Zobraziť v EDS

Efficient Coupling of Urban Wind Fields and Drone Flight Dynamics Using Convolutional Autoencoders

Uložené v:
Podrobná bibliografia
Názov: Efficient Coupling of Urban Wind Fields and Drone Flight Dynamics Using Convolutional Autoencoders
Autori: Zack Krawczyk, Ryan Paul, Kursat Kara
Zdroj: Drones, Vol 9, Iss 11, p 802 (2025)
Informácie o vydavateľovi: MDPI AG, 2025.
Rok vydania: 2025
Zbierka: LCC:Motor vehicles. Aeronautics. Astronautics
Predmety: urban wind fields, urban boundary layer, convolutional autoencoders, Reduced-Order Modeling (ROM), Non-Intrusive ROM, Large-Eddy Simulation (LES), Motor vehicles. Aeronautics. Astronautics, TL1-4050
Popis: Flight safety is central to the certification process and relies on assessment methods that provide evidence acceptable to regulators. For drones operating as Advanced Air Mobility (AAM) platforms, this requires an accurate representation of the complex wind fields in urban areas. Large-eddy simulations (LES) of such environments generate datasets from hundreds of gigabytes to several terabytes, imposing heavy storage demands and limiting real-time use in simulation frameworks. To address this challenge, we apply a Convolutional Autoencoder (CAE) to compress a 40 m-deep section of an LES wind field. The dataset size was reduced from 7.5 GB to 651 MB, corresponding to a 91% compression ratio, while maintaining maximum magnitude errors within a few tenths of the spatio-temporal wind velocity. Predicted vehicle responses showed only marginal differences, with close agreement between the full LES and CAE reconstructions. These findings demonstrate that CAEs can significantly reduce the computational cost of urban wind field integration without compromising fidelity, thereby enabling the use of larger domains in real-time and supporting efficient sharing of disturbance models in collaborative studies.
Druh dokumentu: article
Popis súboru: electronic resource
Jazyk: English
ISSN: 2504-446X
Relation: https://www.mdpi.com/2504-446X/9/11/802; https://doaj.org/toc/2504-446X
DOI: 10.3390/drones9110802
Prístupová URL adresa: https://doaj.org/article/1d4b41821c8e43b9bcc79eda0400cdc8
Prístupové číslo: edsdoj.1d4b41821c8e43b9bcc79eda0400cdc8
Databáza: Directory of Open Access Journals
Popis
Abstrakt:Flight safety is central to the certification process and relies on assessment methods that provide evidence acceptable to regulators. For drones operating as Advanced Air Mobility (AAM) platforms, this requires an accurate representation of the complex wind fields in urban areas. Large-eddy simulations (LES) of such environments generate datasets from hundreds of gigabytes to several terabytes, imposing heavy storage demands and limiting real-time use in simulation frameworks. To address this challenge, we apply a Convolutional Autoencoder (CAE) to compress a 40 m-deep section of an LES wind field. The dataset size was reduced from 7.5 GB to 651 MB, corresponding to a 91% compression ratio, while maintaining maximum magnitude errors within a few tenths of the spatio-temporal wind velocity. Predicted vehicle responses showed only marginal differences, with close agreement between the full LES and CAE reconstructions. These findings demonstrate that CAEs can significantly reduce the computational cost of urban wind field integration without compromising fidelity, thereby enabling the use of larger domains in real-time and supporting efficient sharing of disturbance models in collaborative studies.
ISSN:2504446X
DOI:10.3390/drones9110802