Vortex detection for fluid dynamics data
Vortex detection can provide benefits in a wide range of fields, including aerospace engineering and meteorology. Vortices are swirling patterns of fluid, which can bring both positive impact in processes like mixings, and negative impacts such as affecting the performance and safety of aircrafts. T...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project (FYP) |
| Language: | English |
| Published: |
Nanyang Technological University
2023
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/166242 |
| _version_ | 1826116539743469568 |
|---|---|
| author | Lim, Sheng Jie |
| author2 | Ke Yiping, Kelly |
| author_facet | Ke Yiping, Kelly Lim, Sheng Jie |
| author_sort | Lim, Sheng Jie |
| collection | NTU |
| description | Vortex detection can provide benefits in a wide range of fields, including aerospace engineering and meteorology. Vortices are swirling patterns of fluid, which can bring both positive impact in processes like mixings, and negative impacts such as affecting the performance and safety of aircrafts. Traditionally, vortex detection methods can be classified into global and local methods. Global methods are accurate, with the trade off of performance, while local methods are faster but lose global information and thus have poorer performances Recent advances in machine learning have led to the development of new vortex detection methods that can improve both performance and efficiency. These new vortex detection algorithms borrow model architectures in the field of image segmentation. For example, Vortex U-net borrows the U-net architecture. In this paper, we explore adapting the features from Deeplab, namely atrous convolutions and Atrous Spatial Pyramid Pooling, and propose a novel new architecture, and compare the performance and efficiency of our new model with existing models. We also explore and evaluate fully connected Conditional Random Field as a post processing layer in our segmentation model. |
| first_indexed | 2024-10-01T04:13:04Z |
| format | Final Year Project (FYP) |
| id | ntu-10356/166242 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T04:13:04Z |
| publishDate | 2023 |
| publisher | Nanyang Technological University |
| record_format | dspace |
| spelling | ntu-10356/1662422023-04-28T15:40:06Z Vortex detection for fluid dynamics data Lim, Sheng Jie Ke Yiping, Kelly School of Computer Science and Engineering ypke@ntu.edu.sg Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence Vortex detection can provide benefits in a wide range of fields, including aerospace engineering and meteorology. Vortices are swirling patterns of fluid, which can bring both positive impact in processes like mixings, and negative impacts such as affecting the performance and safety of aircrafts. Traditionally, vortex detection methods can be classified into global and local methods. Global methods are accurate, with the trade off of performance, while local methods are faster but lose global information and thus have poorer performances Recent advances in machine learning have led to the development of new vortex detection methods that can improve both performance and efficiency. These new vortex detection algorithms borrow model architectures in the field of image segmentation. For example, Vortex U-net borrows the U-net architecture. In this paper, we explore adapting the features from Deeplab, namely atrous convolutions and Atrous Spatial Pyramid Pooling, and propose a novel new architecture, and compare the performance and efficiency of our new model with existing models. We also explore and evaluate fully connected Conditional Random Field as a post processing layer in our segmentation model. Bachelor of Engineering (Computer Science) 2023-04-24T07:22:33Z 2023-04-24T07:22:33Z 2023 Final Year Project (FYP) Lim, S. J. (2023). Vortex detection for fluid dynamics data. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/166242 https://hdl.handle.net/10356/166242 en SCSE22-0301 application/pdf Nanyang Technological University |
| spellingShingle | Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence Lim, Sheng Jie Vortex detection for fluid dynamics data |
| title | Vortex detection for fluid dynamics data |
| title_full | Vortex detection for fluid dynamics data |
| title_fullStr | Vortex detection for fluid dynamics data |
| title_full_unstemmed | Vortex detection for fluid dynamics data |
| title_short | Vortex detection for fluid dynamics data |
| title_sort | vortex detection for fluid dynamics data |
| topic | Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence |
| url | https://hdl.handle.net/10356/166242 |
| work_keys_str_mv | AT limshengjie vortexdetectionforfluiddynamicsdata |