Particle reconstruction of volumetric particle image velocimetry with the strategy of machine learning
Abstract Three-dimensional particle reconstruction with limited two-dimensional projections is an under-determined inverse problem that the exact solution is often difficult to be obtained. In general, approximate solutions can be obtained by iterative optimization methods. In the current work, a pr...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2021-09-01
|
| Series: | Advances in Aerodynamics |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s42774-021-00087-6 |
| _version_ | 1818619880905113600 |
|---|---|
| author | Qi Gao Shaowu Pan Hongping Wang Runjie Wei Jinjun Wang |
| author_facet | Qi Gao Shaowu Pan Hongping Wang Runjie Wei Jinjun Wang |
| author_sort | Qi Gao |
| collection | DOAJ |
| description | Abstract Three-dimensional particle reconstruction with limited two-dimensional projections is an under-determined inverse problem that the exact solution is often difficult to be obtained. In general, approximate solutions can be obtained by iterative optimization methods. In the current work, a practical particle reconstruction method based on a convolutional neural network (CNN) with geometry-informed features is proposed. The proposed technique can refine the particle reconstruction from a very coarse initial guess of particle distribution that is generated by any traditional algebraic reconstruction technique (ART) based methods. Compared with available ART-based algorithms, the novel technique makes significant improvements in terms of reconstruction quality, robustness to noise, and at least an order of magnitude faster in the offline stage. |
| first_indexed | 2024-12-16T17:44:31Z |
| format | Article |
| id | doaj.art-b0f2a9f492af4c71852a62ee97aa8147 |
| institution | Directory Open Access Journal |
| issn | 2524-6992 |
| language | English |
| last_indexed | 2024-12-16T17:44:31Z |
| publishDate | 2021-09-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | Advances in Aerodynamics |
| spelling | doaj.art-b0f2a9f492af4c71852a62ee97aa81472022-12-21T22:22:30ZengSpringerOpenAdvances in Aerodynamics2524-69922021-09-013111410.1186/s42774-021-00087-6Particle reconstruction of volumetric particle image velocimetry with the strategy of machine learningQi Gao0Shaowu Pan1Hongping Wang2Runjie Wei3Jinjun Wang4School of Aeronautics and Astronautics, Zhejiang UniversityDepartment of Aerospace Engineering, University of MichiganState Key Laboratory of Nonlinear Mechanics, Institute of Mechanics, Chinese Academy of SciencesMicroVec. Inc.Key Laboratory of Fluid Mechanics of Ministry of Education, Beihang UniversityAbstract Three-dimensional particle reconstruction with limited two-dimensional projections is an under-determined inverse problem that the exact solution is often difficult to be obtained. In general, approximate solutions can be obtained by iterative optimization methods. In the current work, a practical particle reconstruction method based on a convolutional neural network (CNN) with geometry-informed features is proposed. The proposed technique can refine the particle reconstruction from a very coarse initial guess of particle distribution that is generated by any traditional algebraic reconstruction technique (ART) based methods. Compared with available ART-based algorithms, the novel technique makes significant improvements in terms of reconstruction quality, robustness to noise, and at least an order of magnitude faster in the offline stage.https://doi.org/10.1186/s42774-021-00087-6Particle reconstructionVolumetric particle image velocimetryConvolutional neural network |
| spellingShingle | Qi Gao Shaowu Pan Hongping Wang Runjie Wei Jinjun Wang Particle reconstruction of volumetric particle image velocimetry with the strategy of machine learning Advances in Aerodynamics Particle reconstruction Volumetric particle image velocimetry Convolutional neural network |
| title | Particle reconstruction of volumetric particle image velocimetry with the strategy of machine learning |
| title_full | Particle reconstruction of volumetric particle image velocimetry with the strategy of machine learning |
| title_fullStr | Particle reconstruction of volumetric particle image velocimetry with the strategy of machine learning |
| title_full_unstemmed | Particle reconstruction of volumetric particle image velocimetry with the strategy of machine learning |
| title_short | Particle reconstruction of volumetric particle image velocimetry with the strategy of machine learning |
| title_sort | particle reconstruction of volumetric particle image velocimetry with the strategy of machine learning |
| topic | Particle reconstruction Volumetric particle image velocimetry Convolutional neural network |
| url | https://doi.org/10.1186/s42774-021-00087-6 |
| work_keys_str_mv | AT qigao particlereconstructionofvolumetricparticleimagevelocimetrywiththestrategyofmachinelearning AT shaowupan particlereconstructionofvolumetricparticleimagevelocimetrywiththestrategyofmachinelearning AT hongpingwang particlereconstructionofvolumetricparticleimagevelocimetrywiththestrategyofmachinelearning AT runjiewei particlereconstructionofvolumetricparticleimagevelocimetrywiththestrategyofmachinelearning AT jinjunwang particlereconstructionofvolumetricparticleimagevelocimetrywiththestrategyofmachinelearning |