Mapping Multivariate Influence of Alloying Elements on Creep Behavior for Design of New Martensitic Steels


Heritage data for the class of 9 to 12 wt pct Cr steels are studied using data science to quantify the statistically significant relationships among multiple processing/microstructure and performance variables. The effort is undertaken to find new martensitic steels for creep life of \(10^5{{\text { hours}}}\) or greater at 650 °C and 100 MPa using machine learning. Linear regression and lasso regression were utilized to identify alloying elements that contribute towards better creep strength. Visualization techniques such as t-distributed stochastic neighbor embedding and pair-wire element specific comparisons were utilized to explore information gaps that exist within the data and are in conflict with existing domain knowledge. Combining all results suggest that the next alloy design to be explored should be 9 wt pct Cr with high W (2 to 3 wt pct) and high Co (2 to 3 wt pct) for creep life of \(10^5\,\,{\text { hours}}\) or greater at 650 °C, 100 MPa.

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

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9


  1. 1.

    U.S. Energy Information Administration: What is U.S. electricity generation by energy source? U.S. Energy Information Administration (EIA) Apr 2017.

  2. 2.

    J. Shingledecker, R. Purgert, and P. Rawls: in Proceeding the 7th International Conference on Advances in Materials Technology for Fossil Power Plants, 2013, pp. 41--52.

  3. 3.

    R. Viswanathan and J. Nutting: in Advanced Heat Resistant Steels for Power Generation: Conference Proceedings, 27--29 April 1998, San Sebastian, Spain: IOM Communications, 1999.

  4. 4.

    F. Abe: J. Pressure Vessel Technol. 2016, 138 (4), 040804

    Article  Google Scholar 

  5. 5.

    V.K. Sikka: in Topical Conference on Ferritic Alloys for Use in Nuclear Energy Technologies, J.W. Davis and D.L. Michel, eds., Snowbird, UT, June 1983, pp. 19--23.

  6. 6.

    F. Abe, S. Nakazawa: MTA 1992, 23(11), 3025--3034.

    Article  Google Scholar 

  7. 7.

    K. Yamada, M. Igarashi, S. Muneki, F. Abe: ISIJ Int. 2003, 43(9), 1438--1443.

    Article  Google Scholar 

  8. 8.

    T. Horiuchi, M. Igarashi, F. Abe: ISIJ Int. 2002, 42(Suppl), S67--S71.

    Article  Google Scholar 

  9. 9.

    Materials Genome Initiative for Global Competitiveness: Tech. rep. Jun. 2011.

  10. 10.

    S.M. Arnold, F. Holland, T.P. Gabb, M. Nathal, and T.T. Wong: The Coming ICME Data Tsunami and What Can be Done, American Institute of Aeronautics and Astronautics, 2013.

  11. 11.

    S.M. Arnold, F. Holland, and B.A. Bednarcyk: Robust Informatics Infrastructure Required for ICME: Combining Virtual and Experimental Data, American Institute of Aeronautics and Astronautics, 2014.

  12. 12.

    K. Rajan: Informatics for Materials Science and Engineering Data-Driven Discovery for Accelerated Experimentation and Application, 2013.

  13. 13.

    T.M. Mitchell: Machine Learning, 1st Edn, McGraw-Hill Education, New York, 1997.

    Google Scholar 

  14. 14.

    H.K.D.H. Bhadeshia: ISIJ Int. 2001, 41(6), 626--640.

    Article  Google Scholar 

  15. 15.

    H. K. D. H. Bhadeshia: ISIJ Int. 1999, 39(10), 966--979.

    Article  Google Scholar 

  16. 16.

    I.E. Castelli, K.W. Jacobsen: Model. Simul. Mater. Sci. Eng. 2016, 5, 055007

    Google Scholar 

  17. 17.

    G. James, D. Witten, T. Hastie, R. Tibshirani: An Introduction to Statistical Learning, Springer Texts in Statistics, Vol 103. Springer, New York, 2013.

    Google Scholar 

  18. 18.

    R. Klueh and D. Harries: in: High-Chromium Ferritic and Martensitic Steels for Nuclear Applications, R. Klueh and D. Harries, eds., ASTM International, West Conshohocken, PA, 2001, pp. 5--23. 10.1520/MONO10017M.

  19. 19.

    G. Dimmler, P. Weinert, E. Kozeschnik, H. Cerjak: Mater. Charact. 2003, 51 (5), 341--352.

    Article  Google Scholar 

  20. 20.

    K. Maruyama, K. Sawada, J.-I. Koike: ISIJ Int. 2001, 41(6), 641--653.

    Article  Google Scholar 

  21. 21.

    H. Semba, F. Abe: Energy Mater. 2006, 1(4), 238--244.

    Article  Google Scholar 

  22. 22.

    H. Cerjak, P. Hofer, B. Schaffernak: Key Eng. Mater. 2000, 171174, 453--460.

    Google Scholar 

  23. 23.

    K. Sawada, M. Takeda, K. Maruyama, R. Ishii, M. Yamada, Y. Nagae, R. Komine: Mater. Sci. Eng. A 1999, 267(1), 19--25.

    Article  Google Scholar 

  24. 24.

    V. Sklenicka, K. Kuchacova, M. Svoboda, L. Kloc, J. Bursik, A. Kroupa: Mater. Charact. 2003, 51(1), 35--48.

    Article  Google Scholar 

  25. 25.

    K. Hald (2008) Int. J. Press. Vessels Pip. 85(1--2): 30--37.

    Article  Google Scholar 

  26. 26.

    S. B. Singh, H. K. D. H. Bhadeshia: Mater. Sci. Eng. A 1998, 245 (1), 72--79.

    Article  Google Scholar 

  27. 27.

    F. S. Buffington, K. Hirano, M. Cohen: Acta Metal. 1961, 9(5), 434--439.

    Article  Google Scholar 

  28. 28.

    B. J. Ganesh, S. Raju, A. KumarRai, E. Mohandas, M. Vijayalakshmi, K. B. S. Rao, B. Raj (2011) Mater. Sci. Technol. 27(2), 500--512.

    Article  Google Scholar 

  29. 29.

    J. Lecomte-Beckers, F. Schubert, and P.J. Ennis (Eds.): Materials for advanced power engineering 1998, Abstracts of the 6th Conference: no. v. 4 in Schriften des Forschungszentrums Jülich: Forschungszentrum Jülich, Jülich, Germany, 1998.

  30. 30.

    H. K. Danielsen, J. Hald: Calphad 2007, 31(4), 505--514.

    Article  Google Scholar 

  31. 31.

    H. K. Danielsen, P. E. D. Nunzio, J. Hald, H. K. Danielsen, J. Hald: Metall Mater. Trans. A 2013, 44A (5), 2445--2452.

    Google Scholar 

  32. 32.

    H. Finkler, M. Schirra: Steel Res. 1996, 67(8), 328--342

    Article  Google Scholar 

  33. 33.

    X. Zhou, C. Liu, L. Yu, Y. Liu, H. Li: J. Mater. Sci. Technol. 2015, 31 (3), 235--242.

    Article  Google Scholar 

  34. 34.

    K. Yadi: NIMS Creep Data Sheet (JIS SUS 403-B, 12cr, bar), Tech. Rep. 13B, NIMS, Tokyo, 1994.

  35. 35.

    H. Irie: NIMS Creep Data Sheet (JIS STBA 26, 9cr-1mo, tube), Tech. Rep. 19B, NIMS, Tsukuba, 1997.

  36. 36.

    H. Irie: NIMS Creep Data Sheet (1cr-0.5mo-0.25v and 12cr-1mo-1w-0.25v, bolting material), Tech. Rep. 44, NIMS: Tsukuba 1997.

  37. 37.

    H. Irie: NIMS Creep Data Sheet (JIS SUH 616-B, 12cr-1mo-1w-0.3v, bar), Tech. Rep. 10B, NIMS, Tsukuba 1998.

  38. 38.

    S. Matsuoka: NIMS Creep Data Sheet (KA-STBA 27, 9cr-2mo, tube), Tech. Rep. 46A, NIMS, Tsukuba 2005.

  39. 39.

    NIMS Creep Data Sheet: Tech. Rep. 48A, NIMS, Japan 2012.

  40. 40.

    NIMS Creep Data Sheet (KA-SUS 410 J3, 12cr-2w-0.4mo-1cu-Nb-V): No. 51a, Tech. rep., NIMS, Japan 2013.

  41. 41.

    NIMS Creep Data Sheet (KA-SUS 410j3 DTB, 12cr-2w-0.4mo-1cu-Nb-V (Tube)): No. 52a, Tech. rep., NIMS, Japan 2013.

  42. 42.

    NIMS Creep Data Sheet (9cr-1mo-V-Nb): Tech. Rep. 43A, NIMS, Japan 2014.

  43. 43.

    L. V. D. Maaten, G. Hinton: J. Mach. Learn. Res. 2008, 9(Nov), 2579--2605.

  44. 44.

    F. Masuyama: ISIJ Int. 2001, 41(6), 612--625.

    Article  Google Scholar 

  45. 45.

    L. V. D. Maaten: J. Mach. Learn. Res. 2014, 15, 3221--3245.

    Google Scholar 

  46. 46.

    R Core Team: in R: A Language and Environment for Statistical Computing: R Foundation for Statistical Computing, Vienna, Austria, 2017.

  47. 47.

    J. H. Krijthe: Rtsne: T-Distributed Stochastic Neighbor Embedding using Barnes-Hut Implementation, R Package version 0.13 2015.

  48. 48.

    V. M. Muggeo: R News 2008, 8(1), 20--25.

    Google Scholar 

  49. 49.

    V. M. R. Muggeo: Stat. Med. 2003, 22(19), 3055--3071.

    Article  Google Scholar 

  50. 50.

    T. Lumley based on Fortran code by Alan Miller: Leaps: Regression Subset Selection, R Package version 3.0 2017.

  51. 51.

    P. M. Narendra, K. Fukunaga: IEEE Trans. Comput. 1977, 9 (26), 917--922.

    Google Scholar 

  52. 52.

    T. Hastie, R. Tibshirani, J. Friedman: in The Elements of Statistical Learning: Data Mining, Inference, and Prediction, 2nd edn., Springer Series in Statistics, Springer, New York, 2009.

  53. 53.

    J. Friedman, T. Hastie, R. Tibshirani: J Stat Softw 2010, 33 (1), 1--22.

    Article  Google Scholar 

  54. 54.

    A. E. Hoerl, R. W. Kennard: Technometrics 1970, 12 (1), 55.

    Article  Google Scholar 

  55. 55.

    R. Tibshirani (1996) J. R. Soc. Ser. B Methodol. 58(1), 267--288.

    Google Scholar 

  56. 56.

    N. Simon, J. Friedman, T. Hastie, R. Tibshirani: J. Stat. Softw. 2011, 39 (5), 1–13.

    Article  Google Scholar 

  57. 57.

    J. Friedman, T. Hastie, H. Höfling, R. Tibshirani: Ann. Appl. Stat. 2007, 1(2), 302--332.

    Article  Google Scholar 

  58. 58.

    F. R. Larson, J. Miller: Trans. ASME 1952, 74, 765--771.

    Google Scholar 

  59. 59.

    F. T. Furillo, S. Purushothaman, J. K. Tien: Scripta Metall. 1977, 11(6), 493--496.

    Article  Google Scholar 

  60. 60.

    M. Tamura, F. Abe, K. Shiba, H. Sakasegawa, H. Tanigawa: Metall. Mater. Trans. A 2013, 44 (6), 2645--2661.

    Article  Google Scholar 

  61. 61.

    J. W. Tukey: Biometrics 1949, 5 (2), 99--114.

    Article  Google Scholar 

  62. 62.

    R. D. Cook: Technometrics 1977, 19 (1), 15--18.

    Google Scholar 

  63. 63.

    F. Abe, R. Viswanathan, T.-U. Kern (eds.): Creep Resistant Steels, Woodhead Publishing, Cambridge, 2008.

    Google Scholar 

  64. 64.

    D. C. Montgomery, E. A. Peck, G. G. Vining: Introduction to Linear Regression Analysis, Wiley, New York, 2012

    Google Scholar 

  65. 65.

    J. A. Knottnerus, P. Tugwell: J. Clin. Epidemiol. 2013, 66 (10), 1061--1063.

    Article  Google Scholar 

  66. 66.

    H. Nickel, Y. Wouters, M. Thiele, W. J. Quadakkers: Fresenius J. Anal. Chem. 1998, 361 (6-7), 540--544.

    Article  Google Scholar 

  67. 67.

    F. Liu, M. Rashidi, L. Johansson, J. Hald, H.-O. Andrén: Scripta Mater. 2016, 113, 93--96.

    Article  Google Scholar 

  68. 68.

    M. Subanović, J. Pirón, F. Zeller, M. Jarrar, A. Schneider: 2018, V001T01A008.

  69. 69.

    V. Rohr, M. Schütze, E. Fortuna, D. N. Tsipas, A. Milewska, F. J. Pérez: Mater. Corros. 2005, 56(12), 874--881.

    Article  Google Scholar 

  70. 70.

    Y. Yamamoto, M. P. Brady, G. Muralidharan, B. A. Pint, P. J. Maziasz, D. Shin, B. Shassere, S. S. Babu, C.-H. Kuo: Development of Creep-Resistant, Alumina-Forming Ferrous Alloys for High-Temperature Structural Use, American Society of Mechanical Engineers, 2018, pp. V001T04A003

  71. 71.

    Y. Shen, H. Liu, Z. Shang, Z. Xu: J. Nucl. Mater. 2015, 465, 373--382.

    Article  Google Scholar 

  72. 72.

    F. Abe, T. Horiuchi, M. Taneike, K. Sawada: Mater. Sci. Eng. A 2004, 378 (1--2), 299--303.

    Article  Google Scholar 

  73. 73.

    F. Abe: Mater. Sci. Eng. A 2004, 387389, 565--569.

    Article  Google Scholar 

  74. 74.

    L. Helis, Y. Toda, T. Hara, H. Miyazaki, F. Abe: Mater. Sci. Eng. A 2009, 510511, 88--94.

    Article  Google Scholar 

  75. 75.

    G. George, H. Shaikh: in Corrosion of Austenitic Stainless Steels, Woodhead Publishing Series in Metals and Surface Engineering, H. S. Khatak, B. Raj, eds., Woodhead Publishing, Cambridge, 2002, pp. 1--36.

  76. 76.

    Y. F. Yin, R. G. Faulkner: Mater. Sci. Eng. A 2003, 344 (1), 92--102.

    Article  Google Scholar 

  77. 77.

    J. Neyman (1937) Phil. Trans. R. Soc. Lond. A 236(767), 333--380.

    Article  Google Scholar 

  78. 78.

    A. E. Fedoseeva, N. R. Dudova, R. O. Kaibyshev (2017) Phys. Metals Metallogr. 118(6), 591--600.

    Article  Google Scholar 

  79. 79.

    F. Abe, T. Ohba, H. Miyazaki, Y. Toda, M. Tabuchi: Mater. High Temp. 2019, 0 (0), 1--11.

  80. 80.

    A. Fedoseeva, N. Dudova, R. Kaibyshev, A. Belyakov: Metals 2017, 7 (12), pp. 573.

    Article  Google Scholar 

  81. 81.

    A. Fedoseeva, N. Dudova, R. Kaibyshev: Mater. Sci. Eng. A 2016, 654, 1--12.

    Article  Google Scholar 

  82. 82.

    R. Mishnev, N. Dudova, R. Kaibyshev: Mater. Sci. Eng. A 2018, 713, 161--173.

    Article  Google Scholar 

  83. 83.

    A. Fedoseeva, N. Dudova, R. Kaibyshev: J Mater Sci Mar. 2017, 52 (5), 2974--2988.

    Article  Google Scholar 

  84. 84.

    A. Fedoseeva, I. Nikitin, N. Dudova, R. Kaibyshev: Mater. Sci. Eng. A 2018, 724, 29--36.

    Article  Google Scholar 

Download references


This work made use of the High Performance Computing Resource in the Core Facility for Advanced Research Computing at Case Western Reserve University. This project was funded by the Department of Energy (Grant DE-FE0028685), National Energy Technology Laboratory, an agency of the United States Government.


This project was funded by the Department of Energy, National Energy Technology Laboratory, an agency of the United States Government. Neither the United States Government nor any agency thereof, nor any of their employees, makes any warranty, expressed or implied, or assumes any legal liability or responsibility for the accuracy, completeness, or usefulness of any information, apparatus, product, or process disclosed, or represents that its use would not infringe privately owned rights. Reference herein to any specific commercial product, process, or service by trade name, trademark, manufacturer, or otherwise does not necessarily constitute or imply its endorsement, recommendation, or favoring by the United States Government or any agency thereof. The views and opinions of authors expressed herein do not necessarily state or reflect those of the United States Government or any agency thereof.

Author information



Corresponding author

Correspondence to Jennifer L. W. Carter.

Additional information

Publisher's Note

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

Manuscript submitted November 28, 2018.

Appendix A: Regression Coefficients

Appendix A: Regression Coefficients

The rank-ordered contributors presented in Tables II through V represents the fitted equations, minus the magnitude of regression coefficients. For example, rupture time (RT) model in Table III can be translated to:

$$\begin{aligned} \log_{10} (RT) = \beta _0 - \beta _1 \log_{10} (\sigma ) - \beta _2 Temp + \beta _3 {{\text{Nb}}} + \beta _4 {{\text{W}}} + \beta _5 {{\text{Mo}}} + \beta _6 {{\text{Ni}}} + \beta _7 {{\text{B}}} \end{aligned}$$

The magnitude of regression coefficients are a function of magnitude of the associated variable. For example, change in B at ppm level may bring about small changes in response, although being the changes at ppm level will push the magnitude of regression coefficient to a very high value. This might appear to a reader at first glance that changes in B might bring about better results than W or Co. As the focus is on inference throughout the paper, except for Section III–C, the positive and negative signs served the purpose for the results, and avoided the unwanted confusion. Here, we present regression coefficients and their scaled counterparts to show the complete breadth of the fitted models. The scaling was done by subtracting the mean and dividing by the standard deviation of a variable (Table AI through AIV).

Table AI Rank-Ordered Contributors for Yield Strength (YS) at Low and High Temperature Regions with Regression Coefficients and Their Scaled Counterparts
Table AII Rank-Ordered Contributors for Larson–Miller Parameter (LMP) and Rupture Time (RT) for All Creep Data with Regression Coefficients and Their Scaled Counterparts
Table AIII Temperature (Temp) Specific Rank-Ordered Contributors for Rupture Time (\({\text {log}}_{10}\)(RT)) with Regression Coefficients and Their Scaled Counterparts
Table AIV Temperature Specific Rank-Ordered Contributors for Rupture Time After Correction with Lasso Regression Along with Regression Coefficients and Their Scaled Counterparts

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Verma, A.K., Hawk, J.A., Bruckman, L.S. et al. Mapping Multivariate Influence of Alloying Elements on Creep Behavior for Design of New Martensitic Steels. Metall Mater Trans A 50, 3106–3120 (2019).

Download citation