EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Predicting grain growth kinetic in steels using machine learning and XAI for mechanical properties

Selim Demirci, Durmuş Özkan Şahin iD, Sercan Demirci, Mehmet Masum Tünçay iD, Moataz M Attallah iD

PLOS One · 2026

DOI: 10.1371/journal.pone.0341053 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, 2026. Verfasst von Selim Demirci und 4 weiteren Autor:innen. Beteiligte Einrichtung: Marmara University, Faculty of Engineering, Department of Metallurgical and Materials Engineering, Istanbul, Turkey. Hauptthemen laut MEDLINE: Machine Learning, Stainless Steel. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 90 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Understanding and controlling grain growth kinetics in steels is crucial for optimizing mechanical properties during thermomechanical processing. However, traditional empirical models often fail to account for the complex, nonlinear interactions between alloying elements and processing parameters. In this study, we introduce a novel machine learning (ML) based framework that predicts austenitic grain growth behaviour directly from chemical composition and process conditions, utilizing a comprehensive dataset of 1039 experimentally validated samples. Among various algorithms tested, the XGBoost model demonstrated exceptional predictive capability, achieving an R 2 value of 0.9728 after hyperparameter optimization. Feature selection methods (Pearson correlation, CfsSubset, ReliefF) and SHAP-based explainable AI analyses were employed to identify the most influential parameters, revealing temperature, initial grain size, and holding time as dominant factors. Experimental validation was conducted on 316L stainless steel samples annealed at 1100 °C. The predicted grain sizes showed strong agreement with experimental measurements, and the observed hardness variations followed the expected Hall–Petch behaviour. This study demonstrates the first integrated ML and experimental approach for predicting grain growth kinetics in steels, offering a powerful tool for alloy design and process optimization. Future work will extend this framework to additional process variables and alloy systems.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningStainless SteelKineticsBoosting Machine Learning AlgorithmsPredictive Learning ModelsPrediction AlgorithmsTemperatureAlgorithmsHardness

Substanzen

Stainless Steel

Autor:innen und Institutionen

  • Marmara University, Faculty of Engineering, Department of Metallurgical and Materials Engineering, Istanbul, Turkey.
  • University of Birmingham, School of Metallurgy and Materials, Birmingham, United Kingdom.
  • Ondokuz Mayıs University, Faculty of Engineering, Department of Computer Engineering, Samsun, Turkey.

ORCID-Profile: Durmuş Özkan Şahin, Mehmet Masum Tünçay, Moataz M Attallah

Zitieren

APA

Demirci, S., Şahin, D. Ö., Demirci, S., Tünçay, M. M., & Attallah, M. M. (2026). Predicting grain growth kinetic in steels using machine learning and XAI for mechanical properties. PLOS One. https://doi.org/10.1371/journal.pone.0341053

Vancouver

Demirci S, Şahin DÖ, Demirci S, Tünçay MM, Attallah MM. Predicting grain growth kinetic in steels using machine learning and XAI for mechanical properties. PLOS One. 2026. doi:10.1371/journal.pone.0341053

BibTeX
@article{Demirci2026,
  author = {Demirci, Selim and Şahin, Durmuş Özkan and Demirci, Sercan and Tünçay, Mehmet Masum and Attallah, Moataz M},
  title = {Predicting grain growth kinetic in steels using machine learning and XAI for mechanical properties},
  journal = {PLOS One},
  year = {2026},
  doi = {10.1371/journal.pone.0341053}
}
Kostenlos starten →