Matches in SemOpenAlex for { <https://semopenalex.org/work/W4312669757> ?p ?o ?g. }
Showing items 1 to 62 of
62
with 100 items per page.
- W4312669757 abstract "Abstract Scalar fields, such as stress or temperature fields, are often calculated in shape optimization and design problems in engineering. For complex problems where shapes have varying topology and cannot be parametrized, data-driven scalar field prediction can be faster than traditional finite-element methods. However, current data-driven techniques to predict scalar fields are limited to a fixed grid domain, instead of arbitrary graph/mesh structures. In this work, we propose a method to predict scalar fields on meshes of arbitrary refinement and topology. It uses features that capture shape geometry on a local and global scale as input to a multilayer perceptron to predict solutions to partial differential equations on graph data structures. The proposed set of global features is a vector that concisely represents the entire mesh as a spectral shape encoding. The model is trained on finite-element von Mises stress fields, and once trained it can estimate stress values at each node on any input mesh. Two shape datasets are investigated, and the model demonstrates decent performance on both, with a median R-squared value of 0.75. We also demonstrate the model’s performance on a temperature field in a conduction problem, where its predictions have a median R-squared value of 0.98. By predicting from a simple, yet rich, set of mesh features, our method provides a potential flexible alternative to finite-element simulation in engineering design contexts. Code and datasets are available at: https://github.com/kevinferg/spectral-shape-encoding." @default.
- W4312669757 created "2023-01-05" @default.
- W4312669757 creator A5000122587 @default.
- W4312669757 creator A5004112888 @default.
- W4312669757 creator A5025602698 @default.
- W4312669757 creator A5048339797 @default.
- W4312669757 date "2022-08-14" @default.
- W4312669757 modified "2023-09-26" @default.
- W4312669757 title "Scalar Field Prediction on Topologically-Varying Graphs Using Spectral Shape Encoding" @default.
- W4312669757 doi "https://doi.org/10.1115/detc2022-91209" @default.
- W4312669757 hasPublicationYear "2022" @default.
- W4312669757 type Work @default.
- W4312669757 citedByCount "0" @default.
- W4312669757 crossrefType "proceedings-article" @default.
- W4312669757 hasAuthorship W4312669757A5000122587 @default.
- W4312669757 hasAuthorship W4312669757A5004112888 @default.
- W4312669757 hasAuthorship W4312669757A5025602698 @default.
- W4312669757 hasAuthorship W4312669757A5048339797 @default.
- W4312669757 hasConcept C110521144 @default.
- W4312669757 hasConcept C11413529 @default.
- W4312669757 hasConcept C114614502 @default.
- W4312669757 hasConcept C121332964 @default.
- W4312669757 hasConcept C135628077 @default.
- W4312669757 hasConcept C184720557 @default.
- W4312669757 hasConcept C2524010 @default.
- W4312669757 hasConcept C28826006 @default.
- W4312669757 hasConcept C31487907 @default.
- W4312669757 hasConcept C33923547 @default.
- W4312669757 hasConcept C37914503 @default.
- W4312669757 hasConcept C41008148 @default.
- W4312669757 hasConcept C57691317 @default.
- W4312669757 hasConcept C97355855 @default.
- W4312669757 hasConceptScore W4312669757C110521144 @default.
- W4312669757 hasConceptScore W4312669757C11413529 @default.
- W4312669757 hasConceptScore W4312669757C114614502 @default.
- W4312669757 hasConceptScore W4312669757C121332964 @default.
- W4312669757 hasConceptScore W4312669757C135628077 @default.
- W4312669757 hasConceptScore W4312669757C184720557 @default.
- W4312669757 hasConceptScore W4312669757C2524010 @default.
- W4312669757 hasConceptScore W4312669757C28826006 @default.
- W4312669757 hasConceptScore W4312669757C31487907 @default.
- W4312669757 hasConceptScore W4312669757C33923547 @default.
- W4312669757 hasConceptScore W4312669757C37914503 @default.
- W4312669757 hasConceptScore W4312669757C41008148 @default.
- W4312669757 hasConceptScore W4312669757C57691317 @default.
- W4312669757 hasConceptScore W4312669757C97355855 @default.
- W4312669757 hasLocation W43126697571 @default.
- W4312669757 hasOpenAccess W4312669757 @default.
- W4312669757 hasPrimaryLocation W43126697571 @default.
- W4312669757 hasRelatedWork W135182427 @default.
- W4312669757 hasRelatedWork W1983671900 @default.
- W4312669757 hasRelatedWork W2039377291 @default.
- W4312669757 hasRelatedWork W2074518865 @default.
- W4312669757 hasRelatedWork W2361126117 @default.
- W4312669757 hasRelatedWork W2965585506 @default.
- W4312669757 hasRelatedWork W3134305408 @default.
- W4312669757 hasRelatedWork W4254946536 @default.
- W4312669757 hasRelatedWork W4312045615 @default.
- W4312669757 hasRelatedWork W4317532093 @default.
- W4312669757 isParatext "false" @default.
- W4312669757 isRetracted "false" @default.
- W4312669757 workType "article" @default.