Denoising the Design Space: Diffusion Models for Accelerated Airfoil Shape Optimization

dc.contributor.advisorFuge, Mark Den_US
dc.contributor.authorDiniz, Cashenen_US
dc.contributor.departmentMechanical Engineeringen_US
dc.contributor.publisherDigital Repository at the University of Marylanden_US
dc.contributor.publisherUniversity of Maryland (College Park, Md.)en_US
dc.date.accessioned2024-07-02T05:37:15Z
dc.date.available2024-07-02T05:37:15Z
dc.date.issued2024en_US
dc.description.abstractGenerative models offer the possibility to accelerate and potentially substitute parts of the often expensive traditional design optimization process. We present Aero-DDM, a novel application of a latent denoising diffusion model (DDM) capable of generating airfoil geometries conditioned on flow parameters and an area constraint. Additionally, we create a novel, diverse dataset of optimized airfoil designs that better reflects a realistic design space than has been done in previous work. Aero-DDM is applied to this dataset, and key metrics are assessed both statistically and with an open-source computational fluid dynamics (CFD) solver to determine the performance of the generated designs. We compare our approach to an optimal transport GAN, and demonstrate that our model can generate designs with superior performance statistically, in aerodynamic benchmarks, and in warm-start scenarios. We also extend our diffusion model approach, and demonstrate that the number of steps required for inference can be reduced by as much as ~86%, compared to an optimized version of the baseline inference process, without meaningful degradation in design quality, simply by using the initial design to start the denoising process.en_US
dc.identifierhttps://doi.org/10.13016/l3ax-p5gp
dc.identifier.urihttp://hdl.handle.net/1903/33032
dc.language.isoenen_US
dc.subject.pqcontrolledAerospace engineeringen_US
dc.subject.pqcontrolledArtificial intelligenceen_US
dc.subject.pqcontrolledDesignen_US
dc.subject.pquncontrolledAircraft Designen_US
dc.subject.pquncontrolledComputational Fluid Dynamics (CFD)en_US
dc.subject.pquncontrolledDiffusion Modelsen_US
dc.subject.pquncontrolledGenerative Modelsen_US
dc.subject.pquncontrolledMachine Learningen_US
dc.subject.pquncontrolledNumerical Optimizationen_US
dc.titleDenoising the Design Space: Diffusion Models for Accelerated Airfoil Shape Optimizationen_US
dc.typeThesisen_US

Files

Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
Diniz_umd_0117N_24313.pdf
Size:
6.29 MB
Format:
Adobe Portable Document Format