基于神经网络的变截面再生冷却结构优化设计

doi:10.13675/j.cnki.tjjs.190832

推进技术 ›› 2021, Vol. 42 ›› Issue (5): 1112-1120.DOI: 10.13675/j.cnki.tjjs.190832

基于神经网络的变截面再生冷却结构优化设计

陶焰明，肖为，罗莲军，吴良成，江立军

中国航发湖南动力机械研究所燃烧室研究部，湖南株洲 412002

出版日期:2021-05-15 发布日期:2021-08-15
基金资助:
国家自然科学基金（51906234）。

Structural Optimal Design of Regenerative Cooling with Variable Section Based on Neural Network

Combustor Research Department，AECC Hunan Aviation Powerplant Research Institute，Zhuzhou 412002，China

Online:2021-05-15 Published:2021-08-15

摘要/Abstract

摘要： 针对目前再生冷却结构优化研究存在参数对比范围窄、依赖于经验关系式等问题，根据航空发动机燃烧室特点提出了一种变截面宽度再生冷却通道，并采用神经网络模型结合数值模拟结果，以通道出口燃油温度相对标准差、燃气侧最高壁温及壁温相对标准差为目标，预测了全参数范围内不同槽宽和、槽宽比及肋高下目标函数的变化规律。预测结果表明：当槽宽和较小时，增大肋高可以强化换热，但当槽宽和较大时，需减小肋高才能强化换热，这也揭示了为何有些文献中关于肋高对换热性能影响的结论会相反；此外，存在一个最佳槽宽比范围，可使得三个目标函数均最低；增大槽宽和可以明显降低燃气侧壁温及其不均匀度，减小肋高可以缩小不同管道出口燃油温度的差异。从预测空间内可选取多组综合流动换热性能较优的结构，优化后三组目标函数的加权值降低了9.09%。

关键词: 再生冷却通道;神经网络;航空发动机燃烧室;流动换热;变截面

Abstract: Nowadays， there are some problems such as narrow range in parametric contrast and dependence on empirical relations existing in the research of structural optimization about regenerative cooling. According to the characteristics of aero-engine combustors， a new structure of channels adopted regenerative cooling with variable sectional width was proposed. Neural network combined with numerical stimulation results was selected with the aim of RSD （Relative Standard Deviation） of fuel temperature in channel exit， maximum temperature of hot wall and RSD of hot wall temperature. Therefore， the changing rules of targeted function in different slot width sum， slot width ratio and fin height within the full parameter range were predicted. The results demonstrated that when the slot width sum is relatively small， heat transfer will be strengthened by increasing the fin height. However， when the slot width sum became relatively large， heat transfer will be enhanced by reducing the fin height. This explains the reasons why controversial conclusion about the relationship between fin height and heat transfer was presented in several essays. Moreover， there is an optimal range of slot width ratio that can make all these three objective functions lowest. The temperature of hot wall and its non-uniformity decline by increasing slot width sum， and the fall of the fin height leads to the difference of fuel temperature at the outlet of channels deceasing. Multiple structures with better performance in comprehensive flow-heat transfer can be obtained from the range of prediction. After this optimization， the weighted value of three objective functions dropped by 9.09%.

Key words: Regenerative cooling channel;Neural network;Aero-engine combustor;Flow and heat transfer;Variable section

陶焰明，肖为，罗莲军，吴良成，江立军. 基于神经网络的变截面再生冷却结构优化设计[J]. 推进技术, 2021, 42(5): 1112-1120.

TAO Yan-ming, XIAO Wei, LUO Lian-jun, WU Liang-cheng, JIANG Li-jun. Structural Optimal Design of Regenerative Cooling with Variable Section Based on Neural Network[J]. Journal of Propulsion Technology, 2021, 42(5): 1112-1120.

参考文献

[1] 尉曙明. 先进燃气轮机燃烧室设计研发［M］. 上海：上海交通大学出版社， 2014.
[2] Gascoin N， Abraham G， Gillard P. Thermal and Hydraulic Effects of Coke Deposit in Hydrocarbon Pyrolysis Process［J］. Journal of Thermophysics and Heat Transfer， 2012， 26（1）： 57-65.
[3] Taddeo L， Gascoin N， Fedioun I， et al. Dimensioning of Automated Regenerative Cooling： Setting of High-End Experiment［J］. Aerospace Science and Technology， 2015， 43： 350-359.
[4] Zhang C， Qin J， Yang Q， et al. Design and Heat Transfer Characteristics Analysis of Combined Active and Passive Thermal Protection System for Hydrogen Fueled Scramjet［J］. International Journal of Hydrogen Energy， 2015， 40（1）： 675-682.
[5] Zhang C， Qin J， Yang Q， et al. Indirect Measurement Method of Inner Wall Temperature of Scramjet with a State Observer［J］. Acta Astronautica， 2015， 115： 330-337.
[6] 章思龙，秦江，周伟星，等. 高超声速推进再生冷却研究综述［J］. 推进技术， 2018， 39（10）： 2177-2190.
[7] Jiang Y， Xu Y， Qin J， et al. The Flow Rate Distribution of Hydrocarbon Fuel in Parallel Channels with Different Cross Section Shapes［J］. Applied Thermal Engineering， 2018， 137（6）： 173-183.
[8] Jiang Y， Qin J， Chetehouna K， et al. Parametric Study on the Hydrocarbon Fuel Flow Rate Distribution and Cooling Effect in Non-Uniformly Heated Parallel Cooling Channels［J］. International Journal of Heat and Mass Transfer， 2018， 126（5）： 267-276.
[9] Zhang S， Feng Y， Zhang D， et al. Parametric Numerical Analysis of Regenerative Cooling in Hydrogen Fueled Scramjet Engines［J］. International Journal of Hydrogen Energy. 2016， 41（25）： 10942-10960.
[10] 牛禄，程惠尔，李明辉. 高宽比和粗糙度对再生冷却通道流动的影响［J］. 上海交通大学学报， 2002， 36（11）： 1612-1615.
[11] Zhang S， Qin J， Xie K， et al. Thermal Behavior Inside Scramjet Cooling Channels at Different Channel Aspect Ratios［J］. Journal of Propulsion and Power， 2015， 32（1）： 57-70.
[12] Husaini Y， Mitchell A， Rosengarten G， et al. Manifold Design for Uniform Fluid Distribution in Parallel Micro-Channels［C］. Bandung-Indonesia： 6th International Conference on System Engineering and Technology， 2016.
[13] Pistoresi C， Fan Y， Luo L. Numerical Study on the Improvement of Flow Distribution Uniformity Among Parallel Mini-Channels［J］. Chemical Engineering and Processing Process Intensification， 2015， 95： 63-71.
[14] 曹杰. 超临界碳氢燃料流动及凹陷强化传热数值研究［D］. 哈尔滨：哈尔滨工业大学， 2017.
[15] Xu K， Tang L， Meng H. Numerical Study of Supercritical Pressure Fluid Flows and Heat Transfer of Methane in Ribbed Cooling Tubes［J］. International Journal of Heat and Mass Transfer， 2015， 84： 346-358.
[16] Jiang Y， Qin J， Xu Y， et al. The Influences of Variable Sectional Area Design on Improving the Hydrocarbon Fuel Flow Distribution in Parallel Channels under Supercritical Pressure［J］. Fuel， 2018， 233（3）： 442-453.
[17] Fayyad U， Uthurusamy R. Evolving Data Mining into Solutions for Insights［J］. Communications of the ACM， 2002， 45（8）： 28-31.
[18] Svorcan J， Stupar S， Trivkovi? S， et al. Active Boundary Layer Control in Linear Cascades Using CFD and Artificial Neural Networks［J］. Aerospace Science and Technology， 2014， 39： 243-249.
[19] Zhou H， Soh Y C， Wu X. Integrated Analysis of CFD Data with K-Means Clustering Algorithm and Extreme Learning Machine for Localized HVAC Control［J］. Applied Thermal Engineering， 2015， 76（5）： 98-104.
[20] Calisto H， Martins N， Afgan N. Diagnostic System for Boilers and Furnaces Using CFD and Neural Networks［J］. Expert Systems with Applications， 2008， 35（4）： 1780-1787.
[21] 秦昂，张登成，魏扬，等. 超燃冲压发动机再生冷却结构的多目标优化设计［J］. 推进技术， 2018， 39（6）： 1331-1339.
[22] 何嘉华，周宏甫，刘二辉，等. 基于神经网络和遗传算法的温差发电器优化设计［J］. 机械设计， 2018， 35（9）： 31-36.
[23] Kantardzic M. Data Mining Concepts， Models， Methods， and Algorithm［M］. Piscatauow：IEEE Press， 2002.
[24] 张建强，朱谷君. 燃烧室中辐射热流分布的蒙特卡罗计算［J］. 航空动力学报， 1999， 14（3）： 251-254.
[25] 刘晗，刘跃凡. 小型航空发动机燃烧室热辐射环境数值模拟［J］. 应用科技， 2016， 43（1）： 72-75.
[26] 中国航空材料手册编辑委员会. 中国航空材料手册［M］. 北京：中国标准出版社， 2001.
[27] Zhong F， Fan X， Yu G， et al. Heat Transfer of Aviation Kerosene at Supercritical Conditions［J］. Journal of Thermophysics and Heat Transfer， 2009， 23（3）： 543-550.
[28] Wang C， Yang K， Tsai J， et al. Characteristics of Flow Distribution in Compact Parallel Flow Heat Exchangers， Part I： Typical Inlet Header［J］. Applied Thermal Engineering， 2011， 31（16）： 3326-34.
[29] 秦昂，周章文，张登成，等. 再生冷却结构参数对煤油流动换热的影响及优化［J］. 空军工程大学学报（自然科学版）， 2017， 18（4）： 7-11.
[30] 杨世铭，陶文铨. 传热学［M］. 北京：高等教育出版社， 2006.

基于神经网络的变截面再生冷却结构优化设计

Structural Optimal Design of Regenerative Cooling with Variable Section Based on Neural Network

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 0

编辑推荐

Metrics

本文评价