A probabilistic model for fast-to-evaluate 2D crack path prediction in heterogeneous materials

TL;DR

This paper introduces a fast probabilistic model for predicting 2D crack paths in heterogeneous materials, significantly reducing computation time while maintaining accuracy by using a Markov chain-based segmentation approach learned from detailed simulations.

Contribution

The paper presents a novel, efficient probabilistic model for crack path prediction that leverages Markov chains and machine learning from finite element simulations.

Findings

Model achieves faster predictions than full finite element simulations.

Crack paths are represented as piecewise linear segments with Markov chain-based segmentation.

Significant reduction in computational time compared to traditional simulation methods.

Abstract

This paper is devoted to the construction of a new fast-to-evaluate model for the prediction of 2D crack paths in concrete-like microstructures. The model generates piecewise linear cracks paths with segmentation points selected using a Markov chain model. The Markov chain kernel involves local indicators of mechanical interest and its parameters are learnt from numerical full-field 2D simulations of craking using a cohesive-volumetric finite element solver called XPER. The resulting model exhibits a drastic improvement of CPU time in comparison to simulations from XPER.