基于神经网络的类乘波体飞行器FADS算法研究

Research on Algorithms of Quasi-waverider Vehicle FADS Based on Neural Network

大气数据是飞行器飞行的重要参数,大气数据系统是必备的机载航电系统。嵌入式大气数据系统(FADS)是新一代大气数据系统,可用于类乘波体飞行器。飞行器外形特殊,大飞行包线内FADS压力场模型复杂,解算算法尚不完备。针对飞行器的特点,利用三维几何建模和计算流体动力学(CFD)计算的方法,分析FADS压力场模型特性,设计并验证了基于神经网络的类乘波体飞行器FADS算法,结果表明,算法对马赫数、攻角和侧滑角大气参数的解算可行有效。

Air data is important flight data and air data system is essential airborne avionics system.The flush air data system（FADS） is a new kind of air data system which is suitable to the quasi-waverider vehicle.The quasi-waverider vehicle has special configuration.Its FADS model of pressure field is complex and algorithm is not complete in large flight envelope.Aimed at the characteristic of the vehicle,the model characteristic of FADS pressure field is analyzed with three-dimensional geometric modeling and CFD computing.FADS algorithms of the vehicle are designed and tested based on neural network.The results show that the algorithms are effective for computing of mach number、angle of attack and angle of sideslip.