Open Access

ARTICLE

Physics-Informed Neural Networks for Multiaxial Fatigue Life Prediction of Aluminum Alloy

Ehsan Akbari¹, Tajbakhsh Navid Chakherlou¹, Hamed Tabrizchi^2,3,*, Amir Mosavi^3,4,5,6

1 Faculty of Mechanical Engineering, University of Tabriz, Tabriz, 51666-16471, Iran
2 Department of Computer Science, Faculty of Mathematics, Statistics, and Computer Science, University of Tabriz, Tabriz, 51666-16471, Iran
3 Doctoral School of Applied Informatics and Applied Mathematics, John von Neumann Faculty of Informatics, Obuda University, Budapest, 1034, Hungary
4 Institute of the Information Society, Ludovika University of Public Service, Budapest, 1083, Hungary
5 Faculty of Innovative Technologies, Abylkas Saginov Karaganda Technical University, Karaganda, 100000, Kazakhstan
6 Faculty of Economics and Informatics, Univerzita J. Selyeho, Komarno, 945 01, Slovakia

* Corresponding Author: Hamed Tabrizchi. Email:

Computer Modeling in Engineering & Sciences 2025, 145(1), 305-325. https://doi.org/10.32604/cmes.2025.068581

Received 01 June 2025; Accepted 22 July 2025; Issue published 30 October 2025

Abstract

The ability to predict multiaxial fatigue life of Al-Alloy 7075-T6 under complex loading conditions is critical to assessing its durability under complex loading conditions, particularly in aerospace, automotive, and structural applications. This paper presents a physical-informed neural network (PINN) model to predict the fatigue life of Al-Alloy 7075-T6 over a variety of multiaxial stresses. The model integrates the principles of the Geometric Multiaxial Fatigue Life (GMFL) approach, which is a novel fatigue life prediction approach to estimating fatigue life by combining multiple fatigue criteria. The proposed model aims to estimate fatigue damage accumulation by the GMFL method. The proposed GMFL-PINN combines this physics-based approach with data-driven neural networks. Experimental validation demonstrates that GMFL-PINN outperforms FS, Smith–Watson–Topper (SWT) and Li–Zhang (LZH) fatigue life prediction methods which provides a reliable and scalable solution for structural health assessment and fatigue analysis.

---

Keywords

---