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, a mechanistic data-driven approach is proposed to acceleratestructural topology optimization, employing an in-house developed finiteelement convolutional neural network (FE-CNN). Our approach can be divided intotwo stages: offline training, and online optimization. During offline training,a mapping function is built between high and low resolution representations ofa given design domain. The mapping is expressed by a FE-CNN, which targets acommon objective function value (e.g., structural compliance) across designdomains of differing resolutions. During online optimization, an arbitrarydesign domain of high resolution is reduced to low resolution through thetrained mapping function. The original high-resolution domain is thus designedby computations performed on only the low-resolution version, followed by aninverse mapping back to the high-resolution domain. Numerical examplesdemonstrate that this approach can accelerate optimization by up to an order ofmagnitude in computational time. Our proposed approach therefore shows greatpotential to overcome the curse-of-dimensionality incurred by density-basedstructural topology optimization. The limitation of our present approach isalso discussed.

A mechanistic-based data-driven approach to accelerate structural topology optimization through finite element convolutional neural network (FE-CNN)