基于启发强化学习的大规模ADR任务优化方法

随着航天事业的蓬勃发展,空间碎片尤其是低轨碎片已成为航天任务不可忽视的威胁。考虑到碎片清除的紧迫性和成本,低轨多碎片主动清除（ADR）技术成为缓解现状的必要手段。针对大规模多碎片主动清除任务规划问题,首先,基于任务规划的最大收益模型,提出一种强化学习（RL）优化方法,并依照强化学习框架定义了该问题的状态、动作以及收益函数;其次,基于高效启发因子,提出一种专用的改进蒙特卡罗树搜索（MCTS）算法,该算法使用MCTS算法作为内核,加入高效启发算子以及强化学习迭代过程;最后,在铱星33碎片云的全数据集中检验了所提算法有效性。与相关MCTS变体方法以及贪婪启发算法对比,所提方法能在测试数据集上更高效地获得较优规划结果,较好地平衡了探索与利用。     

基于能量最优的敏捷遥感卫星在轨任务规划

针对敏捷遥感卫星对多个离散观测点在轨自主任务规划问题,在考虑姿态运动方程耦合性的基础上,将问题分解为空间资源调度问题和连续最优控制问题,进而提出了一种结合伪谱法和遗传算法的混合求解算法。该算法针对基于行商问题(TSP)模型建立的空间资源调度问题模型,选用二维编码结构对观测顺序和相对观测时间进行实数编码,并采用遗传算法求解观测序列和观测时间;针对判断观测时间可行性时涉及的时间最优控制问题、以及姿态转移过程中涉及的最小能量消耗问题,将其归结为连续最优控制问题,并基于Gauss伪谱协态变量映射定理,采用Gauss伪谱法进行求解。通过与基于单纯遗传算法的规划算法进行对比试验,本文所提出的基于伪谱法和遗传算法的混合求解策略针对目标问题,在典型工况下姿态转移过程中能量消耗降低60%。     

基于弹道逃逸和小推力捕获的地月转移轨道设计

针对地月空间货运任务和环月轨道空间设施建设任务,提出一种弹道逃逸和小推力捕获相结合的新型地月轨道转移模式,并建立了一整套该类型轨道设计方法。首先,在三体模型假设下分别建立地心弹道逃逸轨道和月心小推力捕获轨道的二维极坐标动力学模型。对于弹道逃逸轨道,将地心旋转系对准角和地月转移加速速度增量作为控制变量,提出初值估计解析公式,并应用序列二次规划算法进行快速求解。对于小推力捕获轨道,以月心距为参考量设置与弹道逃逸轨道的拼接点约束,提出能量匹配方法预估飞行时间,采用最优螺旋轨道的初始伴随状态解析式预估近月点伴随变量初值。基于混合法和轨道逆推思想,采用人工免疫算法进行小推力捕获轨道求解。仿真结果表明,基于弹道逃逸和小推力捕获的地月轨道转移方式大幅降低了近月制动燃料消耗,能快速穿越地球辐射带,且飞行时间适中;同时,提出的轨道设计方法能快速搜索到基于弹道逃逸和小推力捕获的地月转移轨道,验证了该方法的有效性。     

到达航班排序与调度优化的遗传算法研究

解决机场到达航班的排序与调度(ASS)问题是保持空中交通通畅、减少航班延迟的主要途径.本文针对ASS问题的特点,建立了以航班总延误时间为目标函数的排序模型,提出了基于格里芬斯塔特编码和滚动时域优化策略的遗传算法,并对排序模型进行了仿真分析.结果表明:与先到先服务算法相比,本文算法能显著减少航班总延迟,同时较常规遗传算法...     

Capture and detumbling control for active debris removal by a dual-arm space robot

Active debris removal (ADR) technology is an effective approach to remediate the proliferation of space debris, which seriously threatens the operational safety of orbital spacecraft. This study aims to design a controller for a dual-arm space robot to capture tumbling debris, including capture control and detumbling control. Typical space debris is considered as a non-cooperative target, which has no specific capture points and unknown dynamic parameters. Compliant clamping control and the adaptive backstepping-based prescribed trajectory tracking control (PTTC) method are proposed in this paper. First, the differential geometry theory is utilized to establish the constraint equations, the dynamic model of the chaser-target system is obtained by applying the Hamilton variational principle, and the compliance clamping controller is further designed to capture the non-cooperative target without contact force feedback. Next, in the post-capture phase, an adaptive backstepping-based PTTC is proposed to detumble the combined spacecraft in the presence of model uncertainties. Finally, numerical simulations are carried out to validate the feasibility of the proposed capture and detumbling control method. Simulation results indicate that the target detumbling achieved by the PTTC method can reduce propellant consumption by up to 24.11%.     

面向突发任务的空间站任务重规划方法

针对空间站在轨运营出现突发任务的情况,提出一种基于启发式规则的任务重规划方法,满足了方案重规划的快速响应需求。根据任务执行的连续性特点和冲突状态,建立了空间站突发任务规划领域模型。考虑重规划过程中任务包含活动间复杂约束关系传播的影响,提出了时间回溯迭代冲突化解策略,同时依据任务执行时间间隔,提出针对间隔插空的时间冗余启发式规则。基于时间回溯迭代冲突化解策略和时间冗余启发式规则,对原任务执行计划进行实时重规划,实现了突发任务的快速响应。应用算例分析表明,提出的重规划方法可以成功地满足空间站突发任务规划需求,实现实时更新空间站在轨任务执行详单的目的。     

Performance deterioration modeling and optimal preventive maintenance strategy under scheduled servicing subject to mission time

Servicing is applied periodically in practice with the aim of restoring the system state and prolonging the lifetime. It is generally seen as an imperfect maintenance action which has a chief influence on the maintenance strategy. In order to model the maintenance effect of servicing, this study analyzes the deterioration characteristics of system under scheduled servicing. And then the deterioration model is established from the failure mechanism by compound Poisson process. On the basis of the system damage value and failure mechanism, the failure rate refresh factor is proposed to describe the maintenance effect of servicing. A maintenance strategy is developed which combines the benefits of scheduled servicing and preventive maintenance. Then the optimization model is given to determine the optimal servicing period and preventive maintenance time, with an objective to minimize the system expected life-cycle cost per unit time and a constraint on system survival probability for the duration of mission time. Subject to mission time, it can control the ability of accomplishing the mission at any time so as to ensure the high dependability. An example of water pump rotor relating to scheduled servicing is introduced to illustrate the failure rate refresh factor and the proposed maintenance strategy. Compared with traditional methods, the numerical results show that the failure rate refresh factor can describe the maintenance effect of servicing more intuitively and objectively. It also demonstrates that this maintenance strategy can prolong the lifetime, reduce the total lifetime maintenance cost and guarantee the dependability of system.     

散点状分布危险天气区域下的航班改航路径规划

针对沿航线散点状分布的危险天气区域影响下的航班改航问题,提出了基于多目标遗传算法(MOGA)的航班改航路径规划方法。首先建立了基于网格的改航环境模型,并给出散点状分布危险天气区域的描述方法。然后以改航航段的航段距离、平均偏离距离和转弯点个数为目标,应用带精英保留策略的非支配排序遗传算法(NSGA-II)对改航路径规划进行研究,提出了适用于改航路径规划的编码方法,同时引入了删除算子。最后,以昆明—广州航线为例,研究了散点状分布危险天气区域下的改航路径规划,并与基于多边形的改航路径规划算法作了比较。仿真结果表明：采用本文方法运行一次即可得到多条安全、可行的改航路径,且无需先验知识,为决策者选择改航路径提供了充足的依据。     

考虑运动学约束的不规则目标遗传避碰规划算法

 针对复杂环境下不规则目标的路径规划问题,提出了一种带有运动学约束的遗传避碰规划算法。以舰载机在航母甲板上的路径规划问题作为研究对象,并且该算法可推广至其他具有此类约束的路径规划问题中,它较好地解决了目标形状复杂、障碍环境复杂、目标运动时带有回转半径约束等特殊问题。在传统遗传路径规划算法的基础上,针对性地设计了三维位置和姿态混合编码、三段法路径解码、轨迹包围盒的碰撞检测及距离计算等方法,并在遗传操作中引入惩罚项和修补策略来辅助算法寻优。最后,为得出复杂环境下的最优路径,基于VC++平台对算法进行了仿真验证。结果表明,在复杂障碍环境下,本文提出的算法可求得最优避碰路径,并满足预先设定的目标回转半径约束,能够有效地解决此类目标的避碰路径规划问题。     

A new algorithm to optimize Barker code sidelobe suppressionfilters

The authors suggest a new algorithm for binary coding waveform sidelobe reduction after matched filtering and present a general method by which optimized sidelobe suppression filters for Barker codes can be obtained with a peak output sidelobe 2.62 dB lower than the results found in the literature (for 13-b Barker code). This optimization algorithm is also promising for other binary coding waveforms, such as truncated pseudonoise (PN) sequences and concatenated codes. This new approach can readily be applied to sidelobe-reduction filter design for other binary coding waveforms, such as truncated PN sequences, concatenated codes, etc., which often find their applications in radar systems and spread spectrum communication systems     

面向结构振动控制的压电作动器优化配置研究

 为了研究压电主动结构振动控制当中作动器的位置优化问题,从系统的状态空间方程出发,在系统可控性Gram矩阵特征值的基础上来描述性能指标,以输入的能量吸收率为优化目标函数,提出了一种新的位置优化配置准则。利用有限元分析(FEA)方法分析作动器的配置,并与遗传算法(GA)结合进行优化计算,计算过程中对作动器的位置采用二进制编码加以描述。通过对一压电简支板结构的仿真计算对该方法进行了验证,并与其他几种不同的配置方法进行对比,从而证明了新方法的优越性。     

基于零空间方法的四旋翼无人机避障与协同编队控制

针对四旋翼无人机在编队飞行执行任务时可能遭遇障碍物问题,考虑多无人机避障及机间避撞的需求,提出 1种基于零空间方法的四旋翼无人机避障与协同编队控制算法。首先,建立四旋翼无人机动力学模型,并建立虚拟控制量简化控制模型;其次,基于零空间方法进行避障与协同编队控制算法研究,将无人机任务执行分解为目标趋向任务、避障避撞任务和协同编队任务,并根据优先级进行任务融合得到期望速度;再次,基于 PID方法设计控制律;最后,通过仿真验证所提控制算法的有效性。所提方法可保证四旋翼无人机在编队飞行中遭遇障碍物时的飞行安全。     

基于免疫粒子群算法的滑油屑末支持向量机预测模型设计

将人工免疫理论的克隆选择算法中的抗体克隆、变异和抑制策略引入粒子群优化算法中,提出了一种基于克隆选择的免疫粒子群优化算法,克服了基本粒子群算法易于陷入局部最优解的缺点.针对支持向量机预测模型的参数选择影响其预测精度的问题,引入免疫粒子群优化算法设计了参数自适应优化的航空发动机滑油屑末支持向量机预测模型.仿真结果表明:与传统的交叉验证试算法相比,基于免疫粒子群优化的预测模型实现了参数的自动择优,并且提高了预测精度.      

基于改进鸽群算法的气动捕获轨道优化

针对火星探测器的气动捕获轨道，提出了一种改进的鸽群算法对气动捕获轨道进行优化。首先，考虑成功进行气动捕获所要求的终端约束和过程约束，根据从捕获轨道进行轨道转移进入目标轨道所需的速度增量，提出了进行捕获轨道优化的最优性能指标。然后，针对原始鸽群算法存在的一些不足，提出一种改进算法，并对改进算法的参数取值进行了分析。最后，基于大气内飞行的动力学方程，将气动捕获轨道优化问题转化为多参数优化问题，利用所提出的改进鸽群算法对气动捕获轨道进行优化，并通过仿真实例验证该算法的有效性。     

基于混合神经网络模型的磨粒电荷检测方法研究

由于传统的滑油磨粒在线监测方法无法获取电荷分布位置信息,难以准确测量荷电颗粒数目及其携带的电荷量。为此,本文提出一种基于静电层析成像（Electrostatic tomography,EST）技术和深度学习算法的荷电颗粒检测方法。对EST传感器测量数据采用BP神经网络算法重建出测量截面上电荷的分布图像,采用卷积神经网络（Convolutional neural networks,CNN）算法分析重建图像以识别荷电颗粒数目,将识别的颗粒数目和传感器测量数据组合成输入向量,通过1个多层前馈网络确定带电颗粒数目、感应电荷值与颗粒电荷量值之间的映射关系,得到准确的各颗粒的电荷量值。实验结果表明：混合神经网络模型对数据样本的测量误差为9%,可满足滑油监测对于准确性的要求。     

基于博弈论模型的多机协同对抗多目标任务决策方法

根据多机协同对抗多目标的空战特征,以敌我双方可能的相互攻击组合方式作为策略集,由敌我双方对抗态势分析定量结果确定支付函数,建立完全信息静态博弈模型.通过求解博弈模型的混合策略纳什均衡解,并结合一定作战经验,形成任务决策方法.以无人作战飞机编队对抗敌地对空防御系统为例,对本文所研究的任务决策方法进行了验算.     

伸缩弹翼巡航导弹气动外形优化研究

基于一种伸缩弹翼改变巡航导弹外形的概念,提出超声速巡航与亚声速盘旋相结合的飞行任务,使用Missile Datcom作为气动计算的工具,分别对固定翼、两级伸缩翼和三级伸缩翼的外形参数进行了优化,使三种不同弹翼导弹完成相同飞行任务的燃料消耗分别最小,优化方法选取遗传算法与模式搜索法相结合的混合优化策略.优化结果显示,两级、三级伸缩翼巡航导弹相对固定翼巡航导弹燃料消耗量分别减少7.8%和12%,表明伸缩弹翼有效提高了巡航导弹在整个飞行任务中的气动性能.     

An intelligent control method for a large multi-parameter environmental simulation cabin

The structure and characteristics of a large multi-parameter environmental simulation cabin are introduced.Due to the diffculties of control methods and the easily damaged characteristics,control systems for the large multi-parameter environmental simulation cabin are diffcult to be controlled quickly and accurately with a classical PID algorithm.Considering the dynamic state characteristics of the environmental simulation test chamber,a lumped parameter model of the control system is established to accurately control the multiple parameters of the environmental chamber and a fuzzy control algorithm combined with expert-PID decision is introduced into the temperature,pressure,and rotation speed control systems.Both simulations and experimental results have shown that compared with classical PID control,this fuzzy-expert control method can decrease overshoot as well as enhance the capacity of anti-dynamic disturbance with robustness.It can also resolve the contradiction between rapidity and small overshoot,and is suitable for application in a large multi-parameter environmental simulation cabin control system.     

A multi-agent based intelligent configuration method for aircraft fleet maintenance personnel

A multi-agent based fleet maintenance personnel configuration method is proposed to solve the mission oriented aircraft fleet maintenance personnel configuration problem. The mainte- nance process of an aircraft fleet is analyzed first. In the process each aircraft contains multiple parts, and different parts are repaired by personnel with different majors and levels. The factors and their relationship involved in the process of maintenance are analyzed and discussed. Then the whole maintenance process is described as a 3-layer multi-agent system （MAS） model. A com- munication and reasoning strategy among the agents is put forward. A fleet maintenance personnel configuration algorithm is proposed based on contract net protocol （CNP）. Finally, a fleet of 10 aircraft is studied for verification purposes. A mission type with 3 waves of continuous dispatch is imaged. Compared with the traditional methods that can just provide configuration results, the proposed method can provide optimal maintenance strategies as well.     

研究基地人员分布不均衡的机组任务半环生成问题

国内很多航空公司多基地间存在机组人员和航班任务数量不匹配的情况,导致各基地生成的任务环在机组派遣阶段难以被很好地执行,因此需在任务环生成阶段生成适量的可满足机组人员跨基地支援的任务半环,而传统的生成完整任务环的方案难以适用于该情况。在该问题中,通过顺序方法找到全局最优解是不可能的,因为在配对问题中做出的决策减少了机组分配问题的决策域。对此,创新性地提出了任务半环生成方案,并且创建基于时空网络的集合划分模型,分析任务半环生成总量约束的子问题目标函数项对列生成求解框架的影响,提出可以有效消除该影响的分治策略,采用实际数据验证算法可行性和有效性。与传统的方法相比,可显著节省成本并更好地满足机组人员分配不平衡问题。