English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

In this paper, five different approaches for reduced-order modeling ofbrittle fracture in geomaterials, specifically concrete, are presented andcompared. Four of the five methods rely on machine learning (ML) algorithms toapproximate important aspects of the brittle fracture problem. In addition tothe ML algorithms, each method incorporates different physics-based assumptionsin order to reduce the computational complexity while maintaining the physicsas much as possible. This work specifically focuses on using the ML approachesto model a 2D concrete sample under low strain rate pure tensile loadingconditions with 20 preexisting cracks present. A high-fidelity finiteelement-discrete element model is used to both produce a training dataset of150 simulations and an additional 35 simulations for validation. Results fromthe ML approaches are directly compared against the results from thehigh-fidelity model. Strengths and weaknesses of each approach are discussedand the most important conclusion is that a combination of physics-informed anddata-driven features are necessary for emulating the physics of crackpropagation, interaction and coalescence. All of the models presented here haveruntimes that are orders of magnitude faster than the original high-fidelitymodel and pave the path for developing accurate reduced order models that couldbe used to inform larger length-scale models with important sub-scale physicsthat often cannot be accounted for due to computational cost.

Reduced-Order Modeling through Machine Learning Approaches for Brittle Fracture Applications