Machine learning approaches for predicting and validating mechanical properties of Mg rare earth alloys for light weight applications
Source abstract
Abstract
In this work, we have attempted to predict the mechanical behaviour of light weight Mg based rare earth alloys fabricated through different mechanical and thermal processes. Our approach involves machine learning techniques across a range of different thermomechanical processes such as solution treatment, homogenization, extrusion and aging behaviour. The effectiveness of machine learning models is evaluated using performance metrics, including Coefficient of determination (R2), Mean Absolute Error (MAE) and Root Mean Square Error (RMSE). After modeling and selection of best model, the mechanical behaviour of new alloys was predicted in term of ultimate tensile strength, yield strength and total elongation. The predicted results highlight the superior predictive accuracy of the K-Nearest Neighbors (KNN) machine learning model, demonstrating its better performance metrics comparing with other machine learning approaches. This model has been found to predict the material properties with an effective evaluation matrix (R2 = 0.955, MAE = 3.4% and RMSE = 4.5%).
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Magnesium Alloys: Properties and Applications · Aluminum Alloys Composites Properties · Aluminum Alloy Microstructure Properties
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Sungkyunkwan University
Indian Institute of Technology Delhi
Funding
National Research Foundation of Korea · KISTI supercomputing center · Sungkyunkwan University
References (47)
Show source-provided references
1. 10.1016/j.commatsci.2015.04.03810.1016/j.commatsci.2015.04.038 ↗
2. 10.1016/j.jma.2023.09.03810.1016/j.jma.2023.09.038 ↗
3. 10.1016/j.matchemphys.2023.12742110.1016/j.matchemphys.2023.127421 ↗
4. 10.1007/s13369-023-08063-610.1007/s13369-023-08063-6 ↗
5. 10.1016/j.jma.2023.10.00710.1016/j.jma.2023.10.007 ↗
6. 10.1016/S1468-6996(01)00028-610.1016/S1468-6996(01)00028-6 ↗
7. 10.1016/j.jma.2023.11.00710.1016/j.jma.2023.11.007 ↗
8. 10.1016/j.actamat.2017.05.02910.1016/j.actamat.2017.05.029 ↗
9. 10.1080/14686996.2023.219624210.1080/14686996.2023.2196242 ↗
10. 10.1038/nmat443510.1038/nmat4435 ↗
11. 10.1016/j.jma.2021.04.00110.1016/j.jma.2021.04.001 ↗
12. 10.1088/1468-6996/16/5/05350110.1088/1468-6996/16/5/053501 ↗
13. 10.3390/ma1211177510.3390/ma12111775 ↗
14. 10.2320/matertrans.47.97110.2320/matertrans.47.971 ↗
15. 10.1080/10408436.2021.194718510.1080/10408436.2021.1947185 ↗
16. Jain S. Phase equilibria study and mechanical properties of multicomponent alloys. 2023. Available from: http://hdl.handle.net/10603/544595
17. 10.1016/j.jallcom.2016.04.10910.1016/j.jallcom.2016.04.109 ↗
18. 10.1016/j.matlet.2024.13759710.1016/j.matlet.2024.137597 ↗
19. 10.1155/2022/959715510.1155/2022/9597155 ↗
20. 10.1016/j.mtcomm.2024.11081310.1016/j.mtcomm.2024.110813 ↗
21. 10.1016/j.jalmes.2024.10012810.1016/j.jalmes.2024.100128 ↗
22. 10.1007/s12666-022-02821-010.1007/s12666-022-02821-0 ↗
23. 10.1016/j.actamat.2014.02.01110.1016/j.actamat.2014.02.011 ↗
24. 10.1007/s12613-019-1894-610.1007/s12613-019-1894-6 ↗
25. 10.1016/j.jmrt.2024.03.16410.1016/j.jmrt.2024.03.164 ↗
26. 10.1016/j.jmst.2018.09.02010.1016/j.jmst.2018.09.020 ↗
27. 10.1007/s41403-023-00439-210.1007/s41403-023-00439-2 ↗
28. 10.1016/j.msea.2020.13984610.1016/j.msea.2020.139846 ↗
29. 10.1016/j.mtcomm.2020.10189710.1016/j.mtcomm.2020.101897 ↗
30. 10.1016/j.matlet.2024.13647310.1016/j.matlet.2024.136473 ↗
31. 10.1016/j.actamat.2019.03.01010.1016/j.actamat.2019.03.010 ↗
32. 10.1016/j.jmrt.2024.07.04810.1016/j.jmrt.2024.07.048 ↗
33. 10.1007/s13369-024-09551-z10.1007/s13369-024-09551-z ↗
34. 10.1016/j.actbio.2021.05.01410.1016/j.actbio.2021.05.014 ↗
35. 10.3389/fmats.2021.80490610.3389/fmats.2021.804906 ↗
36. 10.4028/www.scientific.net/MSF.979.16210.4028/www.scientific.net/MSF.979.162 ↗
37. 10.1016/j.jallcom.2023.17200710.1016/j.jallcom.2023.172007 ↗
38. 10.1016/j.mechmat.2022.10422110.1016/j.mechmat.2022.104221 ↗
39. 10.1016/j.msea.2017.07.08010.1016/j.msea.2017.07.080 ↗
40. 10.1016/j.matlet.2023.13460510.1016/j.matlet.2023.134605 ↗
41. 10.1016/j.actbio.2014.07.00510.1016/j.actbio.2014.07.005 ↗
42. 10.1016/j.jmst.2019.01.00710.1016/j.jmst.2019.01.007 ↗
43. 10.1016/j.jma.2023.09.01010.1016/j.jma.2023.09.010 ↗
44. 10.1088/2053-1591/ac99be10.1088/2053-1591/ac99be ↗
45. 10.1016/j.jalmes.2024.10011010.1016/j.jalmes.2024.100110 ↗
46. 10.1016/j.jallcom.2017.11.31510.1016/j.jallcom.2017.11.315 ↗
47. 10.1007/s12598-016-0797-110.1007/s12598-016-0797-1 ↗