论文部分内容阅读
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.
In order to establish aerosol fuel aerosol model for numerical simulation of high-fidelity liquid-vapor combustion, an alternative method to construct coal-based jet fuel based on the hybrid model of artificial neural network is proposed.Based on this construction method, Atomization characteristics, using the multi-component hybrid fuel physical and chemical properties of the database to train the neural network to obtain a hybrid fuel physical and chemical properties of the implicit prediction model, combined with random optimization method to build a well to simulate the coal-based jet fuel target The results showed that the substitute component contained five kinds of hydrocarbon components with the molar fraction of 11.46% n-decane, 23.29% n-dodecane, 49.87% n-tetradecane and 6.66% iso-sy Alkane and 8.72% methylcyclohexane.The atomization characteristics experiments verify the simulation effect of the substitute components on the real fuel atomization performance.The proposed method can be used to solve the problem of non-linear Problem, by changing the target physical and chemical properties can be constructed corresponding substitute components.