Sökning: id:"swepub:oai:lup.lub.lu.se:d1ca6474-e712-46b9-b3f7-d6463194e12f" >
100 kHz CH2O imagin...
100 kHz CH2O imaging realized by lower speed planar laser-induced fluorescence and deep learning
-
- Zhang, Wei (författare)
- Shanghai Jiao Tong University
-
- Dong, Xue (författare)
- Shanghai Jiao Tong University
-
- Sun, Zhiwei (författare)
- University of Adelaide
-
visa fler...
-
- Zhou, Bo (författare)
- Southern University of Science and Technology
-
- Wang, Zhenkan (författare)
- Lund University,Lunds universitet,Förbränningsfysik,Fysiska institutionen,Institutioner vid LTH,Lunds Tekniska Högskola,Combustion Physics,Department of Physics,Departments at LTH,Faculty of Engineering, LTH
-
- Richter, Mattias (författare)
- Lund University,Lunds universitet,Förbränningsfysik,Fysiska institutionen,Institutioner vid LTH,Lunds Tekniska Högskola,Combustion Physics,Department of Physics,Departments at LTH,Faculty of Engineering, LTH
-
visa färre...
-
(creator_code:org_t)
- 2021
- 2021
- Engelska 21 s.
-
Ingår i: Optics Express. - 1094-4087. ; 29:19, s. 30857-30877
- Relaterad länk:
-
http://dx.doi.org/10... (free)
-
visa fler...
-
https://lup.lub.lu.s...
-
https://doi.org/10.1...
-
visa färre...
Abstract
Ämnesord
Stäng
- This paper reports an approach to interpolate planar laser-induced fluorescence (PLIF) images of CH2O between consecutive experimental data by means of computational imaging realized with convolutional neural network (CNN). Such a deep learning based method can achieve higher temporal resolution for 2D visualization of intermediate species in combustion based on high-speed experimental images. The capability of the model was tested for generating 100 kHz PLIF images by interpolating single and multiple PLIF frames into the sequences of experimental images of lower frequencies (50, 33, 25 and 20 kHz). Results show that the prediction indices, including intersection over union (IoU), peak signal to noise ratio (PSNR), structural similarity index (SSIM), and time averaged correlation coefficient at various axial positions could achieve acceptable accuracy. This work sheds light on the utilization of CNN-based models to achieve optical flow computation and image sequence interpolation, also providing an efficient off-line model as an alternative pathway to overcome the experimental challenges of the state-of-the-art ultra-high speed PLIF techniques, e.g., to further increase repetition rate and save data transfer time.
Ämnesord
- NATURVETENSKAP -- Fysik -- Atom- och molekylfysik och optik (hsv//swe)
- NATURAL SCIENCES -- Physical Sciences -- Atom and Molecular Physics and Optics (hsv//eng)
- TEKNIK OCH TEKNOLOGIER -- Maskinteknik -- Energiteknik (hsv//swe)
- ENGINEERING AND TECHNOLOGY -- Mechanical Engineering -- Energy Engineering (hsv//eng)
Publikations- och innehållstyp
- art (ämneskategori)
- ref (ämneskategori)
Hitta via bibliotek
Till lärosätets databas