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

Design and analysis of inelastic materials requires prediction of physicalresponses that evolve under loading. Numerical simulation of such behaviorusing finite element (FE) approaches can call for significant time andcomputational effort. To address this challenge, this paper demonstrates a deeplearning (DL) framework that is capable of predicting micro-scaleelasto-plastic strains and stresses in a two-phase medium, at a much greaterspeed than traditional FE simulations. The proposed framework uses a deepconvolutional neural network (CNN), specifically a U-Net architecture with 3Doperations, to map the composite microstructure to the corresponding stress andstrain fields under a predetermined load path. In particular, the model isapplied to a two-phase fiber reinforced plastic (FRP) composite microstructuresubjected to a given loading-unloading path, predicting the correspondingstress and strain fields at discrete intermediate load steps. A novel two-steptraining approach provides more accurate predictions of stress, by firsttraining the model to predict strain fields and then using those strain fieldsas input to the model that predicts the stress fields. This efficientdata-driven approach enables accurate prediction of physical fields ininelastic materials, based solely on microstructure images and loadinginformation.

Prediction of local elasto-plastic stress and strain fields in a two-phase composite microstructure using a deep convolutional neural network