Optimal Design of Regenerative Cooling Structure Based on Backpropagation Neural Network

Xu, Shaotong; Wang, Changhui; Yang, Chengxiao

doi:10.2514/1.t6447

Cited by 4 publications

(4 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In recent years, data-based modeling techniques are studied for various applications in the aerospace segment, for example for the design of rocket injector elements [21] or cooling channels [2,22], and for different flow phenomena [23,24].…”

Section: Data-based Surrogate Model For Wall Temperature Predictionmentioning

confidence: 99%

Improved Wall Temperature Prediction for the LUMEN Rocket Combustion Chamber with Neural Networks

et al. 2023

View full text Add to dashboard Cite

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.

show abstract

Section: Data-based Surrogate Model For Wall Temperature Predictionmentioning

confidence: 99%

Improved Wall Temperature Prediction for the LUMEN Rocket Combustion Chamber with Neural Networks

et al. 2023

View full text Add to dashboard Cite

show abstract

“…In recent years, with the rapid advancement of artificial intelligence (AI) technology, machine learning techniques have found widespread application in the engineering field, with neural networks emerging as a popular choice for engineering design. Neural networks exhibit superior capabilities compared to traditional modeling methods in handling complex data and extracting nonlinear relationships [7]. Numerous scholars have applied machine learning to the field of vibration damper design.…”

Section: Introductionmentioning

confidence: 99%

Performance Prediction of the Elastic Support Structure of a Wind Turbine Based on Multi-Task Learning

Zhu,

Qi,

et al. 2024

Machines

View full text Add to dashboard Cite

The effectiveness of a wind turbine elastic support in reducing vibrations significantly impacts the unit’s lifespan. During the structural design process, it is necessary to consider the influence of structural design parameters on multiple performance indicators. While neural networks can fit the relationships between design parameters on multiple performance indicators, traditional modeling methods often isolate multiple tasks, hindering the learning on correlations between tasks and reducing efficiency. Moreover, acquiring training data through physical experiments is expensive and yields limited data, insufficient for effective model training. To address these challenges, this research introduces a data generation method using a digital twin model, simulating physical conditions to generate data at a lower cost. Building on this, a Multi-gate Mixture-of-Experts multi-task prediction model with Long Short-Term Memory (MMoE-LSTM) module is developed. LSTM enhances the model’s ability to extract nonlinear features from data, improving learning. Additionally, a dynamic weighting strategy, based on coefficient of variation weighting and ridge regression, is employed to automate loss weight adjustments and address imbalances in multi-task learning. The proposed model, validated on datasets created using the digital twin model, achieved over 95% predictive accuracy for multiple tasks, demonstrating that this method is effective.

show abstract

“…The optimized structures have the same characteristics of a higher aspect ratio and thinner wall thickness. Xu et al [27] establish an optimal design model based on the backpropagation (BP) neural network method and the global search algorithm to attain the optimal design results of the regenerative cooling structural parameters. The optimized SSME-MCC regenerative cooling channel reduces both the maximum wall temperature and the coolant pressure loss.…”

Section: Introductionmentioning

confidence: 99%

Heat Transfer Analysis and Structural Optimization for Spiral Channel Regenerative Cooling Thrust Chamber

Ping

et al. 2023

International Journal of Aerospace Engineering

View full text Add to dashboard Cite

There is currently a lack of efficient heat transfer analysis methodologies for spiral channel regenerative cooling that has been increasingly applied in liquid rocket engines. To figure out the heat transfer characteristics of the spiral channel regenerative cooling thrust chamber, a simple 1D method based on the traditional semi-empirical formula after correcting the flow velocity is proposed. The accuracy of this approach is verified by the 3D numerical simulation. The verified method is further used to analyze the distribution of inner wall temperature in the test case and optimize the channel’s parameters. The research shows that the maximum inner wall temperature cooled by the spiral channel is 8.5% lower than that of the straight channel under the same channel size and boundary condition, indicating that the application of the spiral channel significantly improves the cooling effect. In addition, the 1D model combined with the second-order response surface model is employed to optimize the channel width, channel height, pitch, and inner wall thickness aiming for the best cooling effect. The calculated maximum temperature of the inner wall after the structure optimization is 586.6 K, which is 29.8% lower than the initial structure before optimization.

show abstract

Optimal Design of Regenerative Cooling Structure Based on Backpropagation Neural Network

Cited by 4 publications

References 11 publications

Improved Wall Temperature Prediction for the LUMEN Rocket Combustion Chamber with Neural Networks

Improved Wall Temperature Prediction for the LUMEN Rocket Combustion Chamber with Neural Networks

Performance Prediction of the Elastic Support Structure of a Wind Turbine Based on Multi-Task Learning

Heat Transfer Analysis and Structural Optimization for Spiral Channel Regenerative Cooling Thrust Chamber

Contact Info

Product

Resources

About