Flow and heat transfer optimization of a fin-tube heat exchanger with vortex generators using Response Surface Methodology and Artificial Neural Network
Using vortex generators (VGs) in fin-tube heat exchangers (FTHEs) is one of the main options to increase their performance. Although numerical models can replace the expensive experimental studies, suggesting an optimum design configuration using numerical models involves trial and error procedures...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2022-11-01
|
| Series: | Case Studies in Thermal Engineering |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2214157X22006815 |
| _version_ | 1798000367458320384 |
|---|---|
| author | Changgui Xie Gongxing Yan Qiong Ma Yasser Elmasry Pradeep Kumar Singh A.M. Algelany Makatar Wae-hayee |
| author_facet | Changgui Xie Gongxing Yan Qiong Ma Yasser Elmasry Pradeep Kumar Singh A.M. Algelany Makatar Wae-hayee |
| author_sort | Changgui Xie |
| collection | DOAJ |
| description | Using vortex generators (VGs) in fin-tube heat exchangers (FTHEs) is one of the main options to increase their performance. Although numerical models can replace the expensive experimental studies, suggesting an optimum design configuration using numerical models involves trial and error procedures and can be very computationally demanding. To alleviate this situation in the present research, the utilization of Response Surface Methodology (RSM) and Artificial Neural Network (ANN) in the optimum design of FTHEs with VGs was proposed. To train the models, three explanatory variables were chosen: the length (L), arc angle (α), and attack angle (β) of the VGs. The target variables were the Nusselt number and the friction factor. The results showed that both ANN and RSM performed reliably, although the ANN outperformed the RSM in predicting the Nusselt number and the friction factor. Considering the Nusselt number value prediction, the ANN and RSM had an R-squared value of 0.990 and 0.954, respectively. Regarding the friction factor, the same performance criteria showed a value of 0.998 for the ANN and 0.972 for the RSM. In the end, based on whether the heat exchange performance or pressure drop reduction is the main objective of design or a balanced approach to both are the target, three optimum design configurations were suggested. |
| first_indexed | 2024-04-11T11:19:08Z |
| format | Article |
| id | doaj.art-3354cbe4ed5a4c0195d6f2ffc017ff52 |
| institution | Directory Open Access Journal |
| issn | 2214-157X |
| language | English |
| last_indexed | 2024-04-11T11:19:08Z |
| publishDate | 2022-11-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Case Studies in Thermal Engineering |
| spelling | doaj.art-3354cbe4ed5a4c0195d6f2ffc017ff522022-12-22T04:27:07ZengElsevierCase Studies in Thermal Engineering2214-157X2022-11-0139102445Flow and heat transfer optimization of a fin-tube heat exchanger with vortex generators using Response Surface Methodology and Artificial Neural NetworkChanggui Xie0Gongxing Yan1Qiong Ma2Yasser Elmasry3Pradeep Kumar Singh4A.M. Algelany5Makatar Wae-hayee6School of Intelligent Manufacturing & Transportation, Chongqing Vocational Institute of Engineering, Chongqing, 402160, ChinaSchool of Intelligent Construction, Luzhou Vocational and Technical College, Luzhou, 646000, Sichuan, ChinaSchool of Intelligent Manufacturing & Transportation, Chongqing Vocational Institute of Engineering, Chongqing, 402160, ChinaDepartment of Mathematics, Faculty of Science, King Khalid University, P.O. Box 9004, Abha, 61466, Saudi Arabia; Department of Mathematics, Faculty of Science, Mansoura University, Mansoura, 35516, EgyptDepartment of Mechanical Engineering, Institute of Engineering & Technology, GLA University, Mathura, U.P., 281406, India; Corresponding author.Department of Mathematics, College of Science and Humanities in AL-Kharj, Prince Sattam bin Abdulaziz University, AL-Karj, 11942, Saudi Arabia; Department of Mathematics, Faculty of Sciences, Fayoum University, Fayoum, 63514, EgyptDepartment of Mechanical and Mechatronics Engineering, Faculty of Engineering, Prince of Songkla University, Hatyai, Songkhla, 90110, Thailand; Corresponding author.Using vortex generators (VGs) in fin-tube heat exchangers (FTHEs) is one of the main options to increase their performance. Although numerical models can replace the expensive experimental studies, suggesting an optimum design configuration using numerical models involves trial and error procedures and can be very computationally demanding. To alleviate this situation in the present research, the utilization of Response Surface Methodology (RSM) and Artificial Neural Network (ANN) in the optimum design of FTHEs with VGs was proposed. To train the models, three explanatory variables were chosen: the length (L), arc angle (α), and attack angle (β) of the VGs. The target variables were the Nusselt number and the friction factor. The results showed that both ANN and RSM performed reliably, although the ANN outperformed the RSM in predicting the Nusselt number and the friction factor. Considering the Nusselt number value prediction, the ANN and RSM had an R-squared value of 0.990 and 0.954, respectively. Regarding the friction factor, the same performance criteria showed a value of 0.998 for the ANN and 0.972 for the RSM. In the end, based on whether the heat exchange performance or pressure drop reduction is the main objective of design or a balanced approach to both are the target, three optimum design configurations were suggested.http://www.sciencedirect.com/science/article/pii/S2214157X22006815Fin-tube heat exchangerVortex generatorResponse surface methodologyArtificial neural networkHeat transfer enhancement |
| spellingShingle | Changgui Xie Gongxing Yan Qiong Ma Yasser Elmasry Pradeep Kumar Singh A.M. Algelany Makatar Wae-hayee Flow and heat transfer optimization of a fin-tube heat exchanger with vortex generators using Response Surface Methodology and Artificial Neural Network Case Studies in Thermal Engineering Fin-tube heat exchanger Vortex generator Response surface methodology Artificial neural network Heat transfer enhancement |
| title | Flow and heat transfer optimization of a fin-tube heat exchanger with vortex generators using Response Surface Methodology and Artificial Neural Network |
| title_full | Flow and heat transfer optimization of a fin-tube heat exchanger with vortex generators using Response Surface Methodology and Artificial Neural Network |
| title_fullStr | Flow and heat transfer optimization of a fin-tube heat exchanger with vortex generators using Response Surface Methodology and Artificial Neural Network |
| title_full_unstemmed | Flow and heat transfer optimization of a fin-tube heat exchanger with vortex generators using Response Surface Methodology and Artificial Neural Network |
| title_short | Flow and heat transfer optimization of a fin-tube heat exchanger with vortex generators using Response Surface Methodology and Artificial Neural Network |
| title_sort | flow and heat transfer optimization of a fin tube heat exchanger with vortex generators using response surface methodology and artificial neural network |
| topic | Fin-tube heat exchanger Vortex generator Response surface methodology Artificial neural network Heat transfer enhancement |
| url | http://www.sciencedirect.com/science/article/pii/S2214157X22006815 |
| work_keys_str_mv | AT changguixie flowandheattransferoptimizationofafintubeheatexchangerwithvortexgeneratorsusingresponsesurfacemethodologyandartificialneuralnetwork AT gongxingyan flowandheattransferoptimizationofafintubeheatexchangerwithvortexgeneratorsusingresponsesurfacemethodologyandartificialneuralnetwork AT qiongma flowandheattransferoptimizationofafintubeheatexchangerwithvortexgeneratorsusingresponsesurfacemethodologyandartificialneuralnetwork AT yasserelmasry flowandheattransferoptimizationofafintubeheatexchangerwithvortexgeneratorsusingresponsesurfacemethodologyandartificialneuralnetwork AT pradeepkumarsingh flowandheattransferoptimizationofafintubeheatexchangerwithvortexgeneratorsusingresponsesurfacemethodologyandartificialneuralnetwork AT amalgelany flowandheattransferoptimizationofafintubeheatexchangerwithvortexgeneratorsusingresponsesurfacemethodologyandartificialneuralnetwork AT makatarwaehayee flowandheattransferoptimizationofafintubeheatexchangerwithvortexgeneratorsusingresponsesurfacemethodologyandartificialneuralnetwork |