Fracture and Structural Integrity e-ISSN 1971-8993 Open access
Fatigue and Fracture of metallic alloys Vol. 20, No. 76 (2026)

Predicting fatigue limits of defective A356-T6 and A357-T6 cast aluminum alloys using a hybrid empirical–machine learning approach

Author and affiliation details
  • Nesrine Majed Corresponding author LGM, ENIM, University of Monastir, Avenue Ibn El Jazzar 5019, Monastir, Tunisia ORCID iD0009-0009-9157-8003 nesrine.majed@gmail.com
  • Anouar Nasr LGM, ENIM, University of Monastir, Avenue Ibn El Jazzar 5019, Monastir, Tunisia; IPEIM, University of Monastir, Avenue Ibn El Jazzar 5019, Monastir, Tunisia. ORCID iD0000-0002-2152-9910
  • Wided Bel Haj Sghaier Sup’Com, Université El Manar, Route de Raoued Km 3,5-2083, Ariana, Tunisia
  • Marwa Youssef LGM, ENIM, University of Monastir, Avenue Ibn El Jazzar 5019, Monastir, Tunisia ORCID iD0000-0002-4902-2097
DOI
10.3221/IGF-ESIS.76.16
Pages
265-276
Published
Licence
CC BY 4.0
Published inVol. 20, No. 76 (2026)Go to the issue

Abstract

The present study develops a knowledge-based machine learning framework for estimating the fatigue life of Al alloy using a combination of data-driven models and an empirical equation. Three different ML models were developed and tested, including Support Vector Regression, Random Forest and Gaussian Process Regression, to predict the fatigue limit for the spherical defective cast A356-T aluminum alloy, considering different Second Dendrite Army spacing (SDAS) values and different defect sizes. The effectiveness of the models is assessed using standard analytical metrics, like Root Mean Squared Error (RMSE) and R-squared ( ). With R² value 0.99, the SVR model outperformed the others.

Keywords

Article history

  1. ReceivedUntil the next stage: 34 days
  2. Revision requestedUntil the next stage: 77 days
  3. RevisedUntil the next stage: 16 days
  4. AcceptedUntil the next stage: 35 days
  5. Published

How to cite

APA

Majed, N., Nasr, A., Bel Haj Sghaier, W., & Youssef, M. (2026). Predicting fatigue limits of defective A356-T6 and A357-T6 cast aluminum alloys using a hybrid empirical–machine learning approach. Fracture and Structural Integrity, 20(76), 265–276. https://doi.org/10.3221/IGF-ESIS.76.16

IEEE

N. Majed, A. Nasr, W. Bel Haj Sghaier, and M. Youssef, “Predicting fatigue limits of defective A356-T6 and A357-T6 cast aluminum alloys using a hybrid empirical–machine learning approach,” Fracture and Structural Integrity, vol. 20, no. 76, pp. 265–276, 2026, doi: 10.3221/IGF-ESIS.76.16.

MLA

Majed, Nesrine, et al. “Predicting fatigue limits of defective A356-T6 and A357-T6 cast aluminum alloys using a hybrid empirical–machine learning approach.” Fracture and Structural Integrity, vol. 20, no. 76, 2026, pp. 265–276. https://doi.org/10.3221/IGF-ESIS.76.16.

Chicago

Majed, Nesrine, Anouar Nasr, Wided Bel Haj Sghaier, and Marwa Youssef. 2026. “Predicting fatigue limits of defective A356-T6 and A357-T6 cast aluminum alloys using a hybrid empirical–machine learning approach.” Fracture and Structural Integrity 20 (76): 265–276. https://doi.org/10.3221/IGF-ESIS.76.16.

Harvard

Majed, N., Nasr, A., Bel Haj Sghaier, W. and Youssef, M. (2026) ‘Predicting fatigue limits of defective A356-T6 and A357-T6 cast aluminum alloys using a hybrid empirical–machine learning approach’, Fracture and Structural Integrity, 20(76), pp. 265–276. doi: 10.3221/IGF-ESIS.76.16.

Vancouver

Majed N, Nasr A, Bel Haj Sghaier W, Youssef M. Predicting fatigue limits of defective A356-T6 and A357-T6 cast aluminum alloys using a hybrid empirical–machine learning approach. Fracture and Structural Integrity. 2026;20(76):265-276. doi:10.3221/IGF-ESIS.76.16

BibTeX

@article{majed2026, author = {Majed, Nesrine and Nasr, Anouar and Bel Haj Sghaier, Wided and Youssef, Marwa}, title = {Predicting fatigue limits of defective A356-T6 and A357-T6 cast aluminum alloys using a hybrid empirical–machine learning approach}, journal = {Fracture and Structural Integrity}, year = {2026}, volume = {20}, number = {76}, pages = {265--276}, doi = {10.3221/IGF-ESIS.76.16}, url = {https://doi.org/10.3221/IGF-ESIS.76.16}, issn = {1971-8993} }

RIS

TY - JOUR AU - Majed, Nesrine AU - Nasr, Anouar AU - Bel Haj Sghaier, Wided AU - Youssef, Marwa TI - Predicting fatigue limits of defective A356-T6 and A357-T6 cast aluminum alloys using a hybrid empirical–machine learning approach JO - Fracture and Structural Integrity T2 - Fracture and Structural Integrity PY - 2026 DA - 2026/03/18 VL - 20 IS - 76 SP - 265 EP - 276 DO - 10.3221/IGF-ESIS.76.16 UR - https://doi.org/10.3221/IGF-ESIS.76.16 SN - 1971-8993 ER -

Licence

Creative Commons Attribution 4.0 International

May be shared and adapted, provided appropriate credit is given. Copyright © 2026 Nesrine Majed, Anouar Nasr, Wided Bel Haj Sghaier, Marwa Youssef.

Copyright 
Authors are allowed to retain both the copyright and the publishing rights of their articles without restrictions.  

Open Access Statement

Fracture and Structural Integrity (F&SI) is an open-access journal which means that all content is freely available without charge to the user or his/her institution. Users are allowed to read, download, copy, distribute, print, search, or link to the full texts of the articles in this journal without asking prior permission from the publisher or the author. This is in accordance with the DOAI definition of open access.

F&SI operates under the Creative Commons Licence Attribution 4.0 International (CC-BY 4.0). This allows to copy and redistribute the material in any medium or format, to remix, transform and build upon the material for any purpose, even commercially, but giving appropriate credit, providing a link to the license, and indicating if changes were made.