journal article·2026-08-01Open access

Interpretable machine learning integrated with physicochemical feature for developing additively manufactured ultra-high strength and ductility steel

Yating Luo, Tao Zhu, Cunliang Pan, Xu Ben, Xudong An, Xiaoming Wang, Hongmei Zhu

Abstract

Abstract The multi-component complexity of ultra-high strength and ductility steels (UHSDS) imposes significant challenges for physical metallurgy-guided machine learning (ML) and CALPHAD-combined ML optimization design. Currently, the reported additively manufactured UHSDS necessitate multi-step heat treatments and expensive alloying elements while exhibiting poor corrosion resistance. In this study, a physicochemical feature-integrated, interpretable ML strategy was employed to design multi-component UHSDS fabricated via laser-directed energy deposition (LDED). SHapley additive exPlanation (SHAP) analysis was performed to reveal the critical intrinsic factors and their effects on the tensile mechanical performance, including ultimate tensile strength (UTS), yield strength (YS), and elongation (EL). Accordingly, the candidate alloying elements were identified, and a simple single-step tempering heat treatment was adopted, enabling the synchronous enhancement of strength and ductility. As a consequence, we designed a novel cost-effective and short-process LDEDed Fe-15Cr-3.2Ni-0.8Mn-0.6Cu-0.56Si-0.4Al-0.16C UHSDS, followed by tempering at 480 °C for 6 h. The as-tempered specimen mainly consisted of lath martensite, together with some austenite, carbides and nano-precipitates (AlN, NiAl, and ɛ-Cu). Both striking mechanical properties (i.e., UTS: (1 713 ± 17) MPa, YS: (1 502 ± 33) MPa, EL: (15.5 ± 0.7)%) and excellent corrosion resistance, with a corrosion rate of 0.105 mm·a −1 , have been achieved, superior to the reported additively manufactured UHSDS. The ultra-high strength and ductility are attributed to solid–solution strengthening, precipitate strengthening and transformation-induced plasticity (TRIP) effects. This work will be of great significance to provide new insights into the development of low-cost and process-simplified UHSDS, especially for the laser fabrication of high-value-added steel components with excellent comprehensive performance.
Source: crossref · Quality: baseline

Research context

OpenAlex topics: Additive Manufacturing Materials and Processes · High Entropy Alloys Studies · Surface Treatment and Residual Stress

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

References (89)

Show source-provided references
1. Programmable mechanical properties of additively manufactured novel steel10.1088/2631-7990/ad88bc ↗
2. Progress and perspectives in laser additive manufacturing of key aeroengine materials10.1016/j.ijmachtools.2021.103804 ↗
3. Additive manufacturing metallurgy guided machine learning design of versatile alloys10.1016/j.mattod.2025.06.031 ↗
4. Design and development of TiC-reinforced 410 martensitic stainless steel coatings fabricated by laser cladding10.1016/j.ceramint.2021.01.108 ↗
5. High-strength Damascus steel by additive manufacturing10.1038/s41586-020-2409-3 ↗
6. Effect of different heat input on the microstructure and mechanical properties of laser cladding repaired 300M steel10.1016/j.jmrt.2022.11.153 ↗
7. Hydrogen diffusion and trapping in laser additively manufactured ultra-high strength AerMet100 steel10.5006/3812 ↗
8. Microstructure and mechanical properties of laser solid formed 30Cr–Mn–Si–Ni–2A ultra-high-strength steel10.1080/13621718.2019.1592359 ↗
9. Laser powder bed fusion of ultra-high-strength 420 stainless steel: microstructure characterization, texture evolution and mechanical properties10.1016/j.msea.2021.140790 ↗
10. Machine learning enhanced metal 3D printing: high throughput optimization and material transfer extensibility10.1088/2631-7990/adbb96 ↗
11. Creep lifetime prediction of 9% Cr martensitic heat-resistant steel based on ensemble learning method10.1016/j.jmrt.2022.11.067 ↗
12. Physical metallurgy-guided machine learning and artificial intelligent design of ultrahigh-strength stainless steel10.1016/j.actamat.2019.08.033 ↗
13. Study on properties prediction and reverse design of weathering steel based on machine learning and multi-objective optimization10.3969/j.issn.1007-2012.2023.11.021 ↗
14. A strategy combining machine learning and physical metallurgical principles to predict mechanical properties for hot rolled Ti micro-alloyed steels10.1016/j.jmatprotec.2022.117810 ↗
15. Machine learning customized novel material for energy-efficient 4D printing10.1002/advs.202206607 ↗
16. An integrated design of novel RAFM steels with targeted microstructures and tensile properties using machine learning and CALPHAD10.20517/jmi.2024.44 ↗
17. SISSO: a compressed-sensing method for identifying the best low-dimensional descriptor in an immensity of offered candidates10.1103/PhysRevMaterials.2.083802 ↗
18. Dramatically enhanced combination of ultimate tensile strength and electric conductivity of alloys via machine learning screening10.1016/j.actamat.2020.09.068 ↗
19. Synchronously enhancing the strength, toughness, and stress corrosion resistance of high-end aluminum alloys via interpretable machine learning10.1016/j.actamat.2024.119873 ↗
20. A multi-objective feature optimization strategy for developing high-entropy alloys with optimal strength and ductility10.1002/mgea.70000 ↗
21. In-situ alloying modulation in additive manufacturing of titanium-tantalum alloy: from melt pool modelling to process development10.1016/j.mser.2025.101082 ↗
22. A reinforcement learning approach for process parameter optimization in additive manufacturing10.1016/j.addma.2023.103556 ↗
23. Additive manufacturing-by-design for support structures: a critical review10.1088/2631-7990/add4d2 ↗
24. Machine learning generative models for automatic design of multi-material 3D printed composite solids10.1016/j.eml.2020.100992 ↗
25. A unified approach to interpreting model predictions
26. An improved CCF detector to handle the problem of class imbalance with outlier normalization using IQR method10.3390/s23094406 ↗
27. Effect of Cu on the evolution of precipitation in an Fe–Cr–Ni–Al–Ti maraging steel10.1016/j.actamat.2010.03.010 ↗
28. Machine learning prediction of mechanical properties in metal additive manufacturing10.1016/j.addma.2024.104320 ↗
29. Coastal water quality prediction based on machine learning with feature interpretation and spatio-temporal analysis10.1016/j.envsoft.2022.105458 ↗
30. XGBoost: a scalable tree boosting system10.1145/2939672.2939785 ↗
31. Hybrid feature selection method based on the genetic algorithm and Pearson correlation coefficient10.1007/978-3-030-02357-7_1 ↗
32. Mean absolute percentage error for regression models10.1016/j.neucom.2015.12.114 ↗
33. Modified non-dominated sorting genetic algorithm III with fine final level selection10.1007/s10489-020-02053-z ↗
34. Development of high strength and ductile martensitic stainless steel coatings with Nb addition fabricated by laser cladding10.1016/j.jallcom.2020.154985 ↗
35. Laser cladding and in-situ nitriding of martensitic stainless steel coating with striking performance10.1016/j.matlet.2019.126829 ↗
36. Application of coefficient of variation in reliability-based mechanical design and manufacture10.1016/s0924-0136(01)00938-4 ↗
37. Heat-resistant aluminum alloy design using explainable machine learning10.1016/j.matdes.2024.113057 ↗
38. Composition design and optimization of Fe–C–Mn–Al steel based on machine learning10.1039/d3cp05453e ↗
39. Surrogate-assisted multi-objective optimization via knee-oriented Pareto front estimation10.1016/j.swevo.2023.101252 ↗
40. Novel machine learning driven design strategy for high strength Zn Alloys optimization with multiple constraints10.1038/s41524-025-01666-7 ↗
41. Superior strength-ductility in laser aided additive manufactured high-strength steel by combination of intrinsic tempering and heat treatment10.1080/17452759.2021.1964268 ↗
42. High strength X3NiCoMoTi 18-9-5 maraging steel prepared by selective laser melting from atomized powder10.3390/ma12244174 ↗
43. Additive manufacturing of corrosion-resistant maraging steel M789 by directed energy deposition10.1016/j.msea.2022.144032 ↗
44. Effect of retained austenite on subsequent thermal processing and resultant mechanical properties of selective laser melted 17-4 PH stainless steel10.1016/j.matdes.2015.05.026 ↗
45. Thermally driven changes in the microstructure and mechanical properties of martensitic 15-5 precipitation-hardened stainless steel during directed energy deposition10.1016/j.addma.2023.103729 ↗
46. Tempering effect on the anisotropic mechanical properties of selective laser melted 420 stainless steel10.1007/s11665-022-07450-8 ↗
47. Heat treatment behavior of the 18Ni300 maraging steel additively manufactured by selective laser melting10.4028/www.scientific.net/msf.941.2160 ↗
48. In-situ alloyed ultrahigh strength steels via additive manufacturing10.1016/j.addma.2023.103825 ↗
49. Effects of process variables on the quality and mechanical properties of 18%Ni-M350 maraging steel produced by direct energy deposition laser additive manufacturing10.1016/j.msea.2023.144646 ↗
50. Effect of quenching and tempering treatments on microstructure and mechanical properties of 300M ultra-high strength steel fabricated by laser powder bed fusion10.1016/j.matchar.2024.113935 ↗
51. Development of a new ultrafine grained dual phase steel and examination of the effect of grain size on tensile deformation behavior10.1016/j.msea.2014.01.053 ↗
52. Influence of martensite volume fraction and cooling rate on the properties of thermomechanically processed dual phase steel10.1016/j.msea.2012.01.010 ↗
53. Development and characterization of a novel maraging steel fabricated by laser additive manufacturing10.1016/j.msea.2023.145975 ↗
54. Effect of hydrogen on tensile properties and fracture behavior of PH 13-8 Mo steel10.1016/j.matdes.2016.06.110 ↗
55. Aging condition and trapped hydrogen effects on the mechanical behavior of a precipitation hardened martensitic stainless steel10.1016/j.jallcom.2019.07.112 ↗
56. Exploration of the processing scheme of a novel Ni(Fe, Al)-maraging steel10.1016/j.jmrt.2020.12.020 ↗
57. Effect of Cu addition on phase fraction, mechanical properties and corrosion properties of Fe–Cr–Mn–Al duplex stainless steel10.1016/j.msea.2022.144095 ↗
58. Effects of heat treatment on microstructure, mechanical properties and corrosion resistance 13Cr-2Ni-2Mo martensitic stainless steel10.1016/j.matchar.2025.114909 ↗
59. Formation and behaviour study of an environment-friendly corrosion inhibitor by electrochemical methods10.1016/j.electacta.2005.06.001 ↗
60. Microstructural evolution and its effect on corrosion behavior and mechanism of an austenite-based low-density steel during aging10.1016/j.corsci.2022.110936 ↗
61. Lide · 1997
62. Propagation velocity of longitudinal and transverse acoustic waves and anharmonicity of lattice oscillations10.1134/s1063784209090254 ↗
63. Physical properties of BaRu2X2 (X= P, As) superconducting compound sunder pressure effects: ab initio study10.1016/j.physc.2022.1354176 ↗
64. A comprehensive first-principles study of pure elements: vacancy formation and migration energies and self-diffusion coefficients10.1016/j.actamat.2016.02.031 ↗
65. Phase field theory of proper displacive phase transformations: structural anisotropy and directional flexibility, a vector model, and the transformation kinetics10.1016/j.actamat.2011.03.072 ↗
66. Evolution and strengthening of nanoprecipitates in a high strength maraging stainless steel10.1016/j.msea.2024.147198 ↗
67. Thermal conductivity and Lorenz ratio of metals at intermediate temperatures with mode-level first-principles analysis10.1103/physrevb.102.174306 ↗
68. Deviation from Matthiessen’s rule and lattice thermal conductivity of alloys10.1071/PH590199 ↗
69. Understanding the effect of Ni on mechanical and wear properties of low-carbon steel from a view-point of electron work function10.1007/s11661-018-4616-1 ↗
70. Enhanced strength-ductility synergy in L12-strengthened high-entropy alloys via precipitation-induced matrix thermodynamic tailoring10.1016/j.matchar.2025.115724 ↗
71. Fermi level, work function and vacuum level10.1039/c5mh00160a ↗
72. First-principles investigation on work function of martensitic carbon steels: effect of interstitial carbon on anodic dissolution resistance10.1149/1945-7111/ac3276 ↗
73. Static isotropic pressure induced semiconductor–metal transition and its impact on structural, electronic, elastic, mechanical and optical properties of SrCeO310.1140/epjp/s13360-023-04474-4 ↗
74. Study on the relationship between the refined hierarchical microstructure, yield strength and impact toughness of low-carbon martensitic steel at different quenching temperatures10.1016/j.msea.2024.146271 ↗
75. Effect of block size on the strength of lath martensite in low carbon steels10.1016/j.msea.2005.12.048 ↗
76. Formation of core-shell nanoprecipitates and their effects on work hardening in an ultrahigh-strength stainless steel10.1016/j.ijplas.2024.104184 ↗
77. Enhancing work hardening through tuning TRIP by nano-precipitates in maraging stainless steels10.1016/j.ijplas.2025.104265 ↗
78. Correlation between microstructure and yield strength of as-quenched and Q&P steels with different carbon content (0.06-0.42 wt%C)10.1016/j.msea.2019.03.018 ↗
79. Synergy of strengthening and toughening of a Cu-rich precipitate-strengthened steel10.1016/j.msea.2021.142487 ↗
80. Strengthening mechanisms in directed energy deposited austenitic stainless steel10.1016/j.actamat.2018.11.021 ↗
81. A model for the microstructure behaviour and strength evolution in lath martensite10.1016/j.actamat.2015.07.018 ↗
82. Callister · 2020
83. Simultaneous enhancement of strength-ductility via multiple precipitates and austenite in a novel precipitation-hardened martensitic stainless steel10.1016/j.msea.2023.145062 ↗
84. Microstructure evolution and strengthening behavior of maraging steel fabricated by wire arc additive manufacturing at different heat treatment processes10.1016/j.msea.2024.146804 ↗
85. Austenite and precipitation in secondary-hardening ultra-high-strength stainless steel10.1016/j.matchar.2018.07.038 ↗
86. Role of heat treatment conditions in the high-temperature deformation behavior of laser-powder bed fused Fe–Cr–Ni–Al maraging stainless steel10.1016/j.msea.2024.146837 ↗
87. Breaking strength-ductility trade-off in laser-powder bed fused Fe–Cr–Ni–Al maraging stainless steel: controlled precipitation and preserved dislocations10.1016/j.msea.2023.144761 ↗
88. Microstructure and corrosion resistance of low-carbon martensitic stainless steel 0Cr13Ni4Mo with 3% Cu addition10.11900/0412.1961.2022.00541 ↗
89. The co-precipitation evolution of NiAl and Cu nanoparticles and its influence on strengthening and toughening mechanisms in low-carbon ultra-high strength martensite seamless tube steel10.1016/j.ijplas.2023.103654 ↗