Mapping of in-plane biaxial fatigue crack propagation under different loading conditions using finite-element simulations and neural-network surrogate modelling

Purpose Under biaxial loading conditions, fatigue crack propagation can be very hard to predict, due to different possible propagation modes and the high number of parameters to consider. If mixed mode or out-of-phase conditions are present, crack deflection leads to many possible propagation paths and different failure locations. Therefore, predicting crack behaviour and fatigue life becomes essential if safer part design is to be achieved. This article aims to map crack propagation under different biaxial loading conditions, providing a database of paths and stress intensity factors that can be used as a reference for future part design. Design/methodology/approach To achieve this goal, an idealized reference model was created, where specimen-specific effects on crack propagation can be neglected. When subjected to different stress ratios, biaxial ratios and load phase-shifts, crack propagation was simulated using a previously developed finite element method algorithm. Findings Using randomized loading parameters, a large database was built considering two possible propagation modes. In the end, a machine learning model was used to interpolate the database, providing the full map of possible crack paths, displaying an accurate correlation against the finite element simulations. Originality/value The developed quasi-analytical model provides, for the first time, an extensive map for crack paths and crack driving forces under different biaxial conditions, while the developed machine learning solutions enable the full interpolation of the calculated map. These results enhance fatigue design and unlock optimal specimen development. Highlights:

Authors

Institutions

Publication Details

Journal
International Journal of Structural Integrity
Published
2026-11-16
DOI
https://doi.org/10.1108/ijsi-07-2026-0148
Primary Topic
Fatigue and fracture mechanics
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Mapping of in-plane biaxial fatigue crack propagation under different loading conditions using finite-element simulations and neural-network surrogate modelling

Ricardo Baptista, J.F.A. Madeira, V. Infante, P. Moita
1 links
International Journal of Structural Integrity
Fatigue and fracture mechanics
article

Mapping of in-plane biaxial fatigue crack propagation under different loading conditions using finite-element simulations and neural-network surrogate modelling

Ricardo Baptista, J.F.A. Madeira, V. Infante, P. Moita
article en

Abstract

Purpose Under biaxial loading conditions, fatigue crack propagation can be very hard to predict, due to different possible propagation modes and the high number of parameters to consider. If mixed mode or out-of-phase conditions are present, crack deflection leads to many possible propagation paths and different failure locations. Therefore, predicting crack behaviour and fatigue life becomes essential if safer part design is to be achieved. This article aims to map crack propagation under different biaxial loading conditions, providing a database of paths and stress intensity factors that can be used as a reference for future part design. Design/methodology/approach To achieve this goal, an idealized reference model was created, where specimen-specific effects on crack propagation can be neglected. When subjected to different stress ratios, biaxial ratios and load phase-shifts, crack propagation was simulated using a previously developed finite element method algorithm. Findings Using randomized loading parameters, a large database was built considering two possible propagation modes. In the end, a machine learning model was used to interpolate the database, providing the full map of possible crack paths, displaying an accurate correlation against the finite element simulations. Originality/value The developed quasi-analytical model provides, for the first time, an extensive map for crack paths and crack driving forces under different biaxial conditions, while the developed machine learning solutions enable the full interpolation of the calculated map. These results enhance fatigue design and unlock optimal specimen development. Highlights:

International Journal of Structural Integrity
Instituto de Engenharia de Sistemas e Computadores Investigação e Desenvolvimento (PT), University of Lisbon (PT), Universidade Politécnica de Lisboa (PT), Universidade Politécnica de Setúbal (PT), Instituto Superior Técnico (PT), Centro de Fisíca e Engenharia de Materiais Avançados (PT), Instituto Superior Técnico Instituto de Engenharia Mecânica (PT)
Fundação para a Ciência e a Tecnologia
Fatigue and fracture mechanics
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon