基于遗传神经网络的高能固体推进剂高压燃烧性能计算

建立并利用遗传(GA-BP)神经网络对NEPE类高能固体推进剂高压燃烧性能进行了模拟计算。针对计算需求,对NEPE类高能固体推进剂配方进行了全新表征,提出了13个表征参数。燃速预示结果表明,该方法计算误差小于10%,精度较高,能指导高能固体推进剂高压燃烧性能研究及配方设计;同时,也说明该表征方法能反映出此类配方的本质特征。该研究为高能固体推进剂燃速预估提供了新方法。

Calculation for high-pressure combustion properties of high-energy solid propellant based on GA-BP neural network

A genetic algorithm(GA)-back-propagation(BP)neural network was established.The high-pressure combustion properties of NEPE high-energy solid propellant were simulated and calculated by using the GA-BP neural network.Aiming at calculation requirement,NEPE high-energy solid propellant formulation was characterized,and 13 parameters were put forward.The burning-rate prediction results show that the calculation error of the method is less than 10%,and its accuracy is high;the method can be used for high-pressure combustion property research and formulation design of NEPE high-energy solid propellant.At the same time,the method can reflect essential characteristics of the formulation,and the investigation provides a kind of new method for burning-rate prediction of high-energy solid propellant.