Improved Wall Temperature Prediction for the LUMEN Rocket Combustion Chamber with Neural Networks
Accurate calculations of the heat transfer and the resulting maximum wall temperature are essential for the optimal design of reliable and efficient regenerative cooling systems. However, predicting the heat transfer of supercritical methane flowing in cooling channels of a regeneratively cooled roc...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-05-01
|
| Series: | Aerospace |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2226-4310/10/5/450 |
| _version_ | 1797601619155615744 |
|---|---|
| author | Kai Dresia Eldin Kurudzija Jan Deeken Günther Waxenegger-Wilfing |
| author_facet | Kai Dresia Eldin Kurudzija Jan Deeken Günther Waxenegger-Wilfing |
| author_sort | Kai Dresia |
| collection | DOAJ |
| description | Accurate calculations of the heat transfer and the resulting maximum wall temperature are essential for the optimal design of reliable and efficient regenerative cooling systems. However, predicting the heat transfer of supercritical methane flowing in cooling channels of a regeneratively cooled rocket combustor presents a significant challenge. High-fidelity CFD calculations provide sufficient accuracy but are computationally too expensive to be used within elaborate design optimization routines. In a previous work it has been shown that a surrogate model based on neural networks is able to predict the maximum wall temperature along straight cooling channels with convincing precision when trained with data from CFD simulations for simple cooling channel segments. In this paper, the methodology is extended to cooling channels with curvature. The predictions of the extended model are tested against CFD simulations with different boundary conditions for the representative LUMEN combustor contour with varying geometries and heat flux densities. The high accuracy of the extended model’s predictions, suggests that it will be a valuable tool for designing and analyzing regenerative cooling systems with greater efficiency and effectiveness. |
| first_indexed | 2024-03-11T04:02:55Z |
| format | Article |
| id | doaj.art-a80a6ff9d0874c8793dd0cd4569beaa4 |
| institution | Directory Open Access Journal |
| issn | 2226-4310 |
| language | English |
| last_indexed | 2024-03-11T04:02:55Z |
| publishDate | 2023-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Aerospace |
| spelling | doaj.art-a80a6ff9d0874c8793dd0cd4569beaa42023-11-18T00:00:26ZengMDPI AGAerospace2226-43102023-05-0110545010.3390/aerospace10050450Improved Wall Temperature Prediction for the LUMEN Rocket Combustion Chamber with Neural NetworksKai Dresia0Eldin Kurudzija1Jan Deeken2Günther Waxenegger-Wilfing3Institute of Space Propulsion, German Aerospace Center (DLR), 74239 Lampoldshausen, GermanyInstitute of Space Propulsion, German Aerospace Center (DLR), 74239 Lampoldshausen, GermanyInstitute of Space Propulsion, German Aerospace Center (DLR), 74239 Lampoldshausen, GermanyInstitute of Space Propulsion, German Aerospace Center (DLR), 74239 Lampoldshausen, GermanyAccurate calculations of the heat transfer and the resulting maximum wall temperature are essential for the optimal design of reliable and efficient regenerative cooling systems. However, predicting the heat transfer of supercritical methane flowing in cooling channels of a regeneratively cooled rocket combustor presents a significant challenge. High-fidelity CFD calculations provide sufficient accuracy but are computationally too expensive to be used within elaborate design optimization routines. In a previous work it has been shown that a surrogate model based on neural networks is able to predict the maximum wall temperature along straight cooling channels with convincing precision when trained with data from CFD simulations for simple cooling channel segments. In this paper, the methodology is extended to cooling channels with curvature. The predictions of the extended model are tested against CFD simulations with different boundary conditions for the representative LUMEN combustor contour with varying geometries and heat flux densities. The high accuracy of the extended model’s predictions, suggests that it will be a valuable tool for designing and analyzing regenerative cooling systems with greater efficiency and effectiveness.https://www.mdpi.com/2226-4310/10/5/450neural networksurrogate modelheat transfermachine learningLUMENrocket engine |
| spellingShingle | Kai Dresia Eldin Kurudzija Jan Deeken Günther Waxenegger-Wilfing Improved Wall Temperature Prediction for the LUMEN Rocket Combustion Chamber with Neural Networks Aerospace neural network surrogate model heat transfer machine learning LUMEN rocket engine |
| title | Improved Wall Temperature Prediction for the LUMEN Rocket Combustion Chamber with Neural Networks |
| title_full | Improved Wall Temperature Prediction for the LUMEN Rocket Combustion Chamber with Neural Networks |
| title_fullStr | Improved Wall Temperature Prediction for the LUMEN Rocket Combustion Chamber with Neural Networks |
| title_full_unstemmed | Improved Wall Temperature Prediction for the LUMEN Rocket Combustion Chamber with Neural Networks |
| title_short | Improved Wall Temperature Prediction for the LUMEN Rocket Combustion Chamber with Neural Networks |
| title_sort | improved wall temperature prediction for the lumen rocket combustion chamber with neural networks |
| topic | neural network surrogate model heat transfer machine learning LUMEN rocket engine |
| url | https://www.mdpi.com/2226-4310/10/5/450 |
| work_keys_str_mv | AT kaidresia improvedwalltemperaturepredictionforthelumenrocketcombustionchamberwithneuralnetworks AT eldinkurudzija improvedwalltemperaturepredictionforthelumenrocketcombustionchamberwithneuralnetworks AT jandeeken improvedwalltemperaturepredictionforthelumenrocketcombustionchamberwithneuralnetworks AT guntherwaxeneggerwilfing improvedwalltemperaturepredictionforthelumenrocketcombustionchamberwithneuralnetworks |