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

Despite their recent success, machine learning (ML) models such as graphneural networks (GNNs), suffer from drawbacks such as the need for largetraining datasets and poor performance for unseen cases. In this work, we usetransfer learning (TL) approaches to circumvent the need for retraining withlarge datasets. We apply TL to an existing ML framework, trained to predictmultiple crack propagation and stress evolution in brittle materials underMode-I loading. The new framework, ACCelerated Universal fRAcTure Emulator(ACCURATE), is generalized to a variety of crack problems by using a sequenceof TL update steps including (i) arbitrary crack lengths, (ii) arbitrary crackorientations, (iii) square domains, (iv) horizontal domains, and (v) shearloadings. We show that using small training datasets of 20 simulations for eachTL update step, ACCURATE achieved high prediction accuracy in Mode-I andMode-II stress intensity factors, and crack paths for these problems. %casestudies (i) - (iv). We demonstrate ACCURATE's ability to predict crack growthand stress evolution with high accuracy for unseen cases involving thecombination of new boundary dimensions with arbitrary crack lengths and crackorientations in both tensile and shear loading. We also demonstratesignificantly accelerated simulation times of up to 2 orders of magnitudefaster (200x) compared to an XFEM-based fracture model. The ACCURATE frameworkprovides a universal computational fracture mechanics model that can be easilymodified or extended in future work.

A generalized machine learning framework for brittle crack problems using transfer learning and graph neural networks