EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Neural Network-Based Machine Learning Model for Spatiotemporal Prediction of Temperature and Fraction Solid in Low-Pressure Sand Casting

Ahmed Ktari, Souhail Housni, Jérémie Bourgeois, Mohamed El Mansori

Materials Science Forum · 20.04.2026 · 1188 · 1-10

DOI: 10.4028/p-otm77c ↗

Kurz gefasst

Fachartikel in der Zeitschrift Materials Science Forum, online erschienen am 20.04.2026. Verfasst von Ahmed Ktari und 3 weiteren Autor:innen. Die Arbeit nennt 14 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This paper presents a development methodology for a metamodel-based machine learning approach for spatiotemporal prediction of temperature and solid fraction evolution of aluminum castings during cooling under low pressure sand casting (LPSC) conditions, for various pouring temperatures ( T p ) ranging from 614°C to 720°C. High-fidelity finite element (FE) simulations were performed, based on a representative case study produced by the LPSC process to generate a comprehensive database, recording nodal temperatures across the casting symmetry plane at different cooling times, and for several T p values within the studied domain. Three different machine learning (ML) algorithms were evaluated using comparative metrics (R², MAE and MSE). Among the evaluated algorithms, the artificial neural network (ANN)-based ML model was selected for its superior predictive accuracy and robustness. The accuracy of the selected ML-model was assessed by comparing predicted and FE-simulated temperature fields. The results indicate that the predicted temperature error within the cast symmetry plane remains below 1%. Furthermore, a graphical user interface (GUI) was developed to visualize the predicted casting temperature field for different T p values not used during the learning stage, as well as the corresponding solid fraction, which is computed based on the solidification curve of the aluminum alloy AlSi 7 Mg 0.3 given by the ProCAST ® database. This methodology could provide a fast, robust, and scalable framework for extending predictive models to higher-dimensional cases and diverse LPSC casting process configurations.

Zitieren

APA

Ktari, A., Housni, S., Bourgeois, J., & Mansori, M. E. (2026). Neural Network-Based Machine Learning Model for Spatiotemporal Prediction of Temperature and Fraction Solid in Low-Pressure Sand Casting. Materials Science Forum, 1188, 1-10. https://doi.org/10.4028/p-otm77c

Vancouver

Ktari A, Housni S, Bourgeois J, Mansori ME. Neural Network-Based Machine Learning Model for Spatiotemporal Prediction of Temperature and Fraction Solid in Low-Pressure Sand Casting. Materials Science Forum. 2026;1188:1-10. doi:10.4028/p-otm77c

BibTeX
@article{Ktari2026,
  author = {Ktari, Ahmed and Housni, Souhail and Bourgeois, Jérémie and Mansori, Mohamed El},
  title = {Neural Network-Based Machine Learning Model for Spatiotemporal Prediction of Temperature and Fraction Solid in Low-Pressure Sand Casting},
  journal = {Materials Science Forum},
  year = {2026},
  volume = {1188},
  pages = {1--10},
  doi = {10.4028/p-otm77c}
}
Kostenlos starten →