MRCNN: Multi-input residual convolution neural network for three-dimensional reconstruction of bubble flows from light field images
Accurate measurement of bubbles in air-water two-phase flows holds immense significance in the realm of thermal hydraulics assessments within nuclear reactors. Nevertheless, conventional bubble measurement techniques grapple with challenges encompassing system intricacy, limited real-time capabiliti...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-02-01
|
| Series: | Nuclear Engineering and Technology |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1738573324004595 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832576518699614208 |
|---|---|
| author | Heng Zhang Jiayi Li Niujia Sun Hua Li Qin Hang |
| author_facet | Heng Zhang Jiayi Li Niujia Sun Hua Li Qin Hang |
| author_sort | Heng Zhang |
| collection | DOAJ |
| description | Accurate measurement of bubbles in air-water two-phase flows holds immense significance in the realm of thermal hydraulics assessments within nuclear reactors. Nevertheless, conventional bubble measurement techniques grapple with challenges encompassing system intricacy, limited real-time capabilities, and inaccuracies stemming from their inherent two-dimensional (2-D) nature. In response, we pioneered an innovative three-dimensional (3-D) analysis approach that leverages light field (LF) imaging diagnosis and deep learning algorithms. Unlike traditional 2-D reconstruction methods, our approach enables direct computation of bubble depth from LF images using digital refocusing technology. Following calibration, a seamless transformation is established between the camera coordinate system and the real-world coordinate system using a sharpness evaluation algorithm. This calibration process ensures precise alignment of refocused images with real-world positions. Subsequently, fully automated and highly accurate computations of bubble depth are realized from input images via the incorporation of a multi-input residual convolution neural network (MRCNN). The limitations of traditional two-dimensional imaging techniques are effectively addressed by this methodology, resulting in a reduction in measurement errors. The study confirms the feasibility of employing LF imaging diagnosis and deep learning algorithms for bubble measurements in an air-water two-phase flow, offering a significant improvement over traditional methods. |
| format | Article |
| id | doaj-art-ee371e4f7cc54617ba05880e222cf77c |
| institution | Kabale University |
| issn | 1738-5733 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Nuclear Engineering and Technology |
| spelling | doaj-art-ee371e4f7cc54617ba05880e222cf77c2025-01-31T05:11:08ZengElsevierNuclear Engineering and Technology1738-57332025-02-01572103210MRCNN: Multi-input residual convolution neural network for three-dimensional reconstruction of bubble flows from light field imagesHeng Zhang0Jiayi Li1Niujia Sun2Hua Li3Qin Hang4College of Computer Science and Technology, Chongqing University of Posts and Telecommunications, Chongqing, 400065, ChinaCollege of Computer Science and Technology, Chongqing University of Posts and Telecommunications, Chongqing, 400065, ChinaCollege of Computer Science and Technology, Chongqing University of Posts and Telecommunications, Chongqing, 400065, ChinaInstitute of Plasma Physics, Chinese Academy of Sciences, Hefei, 230031, ChinaCollege of Computer Science and Technology, Chongqing University of Posts and Telecommunications, Chongqing, 400065, China; Corresponding author.Accurate measurement of bubbles in air-water two-phase flows holds immense significance in the realm of thermal hydraulics assessments within nuclear reactors. Nevertheless, conventional bubble measurement techniques grapple with challenges encompassing system intricacy, limited real-time capabilities, and inaccuracies stemming from their inherent two-dimensional (2-D) nature. In response, we pioneered an innovative three-dimensional (3-D) analysis approach that leverages light field (LF) imaging diagnosis and deep learning algorithms. Unlike traditional 2-D reconstruction methods, our approach enables direct computation of bubble depth from LF images using digital refocusing technology. Following calibration, a seamless transformation is established between the camera coordinate system and the real-world coordinate system using a sharpness evaluation algorithm. This calibration process ensures precise alignment of refocused images with real-world positions. Subsequently, fully automated and highly accurate computations of bubble depth are realized from input images via the incorporation of a multi-input residual convolution neural network (MRCNN). The limitations of traditional two-dimensional imaging techniques are effectively addressed by this methodology, resulting in a reduction in measurement errors. The study confirms the feasibility of employing LF imaging diagnosis and deep learning algorithms for bubble measurements in an air-water two-phase flow, offering a significant improvement over traditional methods.http://www.sciencedirect.com/science/article/pii/S1738573324004595Three-dimensional reconstructionBubble flowDeep learningLight field |
| spellingShingle | Heng Zhang Jiayi Li Niujia Sun Hua Li Qin Hang MRCNN: Multi-input residual convolution neural network for three-dimensional reconstruction of bubble flows from light field images Nuclear Engineering and Technology Three-dimensional reconstruction Bubble flow Deep learning Light field |
| title | MRCNN: Multi-input residual convolution neural network for three-dimensional reconstruction of bubble flows from light field images |
| title_full | MRCNN: Multi-input residual convolution neural network for three-dimensional reconstruction of bubble flows from light field images |
| title_fullStr | MRCNN: Multi-input residual convolution neural network for three-dimensional reconstruction of bubble flows from light field images |
| title_full_unstemmed | MRCNN: Multi-input residual convolution neural network for three-dimensional reconstruction of bubble flows from light field images |
| title_short | MRCNN: Multi-input residual convolution neural network for three-dimensional reconstruction of bubble flows from light field images |
| title_sort | mrcnn multi input residual convolution neural network for three dimensional reconstruction of bubble flows from light field images |
| topic | Three-dimensional reconstruction Bubble flow Deep learning Light field |
| url | http://www.sciencedirect.com/science/article/pii/S1738573324004595 |
| work_keys_str_mv | AT hengzhang mrcnnmultiinputresidualconvolutionneuralnetworkforthreedimensionalreconstructionofbubbleflowsfromlightfieldimages AT jiayili mrcnnmultiinputresidualconvolutionneuralnetworkforthreedimensionalreconstructionofbubbleflowsfromlightfieldimages AT niujiasun mrcnnmultiinputresidualconvolutionneuralnetworkforthreedimensionalreconstructionofbubbleflowsfromlightfieldimages AT huali mrcnnmultiinputresidualconvolutionneuralnetworkforthreedimensionalreconstructionofbubbleflowsfromlightfieldimages AT qinhang mrcnnmultiinputresidualconvolutionneuralnetworkforthreedimensionalreconstructionofbubbleflowsfromlightfieldimages |