Machine Learning-Based Multi-Objective Composition Optimization of High-Nitrogen Austenitic Stainless Steels
Materials · 03.12.2025 · 18 (23) · 5460
DOI: 10.3390/ma18235460 ↗Kurz gefasst
Fachartikel in der Zeitschrift Materials, online erschienen am 03.12.2025. Verfasst von Yinghu Wang und 5 weiteren Autor:innen. Beteiligte Einrichtung: National Center for Materials Service Safety, University of Science and Technology Beijing, Beijing 100083, China. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 60 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the Joint Training Scholarship for PhD/Master's Students, Joint Training Scholarship for PhD/Master’s Students in Key Industrial Sectors.
Abstract (Originalsprache)
High-nitrogen austenitic stainless steels (HNASS) require compositional strategies that simultaneously maximize corrosion resistance and microstructural stability while suppressing delta (δ) ferrite and deleterious precipitates. Here, an explainable multi-objective design workflow is developed that couples thermodynamic descriptors from the Calculation of Phase Diagrams (CALPHAD) approach—using both equilibrium and Scheil solidification calculations—with machine learning surrogate models, random forest (RF) and Extreme Gradient Boosting (XGBoost), trained on 60,480 compositions in the Fe–C–N–Cr–Mn–Mo–Ni–Si space. The physics-informed feature set comprises phase fractions; transformation and precipitation temperatures for δ-ferrite, chromium nitride (Cr2N), sigma (σ) phase and M23C6 carbides; liquidus and solidus temperatures; and the pitting-resistance equivalent number (PREN). The RF model achieves consistently low prediction errors, with a PREN root-mean-square error (RMSE) of ≈0.004, and exhibits strong generalization. Shapley additive explanations (SHAP) reveal metallurgically consistent trends: increasing nitrogen (N) suppresses δ-ferrite and promotes Cr2N; carbon (C) promotes M23C6; molybdenum (Mo) promotes the σ-phase; and C and silicon (Si) widen the freezing range. Using the trained surrogate as the objective evaluator, the non-dominated sorting genetic algorithm III (NSGA-III) builds Pareto fronts that minimize the δ-ferrite range, Cr2N, σ-phase, M23C6 and the freezing range (ΔT) while maximizing PREN. The Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) is then applied to rank the Pareto-optimal candidates and to select compositions that combine elevated PREN with controlled precipitation windows. This workflow is efficient, reproducible and interpretable and provides actionable composition candidates together with a transferable methodology for data-driven stainless steel design.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- National Center for Materials Service Safety, University of Science and Technology Beijing, Beijing 100083, China.
- Chengdu Institute of Advanced Metallic Material Technology and Industry Co., Ltd., Chengdu 610300, China.
- School of Materials Science and Engineering, Central South University, Changsha 410083, China.
ORCID-Profile: Yinghu Wang, Zhendong Sheng
Förderung
- the Joint Training Scholarship for PhD/Master's Students
- Joint Training Scholarship for PhD/Master’s Students in Key Industrial Sectors
Zitieren
APA
Wang, Y., Chen, L., Cheng, L., Wang, E., Sheng, Z., & Zhang, L. (2025). Machine Learning-Based Multi-Objective Composition Optimization of High-Nitrogen Austenitic Stainless Steels. Materials, 18(23), 5460. https://doi.org/10.3390/ma18235460
Vancouver
Wang Y, Chen L, Cheng L, Wang E, Sheng Z, Zhang L. Machine Learning-Based Multi-Objective Composition Optimization of High-Nitrogen Austenitic Stainless Steels. Materials. 2025;18(23):5460. doi:10.3390/ma18235460
BibTeX
@article{Wang2025,
author = {Wang, Yinghu and Chen, Long and Cheng, Limei and Wang, Enuo and Sheng, Zhendong and Zhang, Ligang},
title = {Machine Learning-Based Multi-Objective Composition Optimization of High-Nitrogen Austenitic Stainless Steels},
journal = {Materials},
year = {2025},
volume = {18},
number = {23},
pages = {5460},
doi = {10.3390/ma18235460}
}
EUVIMED