|本期目录/Table of Contents|

[1]许全宏,等.基于显式函数和神经网络的喷气燃料混合模型的研究及应用[J].燃烧科学与技术,2017,(05):391-397.[doi:10.11715/rskxjs.R201703025]
 Xu Quanhong,Liu Zhentao,et al.Mixing Model of Jet Fuel Based on Explicit Equations andNeural Networks and Its Application[J].Journal of Combustion Science and Technology,2017,(05):391-397.[doi:10.11715/rskxjs.R201703025]
点击复制

基于显式函数和神经网络的喷气燃料混合 模型的研究及应用()
分享到:

《燃烧科学与技术》[ISSN:1006-8740/CN:12-1240/TK]

卷:
期数:
2017年05
页码:
391-397
栏目:
出版日期:
2017-10-15

文章信息/Info

Title:
Mixing Model of Jet Fuel Based on Explicit Equations and Neural Networks and Its Application
作者:
许全宏1 2刘振涛1张 弛1 2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. 北京航空航天大学先进航空发动机协同创新中心,北京 100191
Author(s):
Xu Quanhong1 2Liu Zhentao1Zhang Chi1 2Lin Yuzhen1 2
1.National Key Laboratory of Science and Technology on Aero-Engine Aero-Thermodynamics,School of Energy and Power Engineering,Beihang University,Beijing 100191,China; 2.Collaborative Innovation Center for Advanced Aero-Engine,Beihang University,Beijing 100191,China
关键词:
喷气燃料代用组分显式函数神经网络混合模型
Keywords:
jet fuelsurrogate componentsexplicit equationsneural networksmixing model
分类号:
V312.1
DOI:
10.11715/rskxjs.R201703025
文献标志码:
A
摘要:
针对喷气燃料复杂的理化性质,采取显式函数和人工神经网络相结合的策略,以氢碳比、黏度和蒸馏曲 线等作为目标性质,发展了喷气燃料代用组分的构建方法,对混合燃料的理化性质具有很好的预测精度.并将此 混合模型应用于煤基喷气燃料的代用组分构建,所获得的代用组分模型与真实燃料之间的理化性质差异符合模拟 要求.
Abstract:
Surrogate model of jet fuel is one of the most important premises to high-fidelity numerical simulations of spray combustion in aero-engine.For complex physico-chemical properties of jet fuel,a strategy was proposed based on a mixing model combining explicit equations and implicit neural networks.Hydrogen-carbon ratio, viscosity,and distillation curve were chosen as the target properties,and the method of jet fuel surrogate formulation was developed,which could well simulate the target properties of mixture.The mixing model was used to build the surrogate of coal-derived synthetic jet fuel,and the difference of physico-chemical properties between surrogate components and real fuel could meet the simulating demands.

备注/Memo

备注/Memo:
收稿日期:2017-03-03. 基金项目:国家自然科学基金资助项目(51306010);北京市自然科学基金资助项目(3152020). 作者简介:许全宏(1969— ),男,博士,副教授,xuquanhong@buaa.edu.cn. 通讯作者:张 弛,男,博士,副教授,zhangchi@buaa.edu.cn.
更新日期/Last Update: