Title:
Shock Wave Prediction in Transonic Flow Fields using Domain-Informed Probabilistic Deep Learning

Simple item page
dc.contributor.author Mufti, Bilal
dc.contributor.author Bhaduri, Anindya
dc.contributor.author Ghosh, Sayan
dc.contributor.author Wang, Liping
dc.contributor.author Mavris, Dimitri N.
dc.contributor.corporatename Georgia Institute of Technology. School of Aerospace Engineering
dc.contributor.corporatename American Institute of Aeronautics and Astronautics
dc.date.accessioned 2024-01-11T14:29:21Z
dc.date.available 2024-01-11T14:29:21Z
dc.date.issued 2024-01
dc.description.abstract Transonic flow fields are marked by shock waves of varying strength and location and are crucial for the aerodynamic design and optimization of high-speed transport aircraft. While deep learning methods offer the potential for predicting these fields, their deterministic outputs often lack predictive uncertainty. Moreover, their accuracy, especially near critical shock regions, needs better quantification. In this paper, we introduce a domain-informed probabilistic (DIP) deep learning framework tailored for predicting transonic flow fields with shock waves called DIP-ShockNet. This methodology utilizes Monte Carlo Dropout (MCD) to estimate predictive uncertainty and enhances flow field predictions near the wall region by employing the inverse wall distance function (IWDF) based input representation of the aerodynamic flow field. The obtained results are benchmarked against the signed distance function (SDF) and the geometric mask input representations. The proposed framework further improves prediction accuracy in shock wave areas using a domain-informed loss function. To quantify the accuracy of our shock wave predictions, we developed metrics to assess errors in shock wave strength and location, achieving errors of 6.4% and 1%, respectively. Assessing the generalizability of our method, we tested it on different training sample sizes and compared it against the proper orthogonal decomposition (POD)-based reduced order model (ROM). Our results indicate that DIP-ShockNet outperforms POD-ROM by 60% in predicting the complete transonic flow field.
dc.identifier.citation Bilal, M., et al. "Shock Wave Prediction in Transonic Flow Fields using Domain-Informed Probabilistic Deep Learning". Phys. Fluids 36, 016121 (2024); doi: 10.1063/5.0185370
dc.identifier.doi https://doi.org/10.1063/5.0185370
dc.identifier.uri https://hdl.handle.net/1853/73225
dc.publisher Georgia Institute of Technology
dc.publisher.original American Institute of Aeronautics and Astronautics (AIAA)
dc.rights.metadata https://creativecommons.org/publicdomain/zero/1.0/
dc.subject Transonic flow field
dc.subject Shock wave
dc.subject Probabilistic deep learning
dc.subject Uncertainty quantification
dc.subject Domain informed loss
dc.title Shock Wave Prediction in Transonic Flow Fields using Domain-Informed Probabilistic Deep Learning
dc.type Text
dc.type.genre Post-print
dspace.entity.type Publication
local.contributor.author Mavris, Dimitri N.
local.contributor.corporatename College of Engineering
local.contributor.corporatename Aerospace Systems Design Laboratory (ASDL)
local.contributor.corporatename Daniel Guggenheim School of Aerospace Engineering
relation.isAuthorOfPublication d355c865-c3df-4bfe-8328-24541ea04f62
relation.isOrgUnitOfPublication 7c022d60-21d5-497c-b552-95e489a06569
relation.isOrgUnitOfPublication a8736075-ffb0-4c28-aa40-2160181ead8c
relation.isOrgUnitOfPublication a348b767-ea7e-4789-af1f-1f1d5925fb65
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Shock Wave Prediction in Transonic Flow Fields Accepted Manuscript.pdf
Size:
7.02 MB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
3.13 KB
Format:
Item-specific license agreed upon to submission
Description:
Download
Collections
Research Publications