Prediction of the tensile properties of ODS ferritic/martensitic steels under various temperature conditions using interpretable machine learning models
Source abstract
Abstract
It is crucial to accurately and reliably predict the mechanical properties of oxide dispersion strengthened (ODS) steels for their application in Generation IV nuclear reactors. In this work, six machine learning models were utilized to predict the ultimate tensile strength and total elongation of ODS steels under various temperature conditions. The extreme gradient boosting (XGBoost) models exhibited the best predictive performance, with R 2 , RMSE, and MAE values of 0.96, 79 MPa, and 57 MPa for ultimate tensile strength prediction, respectively, and 0.90, 1.9%, and 1.6% for total elongation prediction, respectively. Shapley Additive Explanations (SHAP) method was used to interpret the model by analyzing feature importance and its corresponding impact trends. The key chemical compositions affecting ultimate tensile strength are Ti, Y 2 O 3 , Cr, and W, whereas significant process parameters include heat treatment temperature (HT) and consolidation temperature (CT). Among these, Ti, Y 2 O 3 , and W positively correlate with ultimate tensile strength, whereas HT and CT negatively correlate. However, the key chemical compositions affecting total elongation are Y 2 O 3 , W, Cr, and Ti, whereas significant process parameters include HT and CT. Among these, W, HT, and CT positively correlate with total elongation, whereas Ti negatively correlates. Furthermore, the interactions between important features obtained through SHAP analysis were discussed. This study established relationships among composition, processing, and tensile properties of ODS steels, thereby supporting the optimization of composition design and process improvements.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Hydrogen embrittlement and corrosion behaviors in metals · Fusion materials and technologies · Nuclear Materials and Properties
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (67)
Show source-provided references
1. Materials challenges in nuclear energy10.1016/j.actamat.2012.11.004 ↗
2. Energy: nuclear power's new dawn10.1038/429238a ↗
3. Mechanical performance and oxidation resistance of an ODS γ-TiAl alloy processed by spark plasma sintering and laser additive manufacturing10.1016/j.intermet.2017.09.004 ↗
4. Development of Al added high-Cr ODS steels for fuel cladding of next generation nuclear systems10.1016/j.jnucmat.2010.12.300 ↗
5. Microstructure, hardness and defect structure of the He irradiated ODS ferritic steel10.1016/j.jallcom.2016.08.312 ↗
6. Alternative fabrication routes toward oxide-dispersion-strengthened steels and model alloys10.1007/s11661-016-3616-2 ↗
7. Research progress of ODS FeCrAl alloys-a review of composition design10.3390/ma16186280 ↗
8. Small data machine learning in materials science10.1038/s41524-023-01000-z ↗
9. Effects of Hf and/or Ti addition on the morphology, crystal, and metal/oxide interface structures of nanoparticles in FeCrAl-ODS steels10.1016/j.vacuum.2024.113507 ↗
10. Microstructure and oxide particle stability in a novel ODS γ-TiAl alloy processed by spark plasma sintering and laser additive manufacturing10.1016/j.intermet.2017.07.004 ↗
11. Prediction of formation energy for oxides in ODS steels by machine learning10.1016/j.matdes.2024.113503 ↗
12. Composition optimization of radiation resistance ODS alloy with high strength and ductility for advanced reactor based on machine learning10.1080/00223131.2021.2004952 ↗
13. Structural damage identification based on autoencoder neural networks and deep learning10.1016/j.engstruct.2018.05.109 ↗
14. Artificial intelligence and machine learning in design of mechanical materials10.1039/D0MH01451F ↗
15. Metallurgy, mechanistic models and machine learning in metal printing10.1038/s41578-020-00236-1 ↗
16. Tensile property prediction by feature engineering guided machine learning in reduced activation ferritic/martensitic steels10.1016/j.jnucmat.2019.151823 ↗
17. Machine learning - assisted prediction of yield strength in irradiated type 316 stainless steels10.1016/j.fusengdes.2024.114691 ↗
18. Harnessing machine learning for predicting mechanical properties of lightweight Mg alloys10.1016/j.matlet.2024.137597 ↗
19. Preparation and property optimization of FeCrAl-based ODS alloy by machine learning combined with wedge-shaped hot-rolling10.1016/j.matchar.2022.111894 ↗
20. Prediction of hardness or yield strength for ODS steels based on machine learning10.1016/j.matchar.2024.113886 ↗
21. Explaining individual predictions when features are dependent: more accurate approximations to Shapley values10.1016/j.artint.2021.103502 ↗
22. Prediction and analysis of mechanical properties of hot-rolled strip steel based on an interpretable machine learning
23. Composition optimization of high strength and ductility ODS alloy based on machine learning10.1016/j.fusengdes.2020.111939 ↗
24. Scikit-learn: machine learning in python
25. Microstructure evolution and yield strength of CLAM steel in low irradiation condition10.1016/j.msea.2016.11.057 ↗
26. Plastic deformation behavior of metal materials: a review of constitutive models10.3390/met12122077 ↗
27. Plastic deformation behavior and constitutive modeling of Cu-50Ta alloy during hot compression10.1088/2053-1591/ac49bd ↗
28. Evaluation of thermal stability of ODS FeCrAl alloy at short-term high temperature10.1007/s11837-023-05783-w ↗
29. Early-stage thermal ageing behavior of 12Cr, 12Cr–7Al and 18Cr–9Al ODS steels10.1016/j.jnucmat.2020.152164 ↗
30. Selection of fuel cladding material for nuclear fission reactors10.1016/j.engfailanal.2011.06.010 ↗
31. Characterization and strengthening mechanism of high-strength medium carbon spring steels10.1016/j.jmrt.2023.09.314 ↗
32. Strengthening mechanisms and their relative contributions to the yield strength of microalloyed steels10.1007/s11661-012-1135-3 ↗
33. Effects of contents of Al, Zr and Ti on oxide particles in Fe–15Cr–2W–0.35Y2O3 ODS steels10.1016/j.jnucmat.2020.152025 ↗
34. Alloying design of oxide dispersion strengthened ferritic steel for long life FBRs core materials10.1016/0022-3115(93)90200-I ↗
35. Effects of titanium concentration and tungsten addition on the nano-mesoscopic structure of high-Cr oxide dispersion strengthened (ODS) ferritic steels10.1016/j.jnucmat.2013.04.090 ↗
36. Formation of Y2O3 nanoclusters in nano-structured ferritic alloys: modeling of precipitation kinetics and yield strength10.1016/j.jnucmat.2010.04.020 ↗
37. Atomic structure of nanoclusters in oxide-dispersion-strengthened steels10.1038/nmat3150 ↗
38. Kelly · 1971
39. Microstructure morphology and tensile properties of 9Cr-ODS steels added different Y2O3 contents
40. Effects of the forming processes and Y2O3 content on ODS-Eurofer mechanical properties10.1016/j.jnucmat.2008.12.177 ↗
41. Influence of yttria on oxide dispersion dtrengthened (ODS) ferritic steel10.1016/j.matpr.2017.11.646 ↗
42. The influence of Cr content on the mechanical properties of ODS ferritic steels10.1016/j.jnucmat.2014.05.061 ↗
43. Effects of Cr, Mo, Al, Zr, Y2O3 on the microstructures and tensile properties of ODS ferritic/martensitic alloys10.3365/KJMM.2014.52.9.705 ↗
44. Theoretical calculation of absolute radii of atoms and ions. Part 1. The atomic radii10.3390/i3020087 ↗
45. Effect of Ti and W on the mechanical properties and microstructure of 12% Cr base mechanical-alloyed nano-sized ODS ferritic alloys10.2355/isijinternational.43.1640 ↗
46. The effect of tungsten on microstructure and mechanical performance of an ultrafine Fe-Cr steel10.1016/j.matlet.2018.05.098 ↗
47. Eight routes to improve the tensile ductility of bulk nanostructured metals and alloys10.1007/s11837-006-0215-5 ↗
48. Effects of extrusion temperature on the nano-mesoscopic structure and mechanical properties of an Al-alloyed high-Cr ODS ferritic steel10.1016/j.jnucmat.2011.01.061 ↗
49. Hot deformation induced microstructural evolution in Fe14Cr ODS alloy manufactured by selective laser melting10.1016/j.intermet.2025.108736 ↗
50. Tailoring the secondary phases and mechanical properties of ODS steel by heat treatment10.1016/j.jmst.2018.12.008 ↗
51. Effects of sintering temperature and Y2O3/Ti addition on microstructure and hardness of ODS-AlCrFeNi HEAs10.1016/j.intermet.2022.107469 ↗
52. Role of Cr and Ti contents on the microstructure and mechanical properties of ODS ferritic steels
53. Vacancy mechanism of high oxygen solubility and nucleation of stable oxygen-enriched clusters in Fe10.1103/PhysRevLett.99.225502 ↗
54. Chemical and structural evolution of nano-oxides from mechanical alloying to consolidated ferritic oxide dispersion strengthened steel10.1016/j.actamat.2022.117992 ↗
55. Polymorphic and coherency transition of Y–Al complex oxide particles with extrusion temperature in an Al-alloyed high-Cr oxide dispersion strengthened ferritic steel10.1016/j.actamat.2010.10.026 ↗
56. Effects of hybrid alloy compositions on the dispersion morphology and crystal & interface structures of Y–O oxides in FeCrAl ODS steel10.1016/j.vacuum.2025.114323 ↗
57. Development and characterisation of a new ODS ferritic steel for fusion reactor application10.1016/j.jnucmat.2009.05.013 ↗
58. Hot compression bonding of a 9Cr oxide dispersion strengthened alloy and a 9Cr reduced-activation ferritic/martensitic alloy10.1016/j.jmst.2024.02.087 ↗
59. Development of oxide dispersion strengthened ferritic steel with enhanced strength–ductility combination through dispersion strengthening and back stress hardening10.1016/j.jmrt.2023.01.060 ↗
60. Microstructure and mechanical properties of thin-walled ODS ferritic steel tubes fabricated by a near-net forming method10.1016/j.msea.2024.146436 ↗
61. Effect of Y2Ti2O7 on microstructure and tensile properties of ODS-CLAM steel10.1016/j.jnucmat.2024.155208 ↗
62. Mechanical properties and microstructure of a FeCrAl-ODS alloy under long-term thermal aging at 700 °C up to 10000 h10.1016/j.jallcom.2025.179627 ↗
63. Creep behavior of a novel ODS ferrite steel reinforced with ultra-fine Y2(Zr0.6, Ti0.4)2O7 particles10.1016/j.matchar.2024.114231 ↗
64. Crystal and metal/oxide interface structures of nanoparticles in 15Cr–2W–0.1Ti–4Al–0.6Hf–0.35Y2O3 ODS steel10.1016/j.jnucmat.2020.152029 ↗
65. The mechanisms of microstructure formation in a nanostructured oxide dispersion strengthened FeAl alloy obtained by spark plasma sintering10.1016/j.intermet.2006.03.006 ↗
66. Stability of ferritic MA/ODS alloys at high temperatures10.1016/j.intermet.2004.07.036 ↗
67. Diffusion of yttrium in bcc-iron studied by kinetic Monte Carlo simulations10.1016/j.jnucmat.2017.07.021 ↗