Time-varying parameters estimation with adaptive neural network EKF for missile-dual control system

In this paper, a filtering method is presented to estimate time-varying parameters of a missile dual control system with tail fins and reaction jets as control variables. In this method, the long-short-term memory(LSTM) neural network is nested into the extended Kalman filter(EKF) to modify the Kalman gain such that the filtering performance is improved in the presence of large model uncertainties. To avoid the unstable network output caused by the abrupt changes of system states,an adaptive correction factor is introduced to correct the network output online. In the process of training the network, a multi-gradient descent learning mode is proposed to better fit the internal state of the system, and a rolling training is used to implement an online prediction logic. Based on the Lyapunov second method, we discuss the stability of the system, the result shows that when the training error of neural network is sufficiently small, the system is asymptotically stable. With its application to the estimation of time-varying parameters of a missile dual control system, the LSTM-EKF shows better filtering performance than the EKF and adaptive EKF(AEKF) when there exist large uncertainties in the system model.

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.

Recorded recurrent deep reinforcement learning guidance laws for intercepting endoatmospheric maneuvering missiles

This work proposes a recorded recurrent twin delayed deep deterministic(RRTD3)policy gradient algorithm to solve the challenge of constructing guidance laws for intercepting endoatmospheric maneuvering missiles with uncertainties and observation noise.The attack-defense engagement scenario is modeled as a partially observable Markov decision process(POMDP).Given the benefits of recurrent neural networks(RNNs)in processing sequence information,an RNN layer is incorporated into the agent’s policy network to alleviate the bottleneck of traditional deep reinforcement learning methods while dealing with POMDPs.The measurements from the interceptor’s seeker during each guidance cycle are combined into one sequence as the input to the policy network since the detection frequency of an interceptor is usually higher than its guidance frequency.During training,the hidden states of the RNN layer in the policy network are recorded to overcome the partially observable problem that this RNN layer causes inside the agent.The training curves show that the proposed RRTD3 successfully enhances data efficiency,training speed,and training stability.The test results confirm the advantages of the RRTD3-based guidance laws over some conventional guidance laws.

Modelling missile motion system using neural networks

The models of noallnear systems are idendried by recmeive pedctive ermrs(RPE) methed based on thelayered neural networks. To improve the identification precision, gain callcient and arentUm factor are itheucedinto the algorithm for the data are dids by noses and vny suddnly. this lerthm is applied to the twcmedeiling of rolling and pitchng angles of ndssiles. Simulation results shoW tha the proposed algurithm is sultable forthe modelling of nodrinear systems.

Study on Missile Intelligent Fault Diagnosis System Based on Fuzzy NN Expert System

In order to study intelligent fault diagnosis methods based on fuzzy neural network (NN) expert system and build up intelligent fault diagnosis for a type of missile weapon system, the concrete implementation of a fuzzy NN fault diagnosis expert system is given in this paper. Based on thorough research of knowledge presentation, the intelligent fault diagnosis system is implemented with artificial intelligence for a large-scale missile weapon equipment. The method is an effective way to perform fuzzy fault diagnosis. Moreover, it provides a new way of the fault diagnosis for large-scale missile weapon equipment.

Study on Anti-ship Missile Saturation Attack Model

Based on the analysis for the interception process of ship-to-air missile system to the anti-ship missile stream, the antagonism of ship-to-air missile and anti-ship missile stream was modeled by Monte Carlo method. This model containing the probability of acquiring anti-ship missile, threat estimation, firepower distribution, interception, effectiveness evaluation and firepower turning, can dynamically simulate the antagonism process of anti-ship missile attack stream and anti-air missile weapon system. The anti-ship missile's saturation attack stream for different ship-to-air missile systems can be calculated quantitatively. The simulated results reveal the relations among the anti-ship missile saturation attack and the attack intensity of anti-ship missile, interception mode and the main parameters of anti-air missile weapon system. It provides a theoretical basis for the effective operation of anti-ship missile.

Distributed Air &Missile Defense with Spatial Grasp Technology

A high-level technology is revealed that can effectively convert any distributed system into a globally programmable machine capable of operating without central resources and self-recovering from indiscriminate damages. Integral mission scenarios in Distributed Scenario Language (DSL) can be injected from any point, runtime covering & grasping the whole system or its parts, setting operational infrastructures, and orienting local and global behavior in the way needed. Many operational scenarios can be simultaneously injected into this spatial machine from different points, cooperating or competing over the shared distributed knowledge as overlapping fields of solutions. Distributed DSL interpreter organization and benefits of using this technology for integrated air and missile defense are discussed along with programming examples in this and other fields.

Trajectory tracking guidance of interceptor via prescribed performance integral sliding mode with neural network disturbance observer

This paper investigates interception missiles’trajectory tracking guidance problem under wind field and external disturbances in the boost phase.Indeed,the velocity control in such trajectory tracking guidance systems of missiles is challenging.As our contribution,the velocity control channel is designed to deal with the intractable velocity problem and improve tracking accuracy.The global prescribed performance function,which guarantees the tracking error within the set range and the global convergence of the tracking guidance system,is first proposed based on the traditional PPF.Then,a tracking guidance strategy is derived using the integral sliding mode control techniques to make the sliding manifold and tracking errors converge to zero and avoid singularities.Meanwhile,an improved switching control law is introduced into the designed tracking guidance algorithm to deal with the chattering problem.A back propagation neural network(BPNN)extended state observer(BPNNESO)is employed in the inner loop to identify disturbances.The obtained results indicate that the proposed tracking guidance approach achieves the trajectory tracking guidance objective without and with disturbances and outperforms the existing tracking guidance schemes with the lowest tracking errors,convergence times,and overshoots.

Distributed Control Technology for Air and Missile Defence Operations

This paper relates to accepted presentation at international conference Air and Missile Defence Technology,November 16-17,2022,London UK(day two),reflecting contents of the presentation slides.It describes applications of the patented and internationally tested Spatial Grasp Technology(SGT)and its Spatial Grasp Language(SGL)for Integrated Air and Missile Defense(IAMD).Based on holistic space navigation and processing by recursive mobile code self-spreading in distributed words,SGT differs radically from traditional management of large systems as consisting of parts exchanging messages.The dynamic network of SGL interpreters can be arbitrarily large and cover terrestrial and celestial environments as powerful spatial engines.The paper contains an example of tracking and destruction of multiple cruise missiles by self-evolving spatial intelligence in SGL using networks of radar stations.It also briefs the growing multiple satellite constellation in Low Earth Orbits(LEO)for potential IAMD applications.Starting from Strategic Defense Initiative(SDI)of the past and then briefing the latest project of Space Development Agency,the paper shows SGL solutions for discovery,tracking,and destroying ballistic missiles and hypersonic gliders with the use of collectively behaving constellations of LEO satellites.It also shows how to organize higher levels of supervision of groups of mobile chasers fighting multiple targets(both potentially as missiles or drones),by providing their global awareness even consciousness in SGL which can drastically improve their performance.The latest version of SGT can be implemented on any platforms and put into operation in a short time,similarly to its previous versions in different countries.

Design of Closed Loop Optimal Guidance Law Using Neural Networks

It is generally impossible to obtain the analytic optimal guidance law for complex nonlinear guidance systems of homing missiles,and the open loop optimal guidance law is often obtained by numerical methods,which can not be used directly in practice.The neural networks are trained off line using the optimal trajectory of the missile produced by the numerical open loop optimal guidance law,and then,the converged neural networks are used on line as the feedback optimal guidance law in real time.The research shows that different selections of the neural networks inputs,such as the system state variables or the rate of LOS(line of sight),may have great effect on the performances of the guidance systems for homing missiles.The robustness for several guidance laws is investigated by simulations,and the modular neural networks architectures are used to increase the approximating and generalizing abilities in the large state space.Some useful conclusions are obtained by simulation results.

基于概率神经网络的潜舰武器系统故障诊断

针对传统故障诊断方法检测某型潜舰导弹武器系统故障准确率不高、耗时长的问题,提出基于概率神经网络的智能诊断方法。介绍该网络的典型结构及优势所在,以某型潜舰导弹武器系统为验证对象,选取合适特征向量、归纳合理故障类型、建立相应神经网络,并运用Matlab仿真验证。结果表明在现有数据库中,概率神经网络对该系统的故障诊断正确率为77.8%。这表明基于概率神经网络的故障诊断基本能够区分该系统故障类型,大大减少了部队故障诊断时间和人力投入。

基于复杂网络的防空反导体系拓扑特性

信息技术和军用物联网技术的发展不断推动着作战样式的变革,网络复杂性正逐渐成为研究的重要问题之一。基于复杂网络理论,构建防空反导网络模型,并对网络模型的拓扑特性进行仿真分析。结果表明,防空反导网络模型具有较大的平均集群系数和较小的平均路径长度,符合小世界特性,且网络效能系数与网络模型结构有较大关系。仿真结果对防空反导网络模型的建立并揭示其内部机理具有一定的理论意义。

基于生成对抗网络的弹载图像盲去模糊算法

低速旋转弹导引头具有抖动和旋转等运动特性,使得其采集图像存在严重的模糊特点,直接影响了后续图像算法对目标识别的准确性,进而影响制导精度。针对以上问题,提出一种基于生成对抗神经网络的盲去模糊算法。利用复合运动模糊仿真系统,实现了对弹载图像抖动和旋转等运动模糊的模拟,并制作弹载图像模糊数据集。使用卷积神经网络作为生成器和判别器的基本架构,并设计多个损失函数共同优化网络,以减小图像在修复复原过程中的噪声并保持图像平滑。实现了弹载图像的去模糊,并获得更加稳定、清晰的图像序列。实验结果表明,该算法的去模糊效果在峰值信噪比、结构相似性指标上比现阶段其他算法更好,更符合人类视觉的主观感受,具有工程应用价值。

机器学习在空空导弹攻击区解算中的应用及展望

针对机器学习在空空导弹攻击区快速解算上的应用,对国内外的攻击区解算方法进行概述总结,重点介绍基于深度学习攻击区解算法的研究现状,对比分析各种空空导弹攻击区解算方法的特点,提出结合强化学习的空空导弹攻击区解算方法;运用对比与理论分析相结合的方法,考虑实际工程水平,基于深度学习攻击区解算方法,提出了一种基于深度强化学习的空空导弹攻击区快速解算优化策略;与传统空空导弹攻击区解算方法相比BP神经网络拟合法解算速度快、解算精度高,但无法自主决策参数寻优,需要结合强化学习的自主决策能力进行优化;优化后的基于深度Q网络(DQN)和基于深度确定性策略梯度(DDPG)算法的攻击区解算策略能够分别对离散型和连续型网络参数实现自主决策优化;综合来看,利用DQN算法对迭代次数和利用DDPG算法对攻击参数的优化可以提高系统对复杂战场环境和不确定性因素的适应能力,从而改善导弹攻击的精度和有效性。

基于神经网络剩余时间估计的导弹-目标动态分配方法

针对防空导弹动态目标分配问题,设计了一种基于神经网络的剩余飞行时间预测方法,该方法在计算中不仅考虑了弹目相对距离和导弹运动状态,还考虑了敌方目标的运动状态对预测结果的影响,提升了预测精度;结合该方法建立了综合考虑距离优势、角度优势和剩余飞行时间优势的目标分配模型,采用拍卖算法对该模型进行求解,给出整体最优的目标分配方案。仿真结果表明:神经网络模型的测试集预测误差在1 s以内,低于经典算法,拍卖算法的重分配计算用时能够满足系统的实时性要求。

一种弹上电缆网绝缘检测辅助工装的设计

绝缘检测是弹上电缆网性能检测的重要环节,目前有自动检测和传统人工检测2种方式。自动检测存在不易扩展、价格昂贵等缺点,而传统人工检测存在检测效率低的问题。因此设计了一种通过端子任意行间绝缘检测、任意列间绝缘检测代替各端子间绝缘检测的矩阵式绝缘检测方法,并基于此方法设计了一种弹上电缆网绝缘检测辅助工装,从而实现了弹上电缆网绝缘性能的高效检测。该工装具有通用性强、检测效率高、成本低等特点,同时还具有异常点定位的功能,具有较强的工程应用与推广价值。

防空导弹网络化作战C^4ISR系统体系结构研究

网络中心战是信息化战争中一种新的作战概念。按照网络中心战的概念,研究防空导弹网络化作战的C4ISR体系结构。提出了以火力单元的功能系统为基本单元,建立跟踪制导网、指挥控制网和拦截兵器网三层逻辑网结构,并定义各逻辑层的主要功能和基本组成。该结构对实现防空导弹网络中心战有指导意义。

基于动态逆的BTT导弹自动驾驶仪设计

针对BTT(Bank-To-Turn)导弹的复杂非线性特性和冲压发动机带来的飞行姿态限制,在其自动驾驶仪设计问题上,指出了直接应用动态逆方法存在非最小相位特性,提出了基于动态逆的双阶段设计方法:第一阶段采用动态逆方法设计内环控制器实现攻角、侧滑角和滚转角的跟踪;第二阶段分别基于神经网络和动态逆构造攻角和滚转角速度指令生成器,实现外环对法向加速度、侧滑角和滚转角的良好跟踪效果.六自由度数学仿真验证了该方法的三通道的解耦控制能力和鲁棒性,为BTT导弹自动驾驶仪设计提供了一个可行的方案.

涡喷发动机风车启动工况的神经网络建模

弹用涡喷发动机的风车启动工况是复杂的非线性过程 ,由于此时压气机处于非设计工况 (膨胀 )而造成机理建模的困难。神经网络对于非线性映射具有任意逼近能力 ,应用径向基函数神经网络 (RBFN)对涡喷发动机风车启动阶段进行了实验建模 ,通过适当地选取网络参数及训练样本 ,达到了很高的精度 。

异构多导弹网络化分布式协同制导方法

基于相邻局部通信的领弹-被领弹异构网络结构,提出了一种多导弹分布式协同制导方法,设计了分散化的协同制导律.运用图论的描述方法,分析了导弹分布式局部通信拓扑与领弹-被领弹异构网络化分布式协同制导系统性能之间的关系.该分布式协同制导律仅需要相邻导弹之间传输各自的可测状态信息,具有可扩展性好、通信量少等特点.给出了4个被领弹和一个领弹的协同制导律设计仿真算例,结果验证了该制导方法的有效性.