Correlation of Mechanical Properties of Cast Al 3xx Alloys to Processing Variables and Alloy Chemistry Using Regression Analysis and Artificial Neural Network Techniques

Abstract:

The mechanical properties of aluminium alloy castings, such as EL%, YS and UTS, are controlled by the casting and heat treatment variables, alloy’s composition, and melt treatment. Despite the abundance of literature data, the large number of the controlling parameters has made it difficult to predict and model the mechanical properties by the conventional techniques. Another obstacle encountered when making such a prediction is the complex kinetics and interactions that exist among the many variables. The goal of this study was to develop Artificial Neural Network (ANN) and Multiple Regression models to predict the mechanical properties of A356 alloy from the processing variables. Several standard nonlinear regression and multi-layer ANN models were developed and trained using data from the literature and experimental results. Due to the complexity of A356’s solidification behaviour, the nonlinear regression produced results that were not as accurate as those produced by the ANN model. The results indicate that ANN is a suitable technique for predicting mechanical properties from alloy chemistry and processing variables.

• Periodical: Advanced Materials Research (Volumes 463-464)
• Pages: 439-443
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.463-464.439
• Online since: February 2012
• Authors: Daryoush Emadi, Musbah Mahfoud
• Keywords: 3xx Alloys, Aluminum (Al), Artificial Neural Network (ANN), Mechanical Property, Regression Analysis

References

[1] D. Emadi and M. Mahfoud, J. of Materials Sci. & Eng. A, Vol. 527, No. 23 (2010), pp.6123-32.

[2] D. Emadi, L. Whiting, M. Sahoo and P. Burke, AFS Transaction, Vol. 109 (2001), pp.487-99.

[3] S. Shivkumar, S. Ricci and D. Apelian, AFS Transactions Vol. 98 (1990), pp.913-22.

[4] S. Shivkumar, D. Apelian and G. Sigworth, AFS Transactions Vol. 97 (1989), pp.791-810.

[5] R. Sinfield and D.A. Harris, J. of Australian Inst. Of Metals Vol. 20, No. 1(1975), pp.44-48.

[6] E.N. Pan, J.F. Hu and C.C. Fan, AFS Transactions Vol. 104 (1996), pp.1119-32.

[7] B. Chamberlain and V. Zabek, AFS Transactions Vol. 81 (1973), pp.322-327.

[8] M. Adachi and A. Oishi, J. of Japan Institute of Light Metals Vol. 37, No. 8 (1987), pp.524-30.

[9] D.L. Zhang, L.H. Zheng and D.H. St-John, Mater. Sci. Tech. Vol. 14 (July 1998), 619-25.

[10] M. Tsukuda and M. Harada, J. of Japan Inst. of Light Metals Vol. 28, No. 11 (1978) pp.531-40.

[11] M.S. Misra and K.J. Oswalt, AFS Transactions Vol. 90 (1982), pp.1-10.

[12] L. Liu and F.H. Samuel, Journal of Materials Science Vol. 33 (1998), pp.2269-81.

[13] Guo J, Zhu H, and Jia J., Mater. Sci. Technol. Vol. 14 (May1998), pp.476-8.

[14] (Electronic Version) StatSoft Inc. Electronic Statistics Textbook. Tulsa, OK: StatSoft. WEB: http: /www. statsoft. com/textbook/stathome. html (2011).

DOI: 10.1007/s10182-007-0038-x

[15] D. Emadi and L. Sullivan, AFS Transactions Vol. 112 (2004) pp.263-272.

[16] D. Van Camp, Scientific American Vol. 267 (1992), pp.170-2.

[17] J. Principe, Neural and Adaptive Systems, New York, NY: John Wiley & Sons Inc. (2000).

[18] N.A. Weiss and M.J. Hassett, Introductory Statistics, 3rd ed.; Reading, Massachusetts: Addison-Wesley Publishing Company, Inc. (1993), pp.682-3.

[19] U.S. Department of Health and Human Services, Centers for Disease Control and Prevention, National Center for Health Statistics, Division of Data Services, NCHS Definitions Report, Feb. 2002, Online: www. cdc. gov/nchs/datawh/nchsdefs/Relative%20Standard%20Error. htm.

[20] D.D. Steppan, J. Werner and R.P. Yeater, Essential Regression and Experimental Design for Chemists and Engineers, New York, NY: John Wiley & Sons Inc. (1998).

[21] A.C. Cameron, EXCEL: Multiple Regression (Sept. 1999); online access: http: /www. econ. ucdavis. edu/faculty/cameron/excel/exmreg. html.