An interleaved physics-based deep-learning framework as a new cycle jumping approach for microstructurally small fatigue crack growth simulations

Abstract Conventional fracture mechanics asserts that the relevant physics governing small crack growth occurs near the crack front. However, for fatigue, computing these physics for each crack-growth increment over the entire microstructurally small crack regime is computationally intractable. Prop...

Full description

Saved in:
Bibliographic Details
Main Authors: Vignesh Babu Rao, Ashley D. Spear
Format: Article
Language:English
Published: Nature Portfolio 2025-08-01
Series:npj Computational Materials
Online Access:https://doi.org/10.1038/s41524-025-01741-z
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849234961468489728
author Vignesh Babu Rao
Ashley D. Spear
author_facet Vignesh Babu Rao
Ashley D. Spear
author_sort Vignesh Babu Rao
collection DOAJ
description Abstract Conventional fracture mechanics asserts that the relevant physics governing small crack growth occurs near the crack front. However, for fatigue, computing these physics for each crack-growth increment over the entire microstructurally small crack regime is computationally intractable. Properly trained deep-learning surrogate models can massively accelerate fatigue crack-growth predictions by virtually propagating an initial crack using micromechanical fields corresponding to just the initially cracked microstructure. As the predicted crack front advances, however, the fields no longer reflect relevant near-crack-front physics, leading to error and uncertainty accumulation. To address this, we present an interleaved physics-based deep-learning (PBDL) framework, where updates to the crack representation in the physics-based model are triggered intermittently using model uncertainty, thereby updating micromechanical fields passed to the deep-learning model. We show that this framework, representing a novel cycle-jumping approach, effectively limits error accumulation in history-dependent fatigue crack evolution and forms a template for other time-series applications in materials.
format Article
id doaj-art-f3ace7ff7d404a1d922944c09c082dfd
institution Kabale University
issn 2057-3960
language English
publishDate 2025-08-01
publisher Nature Portfolio
record_format Article
series npj Computational Materials
spelling doaj-art-f3ace7ff7d404a1d922944c09c082dfd2025-08-20T04:02:56ZengNature Portfolionpj Computational Materials2057-39602025-08-011111810.1038/s41524-025-01741-zAn interleaved physics-based deep-learning framework as a new cycle jumping approach for microstructurally small fatigue crack growth simulationsVignesh Babu Rao0Ashley D. Spear1Department of Mechanical Engineering, University of UtahDepartment of Mechanical Engineering, University of UtahAbstract Conventional fracture mechanics asserts that the relevant physics governing small crack growth occurs near the crack front. However, for fatigue, computing these physics for each crack-growth increment over the entire microstructurally small crack regime is computationally intractable. Properly trained deep-learning surrogate models can massively accelerate fatigue crack-growth predictions by virtually propagating an initial crack using micromechanical fields corresponding to just the initially cracked microstructure. As the predicted crack front advances, however, the fields no longer reflect relevant near-crack-front physics, leading to error and uncertainty accumulation. To address this, we present an interleaved physics-based deep-learning (PBDL) framework, where updates to the crack representation in the physics-based model are triggered intermittently using model uncertainty, thereby updating micromechanical fields passed to the deep-learning model. We show that this framework, representing a novel cycle-jumping approach, effectively limits error accumulation in history-dependent fatigue crack evolution and forms a template for other time-series applications in materials.https://doi.org/10.1038/s41524-025-01741-z
spellingShingle Vignesh Babu Rao
Ashley D. Spear
An interleaved physics-based deep-learning framework as a new cycle jumping approach for microstructurally small fatigue crack growth simulations
npj Computational Materials
title An interleaved physics-based deep-learning framework as a new cycle jumping approach for microstructurally small fatigue crack growth simulations
title_full An interleaved physics-based deep-learning framework as a new cycle jumping approach for microstructurally small fatigue crack growth simulations
title_fullStr An interleaved physics-based deep-learning framework as a new cycle jumping approach for microstructurally small fatigue crack growth simulations
title_full_unstemmed An interleaved physics-based deep-learning framework as a new cycle jumping approach for microstructurally small fatigue crack growth simulations
title_short An interleaved physics-based deep-learning framework as a new cycle jumping approach for microstructurally small fatigue crack growth simulations
title_sort interleaved physics based deep learning framework as a new cycle jumping approach for microstructurally small fatigue crack growth simulations
url https://doi.org/10.1038/s41524-025-01741-z
work_keys_str_mv AT vigneshbaburao aninterleavedphysicsbaseddeeplearningframeworkasanewcyclejumpingapproachformicrostructurallysmallfatiguecrackgrowthsimulations
AT ashleydspear aninterleavedphysicsbaseddeeplearningframeworkasanewcyclejumpingapproachformicrostructurallysmallfatiguecrackgrowthsimulations
AT vigneshbaburao interleavedphysicsbaseddeeplearningframeworkasanewcyclejumpingapproachformicrostructurallysmallfatiguecrackgrowthsimulations
AT ashleydspear interleavedphysicsbaseddeeplearningframeworkasanewcyclejumpingapproachformicrostructurallysmallfatiguecrackgrowthsimulations