Application of ANN in Preparing Technology of Magnesium Matrix Composites

Abstract:

SiC_p/AZ61 matrix composites were fabricated by stirring process in the paper. Different SiC volume fractions, processing temperature and stirring time have different influence on tensile strength and elongation of SiC; it is very difficult to find out the best processing parameters with traditional method. An effective method is demonstrated here: The orthogonal experiment design method is put into use at first, and then a satisfied ANN(Artificial Neural Network) is achieved by help of GA’s(Genetic Algorithm) global optimizing capacity. Experimental results proved the prediction accuracy and the adaptability of our work.

• Periodical: Advanced Materials Research (Volume 216)
• Pages: 244-249
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.216.244
• Online since: March 2011
• Authors: Jian Xiong Ye, Fa Yun Zhang
• Keywords: Artificial Neural Network (ANN), Composite, Genetic Algorithm (GA), Stirring

References

[1] E Tzimas, A Zavaliangos: A comparative characterization of near-equiaxed microstructures as produced byspray casting．Materials Science and Engineering, Vol. 289 (2000), pp.217-227.

DOI: 10.1016/s0921-5093(00)00907-2

[2] Manoharan M, Gupta M, Lai M O: Application of model for work hardening behavior of SiC reinforced magnesium based metal matrix composites. Materials Science and Technology, Vol. 16(2000), pp.670-674.

DOI: 10.1179/026708300101508252

[3] W. Zhou, Z. M. Xu: Casting of SiC Reinforced Metal Matrix Composites. Journal of Materials Processing Technology, Vol. 63(1997): 358-363.

DOI: 10.1016/s0924-0136(96)02647-7

[4] S. Jayalakshmi, S.V. Kailas, S. Seshan. Tensile behaviour of squeeze cast AM100 magnesium alloy and its SiC fibre reinforced composites. Composites, Part A 33 (2002) , p.1135–1140.

DOI: 10.1016/s1359-835x(02)00049-0

[5] M.C. Gui, J, M. Han , P.Y. Li: Microstructure and mechanical properties of Mg–Al9Zn/SiCp composite produced by vacuum stir casting process. Materials Science and Technology, Vol. 20 (2004), pp.765-771.

DOI: 10.1179/026708304225017319

[6] Hu L X, Wang E D: Fabrication and mechanical properties of SiCw ZK51A magnesium matrix composites by two-step squeeze casting. Materials Science and Engineering, Vol. 27 (2000), P. 267-271.

DOI: 10.1016/s0921-5093(99)00608-5

[7] D.H. Baea , M.H. Lee, K.T. et al. A pplication of quasicrystalline particles as a strengthening phase in Mg–Zn–Y alloys. Journal of Alloys and Compounds, Vol. 342 (2002) , p.445–450.

DOI: 10.1016/s0925-8388(02)00273-6

[8] V. Sklenicka , M. Svoboda , M. Pahutova, et al. Microstructural processes in creep of an AZ91 magnesium-based composite and its matrix alloy. Materials Science and Engineering, Vol. A319–321 (2001) , p.741–745.

DOI: 10.1016/s0921-5093(01)01023-1

[9] Wei Haikun: Theory and Method of Neural Network Structure, Beijing: Defense Industry Press, (2005).

[10] Gu xiao-qing, Yi dang-xiang, Liu chun-he: Optimization of Topological Structure and Weight Value of Artificial Neural Network Using Genetic Algorithm. Journal of Guangdong University of Technology, Vol. 23(2006), pp.64-69.

[11] YAN Tai-shan. Research on neural network training algorithm based on genetic algorithm. Journal of Hunan Institute of Science and Technology (Natural Science), Vol. 20 (2007),: p.31–34.

[12] Dong Zhibo, Wei yan-hong, Zhan xiao-hong etc.: Optimization of mechanical properties prediction models of welded joints combined neural network with genetic algorithm. Transactions of the China Welding Institution, Vol. 28(2007), pp.69-72.

[13] Fecit research center: NN theory and its realization in MATLAB7. 0, publishing house of electronics industry, Beijing, (2005).