Machine learning-based multiphysics model for corrosion fatigue crack propagation in aluminum alloy

The present study predicted the corrosion fatigue crack growth rate of 7075-T7651 aluminum alloy under cyclic sinusoidal loading in an aqueous solution. A corrosion fatigue model of aluminum alloy coupled with chemical field, electric field, and mechanical field was established by combining the elec...

Full description

Saved in:
Bibliographic Details
Main Authors: Hongkun Wang, Zhenshuang Wu, Dongmei Jiang, Haitao Wang, En-Hou Han
Format: Article
Language:English
Published: Elsevier 2025-05-01
Series:Journal of Materials Research and Technology
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2238785425009780
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The present study predicted the corrosion fatigue crack growth rate of 7075-T7651 aluminum alloy under cyclic sinusoidal loading in an aqueous solution. A corrosion fatigue model of aluminum alloy coupled with chemical field, electric field, and mechanical field was established by combining the electrochemical Tafel equation, Nernst-Planck transport equation, and slip oxidation theory. The model considered the influence of cyclic loading on the corrosion fatigue crack growth rate and the convection between the crack interior and external environment caused by pumping effect. In view of the complexity and nonlinearity of model parameter optimization, a particle swarm optimization algorithm was utilized to mutually feedback experimental measurement results with simulation results, optimizing the unknown parameters in the model to obtain a high-fidelity corrosion fatigue model. The model simulated the hydrochemistry changes inside the crack in different solution environments over a certain period of time, and calculated that the crack growth rate is a function of environmental variables (pH value, sodium chloride concentration) and mechanical conditions (loading frequency, stress intensity factor range).
ISSN:2238-7854