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

Integration of machine learning (ML) into the topology optimization (TO)framework is attracting increasing attention, but data acquisition indata-driven models is prohibitive. Compared with popular ML methods, thephysics-informed neural network (PINN) can avoid generating enormous amounts ofdata when solving forward problems and additionally provide better inference.To this end, a dynamically configured PINN-based topology optimization(DCPINN-TO) method is proposed. The DCPINN is composed of two subnetworks,namely the backbone neural network (NN) and the coefficient NN, where thecoefficient NN has fewer trainable parameters. The designed architecture aimsto dynamically configure trainable parameters; that is, an inexpensive NN isused to replace an expensive one at certain optimization cycles. Furthermore,an active sampling strategy is proposed to selectively sample collocationsdepending on the pseudo-densities at each optimization cycle. In this manner,the number of collocations will decrease with the optimization process but willhardly affect it. The Gaussian integral is used to calculate the strain energyof elements, which yields a byproduct of decoupling the mapping of the materialat the collocations. Several examples with different resolutions validate thefeasibility of the DCPINN-TO method, and multiload and multiconstraint problemsare employed to illustrate its generalization. In addition, compared to finiteelement analysis-based TO (FEA-TO), the accuracy of the displacement predictionand optimization results indicate that the DCPINN-TO method is effective andefficient.

Dynamically configured physics-informed neural network in topology optimization applications