Prediction of Friction Stir Processed AZ31 Magnesium Alloy Micro-Hardness Using Artificial Neural Networks

Article Preview

Abstract:

Friction stir processing (FSP) is a microstructural modification technique. In FSP, the material undergoes intense plastic deformation, yielding a dynamically recrystallized fine grain structure. One of the most important issues that need to be tackled in this field is the lack of predictive tools. That enables the selection of the optimum parameters required to achieve the desired modifications on the mechanical properties of the processed materials. In this study, the effects of different FSP parameters (rotational and translational speeds) on the resulting micro-hardness of friction stir processed AZ31 magnesium sheets are examined. Variations of micro-hardness with longitudinal and through-thickness positions are also investigated. Artificial neural networks (ANNs) are used to model and predict the resulting micro-hardness.

You might also be interested in these eBooks

Info:

Periodical:

Pages:

91-95

Citation:

Online since:

October 2014

Export:

Price:

* - Corresponding Author

[1] W. Thomas, E. Nicholas, J. Needham, M. Murch, P. Temple Smith, C. Dawes: Friction stir butt welding, International patent application No. PCT/GB92/02203; December (1991).

Google Scholar

[2] R. Mishra, M. Mahoney: Mater. Sci. Forum. Vol. 357-359 (2001), pp.2869-2877.

Google Scholar

[3] M. Khraisheh, B. Darras, P. Kalu, M. Adams-Hughes, N. Chandra: Mater. Sci. Forum. Vol. 475-479 (2005), pp.3043-3046.

DOI: 10.4028/www.scientific.net/msf.475-479.3043

Google Scholar

[4] A. Alavi, H. Omidvar, S. Nourbaksh: Mater. Des. Vol. 58 (2014), pp.298-304.

Google Scholar

[5] C. Chang, C. Lee, J. Huang: Scripta Mater. Vol. 51 (2004), pp.509-514.

Google Scholar

[6] L. Fratini, G. Buffa: Int. J. Mach. Tool. Manuf. Vol. 45 (2005), pp.1188-1194.

Google Scholar

[7] B. Darras: J. Mater. Eng. Perform . Vol. 21(7) (2012), pp.1243-1248.

Google Scholar

[8] A. Ebnonnasir, F. Kairmzadeh, M. Enayati: Mater. Sci. Technol. Vol. 26 (No. 6) (2011), pp.990-995.

Google Scholar

[9] Y. Yousif, K. Daws, B. Kazem: Jordan J. Mech. Industrial Eng. Vol. 2 (No. 3) (2008), pp.151-155.

Google Scholar

[10] G. Buffa, L. Fratini, F. Micari: J. Manuf. Process. Vol. 14 (No. 3) (2011), pp.289-296.

Google Scholar

[11] M. Taskın, U. Çalıgülü: Math. Comput. Appl. Vol. 11 (No. 3) (2006), pp.163-172.

Google Scholar

[12] Y. Sato, H. Kokawa, M. Enomoto, S. Logan: Metall. Mater. Trans. Vol. 30 (1999), pp.2429-2437.

Google Scholar

[13] B. Darras, M. Omar, M. Khraisheh: Mater. Sci. Forum Vol. 539-543 (2007), pp.3801-3806.

DOI: 10.4028/www.scientific.net/msf.539-543.3801

Google Scholar

[14] I. Deiab, A. Al Shammri: Proceeding of the 6Th International Symposium on Mechatronics and its Applications (lSMA09), Sharjah, UAE, March 24-26, (2009).

Google Scholar

[15] S. Katalopoulos: Understanding neural networks and fuzzy logic: basic concepts and application. IEEE Press, (1996).

Google Scholar

[16] E. Ezugwu, S. Arthur, E. Hines: J. Mater. Process. Technol. Vol. 49 (No. 3-4) (1995), pp.255-264.

Google Scholar