Skip to main content
SpringerLink
Log in

New insight in predicting martensite start temperature in steels

  • Metals & corrosion
  • Published:
Journal of Materials Science Aims and scope Submit manuscript

Abstract

Martensite start temperature (MS) plays an important role in the chemical composition and heat treatment designs of advanced high-strength steels. To improve the performance of MS prediction model trained using machine learning methods, dataset augmentation strategy and the addition of new features play a key role. In the present work, the effects of new features related to atomic parameters on the performance of the prediction model trained using an machine learning algorithm were studied and discussed by using the datasets obtained from the literature and industrial companies. In addition, the effects of the interaction between carbon and alloying elements on martensite start temperature are studied. The results revealed that the new features related to electronegativity difference between the alloying elements and C, the number of covalent electrons and the lattice constant of austenite grains considerably improved the prediction performance of the trained model. Moreover, Si–C interaction intensified the role of C in reducing martensite start temperature, whereas V–C, Ni–C, N–C, Mo–C, Cr–C and Al–C interactions weakened the role of C.

Graphical abstract

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Figure 1
Figure 2
Figure 3
Figure 4
Figure 5
Figure 6
Figure 7
Figure 8
Figure 9
Figure 10
Figure 11
Figure 12
Figure 13

Similar content being viewed by others

References

  1. Barbier D (2014) Extension of the Martensite transformation temperature relation to larger alloying elements and contents. Adv Eng 16(1):122–127

    CAS  Google Scholar 

  2. Kim H, Inoue J, Okada M, Nagata K (2017) Prediction of Ac3 and martensite start temperatures by a data driven model selection approach. ISIJ Int 57(12):2229–2236

    Article  CAS  Google Scholar 

  3. Park J, Shim JH, Lee SJ (2017) New equation for prediction of martensite start temperature in high carbon ferrous alloys. Metall Mater Trans A 49A(2):450–454

    Article  Google Scholar 

  4. Kaar S, Steineder K, Schneider R, Krizan D, Sommitsch C (2021) New Ms-formula for exact microstructural prediction of modern 3rd generation AHSS chemistries. Scripta Mater 200:113923

    Article  CAS  Google Scholar 

  5. Lee SJ, Jung M (2021) Prediction of martensite start temperatures of highly alloyed steels. Arch Metall Mater 66(1):107–111

    CAS  Google Scholar 

  6. Stormvinter A, Borgenstam A, Agren J (2012) Thermodynamically based prediction of the martensite start temperature for commercial steels. Metall Mater Trans A 43A:3870–3879

    Article  Google Scholar 

  7. Seifert M, Theisen W (2016) Modeling hardenable stainless steels using calculated martensite start temperatures in thermodynamic equilibrium calculations. Metall Mater Trans A 47A:5953–5959

    Article  Google Scholar 

  8. Plat J, Leitner H, Turk C, Schnitzer R (2020) Determination of Martensite start temperature of high speed steels based on thermodynamic calculations. Steel Res Int 91:20000063

    Google Scholar 

  9. Luo Q, Chen HC, Chen W, Wang CC, Xu W, Li Q (2020) Thermodynamic prediction of martensitic transformation temperature in Fe-Ni-C system. Scripta Mater 187:413–417

    Article  CAS  Google Scholar 

  10. Chen HC, Xu W, Luo Q, Li Q, Zhang Y, Wang JJ, Chou KC (2022) Thermodynamic prediction of martensitic transformation temperature in Fe-C-X (X=Ni, Mn, Si, Cr) systems with dilatational coefficient model. J Mater Sci Technol 112:291–300. https://doi.org/10.1016/j.jmst.2021.09.060

    Article  Google Scholar 

  11. Rahaman M, Mu WZ, Odqvist J, Hedstrom P (2019) Machine learning to predict the martensite start temperature in steels. Metall Mater Trans A 50:2081–2091

    Article  CAS  Google Scholar 

  12. Lu Q, Liu SL, Li W, Jin XJ (2020) Combination of thermodynamic knowledge and multilayer feed forward neural networks for accurate prediction of MS temperature in steels. Mater Des 192:108696

    Article  Google Scholar 

  13. Xiong B, Zhao XP, Hu YF, Huang HY, Liu Y, Su YJ (2021) Machine learning assisted empirical formula augmentation. Mater Des 210:110037

    Article  CAS  Google Scholar 

  14. Vermeulen WG, Morri PF, Weijer AP, Zwaag SVD (1996) Prediction of martensite start temperature using artificial neural networks. Ironmak Steelmak 23(5):433–437

    CAS  Google Scholar 

  15. Peet M (2014) Prediction of martensite start temperature. Mater Sci Technol 31(11):1370–1375

    Article  Google Scholar 

  16. Sourmail T, Garcia-Mateo C (2005) Critical assessment of models for predicting the Ms temperature of steels. Comput Mater Sci 34:323–334

    Article  CAS  Google Scholar 

  17. Materials Algorithms Project (MAP) https://www.phase-trans.msm.cam.ac.uk/map/data/data-index.html#neural. Accessed 1 June 2017

  18. MAP_DATA_STEEL_MS_2004: https://www.phase-trans.msm.cam.ac.uk/map/data/materials/Ms_data_2004.html. Accessed 1 June 2017

  19. Ghosh G, Olson GB (1994) Kinetics of F.C.C.→B.C.C. heterogeneous martensitic nucleation –I. The critical driving force for athermal nucleation. Acta Metall Mater 42(10):3361–3370

    Article  CAS  Google Scholar 

  20. Ghosh G, Olson GB (1994) Kinetics of F.C.C.→B.C.C. heterogeneous martensitic nucleation II. Thermal activation. Acta Metall Mater 42(10):3371–3379

    Article  CAS  Google Scholar 

  21. Bohemen SMC, Morsdorf L (2017) Predicting the Ms temperature of steels with a thermodynamic based model including the effect of the prior austenite grain size. Acta Mater 125:401–415

    Article  Google Scholar 

  22. Morris JW, Lee CS, Guo Z (2003) The nature and consequences of coherent transformations in steel. ISIJ Int 43:410–419

    Article  CAS  Google Scholar 

  23. Welchowski T, Maloney KO, Mitchell R, Schmid M (2021) Techniques to improve ecological interpretability of black-box machine learning models. J Agric Biol Environ Stat 27:175–197

    Article  Google Scholar 

  24. Yan F, Song K, Liu Y, Chen S, Chen J (2020) Predictions and mechanism analyses of the fatigue strength of steel based on machine learning. J Mater Sci 55(31):15334–15349. https://doi.org/10.1007/s10853-020-05091-7

    Article  CAS  Google Scholar 

  25. Ke GL, Meng Q, Finley T, Wang TF, Chen W et al (2017) LightGBM: a highly efficient gradient boosting decision tree. Neural Inf Process Sys 31:3149–3157

    Google Scholar 

  26. Hao XC, Zhang ZP, Xu QQ et al (2022) Prediction of f-CaO content in cement clinker: a novel prediction method based on LightGBM and Bayesian optimization. Chemom Intell Lab Syst 220:104461

    Article  CAS  Google Scholar 

  27. Liu YN, Yu ZM, Chen C et al (2020) Prediction of protein crotonylation sites through LightGBM classifier based on SMOTE and elastic net. Anal Biochem 609:113903

    Article  CAS  Google Scholar 

  28. Chen C, Zhang QM, Ma Q, Yu B (2019) LightGBM-PPI: predicting protein-protein interactions through LightGBM with multi-information fusion. Chemom Intell Lab Syst 191:54–64

    Article  CAS  Google Scholar 

  29. The first steel mills of Benxi Iron and Steel Company, Metal Materials Teaching and Research Group-Department of Mechanics-Tsinghua University (1978) Transition curves of overcooling austenite of steels. Benxi Iron and Steel Company

  30. Lin HG, Fu DZ (1988) Austenite transition curves of steels: principle, testing and application. China Machine PRESS

    Google Scholar 

  31. Yang KG (1981) Isothermal transition curve of steels. Heilongjiang People’s Publishing House

    Google Scholar 

  32. Zhang SZ (1993) Atlas of transition curve diagrams of overcooling austenite of steels. Metallurgical Industry Press

    Google Scholar 

  33. Capdevila C, Caballero FG (2002) Determination of Ms temperature in steels: a Bayesian neural network model. ISIJ Int 42(8):894–902

    Article  CAS  Google Scholar 

  34. Bohemen SMC (2012) Bainite and martensite start temperature calculated with exponential carbon dependence. Mater Sci Technol 28(4):487–495

    Article  Google Scholar 

  35. Garcia-Mateo C, Peet M, Caballero FG, Bhadeshia HKDH (2004) Tempering of hard mixture of bainitic ferrite and Austenite. Mater Sci Technol 20(7):814–818

    Article  CAS  Google Scholar 

  36. Bennett KP, Demiriz A (1999) Semi-supervised support vector machines. Adv Neural Inf Process Syst 11:368–374

    Google Scholar 

  37. Breiman L (2001) Random forest. Mach Learn 45(1):5–32

    Article  Google Scholar 

  38. Tranmer M, Murphy J, Elliot M et al (2020) Multiple linear regression, 2nd edn. Cathie Marsh Institute Working Paper

  39. Wang JJ, Wolk PJ, Zwaag SVD (2000) Determination of martensite start temperature in engineering steels part I. Empirical relations describing the effect of steel chemistry. Mater Trans, JIM 41(7):761–768

    Article  CAS  Google Scholar 

  40. Wang JJ, Wolk PJ, Zwaag SVD (2000) Determination of martensite start temperature for engineering steels part II. Correlation between critical driving force and Ms temperature. Mater Trans JIM 41(7):769–776

    Article  CAS  Google Scholar 

  41. Bhadeshia HKDH (2001) Bainite in steels, 2nd edn. IOM Communications, London

    Google Scholar 

  42. Xiong J, Zhang TY, Shi SQ (2020) Machine learning of mechanical properties of steels. Science China Technol Sci 63:1247–1255

    Article  CAS  Google Scholar 

Download references

Acknowledgements

The authors gratefully acknowledge the support from National Natural Science Foundation of China (No.52071238 and U20A20279), and the 111 Project (No. D18018). In this work, numerical calculation is supported by High-Performance Computing Center of Wuhan University of Science and Technology.

Author information

Authors and Affiliations

  1. The State Key Laboratory of Refractories and Metallurgy, Hubei Province Key Laboratory of Systems Science on Metallurgical Processing, Collaborative Center on Advanced Steels, International Research Institute for Steel Technology, Wuhan University of Science and Technology, Wuhan, 430081, China

    Zhuang Yan, Lin Cheng, Xingyu Chen & Kaiming Wu

  2. College of Artificial Intelligence and Computer Science, Wuhan Textile University, Wuhan, 430073, China

    Li Li

  3. Metals Valley and Band (Foshan) Metallic Composite Materials Co., Ltd, Foshan, 528000, Guangdong, China

    Lin Cheng & Kaiming Wu

Authors
  1. Zhuang Yan
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Li Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Lin Cheng
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Xingyu Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Kaiming Wu
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to Li Li or Lin Cheng.

Ethics declarations

Conflict of interest

The authors declare that they have no conflict of interest.

Additional information

Handling Editor: Sophie Primig.

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Yan, Z., Li, L., Cheng, L. et al. New insight in predicting martensite start temperature in steels. J Mater Sci 57, 11392–11410 (2022). https://doi.org/10.1007/s10853-022-07329-y

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10853-022-07329-y

Search

Navigation