FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3119019663> ?p ?o ?g. }

• W3119019663 abstract "Abstract A fully connected Artificial Neural Network (ANN) is used to predict the spray characteristics of prefilming airblast atomization. The model is trained from the planar prefilmer experiment from the PhD thesis of Gepperth [Experimentelle Untersuchung des Primärzerfalls an generischen luftgestützten Zerstäubern unter Hochdruckbedingungen, Vol. 75. Logos Verlag Berlin GmbH], in which shadowgraphy images of the liquid breakup at the atomizing edge capture the characteristics of the primary droplets and the ligaments. The quantities extracted from the images are the Sauter Mean Diameter, the mean droplet axial velocity, the mean ligament length and the mean ligament deformation velocity. These are the prescribed output of the ANN model. In total, the training database contains 322 different operating points at which different prefilmers, liquid types, ambient pressures, film loadings and gas velocities were investigated. Two types of model input quantities are investigated. First, nine dimensional parameters related to the geometry, the operating conditions and the properties of the liquid are used as inputs for the model. Second, nine non-dimensional groups commonly used for liquid atomization are derived from the first set of inputs. These two types of inputs are compared. The architecture providing the best fitting is determined after testing over 10000 randomly drawn ANN architectures, with up to 10 layers and up to 128 neurons per layer. The striking results is that for both types of model, the best architectures consist of a shallow net with the hidden layers in the form of a diabolo: three layers with a large number of neurons (≥ 64) in the first and the last layer, and very few neurons (≈12) in middle layer. This shape recalls the shape of an autoencoder, where the middle layer would be the feature space of reduced dimensionality. The trend highlighted by our results, to have a limited number of layers, is in contrast with recent observations in Deep Learning applied to computer vision and speech recognition. It was found that the model with dimensional input quantities always shows a lower test and validation errors than the one with non-dimensional input quantities. The best architectures for both types of inputs (dimensional and non-dimensional input) were tested versus the experiments. Both provide comparable accuracy, which is better than typical correlations of SMD and droplet velocity. As the models takes more input parameters into account compared to the correlations, they can predict the experimental data more accurately. Finally the extrapolation capability of the models was assessed by a training them on a confined domain of parameters and testing them outside this domain. It was found that the models can extrapolate at larger gas velocity. With a larger ambient pressure or a lower trailing edge thickness, the accuracy decreases drastically." @default.
• W3119019663 created "2021-01-18" @default.
• W3119019663 creator A5022084733 @default.
• W3119019663 creator A5026463422 @default.
• W3119019663 creator A5033241643 @default.
• W3119019663 creator A5052150842 @default.
• W3119019663 creator A5086286839 @default.
• W3119019663 date "2020-09-21" @default.
• W3119019663 modified "2023-09-30" @default.
• W3119019663 title "Finding the Best Architecture of an Artificial Neural Network to Model Prefilming Airblast Atomization: Not So Deep Learning" @default.
• W3119019663 cites W1523480373 @default.
• W3119019663 cites W1965947205 @default.
• W3119019663 cites W2122825543 @default.
• W3119019663 cites W2156387975 @default.
• W3119019663 cites W2185213507 @default.
• W3119019663 cites W2185505016 @default.
• W3119019663 cites W2193834300 @default.
• W3119019663 cites W2275212127 @default.
• W3119019663 cites W2605370668 @default.
• W3119019663 cites W2605917215 @default.
• W3119019663 cites W2785192677 @default.
• W3119019663 cites W2884745705 @default.
• W3119019663 cites W2926643075 @default.
• W3119019663 cites W2964212578 @default.
• W3119019663 doi "https://doi.org/10.1115/gt2020-16172" @default.
• W3119019663 hasPublicationYear "2020" @default.
• W3119019663 type Work @default.
• W3119019663 sameAs 3119019663 @default.
• W3119019663 citedByCount "0" @default.
• W3119019663 crossrefType "proceedings-article" @default.
• W3119019663 hasAuthorship W3119019663A5022084733 @default.
• W3119019663 hasAuthorship W3119019663A5026463422 @default.
• W3119019663 hasAuthorship W3119019663A5033241643 @default.
• W3119019663 hasAuthorship W3119019663A5052150842 @default.
• W3119019663 hasAuthorship W3119019663A5086286839 @default.
• W3119019663 hasConcept C120665830 @default.
• W3119019663 hasConcept C121332964 @default.
• W3119019663 hasConcept C127413603 @default.
• W3119019663 hasConcept C154945302 @default.
• W3119019663 hasConcept C159985019 @default.
• W3119019663 hasConcept C186060115 @default.
• W3119019663 hasConcept C192562407 @default.
• W3119019663 hasConcept C204366326 @default.
• W3119019663 hasConcept C2524010 @default.
• W3119019663 hasConcept C2777871205 @default.
• W3119019663 hasConcept C2778260026 @default.
• W3119019663 hasConcept C2779917225 @default.
• W3119019663 hasConcept C33923547 @default.
• W3119019663 hasConcept C41008148 @default.
• W3119019663 hasConcept C50644808 @default.
• W3119019663 hasConcept C520434653 @default.
• W3119019663 hasConcept C56200935 @default.
• W3119019663 hasConcept C57879066 @default.
• W3119019663 hasConcept C78519656 @default.
• W3119019663 hasConcept C86803240 @default.
• W3119019663 hasConceptScore W3119019663C120665830 @default.
• W3119019663 hasConceptScore W3119019663C121332964 @default.
• W3119019663 hasConceptScore W3119019663C127413603 @default.
• W3119019663 hasConceptScore W3119019663C154945302 @default.
• W3119019663 hasConceptScore W3119019663C159985019 @default.
• W3119019663 hasConceptScore W3119019663C186060115 @default.
• W3119019663 hasConceptScore W3119019663C192562407 @default.
• W3119019663 hasConceptScore W3119019663C204366326 @default.
• W3119019663 hasConceptScore W3119019663C2524010 @default.
• W3119019663 hasConceptScore W3119019663C2777871205 @default.
• W3119019663 hasConceptScore W3119019663C2778260026 @default.
• W3119019663 hasConceptScore W3119019663C2779917225 @default.
• W3119019663 hasConceptScore W3119019663C33923547 @default.
• W3119019663 hasConceptScore W3119019663C41008148 @default.
• W3119019663 hasConceptScore W3119019663C50644808 @default.
• W3119019663 hasConceptScore W3119019663C520434653 @default.
• W3119019663 hasConceptScore W3119019663C56200935 @default.
• W3119019663 hasConceptScore W3119019663C57879066 @default.
• W3119019663 hasConceptScore W3119019663C78519656 @default.
• W3119019663 hasConceptScore W3119019663C86803240 @default.
• W3119019663 hasLocation W31190196631 @default.
• W3119019663 hasOpenAccess W3119019663 @default.
• W3119019663 hasPrimaryLocation W31190196631 @default.
• W3119019663 hasRelatedWork W11853729 @default.
• W3119019663 hasRelatedWork W13678974 @default.
• W3119019663 hasRelatedWork W1383942 @default.
• W3119019663 hasRelatedWork W6680660 @default.
• W3119019663 hasRelatedWork W8021486 @default.
• W3119019663 hasRelatedWork W8203384 @default.
• W3119019663 hasRelatedWork W8286819 @default.
• W3119019663 hasRelatedWork W8821115 @default.
• W3119019663 hasRelatedWork W9190101 @default.
• W3119019663 hasRelatedWork W9333608 @default.
• W3119019663 isParatext "false" @default.
• W3119019663 isRetracted "false" @default.
• W3119019663 magId "3119019663" @default.
• W3119019663 workType "article" @default.