Matches in SemOpenAlex for { <https://semopenalex.org/work/W2786811224> ?p ?o ?g. }
- W2786811224 abstract "Aerodynamic shape optimization has many industrial applications. Existing methods, however, are so computationally demanding that typical engineering practices are to either simply try a limited number of hand-designed shapes or restrict oneself to shapes that can be parameterized using only few degrees of freedom. In this work, we introduce a new way to optimize complex shapes fast and accurately. To this end, we train Geodesic Convolutional Neural Networks to emulate a fluidynamics simulator. The key to making this approach practical is remeshing the original shape using a polycube map, which makes it possible to perform the computations on GPUs instead of CPUs. The neural net is then used to formulate an objective function that is differentiable with respect to the shape parameters, which can then be optimized using a gradient-based technique. This outperforms state- of-the-art methods by 5 to 20% for standard problems and, even more importantly, our approach applies to cases that previous methods cannot handle." @default.
- W2786811224 created "2018-02-23" @default.
- W2786811224 creator A5030971556 @default.
- W2786811224 creator A5038674741 @default.
- W2786811224 creator A5076094010 @default.
- W2786811224 creator A5085044479 @default.
- W2786811224 date "2018-02-12" @default.
- W2786811224 modified "2023-10-04" @default.
- W2786811224 title "Geodesic Convolutional Shape Optimization" @default.
- W2786811224 cites W1515007632 @default.
- W2786811224 cites W171902450 @default.
- W2786811224 cites W1738019091 @default.
- W2786811224 cites W1939266004 @default.
- W2786811224 cites W1980998330 @default.
- W2786811224 cites W2040259398 @default.
- W2786811224 cites W2043386108 @default.
- W2786811224 cites W2071296827 @default.
- W2786811224 cites W2083164646 @default.
- W2786811224 cites W2114863568 @default.
- W2786811224 cites W2116621195 @default.
- W2786811224 cites W2125569215 @default.
- W2786811224 cites W2157598657 @default.
- W2786811224 cites W2159405116 @default.
- W2786811224 cites W2161987835 @default.
- W2786811224 cites W2194775991 @default.
- W2786811224 cites W2489719043 @default.
- W2786811224 cites W2515505748 @default.
- W2786811224 cites W2519887557 @default.
- W2786811224 cites W2558460151 @default.
- W2786811224 cites W2582926418 @default.
- W2786811224 cites W2597874755 @default.
- W2786811224 cites W2621067911 @default.
- W2786811224 cites W2750814605 @default.
- W2786811224 cites W2758626922 @default.
- W2786811224 cites W2963840672 @default.
- W2786811224 cites W2964288706 @default.
- W2786811224 cites W3103514034 @default.
- W2786811224 hasPublicationYear "2018" @default.
- W2786811224 type Work @default.
- W2786811224 sameAs 2786811224 @default.
- W2786811224 citedByCount "2" @default.
- W2786811224 countsByYear W27868112242019 @default.
- W2786811224 crossrefType "posted-content" @default.
- W2786811224 hasAuthorship W2786811224A5030971556 @default.
- W2786811224 hasAuthorship W2786811224A5038674741 @default.
- W2786811224 hasAuthorship W2786811224A5076094010 @default.
- W2786811224 hasAuthorship W2786811224A5085044479 @default.
- W2786811224 hasConcept C11413529 @default.
- W2786811224 hasConcept C121332964 @default.
- W2786811224 hasConcept C126255220 @default.
- W2786811224 hasConcept C134306372 @default.
- W2786811224 hasConcept C135628077 @default.
- W2786811224 hasConcept C154945302 @default.
- W2786811224 hasConcept C165464430 @default.
- W2786811224 hasConcept C165818556 @default.
- W2786811224 hasConcept C202615002 @default.
- W2786811224 hasConcept C208081375 @default.
- W2786811224 hasConcept C2524010 @default.
- W2786811224 hasConcept C26517878 @default.
- W2786811224 hasConcept C29513896 @default.
- W2786811224 hasConcept C33923547 @default.
- W2786811224 hasConcept C38652104 @default.
- W2786811224 hasConcept C41008148 @default.
- W2786811224 hasConcept C45374587 @default.
- W2786811224 hasConcept C62520636 @default.
- W2786811224 hasConcept C81363708 @default.
- W2786811224 hasConcept C97355855 @default.
- W2786811224 hasConceptScore W2786811224C11413529 @default.
- W2786811224 hasConceptScore W2786811224C121332964 @default.
- W2786811224 hasConceptScore W2786811224C126255220 @default.
- W2786811224 hasConceptScore W2786811224C134306372 @default.
- W2786811224 hasConceptScore W2786811224C135628077 @default.
- W2786811224 hasConceptScore W2786811224C154945302 @default.
- W2786811224 hasConceptScore W2786811224C165464430 @default.
- W2786811224 hasConceptScore W2786811224C165818556 @default.
- W2786811224 hasConceptScore W2786811224C202615002 @default.
- W2786811224 hasConceptScore W2786811224C208081375 @default.
- W2786811224 hasConceptScore W2786811224C2524010 @default.
- W2786811224 hasConceptScore W2786811224C26517878 @default.
- W2786811224 hasConceptScore W2786811224C29513896 @default.
- W2786811224 hasConceptScore W2786811224C33923547 @default.
- W2786811224 hasConceptScore W2786811224C38652104 @default.
- W2786811224 hasConceptScore W2786811224C41008148 @default.
- W2786811224 hasConceptScore W2786811224C45374587 @default.
- W2786811224 hasConceptScore W2786811224C62520636 @default.
- W2786811224 hasConceptScore W2786811224C81363708 @default.
- W2786811224 hasConceptScore W2786811224C97355855 @default.
- W2786811224 hasLocation W27868112241 @default.
- W2786811224 hasOpenAccess W2786811224 @default.
- W2786811224 hasPrimaryLocation W27868112241 @default.
- W2786811224 hasRelatedWork W1980278630 @default.
- W2786811224 hasRelatedWork W2062339760 @default.
- W2786811224 hasRelatedWork W2062342217 @default.
- W2786811224 hasRelatedWork W2086745141 @default.
- W2786811224 hasRelatedWork W2099085357 @default.
- W2786811224 hasRelatedWork W2316808356 @default.
- W2786811224 hasRelatedWork W2331908441 @default.
- W2786811224 hasRelatedWork W2403927471 @default.
- W2786811224 hasRelatedWork W2544917569 @default.
- W2786811224 hasRelatedWork W2828819834 @default.