h1

% IMPORTANT: The following is UTF-8 encoded.  This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.

@MASTERSTHESIS{Vanvinckenroye:992307,
      author       = {Vanvinckenroye, Joris Vincent},
      othercontributors = {Müller, Matthias S. and Pitsch, Heinz and Orland, Fabian
                          and Nista, Ludovico},
      title        = {{A} {P}osteriori {U}ntersuchung von {CNN}s zur
                      {M}odellierung von {W}asserstoffverbrennung},
      school       = {RWTH Aachen University},
      type         = {Masterarbeit},
      address      = {Aachen},
      publisher    = {RWTH Aachen University},
      reportid     = {RWTH-2024-08139},
      pages        = {1 Online-Ressource : Illustrationen},
      year         = {2024},
      note         = {Veröffentlicht auf dem Publikationsserver der RWTH Aachen
                      University; Masterarbeit, RWTH Aachen University, 2024},
      abstract     = {Due to the very low pollutant emissions of hydrogen
                      combustion, the fuel plays an important role in combating
                      climate change and limiting global warming to 1.5C. Accurate
                      modeling methods for hydrogen combustion are crucial to
                      reduce the huge computational demand of direct numerical
                      simulations and bring the technology to market maturity. In
                      this thesis, the application of Convolutional Neural
                      Networks, specifically U-Net and UNet++, to model lean
                      hydrogen flames in laminar flows is investigated. We couple
                      these networks with the physical solver CIAO using two
                      approaches: MLLib and AIxeleratorService, and evaluate and
                      compare their performance both in terms of accuracy and
                      scalability. Distributed network inference using the
                      AIxeleratorService is implemented to speed up the coupled
                      simulation. However, we observe unphysical behavior in the
                      coupled simulations. To combat this, we optimize the models
                      with additional training data, hyperparameter tuning, and
                      post-training pruning. Despite reducing the a-priori
                      prediction errors, these methods did not consistently
                      improve a-posteriori simulation results. Our findings
                      emphasize the need for a-posteriori evaluation for neural
                      networks in hydrogen combustion simulations.},
      cin          = {123010 / 120000 / 022000},
      ddc          = {004},
      cid          = {$I:(DE-82)123010_20140620$ / $I:(DE-82)120000_20140620$ /
                      $I:(DE-82)022000_20140101$},
      typ          = {PUB:(DE-HGF)19},
      doi          = {10.18154/RWTH-2024-08139},
      url          = {https://publications.rwth-aachen.de/record/992307},
}