Imaginary filtered hindsight experience replay for UAV tracking dynamic targets in large-scale unknown environments

As an advanced combat weapon, Unmanned Aerial Vehicles (UAVs) have been widely used in military wars. In this paper, we formulated the Autonomous Navigation Control (ANC) problem of UAVs as a Markov Decision Process (MDP) and proposed a novel Deep Reinforcement Learning (DRL) method to allow UAVs to perform dynamic target tracking tasks in large-scale unknown environments. To solve the problem of limited training experience, the proposed Imaginary Filtered Hindsight Experience Replay (IFHER) generates successful episodes by reasonably imagining the target trajectory in the failed episode to augment the experiences. The well-designed goal, episode, and quality filtering strategies ensure that only high-quality augmented experiences can be stored, while the sampling filtering strategy of IFHER ensures that these stored augmented experiences can be fully learned according to their high priorities. By training in a complex environment constructed based on the parameters of a real UAV, the proposed IFHER algorithm improves the convergence speed by 28.99% and the convergence result by 11.57% compared to the state-of-the-art Twin Delayed Deep Deterministic Policy Gradient (TD3) algorithm. The testing experiments carried out in environments with different complexities demonstrate the strong robustness and generalization ability of the IFHER agent. Moreover, the flight trajectory of the IFHER agent shows the superiority of the learned policy and the practical application value of the algorithm.     

基于输入成形的挠性航天器自适应滑模控制

针对大型挠性航天器姿态机动过程中的振动抑制问题,提出一种输入成形(IS)与自适应滑模控制(ASMC)相结合的控制策略.该控制策略利用输入成形抑制标称挠性系统的残余振动,并通过滑模控制保证实际系统在参数不确定性和外部干扰的影响下实现对标称系统的跟踪,解决了输入成形对参数不确定性和外部干扰的敏感性问题.进一步采用自适应技术去除了滑模切换增益对参数不确定性和干扰上界的先验性要求.仿真结果表明,在参数不确定性和外界干扰的影响下,该控制方法能够保证在完成姿态机动的同时抑制航天器的挠性振动.     

空间绳系机器人抓捕后复合体姿态协调控制

针对空间绳系机器人对目标抓捕后的复合体姿态稳定控制问题进行了研究.首先,对复合体进行动力学建模,并对其动力学特性进行了分析;然后,考虑复合体的特点、空间绳系机器人燃料有限以及自身姿态控制力的限制,分别设计了系绳主动拉力与推力器推力协调控制器和基于滑模变结构的全推力控制器,并设计了其切换条件,利用两种控制器切换对姿态进行稳定控制;最后,利用仿真实验验证了所提方法的正确性.仿真结果表明,系绳拉力和推力器协调控制方法能够实现对姿态的稳定控制,并且有效地节省姿态控制过程中的燃料消耗.     

基于FFT含有饱和环节的非线性等效系统的方法研究

基于快速傅里叶变换(FFT)方法,对系统的输入和输出信号进行快速傅里叶变换,对含有高次谐波的输出信号进行滤波,得到期望主频率的傅里叶频谱,然后进行傅里叶反变换,求得在各主频率下的幅值和相位.利用MATLAB中的非线性最小二乘拟配方法得到含有非线性环节的飞机纵向飞行控制系统的频域等效线性模型.这种方法也为含有非线性环节的飞机纵向飞行控制系统的飞行品质评估提供了一种可行的方法.     

基于航班排队仿真的终端区空域容量评估

为提升多扇区终端区空域容量评估的实效性,基于终端区交通流显著的排队特性,结合考虑扇区耦合关系,建立仿真模型并给出新的评估方法.以成都终端区为例,选取一周航班计划,针对每日运行状况共进行35次仿真,评定成都终端区平行双跑道隔离运行模式下的空域容量为47架次/h,并指出空域划设缺陷.经管制员雷达模拟机演练及实际运行数据验证,新评估方法有效,评估结论更符合实际.     

带落角和末端攻角约束的最优末制导律

针对现代导弹武器多约束、高精度制导的基本要求,在综合考虑带落角和末端攻角约束的条件下,用二次型最优控制推导出一种新的最优末制导律。仿真结果表明,该末制导律既能够满足高精度制导的要求,同时也能够满足对落角和末端攻角的控制要求。     

Trajectory control strategy of cathodes in blisk electrochemical machining

A turbine blisk, which combines blades and a disk together, is one of the most important components of an aero engine. In the process of blisk electrochemical machining (ECM), the sheet cathode, which is usually used as a tool electrode, has a complicated structure. In addition to that, the channel between the adjacent blades is narrow and twisted, so interference is apt to happen when the sheet cathode feeds into the channel. Therefore, it is important to choose suitable trajectory control strategy. In this paper, a new trajectory control strategy of the sheet cathode is presented and corresponding simulation analysis is conducted on the basis of an actual blisk model. The simulation results demonstrate that the sheet cathode can feed into the channel by a spatial line trajectory without interference. Moreover, the verification experiments are carried out according to the simulation. The experimental results show that the cathode can move into the channel without interference. It is verified that the new trajectory control strategy is correct and can be used in the blisk ECM process successfully.     

电液力伺服系统的神经网络并行自适应预测 PI 控制

考虑电液伺服系统的复杂非线性和不确定性特性,提出一类基于神经网络的并行自适应预测PI控制结构,该结构使控制参数的调整和系统的实时控制操作可并行进行,不仅做到了神经模型和控制器的在线辨识和设计,而且避免了神经网络方法通常存在的实时控制的困难,使复杂系统的在线学习控制成为可能。仿真结果表明该控制器具有良好的适应性和鲁棒性。      

自适应变结构神经网络在航空发动机故障诊断上的应用

根据样本空间的内积特性,提出一种无需迭代学习的自适应变结构神经网络。它的特点是学习速度快,准确性高,且能根据出现的新样本,随时改变结构。在对某型航空发动机故障诊断中,比原软件包采用的方法在准确性方面有显着提高,而且维护工作量减少,并具有实时处理能力,因此有着良好的推广应用前景。      

飞行控制系统对驾驶员诱发振荡的影响

着重从飞行控制系统角度谈有人驾驶飞机的驾驶员诱发振荡问题,分析了系统杆力、传动比、间隙、摩擦力以及飞控伺服作动器对驾驶员诱发振荡的影响,用矢量图简明地反映飞机产生驾驶员诱发振荡的可能性和趋势。对飞机飞行控制系统的设计和对驾驶员诱发振荡现象的分析、处理有参考价值。