Thermal Performance in Convection Flow of Nanofluids Using a Deep Convolutional Neural Network
This study develops a geometry adaptive, physical field predictor for the combined forced and natural convection flow of a nanofluid in horizontal single or double-inner cylinder annular pipes with various inner cylinder sizes and placements based on deep learning. The predictor is built with a conv...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-11-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1073/15/21/8195 |
| _version_ | 1797468352113803264 |
|---|---|
| author | Yue Hua Jiang-Zhou Peng Zhi-Fu Zhou Wei-Tao Wu Yong He Mehrdad Massoudi |
| author_facet | Yue Hua Jiang-Zhou Peng Zhi-Fu Zhou Wei-Tao Wu Yong He Mehrdad Massoudi |
| author_sort | Yue Hua |
| collection | DOAJ |
| description | This study develops a geometry adaptive, physical field predictor for the combined forced and natural convection flow of a nanofluid in horizontal single or double-inner cylinder annular pipes with various inner cylinder sizes and placements based on deep learning. The predictor is built with a convolutional-deconvolutional structure, where the input is the annulus cross-section geometry and the output is the temperature and the Nusselt number for the nanofluid-filled annulus. Profiting from the proven ability of dealing with pixel-like data, the convolutional neural network (CNN)-based predictor enables an accurate end-to-end mapping from the geometry input and the desired nanofluid physical field. Taking the computational fluid dynamics (CFD) calculation as the basis of our approach, the obtained results show that the average accuracy of the predicted temperature field and the coefficient of determination <i>R</i><sup>2</sup> are more than 99.9% and 0.998 accurate for single-inner cylinder nanofluid-filled annulus; while for the more complex case of double-inner cylinder, the results are still very close, higher than 99.8% and 0.99, respectively. Furthermore, the predictor takes only 0.038 s for each nanofluid field prediction, four orders of magnitude faster than the numerical simulation. The high accuracy and the fast speed estimation of the proposed predictor show the great potential of this approach to perform efficient inner cylinder configuration design and optimization for nanofluid-filled annulus. |
| first_indexed | 2024-03-09T19:06:14Z |
| format | Article |
| id | doaj.art-366e3af6efaa4a4fa31d3ac17270f6dd |
| institution | Directory Open Access Journal |
| issn | 1996-1073 |
| language | English |
| last_indexed | 2024-03-09T19:06:14Z |
| publishDate | 2022-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj.art-366e3af6efaa4a4fa31d3ac17270f6dd2023-11-24T04:33:20ZengMDPI AGEnergies1996-10732022-11-011521819510.3390/en15218195Thermal Performance in Convection Flow of Nanofluids Using a Deep Convolutional Neural NetworkYue Hua0Jiang-Zhou Peng1Zhi-Fu Zhou2Wei-Tao Wu3Yong He4Mehrdad Massoudi5Sino-French Engineer School, Nanjing University of Science and Technology, Nanjing 210094, ChinaKey Laboratory of Transient Physics, Nanjing University of Science and Technology, Nanjing 210094, ChinaState Key Laboratory of Multiphase Flow in Power Engineering, Xi’an Jiaotong University, Xi’an 710049, ChinaSchool of Mechanical Engineering, Nanjing University of Science and Technology, Nanjing 210094, ChinaSchool of Mechanical Engineering, Nanjing University of Science and Technology, Nanjing 210094, ChinaU.S. Department of Energy, National Energy Technology Laboratory (NETL), 626 Cochrans Mill Road, Pittsburgh, PA 15236, USAThis study develops a geometry adaptive, physical field predictor for the combined forced and natural convection flow of a nanofluid in horizontal single or double-inner cylinder annular pipes with various inner cylinder sizes and placements based on deep learning. The predictor is built with a convolutional-deconvolutional structure, where the input is the annulus cross-section geometry and the output is the temperature and the Nusselt number for the nanofluid-filled annulus. Profiting from the proven ability of dealing with pixel-like data, the convolutional neural network (CNN)-based predictor enables an accurate end-to-end mapping from the geometry input and the desired nanofluid physical field. Taking the computational fluid dynamics (CFD) calculation as the basis of our approach, the obtained results show that the average accuracy of the predicted temperature field and the coefficient of determination <i>R</i><sup>2</sup> are more than 99.9% and 0.998 accurate for single-inner cylinder nanofluid-filled annulus; while for the more complex case of double-inner cylinder, the results are still very close, higher than 99.8% and 0.99, respectively. Furthermore, the predictor takes only 0.038 s for each nanofluid field prediction, four orders of magnitude faster than the numerical simulation. The high accuracy and the fast speed estimation of the proposed predictor show the great potential of this approach to perform efficient inner cylinder configuration design and optimization for nanofluid-filled annulus.https://www.mdpi.com/1996-1073/15/21/8195nanofluidsgeometry adaptivedeep convolutional neural networkinner cylinder configuration design |
| spellingShingle | Yue Hua Jiang-Zhou Peng Zhi-Fu Zhou Wei-Tao Wu Yong He Mehrdad Massoudi Thermal Performance in Convection Flow of Nanofluids Using a Deep Convolutional Neural Network Energies nanofluids geometry adaptive deep convolutional neural network inner cylinder configuration design |
| title | Thermal Performance in Convection Flow of Nanofluids Using a Deep Convolutional Neural Network |
| title_full | Thermal Performance in Convection Flow of Nanofluids Using a Deep Convolutional Neural Network |
| title_fullStr | Thermal Performance in Convection Flow of Nanofluids Using a Deep Convolutional Neural Network |
| title_full_unstemmed | Thermal Performance in Convection Flow of Nanofluids Using a Deep Convolutional Neural Network |
| title_short | Thermal Performance in Convection Flow of Nanofluids Using a Deep Convolutional Neural Network |
| title_sort | thermal performance in convection flow of nanofluids using a deep convolutional neural network |
| topic | nanofluids geometry adaptive deep convolutional neural network inner cylinder configuration design |
| url | https://www.mdpi.com/1996-1073/15/21/8195 |
| work_keys_str_mv | AT yuehua thermalperformanceinconvectionflowofnanofluidsusingadeepconvolutionalneuralnetwork AT jiangzhoupeng thermalperformanceinconvectionflowofnanofluidsusingadeepconvolutionalneuralnetwork AT zhifuzhou thermalperformanceinconvectionflowofnanofluidsusingadeepconvolutionalneuralnetwork AT weitaowu thermalperformanceinconvectionflowofnanofluidsusingadeepconvolutionalneuralnetwork AT yonghe thermalperformanceinconvectionflowofnanofluidsusingadeepconvolutionalneuralnetwork AT mehrdadmassoudi thermalperformanceinconvectionflowofnanofluidsusingadeepconvolutionalneuralnetwork |