基于深度学习驱动的L型定向热疏导机理

doi:10.7527/S1000-6893.2020.24242

流体力学与飞行力学

本期目录 | 过刊浏览 | 高级检索

前一篇 | 后一篇

基于深度学习驱动的L型定向热疏导机理

王泽林¹, 籍日添¹, 惠心雨¹, 丁晨², 汪辉¹, 白俊强¹

1. 西北工业大学航空学院, 西安 710072;
2. 中国运载火箭技术研究院, 北京 100076

收稿日期:2020-05-19 修回日期:2020-06-12 出版日期:2021-06-15 发布日期:1900-01-01
通讯作者: 汪辉 E-mail:wanghui2018@nwpu.edu.cn
基金资助:
国家自然科学基金（11802245）

L-shaped directional heat transfer based on deep learning

WANG Zelin¹, JI Ritian¹, HUI Xinyu¹, DING Chen², WANG Hui¹, BAI Junqiang¹

1. School of Aeronautics, Northwestern Polytechnical University, Xi'an 710072, China;
2. China Academy of Launch Vehicle Technology, Beijing 100076, China

Received:2020-05-19 Revised:2020-06-12 Online:2021-06-15 Published:1900-01-01
Supported by:
National Natural Science Foundation of China (11802245)

摘要/Abstract

摘要： 碳/碳（C/C）复合材料具有热导率大、比强度高、耐烧蚀和耐冲刷等优异特性，被广泛应用于飞行器的热防护系统中，其有效导热系数对于实际应用而言是重要的热物理性质，尽管可以通过有效介质理论、对热扩散方程直接求解和玻尔兹曼输运方程等传统方法计算C/C复合材料有效导热系数，但这些数值方法通常十分耗时。本文引入深度学习方法，将格子玻尔兹曼（LBM）的三维格子模型作为三维卷积神经网络（3D-CNN）微观结构，不仅解决了三维微观结构模型难以捕获的问题，还便于实现数值计算模型和CNN模型的同步简化，利用3D-CNN快速精准地预测三维三相C/C复合结构的有效导热系数，基于此对内置L型高导热碳纤维丝的定向热疏C/C复合结构的有效导热系数进行快速预测和研究。研究表明，CNN模型在LBM传热计算上表现出强大的学习能力，但在测试样本结构孔隙率过分超出训练集时预测误差将大幅增加，且当孔隙率变化范围从30%~35%变化到55%~60%时，CNN模型"内插"预测的相对误差较模型"外推"降低了0.93%~30.72%。在C/C复合结构中内置L型高导热碳纤维丝可以将高温区域的热量沿纤维方向定向疏导至低温区域。

关键词: L型定向热疏导, 有效导热系数, 机器学习, 卷积神经网络, 格子玻尔兹曼方法

Abstract: Carbon/Carbon (C/C) composite materials are widely used in thermal protection systems of aircraft for their excellent characteristics such as high thermal conductivity, high specific strength, ablation resistance and erosion resistance, among which the effective thermal conductivity is an important physical property for practical applications. Traditional methods of studying effective thermal conductivity of composite materials such as the effective medium theory, the direct solution of heat diffusion equation or the Boltzmann transport equation are usually time-consuming. This paper introduces a deep learning method with the Lattice Boltzmann Method's (LBM's) three-dimensional lattice model as the microstructure sample of the Three-Dimensional Convolutional Neural Network (3D-CNN). This method not only overcomes the difficulty of capturing the three-dimensional microstructure model, but facilitates simultaneous simplification of the numerical calculation model and the CNN model. In this way, the effective thermal conductivity of the three-dimensional three-phase C/C composite structure can be predicted quickly and accurately by the 3D-CNN method. In addition, we quickly predict and study the effective thermal conductivity of the directional heat transfer C/C composite structure with built-in L-shaped carbon fiber with high thermal conductivity. Results show that the CNN model displays a strong learning ability in the LBM heat transfer calculation; however, when the porosity of the testing sample structure surpasses the training set excessively, the prediction error will increase significantly. When the porosity changes from 30%-35% to 55%-60%, the relative error of the CNN model "interpolation" is 0.93%-30.72% lower than that of the model "extrapolation". The built-in L-shaped carbon fiber with high thermal conductivity in the C/C composite structure can direct the heat in high temperature areas to low temperature areas along the fiber.

Key words: L-shaped directional heat transfer, effective thermal conductivity, machine learning, convolutional neural networks, lattice Boltzmann method

中图分类号:

V211.3

王泽林, 籍日添, 惠心雨, 丁晨, 汪辉, 白俊强. 基于深度学习驱动的L型定向热疏导机理[J]. 航空学报, 2021, 42(6): 124242-124242.

WANG Zelin, JI Ritian, HUI Xinyu, DING Chen, WANG Hui, BAI Junqiang. L-shaped directional heat transfer based on deep learning[J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2021, 42(6): 124242-124242.

参考文献

[1] LIU X S, FU Q G, WANG H, et al. Microstructure, thermophysical property and ablation behavior of high thermal conductivity carbon/carbon composites after heat-treatment[J]. Chinese Journal of Aeronautics, 2020, 33(5):1541-1548.
[2] 李湘郡, 李彦斌, 郭飞, 等. C/C复合材料的压缩强度分布与可靠性评估[J]. 航空学报, 2019, 40(8):222853. LI X J, LI Y B, GUO F, et al. Compression strength distribution and reliability assessment of C/C composites[J]. Acta Aeronautica et Astronautica Sinica, 2019, 40(8):222853(in Chinese).
[3] CHOWDHURY P, SEHITOGLU H, RATEICK R. Damage tolerance of carbon-carbon composites in aerospace application[J]. Carbon, 2018, 126:382-393.
[4] WANG P P, LI H J, SUN J, et al. The effect of HfB₂ content on the oxidation and thermal shock resistance of SiC coating[J]. Surface and Coatings Technology, 2018, 339:124-131.
[5] LI L, LI H J, YIN X M, et al. Microstructure evolution of SiC-ZrB₂-ZrC coating on C/C composites at 1773 K under different oxygen partial pressures[J]. Journal of Alloys and Compounds, 2016, 687:470-479.
[6] MA J, NAN C W. Effective-medium approach to thermal conductivity of heterogeneous materials[J]. Annual Review of Heat Transfer, 2014, 17:303-331.
[7] PIETRAK K, WIS'NIEWSKI TS. A review of models for effective thermal conductivity of composite materials[J]. Concentrating Solar Power Technology, 2015, 95(1):14.
[8] CHENG P, HSU C T. The effective stagnant thermal conductivity of porous media with periodic structures[J]. Journal of Porous Media, 1999, 2(1):19-38.
[9] TONG Z, LIU M, BAO H. A numerical investigation on the heat conduction in high filler loading particulate composites[J]. International Journal of Heat and Mass Transfer, 2016, 100:355-361.
[10] WANG M R, PAN N. Modeling and prediction of the effective thermal conductivity of random open-cell porous foams[J]. International Journal of Heat and Mass Transfer, 2008, 51(5-6):1325-1331.
[11] HASSELMAN D P H, JOHNSON L F. Effective thermal conductivity of composites with interfacial thermal barrier resistance[J]. Journal of Composite Materials, 1987, 21(6):508-515.
[12] EVERY A G, TZOU Y, HASSELMAN D P H, et al. The effect of particle size on the thermal conductivity of ZnS/diamond composites[J]. Acta Metallurgica et Materialia, 1992, 40(1):123-129.
[13] DEMUTH C, MENDES M A A, RAY S, et al. Performance of thermal lattice Boltzmann and finite volume methods for the solution of heat conduction equation in 2D and 3D composite media with inclined and curved interfaces[J]. International Journal of Heat and Mass Transfer, 2014, 77:979-994.
[14] WANG M R, HE J H, YU J Y, et al. Lattice Boltzmann modeling of the effective thermal conductivity for fibrous materials[J]. International Journal of Thermal Sciences, 2007, 46(9):848-855.
[15] WANG H, CHEN L, QU Z G, et al. Modeling of multi-scale transport phenomena in shale gas production-A critical review[J]. Applied Energy, 2020, 262:114575.
[16] MISHRA S C, ROY H K. Solving transient conduction and radiation heat transfer problems using the lattice Boltzmann method and the finite volume method[J]. Journal of Computational Physics, 2007, 223(1):89-107.
[17] WEI H, BAO H, RUAN X L. Genetic algorithm-driven discovery of unexpected thermal conductivity enhancement by disorder[J]. Nano Energy, 2020, 71:104619.
[18] YU W, XIE H Q, XIN S, et al. Thermal properties of polymethyl methacrylate composite containing copper nanoparticles[J]. Journal of Nanoscience and Nanotechnology, 2015, 15(4):3121-3125.
[19] 陈海昕, 邓凯文, 李润泽. 机器学习技术在气动优化中的应用[J]. 航空学报, 2019, 40(1):522480. CHEN H X, DENG K W, LI R Z. Utilization of machine learning technology in aerodynamic optimization[J]. Acta Aeronautica et Astronautica Sinica, 2019, 40(1):522480(in Chinese).
[20] 高晓光, 李新宇, 岳勐琪, 等. 基于深度学习的地空导弹发射区拟合算法[J]. 航空学报, 2019, 40(9):322858. GAO X G, LI X Y, YUE M Q, et al. Fitting algorithm of ground-to-air missile launching area based on deep learning[J]. Acta Aeronautica et Astronautica Sinica, 2019, 40(9):322858(in Chinese).
[21] WEI H, ZHAO S S, RONG Q Y, et al. Predicting the effective thermal conductivities of composite materials and porous media by machine learning methods[J]. International Journal of Heat and Mass Transfer, 2018, 127:908-916.
[22] RONG Q Y, WEI H, HUANG X Y, et al. Predicting the effective thermal conductivity of composites from cross sections images using deep learning methods[J]. Composites Science and Technology, 2019, 184:107861.
[23] 高峰阁, 迟卫东, 张鸿翔, 等. 国内外MPCF发展概况与展望[J]. 高科技纤维与应用, 2015, 40(5):33-37. GAO F G, CHI W D, ZHANG H X, et al. Development survey and prospect of mesophase pitch-based carbon fiber[J]. Hi-Tech Fiber & Application, 2015, 40(5):33-37(in Chinese).
[24] BENZI R, SUCCI S, VERGASSOLA M. The lattice Boltzmann equation:Theory and applications[J]. Physics Reports, 1992, 222(3):145-197.
[25] ZHAO K, LI Q, XUAN Y M. Investigation on the three-dimensional multiphase conjugate conduction problem inside porous wick with the lattice Boltzmann method[J]. Science in China Series E:Technological Sciences, 2009, 52(10):2973-2980.
[26] WANG J K, WANG M R, LI Z X. A lattice Boltzmann algorithm for fluid-solid conjugate heat transfer[J]. International Journal of Thermal Sciences, 2007, 46(3):228-234.
[27] D'ORAZIO A, CORCIONE M, CELATA G P. Application to natural convection enclosed flows of a lattice Boltzmann BGK model coupled with a general purpose thermal boundary condition[J]. International Journal of Thermal Sciences, 2004, 43(6):575-586.
[28] ZOU Q S, HE X Y. On pressure and velocity boundary conditions for the lattice Boltzmann BGK model[J]. Physics of Fluids, 1997, 9(6):1591-1598.
[29] D'ORAZIO A, SUCCI S, ARRIGHETTI C. Lattice Boltzmann simulation of open flows with heat transfer[J]. Physics of Fluids, 2003, 15(9):2778-2781.
[30] WANG M R, WANG J K, PAN N, et al. Mesoscopic predictions of the effective thermal conductivity for microscale random porous media[J]. Physical Review E, Statistical, Nonlinear, and Soft Matter Physics, 2007, 75(3):036702.
[31] KINGMA D P, BA J. Adam:A method for stochastic optimization[EB/OL]. arXiv preprint:1412.6980, 2015.

E-mail：hkxb@buaa.edu.cn

关于我们

期刊社服务

专业学科

封面文章

友情链接

主管单位：中国科学技术协会主办单位：中国航空学会北京航空航天大学

基于深度学习驱动的L型定向热疏导机理

L-shaped directional heat transfer based on deep learning

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	韩淞宇, 邵海东, 姜洪开, 张笑阳. 基于提升卷积神经网络的航空发动机高速轴承智能故障诊断[J]. 航空学报, 2022, 43(9): 625479-625479.
[2]	段玉聪, 王学德, 周鑫, 张佩宇, 郭西洋, 成星, 樊军伟. 粉末床激光成形熔池辐射强度信号的机器学习[J]. 航空学报, 2022, 43(9): 425855-425855.
[3]	李海泉, 陈小前, 左林玄, 赵卓林. 基于随机森林的飞行载荷代理模型分析方法[J]. 航空学报, 2022, 43(3): 225640-225640.
[4]	吴子轩, 张宁, 高凯烨, 彭锐. 基于风险偏好调整的随机森林算法的航班航程油量预测[J]. 航空学报, 2022, 43(2): 224933-224933.
[5]	奕建苗, 邓枫, 覃宁, 刘学强. 快速预测跨声速流场的深度学习方法[J]. 航空学报, 2022, 43(11): 526747-526747.
[6]	王辉, 贾自凯, 金忍, 林德福, 范军芳, 徐超. 无人机视觉引导对接过程中的协同目标检测[J]. 航空学报, 2022, 43(1): 324854-324854.
[7]	李红光, 于若男, 丁文锐. 基于深度学习的小目标检测研究进展[J]. 航空学报, 2021, 42(7): 24691-024691.
[8]	丁文锐, 刘春蕾, 李越, 张宝昌. 二值卷积神经网络综述[J]. 航空学报, 2021, 42(6): 24504-024504.
[9]	江波, 屈若锟, 李彦冬, 李诚龙. 基于深度学习的无人机航拍目标检测研究综述[J]. 航空学报, 2021, 42(4): 524519-524519.
[10]	李霓, 布树辉, 尚柏林, 李永波, 汤志荔, 张伟伟. 飞行器智能设计愿景与关键问题[J]. 航空学报, 2021, 42(4): 524752-524752.
[11]	叶舒然, 张珍, 王一伟, 黄晨光. 基于卷积神经网络的深度学习流场特征识别及应用进展[J]. 航空学报, 2021, 42(4): 524736-524736.
[12]	任峰, 高传强, 唐辉. 机器学习在流动控制领域的应用及发展趋势[J]. 航空学报, 2021, 42(4): 524686-524686.
[13]	何创新, 邓志文, 刘应征. 湍流数据同化技术及应用[J]. 航空学报, 2021, 42(4): 524704-524704.
[14]	魏晓良, 潮群, 陶建峰, 刘成良, 王立尧. 基于LSTM和CNN的高速柱塞泵故障诊断[J]. 航空学报, 2021, 42(3): 423876-423876.
[15]	余敏, 罗建军, 王明明. 基于机器学习的空间翻滚目标实时运动预测[J]. 航空学报, 2021, 42(2): 324149-324149.