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

Hybrid Optimization Software Suite (HOSS), which is a combinedfinite-discrete element method (FDEM), is one of the advanced approaches tosimulating high-fidelity fracture and fragmentation processes but theapplication of pure HOSS simulation is computationally expensive. At the sametime, machine learning methods, shown tremendous success in several scientificproblems, are increasingly being considered promising alternatives tophysics-based models in the scientific domains. Thus, our goal in this work isto build a new data-driven methodology to reconstruct the crack fractureaccurately in the spatial and temporal fields. We leverage physical constraintsto regularize the fracture propagation in the long-term reconstruction. Inaddition, we introduce perceptual loss and several extra pure machine learningoptimization approaches to improve the reconstruction performance of fracturedata further. We demonstrate the effectiveness of our proposed method throughboth extrapolation and interpolation experiments. The results confirm that ourproposed method can reconstruct high-fidelity fracture data over space and timein terms of pixel-wise reconstruction error and structural similarity. Visualcomparisons also show promising results in long-term

HOSSnet: an Efficient Physics-Guided Neural Network for Simulating Crack Propagation