Print Email Facebook Twitter A Machine Learning Approach to Unresolved-Scale Modeling for Burgers’ Equation Title A Machine Learning Approach to Unresolved-Scale Modeling for Burgers’ Equation Author Robijns, Michel (TU Delft Aerospace Engineering) Contributor Hulshoff, S.J. (mentor) Dwight, R.P. (graduation committee) Chen, B. Y. (graduation committee) Degree granting institution Delft University of Technology Programme Aerospace Engineering Date 2019-04-15 Abstract This thesis is part of a greater effort to use machine learning for the development of flexible and universal unresolved-scale models in large eddy simulation (LES). The novelty in the current work is that a neural network learns to predict the integral forms of the unresolved-scale terms directly without a priori assumptions on the underlying functional relationship. The contribution of this thesis is a validation of a neural-network-based unresolved-scale model for Burgers' equation which paves the way for future application to the Navier-Stokes equations. Subject large eddy simulationLESmachine learningneural networksBurgers' equationvariational multiscale methodunresolved-scale modelsubgrid-scale modelturbulence modelingfinite element method To reference this document use: http://resolver.tudelft.nl/uuid:d79a48f4-de0b-45f0-b9ac-60e5455c85f3 Part of collection Student theses Document type master thesis Rights © 2019 Michel Robijns Files PDF MSc_Thesis_Michel_Robijns.pdf 1002.52 KB Close viewer /islandora/object/uuid:d79a48f4-de0b-45f0-b9ac-60e5455c85f3/datastream/OBJ/view