Global ETD Search

1	Nonlinear Methods of Aerodynamic Data-driven Reduced Order Modeling Forsberg, Arvid January 2022 (has links) Being able to accurately approximate outputs of computationally expensive simulations for arbitrary input parameters, also called missing points estimation, is central in many different areas of research and development with applications ranging from uncertainty propagation to control system design to name a few. This project investigates the potential of kernel transformations and nonlinear autoencoders as methods of improving the accuracy of the proper orthogonal decomposition method combined with regression. The techniques are applied on aerodynamic pressure CFD data around airplane wings in both two- and three-dimensional settings. The novel methods show potential in select situations, but cannot at this stage be generally considered superior. Their performances are similar although the procedure of design and training of a nonlinear autoencoder is less straight forward and more time demanding than using kernel transformations. The results demonstrate the regression bottleneck of the proper orthogonal decomposition method, which partially is improved with the new methods. Future studies should focus on adapting the autoencoder training strategy to the architecture and data as well as improving the regression stage of all methods. machine learning aerodynamics autoencoder kernel transformation principal component analysis nonlinear regression modeling surrogate model reduced order modeling neural network Engineering and Technology Teknik och teknologier Computational Mathematics Beräkningsmatematik Fluid Mechanics and Acoustics Strömningsmekanik och akustik

Search results

Nonlinear Methods of Aerodynamic Data-driven Reduced Order Modeling