Machine learning assisted microstructure optimization and tensile properties improvement of Al-Si-Mg alloy
Source abstract
Abstract
• Employing an excellent prediction accuracy and fitting effect machine learning model for tensile properties of cast Al-Si-Mg alloy. And developing the high tensile performance (ultimate tensile strength, yield strength and Elongation are 356 MPa, 307 MPa and 9.3 %) via machine learning. • Comparing and ranking the importance of microstructure features by SHapley Additive exPlanations analysis and microstructure characterization. • Discussing and explaining the reason for the strengthen by calculation of precipitate strengthen and microstructure characterization. This work quantitatively investigated the relationship between microstructure and tensile properties using a data-driven machine learning model, then strengthen the alloy by optimization. First, a database of cast Al-Si-Mg alloy, including microstructure parameters and tensile properties, was established and applied to six different machine learning models. Among them, the Back-Propagation Artificial Neural Network (BP-ANN) model demonstrated superior accuracy and generalization capability and was selected for subsequent analysis and optimization. The feature importances were ranked using SHapley Additive exPlanations (SHAP) analysis, and the four most important features for ultimate tensile strength (UTS), yield strength (YS) and elongation were listed. Furthermore, a multi-objective optimization is adopted to optimize the microstructure parameters to the best ranges to strengthen the alloys, and the UTS, YS and elongation of validation results are 356 MPa, 307 MPa and 9.3 %. Finally, strengthen mechanism was further explained based on microstructure analysis. The uniform distribution of Mg 2 Si precipitates controlled by Mg content and aging temperature in grains is the main reason for improvement of tensile properties. The refining of β-Fe phase incoherent to α-Al grain reduces detrimental effect; Refining π-Fe phase and Si particle can transform the brittle fracture into ductile fracture, contribute to the improvement the tensile properties.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Aluminum Alloy Microstructure Properties · Machine Learning in Materials Science · Metallurgy and Material Forming
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (56)
Show source-provided references
1. Strontium in Al–Si–Mg alloy: a review10.1007/s12540-021-01054-y ↗
2. Research and development in magnesium alloys for industrial and biomedical applications: a review10.1007/s12540-019-00346-8 ↗
3. Structure, properties and application of alloys of the Al - Mg - Si - (Cu) system10.1007/s11041-012-9412-8 ↗
4. Fluidity of casting Al–Si series alloys for automotive light-weighting: a systematic review10.1080/02670836.2022.2068274 ↗
5. L. Ceschini, I. Boromei, A. Morri, S. Seifeddine, I.L. Svensson, Effect of Fe content and microstructural features on the tensile and fatigue properties of the Al–Si10–Cu2 alloy, Materials & Design (1980-2015) 36 (2012) 522–528. https://doi.org/10.1016/j.matdes.2011.11.047.10.1016/j.matdes.2011.11.047 ↗
6. Grain refining mechanism in the Al/Al–Ti–B system10.1016/j.actamat.2014.10.055 ↗
7. Re-determination of γ/(γ+α-Mg) phase boundary and experimental evidence of R intermetallic compound existing at lower temperatures in the Mg–Al binary system10.1016/j.jallcom.2012.06.074 ↗
8. Influence of Sr, Fe and Mn content and casting process on the microstructures and mechanical properties of AlSi7Cu3 alloy10.1016/j.msea.2017.02.041 ↗
9. On the impact properties and fracture mechanisms of A356.2-type cast alloys
10. A study of tensile properties in Al–Si–Cu and Al–Si–Mg alloys: effect of β-iron intermetallics and porosity10.1016/j.msea.2008.01.028 ↗
11. Grain refinement of A356 alloy by Al-Ti-B-C master alloy and its effect on mechanical properties10.1016/j.matdes.2012.12.033 ↗
12. Comprehensive regulation of mechanical properties and thermal conductivity of Al-Si-Fe alloys through the mixed-additive (Sr and TiB2) strategy10.1016/j.jallcom.2024.175850 ↗
13. Improving long-term thermal stability in twin-roll cast Al-Mg-Si-Cu alloys by optimizing Mg/Si ratios10.1016/j.jmst.2024.04.017 ↗
14. Microstructural features of AlFeSi spherical particles in hypoeutectic Al-Si alloy
15. 3D morphological evolution of the Fe-Rich phase and mechanical properties of the recyclable A356 alloy
16. Prediction and optimization of tensile properties of 2219-T8 aluminum alloy TIG welding joint by machine learning10.1016/j.matdes.2024.113274 ↗
17. Machine learning in prediction of residual stress in laser shock peening for maximizing residual compressive stress formation10.1016/j.matdes.2024.113079 ↗
18. In situ conductometry for studying the homogenization of Al-Mg-Si alloys and predicting extrudate grain structure through machine learning10.1016/j.matdes.2024.113070 ↗
19. Investigation of age-hardening behaviour of Al alloys via feature screening-assisted machine learning10.1016/j.msea.2024.147381 ↗
20. Effects of Cu content and Sintering temperature on microstructure and mechanical properties of SiCp/Al-Cu-Mg composites through experimental study, CALPHAD-type simulation and machine learning10.1016/j.jmrt.2024.09.202 ↗
21. Influences of the composition design on the microstructure and properties of laser additive manufacturing TiAl alloy coatings10.1016/j.jmrt.2024.06.090 ↗
22. Random forests10.1023/A:1010933404324 ↗
23. Bagging predictors10.1023/A:1018054314350 ↗
24. Artificial neural networks: a tutorial10.1109/2.485891 ↗
25. A survey of decision tree classifier methodology10.1109/21.97458 ↗
26. Popular ensemble methods: an empirical study10.1613/jair.614 ↗
27. Fatigue life prediction of aluminum alloy via knowledge-based machine learning10.1016/j.ijfatigue.2021.106716 ↗
28. Computer alloy design of Ti modified Al-Si-Mg-Sr casting alloys for achieving simultaneous enhancement in strength and ductility
29. Inversely optimized design of Al-Mg-Si alloys using machine learning methods10.1016/j.commatsci.2024.113107 ↗
30. Designing unique and high-performance Al alloys via machine learning: mitigating data bias through active learning10.1016/j.commatsci.2024.113204 ↗
31. Machine learning assisted design of high entropy alloys with desired property10.1016/j.actamat.2019.03.010 ↗
32. A method for predicting mechanical properties of composite microstructure with reduced dataset based on transfer learning10.1016/j.compstruct.2021.114444 ↗
33. Effects of microstructure coarsening and casting pores on the tensile and fatigue properties of cast A356-T6 aluminum alloy: a comparative investigation10.1016/j.msea.2022.144106 ↗
34. Uniform fatigue damage tolerance assessment for additively manufactured and cast Al-Si alloys: an elastic-plastic fracture mechanical approach
35. Influence of surface and internal casting defects on the fatigue behaviour of A357-T6 cast aluminium alloy10.1016/j.ijfatigue.2015.07.032 ↗
36. The effect of hot isostatic pressing on the microstructure and tensile properties of an unmodified A356-T6 cast aluminum alloy10.1016/j.jallcom.2005.11.019 ↗
37. Microstructures and high temperature mechanical properties of A356-Mg2Si functionally graded composites in as-cast and artificiallyaged (T6) conditions10.1016/j.jallcom.2019.07.075 ↗
38. Effect of Mg2Si particles on low-temperature fracture behavior of A356 alloy10.1016/j.msea.2016.08.035 ↗
39. From crack-prone to crack-free: eliminating cracks in additively manufacturing of high-strength Mg2Si-modified Al-Mg-Si alloys10.1016/j.jmst.2024.04.009 ↗
40. Deformation-mediated cyclic evolution of precipitates in Al-Mg-Si-Cu alloy by multi-pass ECAP and thermal treatments10.1016/j.jmst.2024.05.075 ↗
41. Mechanical behavior and strengthening mechanisms in ultrafine grain precipitation-strengthened aluminum alloy10.1016/j.actamat.2013.09.042 ↗
42. Strengthening mechanisms in cryomilled ultrafine-grained aluminum alloy at quasi-static and dynamic rates of loading10.1016/j.scriptamat.2008.12.026 ↗
43. Mui Ling Nai, Superior mechanical properties of a selective-laser-melted AlZnMgCuScZr alloy enabled by a tunable hierarchical microstructure and dual-nanoprecipitation10.1016/j.mattod.2021.11.019 ↗
44. Interfacial nanophases stabilize nanotwins in high-entropy alloys10.1016/j.actamat.2019.12.010 ↗
45. Effect of dispersoid formation on age hardening and precipitation behavior of an Al-Si-Mg(-Cu) alloy with Mn and Cr addition10.1016/j.jallcom.2024.176726 ↗
46. Precipitates and tensile fracture mechanism in a sand cast A356 aluminum alloy10.1016/j.jmatprotec.2007.12.050 ↗
47. The effect of the β-al5fesi phases on microstructure, mechanical and fatigue properties in a356.0 cast alloys with higher fe content without additional alloying of mn10.3390/ma14081943 ↗
48. Characteristics of Fe-rich intermetallics compounds and their influence on the cracking behavior of a newly developed high-pressure die cast Al–4Mg–2Fe alloy10.1016/j.jallcom.2020.157121 ↗
49. Enhancing the Strength and Toughness of A356.2-0.15Fe Aluminum Alloy by Trace Mn and Mg Co-Addition10.3390/met13081451 ↗
50. Interactions between Fe-rich intermetallics and Mg-Si phase in Al-7Si-xMg alloys10.1016/j.jallcom.2019.01.352 ↗
51. New method of eutectic silicon modification in cast Al-Si alloys
52. The relationship between residual amount of Sr and morphology of eutectic Si phase in A356 alloy
53. Modification mechanism and microstructural characteristics of eutectic si in casting Al-Si Alloys: a review on experimental and numerical studies10.1007/s11837-014-0968-1 ↗
54. The modification of Al-Si casting alloys: Important practical theoretical aspects
55. D. Teng, G. Zhang, S. Zhang, J. Li, Y. Zhang, R. Guan, Effect of Al-3Ti-1B-1.5Ce Refiner on Microstructure and Mechanical Properties of A356 Aluminum Alloy, in: 2023: pp. 592–598. https://doi.org/10.1007/978-3-031-22532-1_80.10.1007/978-3-031-22532-1_80 ↗
56. Grain-refinement and mechanical properties optimisation of A356 casting Al by ultrasonic-assisted friction stir processing10.1007/s12540-020-00952-x ↗