FIP-GNN: Graph neural networks for scalable prediction of grain-level fatigue indicator parameters

TL;DR

FIP-GNN is a graph neural network model that predicts grain-level fatigue indicators in polycrystals, enabling scalable and accurate fatigue life predictions for structural alloys.

Contribution

The paper introduces FIP-GNN, a novel graph neural network that accurately predicts local fatigue indicators and generalizes to larger microstructures, addressing scalability in fatigue modeling.

Findings

Accurately predicts grain-level fatigue indicators.

Generalizes predictions to larger microstructures.

Enhances computational efficiency in fatigue modeling.

Abstract

High-cycle fatigue is a critical performance metric of structural alloys for many applications. The high cost, time, and labor involved in experimental fatigue testing call for efficient and accurate computer models of fatigue life. We present FIP-GNN -- a graph neural network for polycrystals that (i) predicts fatigue indicator parameters as grain-level inelastic responses to cyclic loading quantifying the local driving force for crack initiation and (ii) generalizes these predictions to large microstructure volume elements with grain populations well beyond those used in training. These advances can make significant contributions to statistically rigorous and computationally efficient modeling of high-cycle fatigue -- a long-standing challenge in the field.