Sage Journals: Discover world-class research

Abstract

Empirical equations, thermodynamics frameworks, and neural network modeling have been developed to predict steel martensite start temperature, $M_{s}$ , but they might not tend to generalize well when composition includes a wide range of alloying elements. In this study, we develop the Gaussian process regression (GPR) model to shed light on the relationship between alloying elements and $M_{s}$ temperature for steels. A total of 1119 steels with $M_{s}$ ranging from 153 K to 938 K are examined. The model has a high degree of accuracy and stability, contributing to fast low-cost $M_{s}$ temperature estimations.

Keywords

Martensite Steel Gaussian process regression machine learning phase transformation

Get full access to this article

View all access options for this article.

References

Bhadeshia

HKDH

Honeycombe

RWK

. Steels: Microstructure and Properties. BH Pub, 2006.

Lai

JKL

Shek

KH.

Stainless Steels: An Introduction and Their Recent Developments. Bentham Science Publishers, 2012.

Wang

Subramanian

Liu

Studies on Nb microalloying of 13Cr super martensitic stainless steel. Metallurg Mater Trans A 2012; 43(12): 4475–4486.

DePaul

Kitchin

AL.

The role of nickel, copper, and columbium (Niobium) in strengthening a low-carbon ferritic steel. Metallurg Mater Trans B, 1(2), pp. 389–393, 1970. doi: 10.1007/BF02811547

Gustafson

Ågren

. Possible effect of Co on coarsening of M23C6 carbide and Orowan stress in a 9% Cr steel. ISIJ Int 2001; 41: 356–360.

Lisovskii

AF.

Cemented carbides alloyed with ruthenium, osmium, and rhenium. Powder Metallurgy Metal Ceram 2000; 39(9–10): 428–433.

Gant

Gee

MG.

Wear of tungsten carbide–cobalt hardmetals and hot isostatically pressed high speed steels under dry abrasive conditions. Wear 2001; 251(1–12): 908–915.

Kwok

Cheng

Man

. Laser-fabricated Fe–Ni–Co–Cr–B austenitic alloy on steels. Part I. Microstructures and cavitation erosion behaviour. Surf Coat Technol 2001; 145(1–3): 194–205.

Capella

Caballero

Garcia

Metal Prog 1944; 46: 108.

10.

Wang

van der Wolk

van der Zwaag

. Determination of martensite start temperature in engineering steels. Part I. Empirical relations describing the effect of steel chemistry. Mater Trans JIM 2000; 41: 769–776.

11.

Andrews

KW.

Empirical formulae for the calculation of some transformation temperatures. J Iron Steel Inst 1965; 61: 721–727.

12.

Sinnott

SB.

Material design and discovery with computational materials science. J Vac Sci Technol A Vac Surf Films 2013; 31(5): 050812.

13.

Srinivasan

Broderick

Zhang

, et al. Mapping chemical selection pathways for designing multicomponent alloys: an informatics framework for materials design. Sci Rep 2015; 5: 17960.

14.

Wang

Yang

Jin

Hong

Study on a numerical method for calculating the heating process of HTS DC induction heater. IEEE Trans Appl Supercond 2013; 24(3): 1–5.

15.

Song

Wang

Simulations of nonuniform behaviors of multiple no-insulation (RE)Ba₂Cu₃O_7−x HTS pancake coils during charging and discharging. IEEE Trans Appl Supercond 2015; 26(4): 2513412.

16.

Guo

Mitra

, et al. Three-dimensional band diagram in lateral polarity junction III-nitride heterostructures. Optica 2019; 6(8): 1058–1062.

17.

Jiang

Gou

Shen

TM.

Numerical simulation of quench initiation and propagation in multi-filamentary Bi₂Sr₂CaCu₂O_x round wires at high magnetic fields. J Appl Phys 2019; 125(16): 163901.

18.

Schwartz

Koch

Zhang

Liu

. Formation of bismuth strontium calcium copper oxide superconductors. U.S. Patent US9773962B2, 26 September 2017. Available at: https://patentimages.storage.googleapis.com/dd/a0/5d/f73e3aa9c2eae4/US9773962.pdf

19.

x Zhang

Johnson

Naderi

Chaubal

Hunt

Schwartz

High critical current density Bi₂Sr₂CaCu₂O _x /Ag wire containing oxide precursor synthesized from nano-oxides. Supercond Sci Technol 2016; 29(9): 095012.

20.

Zhang

Koch

Schwartz

Formation of Bi₂Sr₂CaCu₂O _x/Ag multifilamentary metallic precursor powder-in-tube wires. Supercond Sci Technol 2016; 29(12): 125005.

21.

Zhang

Koch

Schwartz

Synthesis of Bi₂Sr₂CaCu₂O_x superconductors via direct oxidation of metallic precursors. Supercond Sci Technol 2014; 27(5): 055016.

22.

Bouzaiene

Dhahri

Hlil

Bajahzar

Effect of A-site-substitution on structural, magnetic and magnetocaloric properties in La_0.7Sr_0.3Mn_0.9Cu_0.1O₃ manganite. J Magnet Magnet Mater 2019; 491: 165540.

23.

Mosca

Bozzolo

Del Grosso

MF.

Atomistic modeling of ternary additions to NiTi and quaternary additions to Ni–Ti–Pd, Ni–Ti–Pt and Ni–Ti–Hf shape memory alloys. Physica B: Condensed Matter 2012; 407(16): 3244–3247.

24.

Ghosh

Olson

GB.

Kinetics of FCC → BCC heterogeneous martensitic nucleation—I. The critical driving force for athermal nucleation. Acta Metallurg Mater 1994; 42(10): 3361–3370.

25.

Ghosh

Olson

. Kinetics of F.c.c. → b.c.c. Heterogeneous martensitic nucleation—II. Thermal activation. Acta Metallurg Mater 1994; 42(10): 3371–3379.

26.

Bhadeshia

HKDH

. Driving force for martensitic transformation in steels. Metal Sci 1981; 15(4): 175–177.

27.

Bhadeshia

HKDH

. Thermodynamic extrapolation and martensite-start temperature of substitutionally alloyed steels. Metal Sci 1981; 15(4): 178–180.

28.

Zhang

Predicting As_xSe_1−x glass transition onset temperature. Int J Thermophys 2020; 41: 149.

29.

Zhang

Solubility predictions through LSBoost for supercritical carbon dioxide in ionic liquids. New J Chem 2020; 44: 20544–20567.

30.

Zhang

Predictions of the total crack length in solidification cracking through LSBoost. Metallurg Mater Trans A 2021. DOI: 10.1007/s11661-020-06130-3.

31.

Zhang

Yttrium barium copper oxide superconducting transition temperature modeling through Gaussian process regression. Computat Mater Sci 2020; 179: 109583.

32.

Zhang

Predicting doped MgB₂ superconductor critical temperature from lattice parameters using Gaussian process regression. Physica C Supercond Applic 2020; 573: 1353633.

33.

Zhang

Curie temperature modeling of magnetocaloric lanthanum manganites using Gaussian process regression. J Magnet Magnet Mater 2020; 512: 166998.

34.

Zhang

Machine learning the magnetocaloric effect in manganites from lattice parameters/

Appl Phys A 2020; 126: 341.

35.

Zhang

Machine learning the magnetocaloric effect in manganites from compositions and structural parameters. AIP Advances 2020; 10(3): 035220.

36.

Zhang

Predicting the thermal conductivity enhancement of nanofluids using computational intelligence. Phys Lett A 2020; 384: 126500.

37.

Zhang

Machine learning modeling of lattice constants for half-Heusler alloys. AIP Advances 2020; 10: 045121.

38.

Zhang

Machine learning optical band gaps of doped-ZnO films. Optik 2020; 217: 164808.

39.

Zhang

Relative cooling power modeling of lanthanum manganites using Gaussian process regression. RSC Advances 2020; 10: 20646–20653.

40.

Zhang

Machine learning band gaps of doped-TiO₂ photocatalysts from structural and morphological parameters. ACS Omega 2020; 5: 15344–15352.

41.

Zhang

Machine learning lattice constants for cubic perovskite

A_{2} X Y_{6}

compounds. J Solid State Chem 2020; 291: 121558.

42.

Zhang

Machine learning lattice constants for cubic perovskite

A_{2}^{2 +} B B^{'} O_{6}

compounds. Cryst Eng Comm 2020; 22: 6385–6397.

43.

Zhang

Machine learning lattice constants for cubic perovskite

AB X_{3}

compounds. Chem Select 2020; 5: 9999–10009.

44.

Zhang

Lattice misfit predictions via the Gaussian process regression for Ni-based single crystal superalloys. Metals Mater Int 2020. DOI: 10.1007/s12540-020-00883-7.

45.

Bull

AD.

Convergence rates of efficient global optimization algorithms. J Machine Learn Res 2011; 12: 2879–2904.

46.

Gelbart

Snoek

Adams

RP.

Bayesian optimization with unknown constraints. arXiv preprint arXiv:1403.5607, 2014.

47.

Snoek

Larochelle

Adams

RP.

Practical Bayesian optimization of machine learning algorithms. Adv Neur Inf Process Syst 2012; 25: 2951–2959.

48.

Zhang

Machine learning lattice constants from ionic radii and electronegativities for cubic perovskite

A_{2} X Y_{6}

compounds. Phys Chem Minerals 2020; 47: 39.

49.

Zhang

Transformation temperature predictions through computational intelligence for NiTi-based shape memory alloys. Shape Memory Superelast 2020; 6: 374–386.

50.

Zhang

Machine learning lattice parameters of monoclinic double perovskites. Int J Quant Chem 2021; 121(5): e26480.

51.

Zhang

Fe-based superconducting transition temperature modeling through Gaussian process regression. J Low Temp Phys 2020. DOI: 10.1007/s10909-020-02545-9.

52.

Zhang

Machine learning decomposition onset temperature of lubricant additives. J Mater Eng Perform 2020; 29: 6605–6616.

53.

Zhang

Predicting doped Fe-based superconductor critical temperature from structural and topological parameters using machine learning. Int J Mater Res 2021. DOI: 10.3139/146.111975.

54.

Zhang

Machine learning glass transition temperature of polymers. Heliyon 2020; 6: e05055.

55.

Zhang

Machine learning F-doped Bi(Pb)–Sr–Ca–Cu–O superconducting transition temperature. J Supercond Novel Magnet 2021; 34(1): 63–73.

56.

Zhang

Machine learning the central magnetic flux density of superconducting solenoids. Mater Technol 2020. DOI: 10.1080/10667857.2020.1830567.

57.

Zhang

Machine learning lattice constants for spinel compounds. Chem Phys Lett 2020; 760: 137993.

58.

Zhang

Machine learning lattice constants of zircon-group minerals MXO₄. Struct Chem 2021. DOI: 10.1007/s11224-020-01699-2.

59.

Zhang

Machine learning glass transition temperature of styrenic random copolymers. J Mol Graph Modell 2021; 103: 107796.

60.

Zhang

Predictions of adsorption energies of methane-related species on cu-based alloys through machine learning. Machine Learn Applicat 2021; 3: 100010.

61.

Zhang

Machine learning the lattice constant of cubic pyrochlore compounds. Int J Appl Ceram Technol 2021. DOI: 10.1111/ijac.13709.

62.

Zhang

Predicting multiple properties of pervious concrete through the gaussian process regression. Adv Civil Eng Mater 2021; 10(1). DOI: 10.1520/ACEM20200134.

63.

Zhang

Predicting the delamination factor in carbon fibre reinforced plastic composites during drilling through the Gaussian process regression. J Composite Mater 2020. DOI: 10.1177/0021998320984245.

64.

Zhang

Machine learning properties of electrolyte additives: A focus on redox potentials. Indust Eng Chem Res 2021; 60(1): 343–354.

65.

Zhang

Machine learning glass transition temperature of polyacrylamides using quantum chemical descriptors. Polym Chem 2021. DOI: 10.1039/d0py01581d.

66.

Zhang

Predicting lattice parameters for orthorhombic distorted-perovskite oxides via machine learning. Solid State Sci 2021; 113: 106541.

67.

Atkins

Atlas of Continuous Cooling Transformation Diagrams for Engineering Steels. American Society for Metals, 1980, p. 260.

68.

Economopoulos

Lambert

Habraken

Diagrammes de transformation des aciers fabriqués dans le benelux. Centre National de Recherches Metallurgiques, 1967.

69.

Sourmail

Mateo

CG.

MAP_DATA_STEEL_MS_2004. Materials Algorithms Project Program Library, 2004. https://www.phase-trans.msm.cam.ac.uk/map/data/materials/Ms_data_2004.html

70.

Sage

AM.

Atlas of continuous cooling transformation diagrams for vanadium steels. Vanitec Publication 1985; V0285: 1–224.

71.

Wever

Rose

Peter

Strassburg

Rademacher

Atlas zur Wärmebehandlung der Stähle, Vol. 56. Düsseldorf: Verlag Stahleisen, 1954, p. 264.

72.

Cias

WW.

Phase transformation kinetics and hardenability of medium-carbon alloy steels. Climax Molybdenum, 1973; 4: 2257–2266.

73.

British Iron and Steel Research Association. Atlas of Isothermal Transformation Diagrams of BS EN Steels. British Iron and Steel Research Association, London Thermal Treatment Sub Committee, 1949.

74.

Boyer

Gray

AG.

Atlas of Isothermal Transformation and Cooling Transformation Diagrams. American Society for Metals, 1977, p. 13.

75.

Greninger

AB.

The martensite thermal arrest in iron-carbon alloys and plain carbon steels. Transactions ASM 1942; 30: 1–26.

76.

Digges

TG.

Transformation of austenite on quenching high purity iron-carbon alloys. Transactions ASM 1940; 31: 575–607.

77.

Pascover

Radcliffe

SV.

Athermal transformations in the iron-chromium system. Trans Metallurg Soc Amer Inst Mining Metallurg Petrol Eng 1968; 242(4): .

78.

Bell

Owen

WS.

The thermodynamics of the martensite transformation in iron-carbon and iron-nitrogen. Trans Metallurg Soc Amer Inst Mining Metallurg Petrol Eng 1967; 239: 1940–1949.

79.

Oka

Okamoto

Swing back in kinetics near

M_{s}

in hypereutectoid steels. Metallurg Trans A 1988; 19(3): 447–452.

80.

Sastri

West

DRF

. Effect of austenitizing conditions on kinetics of martensite formation in certain medium-alloy steels. J Iron Steel Inst 1965; 203: 138.

81.

Ishida

Nishizawa

Ferrite/austenite stabilizing parameter of alloying elements in steel at 200 ~ 500 C. Trans Japan Inst Metals 1974; 15(3): 217–224.

82.

Yeo

RBG

. Effects of some alloying elements on transformation of Fe-22.5 pct Ni alloys. Trans Metallurg Soc Amer Inst Mining Metallurg Petrol Eng 1963; 227(4): 884.

83.

Lenel

Knott

BR.

Microstructure-composition relationships and

M_{s}

temperatures in Fe-Cr-Mn-N alloys. Metallurg Mater Trans A 1987; 18(5): 767–775.

84.

Steven

The temperature of formation of martensite and bainite in low alloy steels, some effects of chemical composition. J Iron Steel Inst 1956; 183: 349–359.

85.

Goodenow

Hehemann

RF.

Transformations in iron and Fe-9 pct Ni alloys. Trans Metallurg Soc Amer Inst Mining Metallurg Petrol Eng 1965; 233: 1777–1786.

86.

American Society for Metals. Transactions of American Society for Metals. Ohio: American Society for Metals, 1934.

87.

Rao

Winchell

PG.

Growth rate of bainite from low-carbon iron-nickel-carbon austenite. Trans Metallurg Soc Amer Inst Mining Metallurg Petrol Eng 1967; 239(7): 956–960.

88.

Payson

Martensite reactions in alloy steels. Trans Amer Soc Metals 1944; 33; 261–280.

89.

Rowland

Lyle

SR.

The application of

M_{s}

points to case depth measurement. Trans Amer Soc Metals 1946; 37: 27–47.

90.

Koistinen

A general equation prescribing the extent of the austenite-martensite transformation in pure iron-carbon alloys and plain carbon steels. Acta Metallurgica 1959; 7: 59–60.

91.

Goldman

Robertson

WD.

Elastic properties of austenite and martensite in iron-nickel alloys. Acta Metallurgica 1964; 12(11): 1265–1275.

92.

Cool

Bhadeshia

HKDH

. Prediction of martensite start temperature of power plant steels. Mater Sci Technol 1996; 12(1): 40–44.

Machine Learning Steel M s Temperature

Abstract

Keywords

Get full access to this article

References