基于卷积神经网络的运载火箭测发网络流量异常检测技术

运载火箭测发网络是维系各型号运载火箭远距离测试及发射控制的重要国防基础设施,对测发网络流量进行异常检测是保证其正常工作的关键举措。近年来,随着测发网络功能的拓展,其面临的网络安全威胁越来越严重,而当前的安全检测主要依赖于基于异常特征库匹配的流量异常检测方法,这种检测方法对一些新型攻击检测能力非常有限。本文结合运载火箭测发网络实际特点,针对以使用用户数据报协议(UDP)为主的测发网络流量,设计一种新的基于固定数据包数目的流量图片样本生成方法,首次提出在测发网络流量异常检测问题上使用卷积神经网络,以原始网络流量作为输入,避开难以解决的人工特征集设计问题。通过测发网络真实网络流量数据进行实验,取得了较高的精度、召回率和准确率,验证了本方法具备一定的实用性。     

改进升力线理论和风洞试验结合的气动弹性修正方法

本文介绍了一种基于亚音速稳态定常流改进升力线理论与风洞试验相结合的大展弦比亚音速飞机的弹性翼面气动力分布载荷修正方法,设计目的是为了考虑具有大展弦比、弹性翼面结构的飞机翼面结构弹性变形对气动载荷分布的影响。     

弹性基础上预应力任意四边形中厚板的横向振动

本文研究弹性基础上任意四边形中厚板在预加面内荷载作用下的横向振动问题。通过坐标变换将任意四边形区域映照到一个2×2的单位方板区域。用一组数学上完备的二元多项式作为位形函数,采用pb-2Ritz法求得板的自振频率。并通过算例考察了基础刚度参数、预加面内荷载、边界条件、横向剪切变形等对板振动特性的影响。     

基于SAGWO算法的UCAVs动态协同任务分配

通过分析无人作战飞机（UCAV）优势概率和任务联合威胁以及定义任务时间,建立了以目标价值毁伤、编队损耗代价和时间消耗为性能指标的多无人作战飞机（UCAVs）多约束动态任务分配数学模型,采用改进的灰狼优化（GWO）算法对数学模型进行求解;针对基本GWO算法求解早熟的缺点,给出了自适应调整策略和跳出局部最优策略,引入了二次曲线控制方法;对UCAVs动态协同任务分配特点,设计了目标任务序列编码方式,提出了基于自适应GWO（SAGWO）算法的UCAVs多目标动态任务分配方法。从静态与动态2种情况分别对该方法进行仿真验证;仿真结果表明,该方法是有效的,相比较于其他算法,其优化过程快速精准。      

基于NFTET的高超声速飞行器再入容错制导

针对以X-33为对象的三自由度高超声速飞行器,采用相邻可行轨迹存在定理(NFTET)设计了容错制导律以解决再入段执行器发生故障的轨迹重构问题。在标称情况下采用预测校正算法生成满足再入过程约束和终端约束要求的再入轨迹;当执行器发生故障时,飞行器气动参数、结构和舵面力矩都可能发生不可预测的变化,原先的轨迹不再满足制导要求,因此需要设计新型容错制导律。针对实际再入制导模型,基于NFTET设计容错制导算法对轨迹进行重构,得到满足故障情况下制导任务的可行轨迹。从仿真结果中可以看出,容错制导算法生成的新轨迹重新回到了约束范围之内,轨迹呈收敛趋势,使得高超声速飞行器从故障恢复到正常飞行状态,提高了飞行器的自主容错能力。     

Adaptive accurate tracking control of HFVs in the presence of dead-zone and hysteresis input nonlinearities

A novel accurate tracking controller is developed for the longitudinal dynamics of Hypersonic Flight Vehicles (HFVs) in the presence of large model uncertainties, external disturbances and actuator nonlinearities. Distinct from the state-of-the-art, besides being continuity, no restrictive conditions have been imposed on the HFVs dynamics. The system uncertainties are skillfully handled by being seen as bounded “disturbance terms”. In addition, by means of back-stepping adaptive technique, the accurate tracking (i.e. tracking errors converge to zero as time approaches infinity) rather than bounded tracking (i.e. tracking errors converge to residual sets) has been achieved. What’s more, the accurate tracking problems for HFVs subject to actuator dead-zone and hysteresis are discussed, respectively. Then, all signals of closed-loop system are verified to be Semi-Global Uniformly Ultimate Boundness (SGUUB). Finally, the efficacy and superiority of the developed control strategy are confirmed by simulation results.     

基于Kalman滤波的空天飞行器再入制导算法

针对空天飞行器应用传统数值预测校正再入制导算法实时性不佳的问题,提出一种基于Kalman滤波的预测校正制导算法。该算法采取四阶多项式拟合速度-高度飞行剖面,利用Kalman滤波估计选定的速度点对应的高度,得到满足再入走廊及航程要求的拟合系数。在此基础上,减少一个终端约束,增加一个待估计剖面参数,可实现对再入过程飞行时间的调节。研究发现,再入过程中通过在线辨识修正不确定性参数能够提高制导指令的适应性;飞行末段利用跟踪参考剖面制导可有效避免飞行速度与终端速度接近时发生拟合系数求解发散的问题。多组不同再入条件下的算例仿真结果表明,基于Kalman滤波的空天飞行器再入制导算法实时性好,制导精度高,能够实现飞行时间可控,具有较强的鲁棒性和工程应用潜力。     

Simple method for performance evaluation of multistage rockets

Multistage rockets are commonly employed to place spacecraft and satellites in their operational orbits. Performance evaluation of multistage rockets is aimed at defining the maximum payload mass at orbit injection, for specified structural, propulsive, and aerodynamic data of the launch vehicle. This work proposes a simple method for a fast performance evaluation of multistage rockets. The technique at hand is based on three steps: (i) the flight-path angle at each stage separation is guessed, (ii) the spacecraft velocity is maximized at the first and second stage separation, and (iii) for the last stage the thrust direction is obtained through the particle swarm optimization technique, in conjunction with the use of the Euler–Lagrange equations and the Pontryagin minimum principle. The coast duration at the second stage separation is optimized as well. The method at hand is extremely simple and easy-to-implement, but nevertheless it proves to be capable of yielding near-optimal ascending trajectories for a multistage launch vehicle with realistic structural, propulsive, and aerodynamic characteristics. The solutions found with the technique under consideration can be employed either for a rapid evaluation of the multistage rocket performance or as guesses for more refined optimization algorithms.     

基于干扰观测器的高超声速飞行器预测控制器设计

针对具有强耦合特性与模型不确定性特点的高超声飞行器控制问题,提出一种新型的姿态预测控制器设计方法。引入参考模型,建立了飞行器姿态预测控制模型。基于此,利用预测理论设计了飞行器的预测控制器,同时设计了干扰观测器实时观测外界未知干扰来进行补偿控制,从而实现滚动优化的目的;基于干扰观测值与真值的误差,利用Lyapunov稳定性理论,确定了控制精度与预测步长大小的关系;最后,在参数标称与拉偏的情形下进行了高超声速飞行器姿态控制系统仿真,仿真结果表明,干扰观测器能快速跟踪干扰,并且所设计的预测步长可以满足飞行器高精度的控制要求。