Thermodynamics-Informed Neural Networks for the Design of Solar Collectors: An Application on Water Heating in the Highland Areas of the Andes
This study addresses the challenge of optimizing flat-plate solar collector design, traditionally reliant on trial-and-error and simplified engineering design methods. We propose using physics-informed neural networks (PINNs) to predict optimal design conditions in a range of data that not only char...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-10-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1073/17/19/4978 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850185098230497280 |
|---|---|
| author | Mauricio Cáceres Carlos Avila Edgar Rivera |
| author_facet | Mauricio Cáceres Carlos Avila Edgar Rivera |
| author_sort | Mauricio Cáceres |
| collection | DOAJ |
| description | This study addresses the challenge of optimizing flat-plate solar collector design, traditionally reliant on trial-and-error and simplified engineering design methods. We propose using physics-informed neural networks (PINNs) to predict optimal design conditions in a range of data that not only characterized the highlands of Ecuador but also similar geographical locations. The model integrates three interconnected neural networks to predict global collector efficiency by considering atmospheric, geometric, and physical variables, including overall loss coefficient, efficiency factors, outlet fluid temperature, and useful heat gain. The PINNs model surpasses traditional simplified thermodynamic equations employed in engineering design by effectively integrating thermodynamic principles with data-driven insights, offering more accurate modeling of nonlinear phenomena. This approach enhances the precision of solar collector performance predictions, making it particularly valuable for optimizing designs in Ecuador’s highlands and similar regions with unique climatic conditions. The ANN predicted a collector overall loss coefficient of 5.199 W/(m<sup>2</sup>·K), closely matching the thermodynamic model’s 5.189 W/(m<sup>2</sup>·K), with similar accuracy in collector useful energy gain (722.85 W) and global collector efficiency (33.68%). Although the PINNs model showed minor discrepancies in certain parameters, it outperformed traditional methods in capturing the complex, nonlinear behavior of the data set, especially in predicting outlet fluid temperature (55.05 °C vs. 67.22 °C). |
| format | Article |
| id | doaj-art-6f54f4dd0b4d4b02bf3f0c397799b481 |
| institution | OA Journals |
| issn | 1996-1073 |
| language | English |
| publishDate | 2024-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj-art-6f54f4dd0b4d4b02bf3f0c397799b4812025-08-20T02:16:50ZengMDPI AGEnergies1996-10732024-10-011719497810.3390/en17194978Thermodynamics-Informed Neural Networks for the Design of Solar Collectors: An Application on Water Heating in the Highland Areas of the AndesMauricio Cáceres0Carlos Avila1Edgar Rivera2Grupo de Investigación de Energía, Minas y Agua (GIEMA), Facultad de Ciencias, Ingeniería y Construcción, Universidad UTE, Quito 170527, EcuadorGrupo de Investigación de Energía, Minas y Agua (GIEMA), Facultad de Ciencias, Ingeniería y Construcción, Universidad UTE, Quito 170527, EcuadorGrupo de Investigación de Energía, Minas y Agua (GIEMA), Facultad de Ciencias, Ingeniería y Construcción, Universidad UTE, Quito 170527, EcuadorThis study addresses the challenge of optimizing flat-plate solar collector design, traditionally reliant on trial-and-error and simplified engineering design methods. We propose using physics-informed neural networks (PINNs) to predict optimal design conditions in a range of data that not only characterized the highlands of Ecuador but also similar geographical locations. The model integrates three interconnected neural networks to predict global collector efficiency by considering atmospheric, geometric, and physical variables, including overall loss coefficient, efficiency factors, outlet fluid temperature, and useful heat gain. The PINNs model surpasses traditional simplified thermodynamic equations employed in engineering design by effectively integrating thermodynamic principles with data-driven insights, offering more accurate modeling of nonlinear phenomena. This approach enhances the precision of solar collector performance predictions, making it particularly valuable for optimizing designs in Ecuador’s highlands and similar regions with unique climatic conditions. The ANN predicted a collector overall loss coefficient of 5.199 W/(m<sup>2</sup>·K), closely matching the thermodynamic model’s 5.189 W/(m<sup>2</sup>·K), with similar accuracy in collector useful energy gain (722.85 W) and global collector efficiency (33.68%). Although the PINNs model showed minor discrepancies in certain parameters, it outperformed traditional methods in capturing the complex, nonlinear behavior of the data set, especially in predicting outlet fluid temperature (55.05 °C vs. 67.22 °C).https://www.mdpi.com/1996-1073/17/19/4978solar energysolar collectorswater heatingartificial neural networks |
| spellingShingle | Mauricio Cáceres Carlos Avila Edgar Rivera Thermodynamics-Informed Neural Networks for the Design of Solar Collectors: An Application on Water Heating in the Highland Areas of the Andes Energies solar energy solar collectors water heating artificial neural networks |
| title | Thermodynamics-Informed Neural Networks for the Design of Solar Collectors: An Application on Water Heating in the Highland Areas of the Andes |
| title_full | Thermodynamics-Informed Neural Networks for the Design of Solar Collectors: An Application on Water Heating in the Highland Areas of the Andes |
| title_fullStr | Thermodynamics-Informed Neural Networks for the Design of Solar Collectors: An Application on Water Heating in the Highland Areas of the Andes |
| title_full_unstemmed | Thermodynamics-Informed Neural Networks for the Design of Solar Collectors: An Application on Water Heating in the Highland Areas of the Andes |
| title_short | Thermodynamics-Informed Neural Networks for the Design of Solar Collectors: An Application on Water Heating in the Highland Areas of the Andes |
| title_sort | thermodynamics informed neural networks for the design of solar collectors an application on water heating in the highland areas of the andes |
| topic | solar energy solar collectors water heating artificial neural networks |
| url | https://www.mdpi.com/1996-1073/17/19/4978 |
| work_keys_str_mv | AT mauriciocaceres thermodynamicsinformedneuralnetworksforthedesignofsolarcollectorsanapplicationonwaterheatinginthehighlandareasoftheandes AT carlosavila thermodynamicsinformedneuralnetworksforthedesignofsolarcollectorsanapplicationonwaterheatinginthehighlandareasoftheandes AT edgarrivera thermodynamicsinformedneuralnetworksforthedesignofsolarcollectorsanapplicationonwaterheatinginthehighlandareasoftheandes |