Use of a physical approach and artificial neural networks for the simulation of the relation between the yield strength of quenched Al-Si alloys and their structural characteristics
Tóm tắt
Models are developed to relate the yield strength of Al-Si alloys to their structural characteristics. The models are based on the physical theory of strength and artificial neural networks. The simulated and experimental yield strengths agree well. It is wise to use an artificial neural network to predict the properties of alloys whose structural parameters fall in the range of the learning sample.
Tài liệu tham khảo
A. N. Gorban’, Learning of Neural Networks (Paragraph, Moscow, 1990) [in Russian].
A. N. Gorban’ and D. A. Rossiev, Neural Networks on a Personal Computer (Nauka, Moscow, 1996) [in Russian].
Physical Metallurgy, Ed. by R. W. Cahn and P. Haasen (North-Holland, Amsterdam, 1965; Mir, Moscow, 1968).
M. A. Shtremel’, Strength of Alloys. Part 2 (MISiS, Moscow, 1997) [in Russian].
V. S. Zolotarevskii and N. A. Belov, Physical Metallurgy of Cast Aluminum Alloys (MISiS, Moscow, 2005) [in Russian].
M. J. Starink and S. C. Wang, “A Model for the Yield Strength of Overaged Al-Zn-Mg-Cu Alloys,” Acta Mater. 51, 5131 (2003).
A. Yu. Churyumov, N. Yu. Zolotarevskii, A. N. Solonin, and V. S. Zolotarevskii, “Simulation of the Flow Stress of Single-Phase Al-Mg Alloys Quenched after Casting,” Izv. Vyssh. Uchebn. Zaved., Tsvetn. Metall., No. 3, 50–56 (2007).
N. Hansen, “The Effect of Grain Size and Strain on the Tensile Flow Stress of Aluminum at Room Temperature,” Acta Metall. 25, 863 (1977).