Prediction of the Hardness of Cu-Ti-Co Alloy Using Machine Learning Techniques

Abstract:

Diverse machine learning approaches were employed to build regression models for predicting mechanical property of Cu-Ti-Co alloy. The forecasting performance of the least-square support vector machines (LSSVM) model has been compared with other artificial intelligence methods such as GRNN, RBF-PLS and RBFNN. The models were developed and validated utilizing a cross-validation (CV) procedure to improve the forecasting accuracy and generalization ability. The result demonstrates that the generalization performance of the new LSSVM is slightly better or superior to those acquired using GRNN, RBF-PLS and RBFNN. In future, it would be expected that the relatively new model based on machine learning is used as an especially helpful implement to accelerate materials design of copper alloys.

• Periodical: Key Engineering Materials (Volume 777)
• Pages: 372-376
• DOI: https://doi.org/10.4028/www.scientific.net/KEM.777.372
• Online since: August 2018
• Authors: Shan Feng Fang
• Keywords: Copper Alloys, General Regression Neural Network, Machine Learning

References

[1] W.A. Soffa, D.E. Laughlin, High-strength age hardening copper–titanium alloys: redivivus, Prog. Mater. Sci. 49(2004) 347-366.

DOI: 10.1016/s0079-6425(03)00029-x

[2] F. Wang, Y. Li, K. Wakoh, Y. Koizumi, A. Chiba, Cu–Ti–C alloy with high strength and high electrical conductivity prepared by two-step ball-milling processes, Mater. Des. 61(2014) 70-74.

DOI: 10.1016/j.matdes.2014.04.034

[3] S. Semboshi, T. Takasugi, Fabrication of high-strength and high-conductivity Cu–Ti alloy wire by aging in a hydrogen atmosphere, Journal of Alloys and Compounds, 580(2013) 397-S400.

DOI: 10.1016/j.jallcom.2013.03.216

[4] S. Nagarjuna, K.K. Sharma, I Sudhakar, et al., Age hardening studies in a Cu-4.5Ti-0.5Co alloy, Mater. Sci. Eng. A. 313(2001) 251-260.

DOI: 10.1016/s0921-5093(00)01834-7

[5] S. Nagarjuna, D.S. Sarma, Effect of cobalt additions on the age hardening of Cu-4.5Ti alloy, Journal of Materials Science, 37(2002) 1929-(1940).

[6] D.E. Laughlin, J.W. Cahn, Spinodal decomposition in age hardening copper–titanium alloys, Acta Metall. 23 (1975) 329-339.

DOI: 10.1016/0001-6160(75)90125-x

[7] A. Datta, W.A. Soffa, The structure and properties of age hardened Cu–Ti alloys, Acta Metall. 24 (1976) 987-1001.

DOI: 10.1016/0001-6160(76)90129-2

[8] S.F. Fang, Application of data mining methods to high-conductivity and high flexibility copper alloys and other metallic materials, PhD Thesis, Central South University, Changsha, (2009).

[9] J.A.K. Suykens, G.T. Van, B.J. De, J. Vandewalle, Least-Squares Support Vector Machines, World Scientific, Singapore, (2002).

DOI: 10.1142/5089

[10] D.F. Specht, A general regression neural network, IEEE Trans. on Neural Networks, 2 (1991) 568-576.

DOI: 10.1109/72.97934

[11] B. Walczak, D.L. Massart, The Radial Basis Functions-Partial Least Squares approach as a flexible non-linear regression technique, Anal. Chim. Acta. 331 (1996) 177-185.

DOI: 10.1016/0003-2670(96)00202-4

[12] D.M. Hummels, W. Ahemed, M. T. Musavi, Adaptive detection of small sinusoidal Signals in non-gaussian noise using an RBF neural network, IEEE Trans. on Neural Networks, 6 (1995) 991-995.

DOI: 10.1109/72.363435