Zhu, Xiaoyu, Fu, Mengxi, Xu, Chuanlon, Hossain, Md. Moinul, Khoo, Boo Cheong (2024) Volumetric reconstruction of flow particles through light field particle image velocimetry and deep neural network. Physics of Fluids, 36 (7). Article Number 073619. ISSN 1070-6631. E-ISSN 1089-7666. (doi:10.1063/5.0218516) (KAR id:106661)
PDF
Author's Accepted Manuscript
Language: English |
|
Download this file (PDF/2MB) |
Preview |
Request a format suitable for use with assistive technology e.g. a screenreader | |
Official URL: https://doi.org/10.1063/5.0218516 |
Abstract
Tomographic reconstruction of three-dimensional (3D) tracer particle distributions through light field particle image velocimetry (LF-PIV) faces challenges in low reconstruction resolution owing to the elongation effect and extensive computational cost incurred by the iterative process. To resolve these challenges, this study proposes a deep neural network-based volumetric reconstruction approach to alleviate the reconstruction elongation and enhance the reconstruction efficiency. A tailored deep learning model (namely, LF-DNN) incorporating residual neural network architecture and a novel hybrid loss function is established to reconstruct the particle distributions through LF images. The parallax information of the flow field decoded from the raw LF data is leveraged as the input features of the network model. Comparative studies between the proposed method and the traditional tomographic reconstruction algorithms (multiplicative algebraic reconstruction technique, MART and pre-recognition MART, PR-MART) are performed through synthetic datasets. Experiments on a cylinder wake flow are further conducted to validate the performance of the proposed LF-DNN. The results indicate that the LF-DNN outperforms MART and PR-MART in terms of the reconstruction quality, mitigation of elongation effect, and noise resilience. The LF-DNN also improves the reconstruction efficiency which is 9.6 and 7.1 times higher than the MART and PR-MART, respectively. The relative error of the cylinder wake flow achieved by the LF-DNN is lower than the MART. It suggests that the LF-DNN can facilitate accurate volumetric particle reconstruction and hence the three-dimensional flow measurement by single camera-based LF-PIV.
Item Type: | Article |
---|---|
DOI/Identification number: | 10.1063/5.0218516 |
Uncontrolled keywords: | velocity measurement; deep learning; flow visualization; Particle distributions |
Subjects: |
Q Science Q Science > Q Science (General) |
Divisions: | Divisions > Division of Computing, Engineering and Mathematical Sciences > School of Engineering and Digital Arts |
Funders: | National Natural Science Foundation of China (https://ror.org/01h0zpd94) |
Depositing User: | Moinul Hossain |
Date Deposited: | 22 Jul 2024 21:09 UTC |
Last Modified: | 24 Jul 2024 09:46 UTC |
Resource URI: | https://kar.kent.ac.uk/id/eprint/106661 (The current URI for this page, for reference purposes) |
- Link to SensusAccess
- Export to:
- RefWorks
- EPrints3 XML
- BibTeX
- CSV
- Depositors only (login required):