FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4377090437> ?p ?o ?g. }

• W4377090437 endingPage "106436" @default.
• W4377090437 startingPage "106436" @default.
• W4377090437 abstract "In the context of mechanical engineering design, the field of machine learning accelerated topology optimization is dominated by image-based models trained in a supervised manner on datasets with a limited diversity of boundary conditions. State-of-the-art methods show poor generalization capabilities and are strongly coupled to finite element mesh resolution, hindering scalability. In this paper, we leverage the explicit topology parameterization of the moving morphable components (MMC) framework to train a deep learning model that directly generates geometric design variables using a model architecture that is independent of the finite element mesh used for structural analysis. The developed model is trained on a large dataset of boundary conditions. Despite achieving state-of-the-art regression loss, evaluations reveal that direct-design approaches generate topologies with poor mechanical performance. Specifically, the model-generated topologies have, on average, a stiffness 11.48% lower than conventional MMC designs, as evidenced by in-distribution and out-of-distribution test samples. We demonstrate that this is due to the incompatibility between the regression loss function typically used in literature and the topology optimization objective of compliance minimization. To address this issue, we propose a novel acceleration approach that leverages the trained model to generate improved initial designs for conventional optimization. Specifically, the deep learning model is used to generate an initial design, which is then refined by conventional optimization to arrive at a final, optimal design. This approach shows a computation time-saving of 36.84% without sacrificing the final mechanical performance of the optimal topology compared to conventional optimization starting from a uniform initial layout." @default.
• W4377090437 created "2023-05-20" @default.
• W4377090437 creator A5036669118 @default.
• W4377090437 creator A5041475505 @default.
• W4377090437 creator A5070138703 @default.
• W4377090437 creator A5087367510 @default.
• W4377090437 date "2023-08-01" @default.
• W4377090437 modified "2023-10-17" @default.
• W4377090437 title "Supervised deep learning for the moving morphable components topology optimization framework" @default.
• W4377090437 cites W2069697210 @default.
• W4377090437 cites W2146674345 @default.
• W4377090437 cites W2149454052 @default.
• W4377090437 cites W2194775991 @default.
• W4377090437 cites W2194971623 @default.
• W4377090437 cites W2220999736 @default.
• W4377090437 cites W2567642635 @default.
• W4377090437 cites W2761536263 @default.
• W4377090437 cites W2788109773 @default.
• W4377090437 cites W2803594690 @default.
• W4377090437 cites W2808432312 @default.
• W4377090437 cites W2889362692 @default.
• W4377090437 cites W2963556194 @default.
• W4377090437 cites W3003650626 @default.
• W4377090437 cites W3031335110 @default.
• W4377090437 cites W3033396344 @default.
• W4377090437 cites W3033979839 @default.
• W4377090437 cites W3093210795 @default.
• W4377090437 cites W3105070525 @default.
• W4377090437 cites W3128774147 @default.
• W4377090437 cites W3134775088 @default.
• W4377090437 cites W3158281926 @default.
• W4377090437 cites W3159901497 @default.
• W4377090437 cites W3206867662 @default.
• W4377090437 cites W4210267569 @default.
• W4377090437 cites W4221140035 @default.
• W4377090437 cites W4311145812 @default.
• W4377090437 cites W4316876947 @default.
• W4377090437 doi "https://doi.org/10.1016/j.engappai.2023.106436" @default.
• W4377090437 hasPublicationYear "2023" @default.
• W4377090437 type Work @default.
• W4377090437 citedByCount "0" @default.
• W4377090437 crossrefType "journal-article" @default.
• W4377090437 hasAuthorship W4377090437A5036669118 @default.
• W4377090437 hasAuthorship W4377090437A5041475505 @default.
• W4377090437 hasAuthorship W4377090437A5070138703 @default.
• W4377090437 hasAuthorship W4377090437A5087367510 @default.
• W4377090437 hasConcept C111919701 @default.
• W4377090437 hasConcept C11413529 @default.
• W4377090437 hasConcept C114614502 @default.
• W4377090437 hasConcept C119857082 @default.
• W4377090437 hasConcept C121332964 @default.
• W4377090437 hasConcept C126255220 @default.
• W4377090437 hasConcept C135628077 @default.
• W4377090437 hasConcept C151730666 @default.
• W4377090437 hasConcept C153083717 @default.
• W4377090437 hasConcept C154945302 @default.
• W4377090437 hasConcept C184720557 @default.
• W4377090437 hasConcept C189216461 @default.
• W4377090437 hasConcept C199845137 @default.
• W4377090437 hasConcept C2779343474 @default.
• W4377090437 hasConcept C33923547 @default.
• W4377090437 hasConcept C41008148 @default.
• W4377090437 hasConcept C45374587 @default.
• W4377090437 hasConcept C48044578 @default.
• W4377090437 hasConcept C77088390 @default.
• W4377090437 hasConcept C86803240 @default.
• W4377090437 hasConcept C97355855 @default.
• W4377090437 hasConceptScore W4377090437C111919701 @default.
• W4377090437 hasConceptScore W4377090437C11413529 @default.
• W4377090437 hasConceptScore W4377090437C114614502 @default.
• W4377090437 hasConceptScore W4377090437C119857082 @default.
• W4377090437 hasConceptScore W4377090437C121332964 @default.
• W4377090437 hasConceptScore W4377090437C126255220 @default.
• W4377090437 hasConceptScore W4377090437C135628077 @default.
• W4377090437 hasConceptScore W4377090437C151730666 @default.
• W4377090437 hasConceptScore W4377090437C153083717 @default.
• W4377090437 hasConceptScore W4377090437C154945302 @default.
• W4377090437 hasConceptScore W4377090437C184720557 @default.
• W4377090437 hasConceptScore W4377090437C189216461 @default.
• W4377090437 hasConceptScore W4377090437C199845137 @default.
• W4377090437 hasConceptScore W4377090437C2779343474 @default.
• W4377090437 hasConceptScore W4377090437C33923547 @default.
• W4377090437 hasConceptScore W4377090437C41008148 @default.
• W4377090437 hasConceptScore W4377090437C45374587 @default.
• W4377090437 hasConceptScore W4377090437C48044578 @default.
• W4377090437 hasConceptScore W4377090437C77088390 @default.
• W4377090437 hasConceptScore W4377090437C86803240 @default.
• W4377090437 hasConceptScore W4377090437C97355855 @default.
• W4377090437 hasFunder F4320334593 @default.
• W4377090437 hasLocation W43770904371 @default.
• W4377090437 hasOpenAccess W4377090437 @default.
• W4377090437 hasPrimaryLocation W43770904371 @default.
• W4377090437 hasRelatedWork W1871620607 @default.
• W4377090437 hasRelatedWork W2027068156 @default.
• W4377090437 hasRelatedWork W2087806370 @default.
• W4377090437 hasRelatedWork W2093906193 @default.
• W4377090437 hasRelatedWork W3000229446 @default.
• W4377090437 hasRelatedWork W3119895033 @default.

• next