Comparison between conventional and deep learning-based surrogate models in predicting convective heat transfer performance of U-bend channels
Deep neural networks are efficient methods to achieve real-time visualization of physics fields. The main concerns that prevented deep learning from being implemented in the field of energy conversion were the risks of overfitting and the lack of data. Therefore, it is necessary to evaluate differen...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2022-05-01
|
| Series: | Energy and AI |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2666546822000040 |
| _version_ | 1818204408109858816 |
|---|---|
| author | Qi Wang Weiwei Zhou Li Yang Kang Huang |
| author_facet | Qi Wang Weiwei Zhou Li Yang Kang Huang |
| author_sort | Qi Wang |
| collection | DOAJ |
| description | Deep neural networks are efficient methods to achieve real-time visualization of physics fields. The main concerns that prevented deep learning from being implemented in the field of energy conversion were the risks of overfitting and the lack of data. Therefore, it is necessary to evaluate different kinds of surrogate modeling methods and provide guidelines for designers to choose models. In this study, three conventional models (Artificial Neural Network, Radial Bias Function, and Kriging), and two deep learning-based models (Convolutional Neural Network and Conditional Generative Adversarial Neural Network) were established to predict the flow and heat transfer performance of a U-bend with variable geometries. The models were detailly compared in terms of the single-point prediction accuracy, response accuracy, sensitivity to sample size, and other characteristics of interest. Results showed that the conventional models had slightly higher single point accuracy and the relative error of pressure loss and heat transfer were within ±6.6% and ±5.7% respectively, while those of the deep learning-based models were within ±8.0% and ±6.3% respectively. Nevertheless, the deep learning-based models had higher response accuracy and could reconstruct the distributions of surface pressure and wall heat flux with the pixel-wise absolute error within ±2.0 Pa and ±45 W/m2 respectively. The results indicated that deep learning was a promising surrogate modeling approach due to its acceptable prediction error and ability to reconstruct physical fields. This effort was expected to serve as a guide for establishing more reliable data-driven surrogate models for energy conversion and heat transfer problems. |
| first_indexed | 2024-12-12T03:40:45Z |
| format | Article |
| id | doaj.art-6dadc8bf16c344959c12ecff9007feb0 |
| institution | Directory Open Access Journal |
| issn | 2666-5468 |
| language | English |
| last_indexed | 2024-12-12T03:40:45Z |
| publishDate | 2022-05-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Energy and AI |
| spelling | doaj.art-6dadc8bf16c344959c12ecff9007feb02022-12-22T00:39:42ZengElsevierEnergy and AI2666-54682022-05-018100140Comparison between conventional and deep learning-based surrogate models in predicting convective heat transfer performance of U-bend channelsQi Wang0Weiwei Zhou1Li Yang2Kang Huang3School of Mechanical Engineering, Shanghai Jiao Tong University, Shanghai, 200240, China; State Key Laboratory of Aerodynamics, Mianyang, Sichuan, 621000, ChinaSchool of Mechanical Engineering, Shanghai Jiao Tong University, Shanghai, 200240, China; State Key Laboratory of Aerodynamics, Mianyang, Sichuan, 621000, ChinaSchool of Mechanical Engineering, Shanghai Jiao Tong University, Shanghai, 200240, China; State Key Laboratory of Aerodynamics, Mianyang, Sichuan, 621000, China; Corresponding author.State Key Laboratory of Aerodynamics, Mianyang, Sichuan, 621000, China; China Aerodynamics Research and Development Center, Mianyang, Sichuan, 621000, ChinaDeep neural networks are efficient methods to achieve real-time visualization of physics fields. The main concerns that prevented deep learning from being implemented in the field of energy conversion were the risks of overfitting and the lack of data. Therefore, it is necessary to evaluate different kinds of surrogate modeling methods and provide guidelines for designers to choose models. In this study, three conventional models (Artificial Neural Network, Radial Bias Function, and Kriging), and two deep learning-based models (Convolutional Neural Network and Conditional Generative Adversarial Neural Network) were established to predict the flow and heat transfer performance of a U-bend with variable geometries. The models were detailly compared in terms of the single-point prediction accuracy, response accuracy, sensitivity to sample size, and other characteristics of interest. Results showed that the conventional models had slightly higher single point accuracy and the relative error of pressure loss and heat transfer were within ±6.6% and ±5.7% respectively, while those of the deep learning-based models were within ±8.0% and ±6.3% respectively. Nevertheless, the deep learning-based models had higher response accuracy and could reconstruct the distributions of surface pressure and wall heat flux with the pixel-wise absolute error within ±2.0 Pa and ±45 W/m2 respectively. The results indicated that deep learning was a promising surrogate modeling approach due to its acceptable prediction error and ability to reconstruct physical fields. This effort was expected to serve as a guide for establishing more reliable data-driven surrogate models for energy conversion and heat transfer problems.http://www.sciencedirect.com/science/article/pii/S2666546822000040Surrogate modelingDeep learningConvective heat transferU-bend |
| spellingShingle | Qi Wang Weiwei Zhou Li Yang Kang Huang Comparison between conventional and deep learning-based surrogate models in predicting convective heat transfer performance of U-bend channels Energy and AI Surrogate modeling Deep learning Convective heat transfer U-bend |
| title | Comparison between conventional and deep learning-based surrogate models in predicting convective heat transfer performance of U-bend channels |
| title_full | Comparison between conventional and deep learning-based surrogate models in predicting convective heat transfer performance of U-bend channels |
| title_fullStr | Comparison between conventional and deep learning-based surrogate models in predicting convective heat transfer performance of U-bend channels |
| title_full_unstemmed | Comparison between conventional and deep learning-based surrogate models in predicting convective heat transfer performance of U-bend channels |
| title_short | Comparison between conventional and deep learning-based surrogate models in predicting convective heat transfer performance of U-bend channels |
| title_sort | comparison between conventional and deep learning based surrogate models in predicting convective heat transfer performance of u bend channels |
| topic | Surrogate modeling Deep learning Convective heat transfer U-bend |
| url | http://www.sciencedirect.com/science/article/pii/S2666546822000040 |
| work_keys_str_mv | AT qiwang comparisonbetweenconventionalanddeeplearningbasedsurrogatemodelsinpredictingconvectiveheattransferperformanceofubendchannels AT weiweizhou comparisonbetweenconventionalanddeeplearningbasedsurrogatemodelsinpredictingconvectiveheattransferperformanceofubendchannels AT liyang comparisonbetweenconventionalanddeeplearningbasedsurrogatemodelsinpredictingconvectiveheattransferperformanceofubendchannels AT kanghuang comparisonbetweenconventionalanddeeplearningbasedsurrogatemodelsinpredictingconvectiveheattransferperformanceofubendchannels |