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

Recently, physics informed neural networks (PINNs) have been exploredextensively for solving various forward and inverse problems and facilitatingquerying applications in fluid mechanics applications. However, work on PINNsfor unsteady flows past moving bodies, such as flapping wings is scarce.Earlier studies mostly relied on transferring to a body attached frame ofreference which is restrictive towards handling multiple moving bodies ordeforming structures. Hence, in the present work, an immersed boundary awareframework has been explored for developing surrogate models for unsteady flowspast moving bodies. Specifically, simultaneous pressure recovery and velocityreconstruction from Immersed boundary method (IBM) simulation data has beeninvestigated. While, efficacy of velocity reconstruction has been testedagainst the fine resolution IBM data, as a step further, the pressure recoveredwas compared with that of an arbitrary Lagrange Eulerian (ALE) based solver.Under this framework, two PINN variants, (i) a moving-boundary-enabled standardNavier-Stokes based PINN (MB-PINN), and, (ii) a moving-boundary-enabled IBMbased PINN (MB-IBM-PINN) have been formulated. A fluid-solid partitioning ofthe physics losses in MB-IBM-PINN has been allowed, in order to investigate theeffects of solid body points while training. This enables MB-IBM-PINN to matchwith the performance of MB-PINN under certain loss weighting conditions.MB-PINN is found to be superior to MB-IBM-PINN when {\it a priori} knowledge ofthe solid body position and velocity are available. To improve the dataefficiency of MB-PINN, a physics based data sampling technique has also beeninvestigated. It is observed that a suitable combination of physics constraintrelaxation and physics based sampling can achieve a model performancecomparable to the case of using all the data points, under a fixed trainingbudget.

Physics-informed neural networks modeling for systems with moving immersed boundaries: application to an unsteady flow past a plunging foil