Matches in SemOpenAlex for { <https://semopenalex.org/work/W4382201005> ?p ?o ?g. }
Showing items 1 to 82 of
82
with 100 items per page.
- W4382201005 abstract "Engine efficiency, combustion process, and gas emissions are greatly affected by spray strategies. Spray strategies are utilized in engines with internal combustion. Spray strategies are determined by parameters such as nozzle diameter, injection pressure, chamber pressure, cylinder type, and others. These parameters determine spray shape. Spray shape is established by three main spray macroscopic parameters which are cone angle, penetration length, and spray area. Spray cone angle, with other spray macroscopic parameters, is often used to describe the parameters of numerical simulations. In this paper, we propose two new methods for the estimation of spray cone angle which affects the air engulfing and mixing process. Spray images gathered during a single spray injection are highly correlated. To use this fact to our advantage we proposed two deep learning-based methods that use image sequence as input. StackNet is a regression neural network that stacks images and uses them as input. It also uses a feature extractor and a fully connected layer. CNN-LSTM is another regression neural network with a feature extractor, but it utilizes Long Short-Term Memory (LSTM) cells before a fully connected layer. Both of the methods were trained, validated, and tested on preprocessed sequence images. To achieve better generalization and more data diversity, data augmentation was used. Three state-of-the-art feature extractors were tested, VGG16, MobileNetV3, and EfficientNetB0. The proposed methods were compared with the baseline approach which uses a single image as an input. Experimental validation showed that StackNet with VGG as a feature extractor achieved the best result. The proposed method estimated cone angle with a mean absolute error of 0.505 degrees, which is more than two times more accurate than the best baseline approach." @default.
- W4382201005 created "2023-06-28" @default.
- W4382201005 creator A5029256945 @default.
- W4382201005 creator A5063056168 @default.
- W4382201005 creator A5063784962 @default.
- W4382201005 creator A5069912535 @default.
- W4382201005 date "2023-03-10" @default.
- W4382201005 modified "2023-09-25" @default.
- W4382201005 title "Deep Learning-Based Cone Angle Estimation Using Spray Sequence Images" @default.
- W4382201005 cites W1998122548 @default.
- W4382201005 cites W2025183033 @default.
- W4382201005 cites W2068175813 @default.
- W4382201005 cites W2080160985 @default.
- W4382201005 cites W2108598243 @default.
- W4382201005 cites W2789876780 @default.
- W4382201005 cites W2909426367 @default.
- W4382201005 cites W2913275572 @default.
- W4382201005 cites W2982083293 @default.
- W4382201005 doi "https://doi.org/10.1145/3589883.3589915" @default.
- W4382201005 hasPublicationYear "2023" @default.
- W4382201005 type Work @default.
- W4382201005 citedByCount "0" @default.
- W4382201005 crossrefType "proceedings-article" @default.
- W4382201005 hasAuthorship W4382201005A5029256945 @default.
- W4382201005 hasAuthorship W4382201005A5063056168 @default.
- W4382201005 hasAuthorship W4382201005A5063784962 @default.
- W4382201005 hasAuthorship W4382201005A5069912535 @default.
- W4382201005 hasConcept C105923489 @default.
- W4382201005 hasConcept C116705413 @default.
- W4382201005 hasConcept C117978034 @default.
- W4382201005 hasConcept C127413603 @default.
- W4382201005 hasConcept C138885662 @default.
- W4382201005 hasConcept C153180895 @default.
- W4382201005 hasConcept C154945302 @default.
- W4382201005 hasConcept C178790620 @default.
- W4382201005 hasConcept C185592680 @default.
- W4382201005 hasConcept C190894226 @default.
- W4382201005 hasConcept C192562407 @default.
- W4382201005 hasConcept C21880701 @default.
- W4382201005 hasConcept C2776401178 @default.
- W4382201005 hasConcept C41008148 @default.
- W4382201005 hasConcept C41895202 @default.
- W4382201005 hasConcept C50644808 @default.
- W4382201005 hasConcept C52622490 @default.
- W4382201005 hasConcept C56200935 @default.
- W4382201005 hasConcept C78519656 @default.
- W4382201005 hasConceptScore W4382201005C105923489 @default.
- W4382201005 hasConceptScore W4382201005C116705413 @default.
- W4382201005 hasConceptScore W4382201005C117978034 @default.
- W4382201005 hasConceptScore W4382201005C127413603 @default.
- W4382201005 hasConceptScore W4382201005C138885662 @default.
- W4382201005 hasConceptScore W4382201005C153180895 @default.
- W4382201005 hasConceptScore W4382201005C154945302 @default.
- W4382201005 hasConceptScore W4382201005C178790620 @default.
- W4382201005 hasConceptScore W4382201005C185592680 @default.
- W4382201005 hasConceptScore W4382201005C190894226 @default.
- W4382201005 hasConceptScore W4382201005C192562407 @default.
- W4382201005 hasConceptScore W4382201005C21880701 @default.
- W4382201005 hasConceptScore W4382201005C2776401178 @default.
- W4382201005 hasConceptScore W4382201005C41008148 @default.
- W4382201005 hasConceptScore W4382201005C41895202 @default.
- W4382201005 hasConceptScore W4382201005C50644808 @default.
- W4382201005 hasConceptScore W4382201005C52622490 @default.
- W4382201005 hasConceptScore W4382201005C56200935 @default.
- W4382201005 hasConceptScore W4382201005C78519656 @default.
- W4382201005 hasFunder F4320335322 @default.
- W4382201005 hasLocation W43822010051 @default.
- W4382201005 hasOpenAccess W4382201005 @default.
- W4382201005 hasPrimaryLocation W43822010051 @default.
- W4382201005 hasRelatedWork W2009271408 @default.
- W4382201005 hasRelatedWork W2016461833 @default.
- W4382201005 hasRelatedWork W2040186380 @default.
- W4382201005 hasRelatedWork W2070074036 @default.
- W4382201005 hasRelatedWork W2163950129 @default.
- W4382201005 hasRelatedWork W2323842516 @default.
- W4382201005 hasRelatedWork W2546942002 @default.
- W4382201005 hasRelatedWork W2899683012 @default.
- W4382201005 hasRelatedWork W2994855682 @default.
- W4382201005 hasRelatedWork W4226255394 @default.
- W4382201005 isParatext "false" @default.
- W4382201005 isRetracted "false" @default.
- W4382201005 workType "article" @default.