Assessing the implementation of machine learning models for thermal treatments design
Source abstract
Abstract
The latest progress in machine learning (ML) algorithms enabled to predict some steel physical properties previously modelled by linear regression (LR), such as the Ms temperature. Authors claimed that the performance given by ML models could improve the one of previous LR models, although they did not include fair comparisons. In this work, a large database was used to train different ML algorithms, whose Ms temperature predictions were compared to the ones of previous literature empirical models. ML methods were proved to require longer computational times and wider knowledge, while leading to similar results. Therefore, we recommend that ML methods are not always considered as the first option when trying to solve easy problems that can be modelled by LR techniques.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Neural Networks and Applications · Mineral Processing and Grinding · Machine Learning in Materials Science
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Physical Metallurgy, National Center for Metallurgical Research (CENIM-CSIC), Madrid, Spain
Funding
ministerio de ciencia e innovación · ministerio de economía y competitividad · Research Fund for Coal and Steel
References (51)
Show source-provided references
1. Andrews KW. · J Iron Steel Inst · 1965 · 203 · 721
2. Payson P · Trans Am Soc Met · 1944 · 33 · 261
3. Peet M. 2007. Materials algorithms project program library. http://www.phase-trans.msm.cam.ac.uk/map/steel/programs/ms-empirical2014.html
4. 10.1179/1743284714Y.000000071410.1179/1743284714Y.0000000714 ↗
5. Sverdlin A V · Steel Heat Treat Handb · 1997 · 45
6. 10.1179/1743284711Y.000000009710.1179/1743284711Y.0000000097 ↗
7. 10.1002/adem.20130011610.1002/adem.201300116 ↗
8. 10.2320/matertrans1989.41.76110.2320/matertrans1989.41.761 ↗
9. Steven W · J Iron Steel Inst · 1956 · 183 · 349
10. Carapella LA. · Met Prog · 1944 · 46
11. Grange RA · Trans ASM AIME · 1946 · 167 · 467
12. Nehrenberg AE. · Trans AIME · 1946 · 167 · 494
13. Rowland ES.SRL · Trans Of the ASM · 1945 · 37 · 27
14. Eldis GT · 1977 · 397
15. 10.1007/BF0264332710.1007/BF02643327 ↗
16. Kunitake T. · J Japan Soc Heat Treat · 2001 · 41 · 164
17. Kunitake T · SUMITOMO SEARCH · 1969 · 2 · 18
18. 10.1016/j.actamat.2017.05.01410.1016/j.actamat.2017.05.014 ↗
19. 10.1371/journal.pone.021649310.1371/journal.pone.0216493 ↗
20. 10.4028/www.scientific.net/MSF.949.2410.4028/www.scientific.net/MSF.949.24 ↗
21. 10.3390/met905054610.3390/met9050546 ↗
22. 10.1080/14686996.2019.161066810.1080/14686996.2019.1610668 ↗
23. 10.1038/s41598-018-20438-610.1038/s41598-018-20438-6 ↗
24. 10.1038/s41598-018-20037-510.1038/s41598-018-20037-5 ↗
25. 10.1002/adts.20190022710.1002/adts.201900227 ↗
26. 10.2355/isijinternational.ISIJINT-2019-08910.2355/isijinternational.ISIJINT-2019-089 ↗
27. 10.1016/j.msea.2018.12.04910.1016/j.msea.2018.12.049 ↗
28. 10.1007/s11661-019-05170-810.1007/s11661-019-05170-8 ↗
29. 10.1007/s10853-006-0881-210.1007/s10853-006-0881-2 ↗
30. Capdevila C, Caballero FG, De Andrés CG Determination of Ms temperature in steels: A Bayesian neural network model. ISIJ Int [Internet. 2002; 42:894–902. Available from: http://www.scopus.com/inward/record.url?eid=2-s2.0-0036392448&partnerID=40&md5=6fa2e1747e827795cc91d6634580286a.
31. 10.1179/02670830322500190210.1179/026708303225001902 ↗
32. 10.1016/j.commatsci.2005.01.00110.1016/j.commatsci.2005.01.001 ↗
33. 10.1016/j.commatsci.2005.01.00210.1016/j.commatsci.2005.01.002 ↗
34. Vermeulen WG · Ironmak Steelmak · 1996 · 23 · 433
35. 10.1016/0956-7151(94)90468-510.1016/0956-7151(94)90468-5 ↗
36. 10.1016/0956-7151(94)90469-310.1016/0956-7151(94)90469-3 ↗
37. 10.1007/s11661-012-1171-z10.1007/s11661-012-1171-z ↗
38. Pedregosa F · J Mach Learn Res · 2011 · 12 · 2825
39. Buitinck L · arXiv Prepr arXiv13090238 · 2013
40. Sourmail T, Garcia-Mateo C. MAP_DATA_STEEL_MS_ (2004). [Internet]. Mater. Algorithms Proj. 2004 [cited 2021 Mar 1]. Available from: https://www.phase-trans.msm.cam.ac.uk/map/data/materials/Ms_data_2004.html.
41. 10.1126/stke.2003.164.tw1110.1126/stke.2003.164.tw11 ↗
42. 10.1038/323533a010.1038/323533a0 ↗
43. LeCun YA · Springer · 2012 · 9
44. 10.1023/A:101093340432410.1023/A:1010933404324 ↗
45. 10.1142/909710.1142/9097 ↗
46. Breiman L · 1984
47. 10.1006/jcss.1997.150410.1006/jcss.1997.1504 ↗
48. Drucker H. · ICML. Citeseer · 1997 · 107
49. Ripley BD. · 2007
50. 10.1093/oso/9780198538493.001.000110.1093/oso/9780198538493.001.0001 ↗
51. 10.1002/sam.1001810.1002/sam.10018 ↗