煤基喷气燃料代用组分神经网络混合构建方法

刘振涛; 许全宏; 张弛; 霍伟业; 林宇震

doi:10.13224/j.cnki.jasp.2016.11.012

煤基喷气燃料代用组分神经网络混合构建方法

doi: 10.13224/j.cnki.jasp.2016.11.012

刘振涛¹,
许全宏^1,2,
张弛^1,2,
霍伟业¹,
林宇震^1,2

1. 北京航空航天大学能源与动力工程学院航空发动机气动热力国家级重点试验室, 北京 100191;
2. 先进航空发动机协同创新中心, 北京 100191

基金项目:

国家自然科学基金（51306010）；北京市自然科学基金（3152020）

详细信息

作者简介:
刘振涛(1993-),男,辽宁瓦房店人,硕士生,主要从事航空替代燃料的研究.

中图分类号: V312.3
计量
- 文章访问数: 907
- HTML浏览量: 4
- PDF量: 588
- 被引次数: 0
出版历程
- 收稿日期: 2016-02-19
- 刊出日期: 2016-11-28

Surrogate formulation methodology of coal-based jet fuel based on neural network mixing model

1. National Key Laboratory of Science and Technology on Aero-Engine Aero-thermodynamics, School of Energy and Power Engineering, Beijing University of Aeronautics and Astronautics, Beijing 100191, China;
2. Collaborative Innovation Center for Advanced Aero-Engine, Beijing 100191, China

摘要

摘要: 为了建立航空燃料的喷雾模型，用于高保真液雾燃烧数值模拟，提出了基于人工神经网络混合模型的煤基喷气燃料代用组分构建方法.基于这一构建方法，重点针对煤基喷气燃料的雾化特性，利用多组分混合燃料的理化性质数据库对神经网络进行训练，获得了混合燃料理化性质隐式预测模型，结合随机投点优化方法，构建出能够很好地模拟煤基喷气燃料目标理化性质的代用组分.结果表明：该代用组分包含了5种碳氢化合物成分，摩尔分数为11.46%正癸烷、23.29%正十二烷、49.87%正十四烷、6.66%异辛烷和8.72%甲基环己烷.通过雾化特性实验，验证了代用组分对真实燃料雾化性能的模拟效果.该代用组分构建方法可以较好地解决混合燃料模拟过程中的非线性问题，通过改变目标理化性质可构建出相应代用组分.
- 煤基喷气燃料 /
- 代用组分 /
- 神经网络 /
- 优化 /
- 雾化
Abstract: In order to build spray model of aviation fuel for the high-fidelity numerical simulation of spray combustion, a surrogate formulation methodology was proposed for coal-based jet fuel based on artificial neural network mixture model. An implicit prediction model was developed on the blended physico-chemical properties using the multi-component fuel properties data set to train the neural network. And then the surrogate of coal-based jet fuel was formulated from the neural network mixing model by the stochastic points' optimization method, which could well simulate the target physico-chemical properties focusing on its atomization.Result shows that the surrogate is composed of 5 hydrocarbons(n-decane,n-dodecane,n-tetradecane,iso-octane and methylcyclohexane),their mole fraction are 11.46%, 23.29%,49.87%,6.66% and 8.72%, respectively. Compared with the real fuel, the atomization simulation of the surrogate was evaluated by experiments. This surrogate formulation methodology can solve the nonlinear issue in the mixing process, and formulate different surrogates for various requirements.
- coal-based jet fuel /
- surrogate /
- neural network /
- optimization /
- atomization

HTML

参考文献(19)

[1]	白凤华,苏海全,张玉龙,等.F-T合成技术生产替代燃料对环境的影响及对策[J].环境工程学报,2008,2(12):1719-1723. BAI Fenghua,SU Haiquan,ZHANG Yulong,et al.Environmental impact and relevant prevention countermeasure for using F-T synthesis technology to produce alternative fuels[J].Chinese Journal of Environmental Engineering,2008,2(12):1719-1723.(in Chinese)
[2]	白尔铮.费托合成燃料的经济性及发展前景[J].化工进展,2004,23(4):370-374. BAI Erzheng.Economics and prospects of FT synfuels[J].Chemical Industry and Engineering Progress,2004,23(4):370-374.(in Chinese)
[3]	Edwards T,Maurice L Q.Surrogate mixtures to represent complex aviation and rocket fuels[J].Journal of Propulsion and Power,2001,17(2):461-466.
[4]	Kim D,Martz J,Violi A.A surrogate for emulating the physical and chemical properties of conventional jet fuel[J].Combustion and Flame,2014,161(6):1489-1498.
[5]	王玉秀.由等张比容及克分子体积求表面张力[J].天然气化工设计,1979(1):87-89.
[6]	王俊清.BP神经网络及其改进[J].重庆工学院学报,2007,21(3):75-77. WANG Junqing.BP neural network and its improvement[J].Journal of Chongqing Institute of Technology,2007,21(3):75-77.(in Chinese)
[7]	Rocabruno-Valdés C I,Ramírez-Verduzco L F,Hernández J A.Artificial neural network models to predict density,dynamic viscosity,and cetane number of biodiesel[J].Fuel,2015,147:9-17.
[8]	Barradas-Filho A O,Barros A K D,Labidi S,et al.Application of artificial neural networks to predict viscosity,iodine value and induction period of biodiesel focused on the study of oxidative stability[J].Fuel,2015,145:127-135.
[9]	黄丽.BP神经网络算法改进及应用研究[D].重庆:重庆师范大学,2008. HUANG Li.BP neural network algorithm improvement and application research[D].Chongqing:Chong Qing Normal University,2008.(in Chinese)
[10]	柳松青.MATLAB神经网络BP网络研究与应用[J].计算机工程与设计,2003,24(11):81-83,88. LIU Songqing.Research and application on MATLAB BP neural nerwork[J].Computer Engineering and Design,2003,24(11):81-83,88.(in Chinese)
[11]	黄勇,林宇震,樊未军,等.燃烧与燃烧室[M].北京:北京航空航天大学出版社,2009.
[12]	Rizk N K.Fuel atomization effects on combustor performance[R].AIAA-2004-3540,2004.
[13]	Lefebvre H,Ballal D R.Gas turbine combustion[M].3rd ed.Boca Raton:CRC Press Incorporation,2010.
[14]	Han L,Liu G,Zhang X.Alternative jet fuel from hydroisomerization of coal-based Fischer-Tropsch middle distillates[J].American Chemical Society:Division of Energy and Fuels,2012(57):817-818.
[15]	徐建新,张洪起,刘继东,等.电解质NRTL模型的研究进展及应用[J].化工进展,2013,32(9):2023-2029. XU Jianxin,ZHANG Hongqi,LIU Jidong,et al.Research progress and application of electrolyte NRTL model[J].Chemical Industry and Engineering progress,2013,32(9):2023-2029.(in Chinese)
[16]	夏云龙,项曙光.电解质NRTL模型的发展及应用[J].河北化工,2004,27(1):9-12. XIA Yunlong,XIANG Shuguang.The development and application of the electrolyte NRTL model[J].Hebei Chemical Industry,2004,27(1):9-12.(in Chinese)
[17]	王小川,史峰,郁磊,等.MATLAB神经网络43个案例分析[M].北京:北京航空航天大学出版社,2013.
[18]	霍伟业,林宇震,张驰,等.正癸烷作为航空煤油雾化过程代理燃料的研究[J].航空动力学报,2016,31(1):188-195. HUO Weiye,LIN Yuzhen,ZHANG Chi,et al.Research on n-decane as surrogate fuel of aviation kerosene in atomization process[J].Journal of Aerospace Power,2016,31(1):188-195.(in Chinese)
[19]	杨晔,张镇西,蒋大宗.微粒直径及直径分布的激光测量技术[J].激光技术,1997,21(2):122-127. YANG Ye,ZHANG Zhenxi,JIANG Dazong.Laser techniques of measuring particles size and their size distribution[J].Laser Technology,1997,21(2):122-127.(in Chinese)