EUVIMEDEUVIMED entdecken
Crossref

Target-adaptive, physics-informed machine learning for the simultaneous prediction of strength, hardness, and ductility in precipitation-hardening stainless steels

Jingwen Zhang, Jiaying Chen, Wei Zhang, Tao Xia, Wentao Zhou, Jiayu Guo, Nan Qu, Yong Liu, Jingchuan Zhu

Physica Scripta · 13.11.2026 · 101 (45) · 456001

DOI: 10.1088/1402-4896/aebbf8 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Physica Scripta, online erschienen am 12.11.2026. Verfasst von Jingwen Zhang und 8 weiteren Autor:innen. Die Arbeit nennt 44 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The mechanical properties of precipitation-hardening stainless steels (PHSS) are governed by the coupled effects of alloy chemistry, aging, matrix-phase stability, and atomic-scale thermodynamics, and therefore exhibit nonlinear behavior and pronounced trade-offs among strength, hardness, and ductility. Drawing on published literature and unpublished records from the authors’ research group, the datasets contain 310, 282, and 305 records for tensile strength (Rm), hardness, and elongation, respectively. Here, we develop a target-adaptive, interpretable machine-learning framework that couples composition and aging variables with descriptors of precipitation potential, phase stability, composition–aging interactions, and atomic, electronic, and thermodynamic characteristics. Independent feature-selection pipelines define property-specific descriptor spaces for Rm, Rockwell hardness (HRC), and elongation (A). Among six regressors, gradient-boosting regression trees achieve the most balanced performance across the three targets using an 80:20 record-random training/test split, with test-set R 2 values of 0.954, 0.948, and 0.937 and training-set five-fold out-of-fold cross-validation R 2 values of 0.880, 0.875, and 0.915 for Rm, HRC, and A, respectively. Shapley additive explanations reveal property-dependent, nonlinear attributions consistent with precipitation strengthening, aging-induced recovery, matrix stability, and solid-solution and diffusion-related effects, although these attributions do not by themselves constitute mechanistic evidence. The literature comparison shows predictive agreement for the sampled records within the represented composition–aging domain. The framework thus enables physically interpretable, multi-property prediction from heterogeneous, small-sample PHSS datasets. Given the limited AM coverage, this composition–aging framework may serve as a reference baseline for future AM-specific models that incorporate processing and microstructural variables.

Zitieren

APA

Zhang, J., Chen, J., Zhang, W., Xia, T., Zhou, W., Guo, J., Qu, N., Liu, Y., & Zhu, J. (2026). Target-adaptive, physics-informed machine learning for the simultaneous prediction of strength, hardness, and ductility in precipitation-hardening stainless steels. Physica Scripta, 101(45), 456001. https://doi.org/10.1088/1402-4896/aebbf8

Vancouver

Zhang J, Chen J, Zhang W, Xia T, Zhou W, Guo J, et al. Target-adaptive, physics-informed machine learning for the simultaneous prediction of strength, hardness, and ductility in precipitation-hardening stainless steels. Physica Scripta. 2026;101(45):456001. doi:10.1088/1402-4896/aebbf8

BibTeX
@article{Zhang2026,
  author = {Zhang, Jingwen and Chen, Jiaying and Zhang, Wei and Xia, Tao and Zhou, Wentao and Guo, Jiayu and Qu, Nan and Liu, Yong and Zhu, Jingchuan},
  title = {Target-adaptive, physics-informed machine learning for the simultaneous prediction of strength, hardness, and ductility in precipitation-hardening stainless steels},
  journal = {Physica Scripta},
  year = {2026},
  volume = {101},
  number = {45},
  pages = {456001},
  doi = {10.1088/1402-4896/aebbf8}
}
Kostenlos starten →