Multi-objective optimization of corrosion resistance, strength, ductility properties of weathering steel utilizing interpretable attention-based deep learning model
Source abstract
Abstract
A high-performance, low-cost weathering steel was developed using a deep learning-based interpretable Attention mechanism, which identifies key compositional factors and captures complex feature interactions. By revealing the intrinsic drivers of strength, ductility, and corrosion resistance, and introducing a utility function to balance performance and cost, the newly designed steel achieved a UTS of 837 MPa, 20% elongation, and a corrosion rate of 0.54 g/(m 2 ·h) after 576 hours in a simulated marine environment, demonstrating excellent overall properties.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Hydrogen embrittlement and corrosion behaviors in metals · Machine Learning in Materials Science · Welding Techniques and Residual Stresses
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (61)
Show source-provided references
1. Qin, L. et al. Study of the mechanism influencing the initial corrosion behaviour of b2 phase fe-mn-al-C-ni lightweight steels in 3.5% NaCl solution. Jom 75, 2212–2224 (2023).10.1007/s11837-023-05753-2 ↗
2. Wu, W., Qin, L., Cheng, X., Xu, F. & Li, X. Microstructural evolution and its effect on corrosion behavior and mechanism of an austenite-based low-density steel during aging. Corros. Sci. 212, 110936 (2023).10.1016/j.corsci.2022.110936 ↗
3. Pathirana, M., Laleh, M., Somers, A., Hinton, B. & Tan, M. Y. The critical effect of rust layers on localised corrosion of steel exposed to waterline environments. Corros. Sci. 221, 111333 (2023).10.1016/j.corsci.2023.111333 ↗
4. Jiang, B., Doi, K. & Tsuchiya, K. Characterization of microstructures and micromechanical properties of naturally generated rust layer in 60-year old reinforced concrete. Constr. Build. Mater. 366, 130203 (2023).10.1016/j.conbuildmat.2022.130203 ↗
5. Zhao, T., Liu, K. & Li, Q. Comparison of the rusting behaviors of S450EW weathering steel under continuous spray and wet/dry cycling. Constr. Build. Mater. 309, 125211 (2021).10.1016/j.conbuildmat.2021.125211 ↗
6. Yang, F., Han, J., Yang, J. & Li, Z. Study on the application of weathering and cold-formed steel in transmission tower. 2009 Asia-Pac. Power Energy Eng. Conf. (Appeec), 1-7, 2395–2398 (2009).
7. Zhang, T., Xu, X., Li, Y. & Lv, X. The function of cr on the rust formed on weathering steel performed in a simulated tropical marine atmosphere environment. Constr. Build. Mater. 277, 122298 (2021).10.1016/j.conbuildmat.2021.122298 ↗
8. Fan, Y. et al. Effect of chloride ion on corrosion resistance of ni-advanced weathering steel in simulated tropical marine atmosphere. Constr. Build. Mater. 266, 120937 (2021).10.1016/j.conbuildmat.2020.120937 ↗
9. Sun, Y. et al. The dual nature of cu content on the corrosion resistance of low alloy steels in sulfuric acid: A time-dependent reversal of corrosion resistance. Corros. Sci. 224, 111486 (2023).10.1016/j.corsci.2023.111486 ↗
10. Zhang, Y. Zheng, K. Zhu, J. Lei, M. Feng, X. Research on corrosion and fatigue performance of weathering steel and high-performance steel for bridges. Constr. Build. Mater. 289, 123108 (2021).10.1016/j.conbuildmat.2021.123108 ↗
11. Hu, Q. et al. Corrosion failure analysis of engineering structural steels in tropical marine atmospheres: A comparative study of ordinary and new weathering steels. Eng. Fail. Anal. 156, 107830 (2024).10.1016/j.engfailanal.2023.107830 ↗
12. Hu, H. et al. The effects of Nb and Mo addition on transformation and properties in low carbon bainitic steels. Mater. Des. 84, 95–99 (2015).10.1016/j.matdes.2015.06.133 ↗
13. Guo, X. et al. High-throughput screening of green amino acid and surfactant mixtures with high corrosion inhibition efficiency: Experimental and modelling perspectives. Corros. Sci. 240, 112460 (2024).10.1016/j.corsci.2024.112460 ↗
14. Morcillo, M., Díaz, I., Chico, B., Cano, H. & De La Fuente, D. Weathering steels: From empirical development to scientific design. a review. Corros. Sci. 83, 6–31 (2014).10.1016/j.corsci.2014.03.006 ↗
15. Tian, J., Xu, G., Zhou, M., Hu, H. & Xue, Z. Effects of Al addition on bainite transformation and properties of high-strength carbide-free bainitic steels. J. Iron Steel Res. Int. 26, 846–855 (2019).10.1007/s42243-019-00253-7 ↗
16. Jia, J., Liu, Z., Cheng, X., Du, C. & Li, X. Development and optimization of Ni-advanced weathering steel: A review. Corros. Commun. 2, 82–90 (2021).10.1016/j.corcom.2021.09.003 ↗
17. Shi, B. et al. Exploring corrosion protection evolution of rust layer on high-Cr-content weathering bridge steel in simulated tropical marine atmosphere. Int. J. Miner., Metall., Mater. https://doi.org/10.1007/s12613-024-3069-3 (2024).10.1007/s12613-024-3069-3 ↗
18. Cheng, P., Liu, J., Huang, X., Huang, F. & Pang, T. Effect of silicon on the corrosion behaviour of 690 MPa weathering bridge steel in simulated industrial atmosphere. Constr. Build. Mater. 328, 127030 (2022).10.1016/j.conbuildmat.2022.127030 ↗
19. Qin, L. et al. Effect of Sn on the rust layer structure of new high-Cr-content steels in a high chloride ion concentration environment. Mater. Charact. 224, 114981 (2025).10.1016/j.matchar.2025.114981 ↗
20. Ishikawa, T., Takeuchi, K., Kandori, K. & Nakayama, T. Transformation of γ-FeOOH to α-FeOOH in acidic solutions containing metal ions. Colloids Surf., A: Physicochemical Eng. Asp. 266, 155–159 (2005).10.1016/j.colsurfa.2005.06.024 ↗
21. Feng, Y. et al. Improvement of strength in low-carbon Nb–Ti weathering steel through Ce microalloying. J. Mater. Res. Technol. 33, 2136–2152 (2024).10.1016/j.jmrt.2024.09.221 ↗
22. Tang, Y. et al. Optimizing the corrosion performance of rust layers: Role of Al and Mn in lightweight weathering steel. Npj Mater. Degrad. 8, 32 (2024).10.1038/s41529-024-00450-0 ↗
23. Chen, Y. Y. et al. Corrosion resistance and mechanical properties of low-alloy steels under atmospheric conditions. Corros. Sci. 47, 1001–1021 (2005).10.1016/j.corsci.2004.04.009 ↗
24. Yang, X. et al. A new understanding of the effect of cr on the corrosion resistance evolution of weathering steel based on big data technology. J. Mater. Sci. Technol. 104, 67–80 (2022).10.1016/j.jmst.2021.05.086 ↗
25. Sun, B., Zuo, X., Cheng, X. & Li, X. The role of chromium content in the long-term atmospheric corrosion process. Npj Mater. Degrad. 4, 37 (2020).10.1038/s41529-020-00142-5 ↗
26. Cheng, X., Jin, Z., Liu, M. & Li, X. Optimizing the nickel content in weathering steels to enhance their corrosion resistance in acidic atmospheres. Corros. Sci. 115, 135–142 (2017).10.1016/j.corsci.2016.11.016 ↗
27. Eswarappa Prameela, S. et al. Materials for extreme environments. Nat. Rev. Mater. 8, 81–88 (2022).10.1038/s41578-022-00496-z ↗
28. Hart, G. L. W., Mueller, T., Toher, C. & Curtarolo, S. Machine learning for alloys. Nat. Rev. Mater. 6, 730–755 (2021).10.1038/s41578-021-00340-w ↗
29. Jiang, L. et al. Synchronously enhancing the strength, toughness, and stress corrosion resistance of high-end aluminum alloys via interpretable machine learning. Acta Mater 270, 119873 (2024).10.1016/j.actamat.2024.119873 ↗
30. Zhang, H. et al. Dramatically enhanced combination of ultimate tensile strength and electric conductivity of alloys via machine learning screening. Acta Mater 200, https://doi.org/10.1016/j.actamat.2020.09.068 (2020).10.1016/j.actamat.2020.09.068 ↗
31. Zhang, H., Fu, H., Zhu, S., Yong, W. & Xie, J. Machine learning assisted composition effective design for precipitation strengthened copper alloys. Acta Mater 215, 117118 (2021).10.1016/j.actamat.2021.117118 ↗
32. Zhang, Y. et al. A multi‐objective feature optimization strategy for developing high‐entropy alloys with optimal strength and ductility. Mater. Genome Eng. Adv. 3, e70000 (2025).10.1002/mgea.70000 ↗
33. Hu, M. et al. Recent applications of machine learning in alloy design: A review. Mater. Sci. Eng.: R: Rep. 155, 100746 (2023).10.1016/j.mser.2023.100746 ↗
34. Sasidhar, K. N. et al. Enhancing corrosion-resistant alloy design through natural language processing and deep learning. Sci. Adv. 9, eadg7992 (2023).10.1126/sciadv.adg7992 ↗
35. Gao, Z., Jiang, W., Wu, J., Wang, Y. & Zhu, H. A customized dual-transformer framework for remaining useful life prediction of mechanical systems with degraded state. Mech. Syst. Signal Process. 230, 112611 (2025).10.1016/j.ymssp.2025.112611 ↗
36. Gao, Z. et al. VSC-Net: Versatile spatiotemporal convolution network with multi-sensor signals for remaining useful life prediction of mechanical systems. Inf. Fusion 123, 103288 (2025).10.1016/j.inffus.2025.103288 ↗
37. Tian, S. et al. Steel design based on a large language model. Acta Mater 285, 120663 (2025).10.1016/j.actamat.2024.120663 ↗
38. Vaswani, A. et al. Attention is all you need. Adv. Neural Inform. Process. Syst. 30, http://arxiv.org/abs/1706.03762 (2017).
39. Zhang, J. et al. Design high-entropy electrocatalyst via interpretable deep graph attention learning. Joule 7, 1832–1851 (2023).10.1016/j.joule.2023.06.003 ↗
40. Liu, C. et al. Towards a better understanding of localised corrosion induced by typical non-metallic inclusions in low-alloy steels. Corros. Sci. 179, 109150 (2021).10.1016/j.corsci.2020.109150 ↗
41. Dong, B. et al. Clarifying the effect of a small amount of cr content on the corrosion of ni-mo steel in tropical marine atmospheric environment. Corros. Sci. 210, 110813 (2023).10.1016/j.corsci.2022.110813 ↗
42. Jia, J., Cheng, X., Yang, X., Li, X. & Li, W. A study for corrosion behavior of a new-type weathering steel used in harsh marine environment. Constr. Build. Mater. 259, 119760 (2020).10.1016/j.conbuildmat.2020.119760 ↗
43. Nakayama, T., Ishikawa, T. & Konno, T. J. Structure of titanium-doped goethite rust. Corros. Sci. 47, 2521–2530 (2005).10.1016/j.corsci.2004.11.030 ↗
44. Lide, D. R. (Ed.). CRC handbook of chemistry and physics: a ready-reference book of chemical and physical data. (CRC press, 1995).
45. Hou, Y. & Cheng, G. Effect of Nb on the As-cast structure and compactness degree of ferritic stainless steel dual stabilized by Ti and Nb. ISIJ Int. 58, 2298–2307 (2018).10.2355/isijinternational.ISIJINT-2017-595 ↗
46. Pineau, A., Benzerga, A. A. & Pardoen, T. Failure of metals I: Brittle and ductile fracture. Acta Materialia 107, 424–483 (2016).10.1016/j.actamat.2015.12.034 ↗
47. Costa E Silva, A. L. V. D. The effects of non-metallic inclusions on properties relevant to the performance of steel in structural and mechanical applications. J. Mater. Res. Technol. 8, 2408–2422 (2019).10.1016/j.jmrt.2019.01.009 ↗
48. Lajarin, S. F., Nikhare, C. P. & Marcondes, P. V. P. Dependence of plastic strain and microstructure on elastic modulus reduction in advanced high-strength steels. J. Braz. Soc. Mech. Sci. Eng. 40, 87 (2018).10.1007/s40430-018-1008-9 ↗
49. Liu, W. et al. Synergisic effect of mn, cu, P with cr content on the corrosion behavior of weathering steel as a train under the simulated industrial atmosphere. J. Alloy. Compd. 834, 155095 (2020).10.1016/j.jallcom.2020.155095 ↗
50. Wei, Y. et al. Evading the strength–ductility trade-off dilemma in steel through gradient hierarchical nanotwins. Nat. Commun. 5, 3580 (2014).10.1038/ncomms4580 ↗
51. Wu, W. et al. Corrosion and SCC initiation behavior of low-alloy high-strength steels microalloyed with Nb and Sb in a simulated polluted marine atmosphere. J. Mater. Res. Technol. 9, 12976–12995 (2020).10.1016/j.jmrt.2020.09.033 ↗
52. Ong, S. P. et al. Python materials genomics (pymatgen): A robust, open-source python library for materials analysis. Computational Mater. Sci. 68, 314–319 (2013).10.1016/j.commatsci.2012.10.028 ↗
53. Neumann, G. & Tuijn, C. Self-diffusion and impurity diffusion in pure metals: Handbook of experimental data. (Elsevier, 2011).
54. Groover, R. E., Smith, J. A. & Lennox, T. J. Electrochemical potentials of high purity metals in sea water. Corrosion 28, 101–104 (1972).10.5006/0010-9312-28.3.101 ↗
55. Bratsch, S. G. Standard electrode potentials and temperature coefficients in water at 298.15 K. J. Phys. Chem. Ref. Data 18, 1–21 (1989).10.1063/1.555839 ↗
56. Zheng, H. et al. Grain boundary properties of elemental metals. Acta Mater 186, 40–49 (2020).10.1016/j.actamat.2019.12.030 ↗
57. Baldi, P. & Sadowski, P. J. Understanding Dropout. Adv. Neural Inform. Process. Syst. 26. https://proceedings.neurips.cc/paper/2013/hash/71f6278d140af599e06ad9bf1ba03cb0-Abstract.html (2013).
58. Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I. & Salakhutdinov, R. Dropout: A simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15, 1929–1958 (2014).
59. Ng, A. Y. Feature selection, L 1 vs. L 2 regularization, and rotational invariance. Proc. ICML 2004 78, https://doi.org/10.1145/1015330.1015435 (2004).10.1145/1015330.1015435 ↗
60. Sun, M. et al. Fundamental understanding on the effect of Cr on corrosion resistance of weathering steel in simulated tropical marine atmosphere. Corros. Sci. 186, 109427 (2021).10.1016/j.corsci.2021.109427 ↗
61. Feng, Y., Bai, Z., Chen, L. & Wei, D. Correlation of Indoor Accelerated Corrosion with Outdoor Exposure for Corten-A Weathering Steel in Polluted Marine Atmospheric Environments. J. Chin. Soc. Corros. Prot. 39, 519–526 (2019).