.
• [4] E. Mares, J.H. Sokolowski, Artificial intelligence-based control system for the analysis of metal casting properties, Journal of Achievements in Materials and Manufacturing Engineering 40/2 (2010) 149-154.
• [5] B. Smoljan, D. Iljkić, N. Tomašić, Computer simulation of mechanical properties of quenched and tempered steel specimen 40/2 (2010) 155-159.
• [6] L.A. Dobrzański, R. Honysz, Application of artificial neural networks in modelling of quenched and tempered structural steels mechanical properties, Journal of Achievements in Materials and Manufacturing Engineering 40/1 (2010) 50-57.
• [7] U. Markowska-Kaczmar (ed.), Neural networks in applications, Wroclaw University of Technology Publishing Office, Wroclaw, 1996 (in Polish).
• [8] T. Masters, Neural networks in practice, PWN, Warsaw, 1996 (in Polish).
• [9] M. Kulecki, Magnesium and its alloys applications in automotive industry, The International Journal of Advanced Manufacturing Technology 39/9-10 (2008) 851-865.
• [10] C.H. Caceres, C.J. Davidson, J.R. Griffiths, Q.W. Wang, The effect of Mg on the microstructure and mechanical behavior of Al-Si-Mg casting alloys, Metallurgical and Materials Transactions A 30/10 (1999) 2611-2618.
• [11] L.A. Dobrzański, T. Tański, J. Trzaska, L. Čížek, Modelling of hardness prediction of magnesium alloys using artificial neural networks applications, Journal of Achievements in Materials and Manufacturing Engineering 26/2 (2008) 187-190.
• [12] A.T. Tang, B. Liu, F.S. Pan, J. Zhang, J. Peng, J.F. Wang, An improved neural network model for prediction of mechanical properties of magnesium alloys, Science in China Series E: Technological Sciences 52/1 (2009) 155-160.
• [13] Method and Apparatus for Universal Metallurgical Simulation and Analysis - United States Patent, Patent No.: US 7,354,491 B2, 2008.
• [14] L.A. Dobrzański, M. Król, T. Tański, R. Maniara, Effect of cooling rate on the solidification behaviour of magnesium alloys, Archives of Computational Materials Science and Surface Engineering 1/1 (2009) 21-24.
• [15] L.A. Dobrzański, M. Król, Thermal and mechanical characteristics of cast Mg-Al-Zn alloy, Archives of Foundry Engineering 1/10 (2010) 27-30.
• [16] L.A. Dobrzański, T. Tański, J. Domagała, M. Król, S. Malara, A. Klimpel, Structure and properties of the Mg alloys in as-cast state and after heat and laser treatment, Journal of Achievements in Materials Science and Engineering 31/2 (2008) 123-147.
• [17] L.A. Dobrzański, M. Król, T. Tański, Thermal analysis, structure and mechanical properties of the MC MgAl3Zn1 cast alloy, Journal of Achievements in Materials and Manufacturing Engineering 40/2 (2010) 167-174.
• [18] L.A. Dobrzański, M. Król, T. Tański, Influence of cooling rate on crystallization, structure and mechanical properties of MCMgAl6Zn1 alloy, Archives of Foundry Engineering 10/3 (2010) 105-109.