1
Return

Mechanics-guided hybrid neural modeling for fatigue life prediction: Integrating physics-based criteria with data-driven learning

delete2026-04-17
delete0
PRE
AI
E
Ehsan Akbari
T
T.N. Chakherlou *
H
Hesam Khajehsaeid
DOI：10.1016/j.advengsoft.2026.104180delete
deleteOriginal
deleteOriginal request for help
deleteShare
deleteSave
Abstract

Abstract

En 中文
• A Generalized Averaged Multiaxial Fatigue Criterion (GAMFC) is proposed. • GAMFC adaptively blends fatigue criteria to reduce bias and scatter. • A mechanics-guided neural model (GAMFC-PINN) enforces physical constraints. • Highest correlation and lowest error achieved with experimental results.
Keywords:
fatigue life prediction
generalized averaged multiaxial fatigue criterion
physics-informed neural networks
data-driven learning
mechanical modeling

Journal

Advances in Engineering Software cover
Advances in Engineering Software
IF:
5.7
Papers:
3.3K
Citations:
1.2W

Organization

U
University of Tabriz
Scholars:
9.0K
Papers: 8.4K
Citations: 1.0W
U
university of warwick
Scholars:
794
Papers: 441
Citations: 0
Cited Papers

Cited Papers

Citing Papers

Citing Papers