VIRTUAL TARGET DIFFERENTIAL GAME MIDCOURSE GUIDANCE LAW FOR HYPERSONIC CRUISE MISSILE BASED ON NEURAL NETWORK

For the high altitude cruising flight phase of a hypersonic cruise missile （HCM）, a relative motion mod- el between the missile and the target is established by defining virtual target and combining the theory of the dif- ferential geometry with missile motion equations. Based on the model, the motion between the missile and the tar- get is considered as a single target differential game problem, and a new open-loop differential game midcourse guidance law （DGMGL） is deduced by solving the corresponding Hamiltonian Function. Meanwhile, a new struc- ture of a closed-loop DGMGL is presented and the training data for back propagation neural network （BPNN） are designed. By combining the theory of BPNN with the open-loop DGMGL obtained above, the law intelligence is realized. Finally, simulation is carried out and the validity of the law is testified.

Online task planning method of anti-ship missile based on rolling optimization

Based on the wave attack task planning method in static complex environment and the rolling optimization framework, an online task planning method in dynamic complex environment based on rolling optimization is proposed. In the process of online task planning in dynamic complex environment,online task planning is based on event triggering including target information update event, new target addition event, target failure event, weapon failure event, etc., and the methods include defense area reanalysis, parameter space update, and mission re-planning. Simulation is conducted for different events and the result shows that the index value of the attack scenario after re-planning is better than that before re-planning and according to the probability distribution of statistical simulation method, the index value distribution after re-planning is obviously in the region of high index value, and the index value gap before and after re-planning is related to the degree of posture change.

Three-Dimensional Discrete Observability Analysis for Air-to-Air Missile Target Tracking

The interception information of infrared（ IR）-guided air-to-air missiles（ AAM） is mainly estimated only using the basic bearing measurements. In order to intercept highly maneuverable targets,it is essential to study the system observability to improve the target tracking system performance.The uniqueness of this paper is that the observability analysis is derived based on a discrete three-dimensional （3D） system model. During the maneuvering scenario,the system is approximated by a segment-by-segment system. The relationship between missile-target motion and observability is given by direct and dual approaches. Meanwhile sufficient observability conditions are derived. Moreover,a numerical simulation is conducted and an alternate method is provided to reinforce the proposed observability analysis results.

Discussion of the target-missile control scheme with supersonic speed at minimum altitude

An antiship missile with supersonic speed at minimum altitude is an effective weapon to break through a defense line. The former Soviet Union was a leader in this field since it had developed several kinds of antiship missiles which obtained supersonic speed at minimum altitudes. To counter this kind of missile, many countries have been developing corresponding antimissiles. For the purpose of verifing the antimissile missile′s effectiveness in intercepting antiship missiles, a target-missile is needed. A target-missle is cheaper and can imitate the main characteristics of antiship missiles with supersonic speed at minimum altitude. In this paper, the control scheme of a target missile flying with supersonic speed at minimum altitude is studied. To counter the problem of hedgehopping over the sea, a control scheme utilizing a SINS+altimeter was proposed. In this scheme, both the quick response ability of altitude control and the anti-jamming problem were considered. A simulation experiment shows that when an integrated altitude control system is used, the anti-disturbance ability of the integrated altitude is good and the response speed of altitude control system can be dramatically improved.

A distributed decision method for missiles autonomous formation based on potential game

The distributed cooperative decision problems of missiles autonomous formation with network packet loss are investigated by using the potential game based on formation principles.In particular,a dynamic target allocation method for missiles formation is provided based on the potential game and formation principles,after the introduction of cooperative guidance and control system of the missiles formation.Then we seek the optimization of a global utility function through autonomous missiles that are capable of making individually rational decisions to optimize their own utility functions.The first important aspect of the problem is to design an individual utility function considering the characteristics of the missiles formation,with which the objective of the missiles are localized to each missile yet aligned with the global utility function.The second is to equip the missiles with an appropriate coordination mechanism with each missile pursuing the optimization of its own utility function.We present the design procedure for the utility,and present a coordination mechanism based on spatial adaptive play and then introduce the idea of“cyclical selected spatial adaptive play”and“negotiation based on time division multiple address(TDMA)protocol formation support network”.Finally,we present simulations for the distributed dynamic target allocation on the comprehensive digital simulation system,and the results illustrate the effectiveness and engineering applicability of the method.

Variable structure guidance law for attacking surface maneuver targets

The characteristics of surface maneuver targets are analyzed and a 3-D relative motion model for missiles and targets is established. A variable structure guidance law is designed considering the characteristics of targets. In the guidance law, the distance between missiles and targets as well as the missile-target relative velocity are all substituted by estimation values. The estimation errors, the target＇s velocity, and the maneuver acceleration are all treated as bounded disturbance. The guidance law proposed can be implemented conveniently in engineering with little target information. The performance of the guidance system is analyzed theoretically and the numerical simulation result shows the effectiveness of the guidance law.

Extended differential geometric guidance law for intercepting maneuvering targets

Without assumptions made on motion states of missile and target, an extended differential geometric guidance law is derived. Through introducing a line of sight rotation coordinate system, the derivation is simplified and has more explicit physical significances. The extended law is theoretically applicable to any engagement scenarios. Then, on basis of the extended law, a modified one is designed without the requirement of target acceleration and an approach is proposed to determining the applied direction of commanded missile acceleration. Qualitative analysis is carried out to study the capture performance and a criterion for capture is given. Simulation results indicate the two laws are effective and make up the deficiency that pure proportional navigation suitable for endoatmospheric interceptions cannot deal with high-speed maneuvering targets. Furthermore, the correctness of the criterion is validated.

Analysis of echo signal modulation characteristic parameters on aerial and space targets

Based on the scattering characteristic,the comparison of RCS(radar cross-section)at different positions of a target in the same direction of incidence can be obtained first by extruding or deleting part of the entity.A simulation method of aerial&space targets echo characteristics(A&STEC)is proposed that is universal to aerial and space targets.We utilize a fixed-wing UAV(unmanned aerial vehicle)and typical missiles in simulation.The echo signal modulation characteristic parameters are calculated theoretically by the atmospheric attenuation model,the finite element method and a MUMPS solver.The verification simulations show that this method can analyze the influence of the target shape,incident direction,detection position and detection frequency on echo waveform,intensity and energy distribution.The results show that the profile of echo waveform can invert the general shape of the target.The relationship between time and intensity can determine whether the target is moving towards or away from the detector in addition.These conclusions can provide a reference for the ballistic missile target tracking and the defense against UVA intrusion in theory.

一种靶弹多功能控制器设计与实现

靶弹是模拟敌方来袭导弹技战术特性的实体空中靶标;针对退役导弹改装靶弹中面临的改装线路复杂、对动目标供靶精度不足等实际问题,对靶弹飞行控制规律和改装设计方法进行了研究探索,创新了靶弹制导控制方法,综合采用靶弹飞行控制回路状态转换、动目标供靶航路精确控制、靶弹功能扩展等关键技术,设计研制了集电气改装、接口转换、目标导引、安全控制等功能于一体的靶弹多功能控制器,实现了退役飞航导弹到多用途靶弹的通用化、标准化改装,探索了一种经济而有效的靶弹开发方法;试验结果表明,该多功能控制器具备简便可靠、工作量小、通用性好、弹道控制灵活等突出特点,较好地解决了靶弹改装难题,满足了防空武器系统试验训练的需要。

基于深度强化学习的舰船导弹目标分配方法

针对对抗环境下的海上舰船防空反导导弹目标分配问题,本文提出了一种融合注意力机制的深度强化学习算法.首先,构建了舰船多类型导弹目标分配模型,并结合目标多波次拦截特点将问题建模为马尔可夫决策过程.接着,基于编码器–解码器框架搭建强化学习策略网络,融合多头注意力机制对目标进行编码,并在解码中结合整体目标和单个目标编码信息实现舰船可靠的导弹目标分配.最后,对导弹目标分配收益、分配时效以及策略网络训练过程进行了仿真实验.实验结果表明,本文方法能生成高收益的导弹目标分配方案,相较于对比算法的大规模决策计算速度提高10%~94%,同时其策略网络能够快速稳定收敛.

面向多弹拦截的分布式非均衡一致性目标分配算法

针对自组网导弹集群协同拦截多无人机的不确定多对一目标分配问题,提出了一种分布式非均衡目标分配算法。考虑到自组网导弹在有限邻域范围内双向通信和任务分配的去中心化特点,设计了适合于分布式无中心的目标分配模型和基于动态态势感知的多步一致性拍卖算法,通过将目标剩余价值进行多步分解实现多弹对单一目标的非均衡拍卖选择;此外通过改进一致性包算法的共识规则设计了扩展多步一致性冲突消解规则,实现了分布式非均衡拍卖结果的一致性冲突消解。最终仿真结果表明,该方法可适用于分布式弹群在线非均衡目标分配调整,提高对空中多机动目标的拦截效率,并且相较于集中式分配算法在兼顾优化时间条件下可获得全局次优求解。

三维自适应固定时间多导弹协同制导律

针对三维空间内多导弹对机动目标同时攻击的问题,提出一种具有自适应律的三维多导弹固定时间协同制导律。建立三维空间导弹-目标动力学模型,以弹目视线方向和其垂直方向设计制导律,可保证剩余飞行时间和法向速度在固定时间内完成一致性收敛。采用自适应律来跟踪机动目标运动参数策略,提高多导弹系统的稳定性与对机动目标的打击精度。改进多导弹系统收敛条件,所设计的制导律具备了对攻击时间的约束能力。向制导律中加入饱和函数,避免因符号函数带来的系统抖振。通过仿真实验验证所提固定时间协同制导律的有效性及对抗通信拓扑切换的鲁棒性。实验结果表明:相较于对比文献所设计的制导律具有系统快速收敛以及高精度。

反舰导弹大前置角下三维剩余飞行时间估计方法

为解决导弹开启末制导时初始前置角过大或前置角变化幅度较大的问题,设计适用于多种导弹制导律的前置角三维剩余飞行时间估计方法。将导弹速度和目标速度投影分解,在地面坐标系的Oxy面和Oxz面上建立弹目相对运动关系方程,以此为基础建立三维弹目相对运动模型。利用弹目相对运动关系方程和比例导引控制方程,建立1阶非线性微分方程,解析弹目距离与前置角的关系,并利用麦克劳林展开式求解方程。根据视线角速度变化选择合适的内框角,对前置角进行补偿,同时使用中位值平均滤波法降低前置角波动造成的误差。利用已建立的三维弹目相对运动模型进行仿真实验。仿真结果表明,在小角度假设不能成立时,尤其是因制导律进行角度控制而导致前置角变化较大时,前置角剩余飞行时间(Time-to-go,TGO)估计方法的估计值误差收敛时间和最大误差值要小于其他TGO估计方法,估计效果最佳。

层叠型缓冲靶板对弹载测试仪的保护作用研究

使用空气炮模拟火炮发射时的高过载环境对弹载测试仪进行测试时,弹丸撞击靶板会产生尖峰脉冲对测试仪造成严重的损伤,为提高测试仪的存活性,展开对缓冲靶板层叠方式(不同材质的靶板相互叠加的叠层结构)的研究。通过撞击动力学理论描述弹丸对靶板的压缩和侵彻行为,并结合动量守恒和能量守恒定律计算出靶板参数和传递到靶板上的冲量的关系。使用ANSYS/LS-DYNA建立弹丸正侵彻靶板模型,弹丸速度为200 m/s、质量为5.5 kg,仿真结果表明:3层总厚度450 mm的泡沫铝+泡沫铝+橡胶组合方式能有效消除尖峰脉冲并缩短弹丸对靶板的作用时间,加速度均值约为7 000g,脉宽为2.8 ms。受条件限制,空气炮试验采用弹丸质量为5.5 kg、速度为150 m/s,并将缓冲靶板的单层厚度减小到100 mm,结果表明:在泡沫铝+泡沫铝+橡胶组合方式下,弹丸结构和测试仪功能完好,加速度均值约为27 000g,脉宽为0.55 ms。

基于多目标进化算法的防空导弹武器目标分配

有效的武器目标分配(weapon-target assignment,WTA)方法对减少作战损失,提高防御效果具有重要意义。针对防空资源分配问题建立合理的数学模型,以最大化目标毁伤效能和最小化雷达资源消耗为优化目标,同时考虑雷达通道数上限等多个约束,在基于分解的多目标进化算法(multi-objective evolutionary algorithm based on decomposition,MOEA/D)基础上进行改进,种群进化过程中自适应调整交叉与变异的概率以提高个体的质量,最终得到一组可供决策者使用的最优解集。实验结果表明:与其他多目标进化算法相比,该算法能得到适应度更高且分布性良好的结果,能够为防空导弹武器目标分配问题提供可行方案。

基于残差密集连接注意力的红外目标识别算法

针对红外目标识别时目标与干扰混淆、干扰遮挡目标导致算法性能下降的问题,提出了一种基于残差密集连接注意力的空中红外目标识别算法。首先,为跨层实现浅层与深层特征的融合、获取融合深度特征、提升特征复用性并增强语义信息,提出了改进的残差密集连接模块;其次,为增强融合深度特征的自适应表达能力,设计了并行混合注意力模块;最后,通过在大量红外数据集上的测试证明,相比于GoogLeNet算法,所提算法平均识别正确率提高了1.9个百分点,证明了算法的有效性。

引入虚拟目标的高超声速巡航导弹智能机动突防策略

针对高超声速巡航导弹机动突防时弹道偏离难以约束、突防策略对不同作战场景的泛化性能较差等问题,提出一种基于虚拟目标和上下文马尔可夫决策过程的智能机动突防决策算法。在以预定弹道为轴线的管状弹道包络面内选定多个静止的虚拟目标,采用深度强化学习算法对其相对预定弹道的位置参数进行决策;用比例导引律引导巡航弹依次攻击这些虚拟目标,在包络面内塑造出能满足突防要求的机动弹道。基于上下文马尔可夫决策过程,将针对单个作战场景的最优突防策略拓展到作战场景的概率分布上,提升突防策略对不同作战场景的适应性。仿真结果表明:该智能机动突防策略能在突防的同时约束弹道偏离,在拦截弹发射位置和机动能力发生变化时仍能保持良好性能。

贝叶斯优化与集成学习在弹载雷达目标识别中的应用

空空导弹在打击低空、超低空目标时,弹载雷达区分目标和杂波的性能下降。本文针对弹载雷达目标识别问题,应用多种集成学习算法和贝叶斯优化算法,建立了多个目标识别模型,测试并对比了模型性能。通过特征提取、数据标准化和特征选择,构建了优选特征的目标杂波数据集。使用贝叶斯优化算法进行调参,构建了XGBoost、LightGBM和CatBoost目标识别模型并测试。测试结果表明,XGBoost、LightGBM、CatBoost的目标识别效果优于随机森林、支持向量机和AdaBoost。选择XGBoost、LightGBM和CatBoost和随机森林为基分类器,构建了Stacking目标识别模型并测试。测试结果表明,Stacking的目标识别准确率达到98.88%,优于组成它的四个单一模型,但运行效率大幅降低。综合来看,CatBoost的目标识别准确率达到98.03%,虽不是最优,但其测试时间为0.011 s,运行效率的优势更明显。

强跟踪容积卡尔曼滤波在空空导弹制导中的应用

针对传统滤波算法在处理目标复杂机动时非线性逼近能力不足、跟踪精度下降等问题,提出一种强跟踪容积卡尔曼滤波(STCKF)方法。首先,根据战斗机规避空空导弹的机动特征,建立了蛇形机动和桶滚机动两种目标运动模型;其次,引入强跟踪滤波(STF)以增强容积卡尔曼滤波(CKF)对系统状态突变等不确定因素的能力;然后,将STCKF应用于导弹末制导目标运动参数估计中,并通过与CKF、无迹卡尔曼滤波(UKF)和粒子滤波(PF)的对比仿真分析验证了该方法的有效性。仿真结果表明,STCKF具有较强的鲁棒性和系统自适应能力,尤其在目标机动突变时其跟踪误差相比CKF减小约10%,能够满足空空导弹末制导高精度和快速响应要求。

基于深度确定性梯度学习的集群多目标分配方法

针对多弹协同作战进行目标分配时,存在敌方平台和反舰导弹数量不确定性和类型多样化,导致目标分配算法难以建模的问题,为提升高动态协同攻击条件下的攻击效能,建立动态战场环境模型和多目标分配的单回合马尔可夫决策模型,提出一种改进深度确定性策略梯度的分配算法.通过与模拟器的交互自动求解最佳分配策略,利用mask方法对动作空间进行掩码操作,实现算法对平台数量和类型的适应能力.实验结果表明,在各种不同舰船的防御配置和红蓝双方数量配置下,算法求解得到的攻击策略相对于随机策略的性能提升约为87.5%,模型推理时间约为0.04ms.研究结果将加速基于深度确定性梯度学习的方法在高动态环境下智能决策中的应用,对集群自主决策方法的研究具有推动作用.