Matches in SemOpenAlex for { <https://semopenalex.org/work/W3215918416> ?p ?o ?g. }
Showing items 1 to 96 of
96
with 100 items per page.
- W3215918416 endingPage "1875" @default.
- W3215918416 startingPage "1863" @default.
- W3215918416 abstract "This article develops a physics-guided data-driven model for the height evolution of parts printed in droplet-based additive manufacturing. The proposed model is a convolutional recurrent neural network (ConvRNN) whose structure is derived based on the physical understanding of mass conservation during the height evolution. Because of this physics-guided model structure, the model parameters obtained are invariant to the geometry of the printed part and thus portable from one geometry to another, the conditions on physical stability of the evolution translate directly to training stability of the neural network, and the data required to train this model are much less compared to a pure black-box model. These aspects of the model are validated experimentally on an inkjet 3-D printing setup. The proposed model outperforms a black-box off-the-shelf multilayer perceptron (neural network) by using about two orders of magnitude less data for training, at the same time delivering <inline-formula xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink> <tex-math notation=LaTeX>$1.7times $ </tex-math></inline-formula> smaller rms error on test data. The proposed model is also compared with a state-of-the-art reduced order linear model and shows <inline-formula xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink> <tex-math notation=LaTeX>$1.4times $ </tex-math></inline-formula> smaller rms error on test data. Finally, experimental results also underline that the model parameters learned are geometry invariant, that is, the model parameters trained on one geometry can be used to predict the height map evolution for other geometries without relearning." @default.
- W3215918416 created "2021-12-06" @default.
- W3215918416 creator A5083812959 @default.
- W3215918416 creator A5087058552 @default.
- W3215918416 date "2022-09-01" @default.
- W3215918416 modified "2023-09-29" @default.
- W3215918416 title "A Physics-Guided Neural Network Dynamical Model for Droplet-Based Additive Manufacturing" @default.
- W3215918416 cites W1545683735 @default.
- W3215918416 cites W1985475871 @default.
- W3215918416 cites W1994105050 @default.
- W3215918416 cites W1994216106 @default.
- W3215918416 cites W2041684917 @default.
- W3215918416 cites W2046323057 @default.
- W3215918416 cites W2088008046 @default.
- W3215918416 cites W2101834112 @default.
- W3215918416 cites W2125795420 @default.
- W3215918416 cites W2131828811 @default.
- W3215918416 cites W2299930271 @default.
- W3215918416 cites W2343040550 @default.
- W3215918416 cites W2480976862 @default.
- W3215918416 cites W2595206339 @default.
- W3215918416 cites W2595957243 @default.
- W3215918416 cites W2728758501 @default.
- W3215918416 cites W2734256217 @default.
- W3215918416 cites W2751772345 @default.
- W3215918416 cites W2799813480 @default.
- W3215918416 cites W2894805733 @default.
- W3215918416 cites W2956046114 @default.
- W3215918416 cites W2963847595 @default.
- W3215918416 cites W2973065423 @default.
- W3215918416 cites W2976895221 @default.
- W3215918416 cites W2982585804 @default.
- W3215918416 cites W2990153393 @default.
- W3215918416 cites W3034137746 @default.
- W3215918416 cites W3045732604 @default.
- W3215918416 cites W3102140816 @default.
- W3215918416 cites W4254816979 @default.
- W3215918416 doi "https://doi.org/10.1109/tcst.2021.3128422" @default.
- W3215918416 hasPublicationYear "2022" @default.
- W3215918416 type Work @default.
- W3215918416 sameAs 3215918416 @default.
- W3215918416 citedByCount "5" @default.
- W3215918416 countsByYear W32159184162022 @default.
- W3215918416 countsByYear W32159184162023 @default.
- W3215918416 crossrefType "journal-article" @default.
- W3215918416 hasAuthorship W3215918416A5083812959 @default.
- W3215918416 hasAuthorship W3215918416A5087058552 @default.
- W3215918416 hasConcept C112972136 @default.
- W3215918416 hasConcept C11413529 @default.
- W3215918416 hasConcept C119857082 @default.
- W3215918416 hasConcept C154945302 @default.
- W3215918416 hasConcept C16910744 @default.
- W3215918416 hasConcept C199360897 @default.
- W3215918416 hasConcept C28826006 @default.
- W3215918416 hasConcept C33923547 @default.
- W3215918416 hasConcept C41008148 @default.
- W3215918416 hasConcept C45357846 @default.
- W3215918416 hasConcept C50644808 @default.
- W3215918416 hasConcept C60908668 @default.
- W3215918416 hasConcept C81363708 @default.
- W3215918416 hasConcept C94375191 @default.
- W3215918416 hasConceptScore W3215918416C112972136 @default.
- W3215918416 hasConceptScore W3215918416C11413529 @default.
- W3215918416 hasConceptScore W3215918416C119857082 @default.
- W3215918416 hasConceptScore W3215918416C154945302 @default.
- W3215918416 hasConceptScore W3215918416C16910744 @default.
- W3215918416 hasConceptScore W3215918416C199360897 @default.
- W3215918416 hasConceptScore W3215918416C28826006 @default.
- W3215918416 hasConceptScore W3215918416C33923547 @default.
- W3215918416 hasConceptScore W3215918416C41008148 @default.
- W3215918416 hasConceptScore W3215918416C45357846 @default.
- W3215918416 hasConceptScore W3215918416C50644808 @default.
- W3215918416 hasConceptScore W3215918416C60908668 @default.
- W3215918416 hasConceptScore W3215918416C81363708 @default.
- W3215918416 hasConceptScore W3215918416C94375191 @default.
- W3215918416 hasIssue "5" @default.
- W3215918416 hasLocation W32159184161 @default.
- W3215918416 hasOpenAccess W3215918416 @default.
- W3215918416 hasPrimaryLocation W32159184161 @default.
- W3215918416 hasRelatedWork W2167281126 @default.
- W3215918416 hasRelatedWork W2763109982 @default.
- W3215918416 hasRelatedWork W3177125872 @default.
- W3215918416 hasRelatedWork W3193301557 @default.
- W3215918416 hasRelatedWork W4251429894 @default.
- W3215918416 hasRelatedWork W4295190261 @default.
- W3215918416 hasRelatedWork W4310078342 @default.
- W3215918416 hasRelatedWork W4320802194 @default.
- W3215918416 hasRelatedWork W2185463868 @default.
- W3215918416 hasRelatedWork W2623804983 @default.
- W3215918416 hasVolume "30" @default.
- W3215918416 isParatext "false" @default.
- W3215918416 isRetracted "false" @default.
- W3215918416 magId "3215918416" @default.
- W3215918416 workType "article" @default.