Print Email Facebook Twitter Latent Space Modelling of Unsteady Flow Subdomains Title Latent Space Modelling of Unsteady Flow Subdomains: Thesis Report Author Mulder, Boris (TU Delft Aerospace Engineering; TU Delft Aerodynamics) Contributor Hulshoff, Steven (mentor) Degree granting institution Delft University of Technology Programme Aerospace Engineering | Aerodynamics and Wind Energy Date 2019-06-28 Abstract Very complex flows can be expensive to compute using current CFD techniques. In this thesis, models based on deep learning were used to replace certain parts of the flow domain, with the objective of replacing well-known regions with simplified models to increase efficiency. To keep the error produced by the deep learning model bounded, a traditional CFD model and deep learning model were coupled using a boundary overlap area. In this overlap area, the flow computed by the traditional CFD model was used by the deep learning model as an input. It was demonstrated that since traditional CFD model continuously feeds in reliable information into the deep learning domain, the error remains bounded. Furthermore, it was found that the accuracy of the deep learning models depends significantly on the random initial weights. Therefore, deep learning models trained differently must be carefully compared. Subject AerodynamicsCFDDeep LearningLatent SpaceAutoencoderRecurrent Neural Network To reference this document use: http://resolver.tudelft.nl/uuid:fbf93d6e-211f-4b92-a057-956d694db315 Part of collection Student theses Document type master thesis Rights © 2019 Boris Mulder Files PDF Boris_Mulder_4100794_Thesis.pdf 2.79 MB Close viewer /islandora/object/uuid:fbf93d6e-211f-4b92-a057-956d694db315/datastream/OBJ/view