用TH神经网络方法外推数据的超分辨雷达成象

研究用Ｔａｎｋ－Ｈｏｐｆｉｅｌｄ神经网络（ＴＨＮＮ）求解ＡＲ模型参数作数据外推的超分辨雷达成象,并用微波暗室实测数据对ＴＨＮＮ方法和Ｂｕｒｇ方法作了验证,结果表明,两种方法均能在较低的信噪比条件下实现超分辨成象,且随着ＶＬＳＩ技术的发展,神经网络方法将是一种很有希望的超分辨成象方法。     

人工神经网络在CAPP系统开发工具中的应用

探讨了基于神经网络理论在ＣＡＰＰ系统开发工具的应用;建立了工艺过程设计系统的ＡＮＮ模型;详细讨论了工艺过程设计系统的推理机制,并给出了用集成ＢＰ网络选择加工方法及通过改进Ｈｏｐｆｉｅｌｄ网络确定工艺路线的过程。     

基于PEV准则的不确定随机多目标规划问题求解

为解决独立变量的不确定随机多目标规划问题在传统求解中存在分析不全面等问题,在期望值-方差准则下提出了一种新的求解方法。基于机会理论,引入不确定随机变量,在此基础上提出了不确定随机多目标规划问题;引入不确定随机变量的序关系,利用变量间的序关系把不确定随机多目标规划问题转化成不确定随机单目标规划问题,并通过期望值-方差准则把不确定随机单目标规划问题转化成确定的单目标规划问题进行求解;通过理论推导证明,在新准则下转化后的问题得到的最优解是原不确定随机多目标规划问题的有效解;最后,通过对无人机情报侦察监视任务分配问题的求解,利用改进的萤火虫算法求得有效飞行序列,验证了所提方法的可行性和有效性。     

Differential code bias estimation based on uncombined PPP with LEO onboard GPS observations

Differential Code Bias (DCB) is an essential correction that must be provided to the Global Navigation Satellite System (GNSS) users for precise position determination. With the continuous deployment of Low Earth Orbit (LEO) satellites, DCB estimation using observations from GNSS receivers onboard the LEO satellites is drawing increasing interests in order to meet the growing demands on high-quality DCB products from LEO-based applications, such as LEO-based GNSS signal augmentation and space weather research. Previous studies on LEO-based DCB estimation are usually using the geometry-free combination of GNSS observations, and it may suffer from significant leveling errors due to non-zero mean of multipath errors and short-term variations of receiver code and phase biases. In this study, we utilize the uncombined Precise Point Positioning (PPP) model for LEO DCB estimation. The models for uncombined PPP-based LEO DCB estimation are presented and GPS observations acquired from receivers onboard three identical Swarm satellites from February 1 to 28, 2019 are used for the validation. The results show that the average Root Mean Square errors (RMS) of the GPS satellite DCBs estimated with onboard data from each of the three Swarm satellites using the uncombined PPP model are less than 0.18 ns when compared to the GPS satellite DCBs obtained from IGS final daily Global Ionospheric Map (GIM) products. Meanwhile, the corresponding average RMS of GPS satellite DCBs estimated with the conventional geometry-free model are 0.290, 0.210, 0.281 ns, respectively, which are significantly larger than those obtained with the uncombined PPP model. It is also noted that the estimated GPS satellite DCBs by Swarm A and C satellites are highly correlated, likely attributed to their similar orbit type and space environment. On the other hand, the Swarm receiver DCBs estimated with uncombined PPP model, with Standard Deviation (STD) of 0.065, 0.037 and 0.071 ns, are more stable than those obtained from the official Swarm Level 2 products with corresponding STD values of 0.115, 0.101, and 0.109 ns, respectively. The above indicates that high-quality DCB products can be estimated based on uncombined PPP with LEO onboard observations.     

Mission-driven autonomous perception and fusion based on UAV swarm

Distributed autonomous situational awareness is one of the most important foundation for Unmanned Aerial Vehicle (UAV) swarm to implement various missions. Considering the application environment being usually characterized by strong confrontation, high dynamics, and deep uncertainty, the distributed situational awareness system based on UAV swarm needs to be driven by the mission requirements, while each node in the network can autonomously avoid collisions and perform detection mission through limited resource sharing as well as complementarity of respective advantages. By efficiently solving the problems of self-avoidance, autonomous flocking and splitting, joint estimation and control, etc., perception data from multi-platform multi-source should be extracted and fused reasonably, to generate refined, tailored target information and provide reliable support for decision-making.     

Decentralized formation pose estimation for spacecraft swarms

For spacecraft swarms, the multi-agent localization algorithm must scale well with the number of spacecraft and adapt to time-varying communication and relative sensing networks. In this paper, we present a decentralized, scalable algorithm for swarm localization, called the Decentralized Pose Estimation (DPE) algorithm. The DPE considers both communication and relative sensing graphs and defines an observable local formation. Each spacecraft jointly localizes its local subset of spacecraft using direct and communicated measurements. Since the algorithm is local, the algorithm complexity does not grow with the number of spacecraft in the swarm. As part of the DPE, we present the Swarm Reference Frame Estimation (SRFE) algorithm, a distributed consensus algorithm to co-estimate a common Local-Vertical, Local-Horizontal (LVLH) frame. The DPE combined with the SRFE provides a scalable, fully-decentralized navigation solution that can be used for swarm control and motion planning. Numerical simulations and experiments using Caltech’s robotic spacecraft simulators are presented to validate the effectiveness and scalability of the DPE algorithm.     

Decentralized differential drag based control of nanosatellites swarm spatial distribution using magnetorquers

Nanosatellites in the swarm initially move along arbitrary unbounded relative trajectories according to the launch initial conditions. Control algorithms developed in the paper are aimed to achieve the required spatial distribution of satellites in the along-track direction. The paper considers a swarm of 3U CubeSats in LEO, their form-factor is suitable for the aerodynamic control since the ratio of the satellite maximum to minimum cross-section areas is 3. Each satellite is provided with the information about the relative motion of neighboring satellites inside a specified communication area. The paper develops the corresponding decentralized control algorithms using the differential drag force. The required attitude control for each satellite is implemented by the active magnetic attitude control system. A set of decentralized control strategies is proposed taking into account the communicational constraints. The performance of these strategies is studied numerically. The swarm separation effect is demonstrated and investigated.     

不确定航迹自适应预测模型

针对现有航迹预测技术中，存在无模技术缺乏理论分析支持、能力有限、适用范围窄、有模技术先验假设过多、前提条件严苛、通用性差等问题，通过理论推导，利用循环和多层神经网络结构，研究提出了具有理论严谨、先验假设少、适用范围广、通用性强等优点的不确定航迹自适应预测模型，同时给出了典型的实现方法。该模型克服了现有航迹预测方法的缺点与不足，并具有无模与有模两类技术的优点与长处，仿真和实测实验验证表明：该模型能很好地提取识别出数据中存在的模式，并基于模式，进行正确有效地预测，能有效解决不同实际环境中的航迹预测问题，效果明显。     

群智能机制启发的传感器网络能量感知服务质量路由树

提出一种理论优化路由树的启发式算法,实现地理信息辅助的传感器网络服务质量数据收集架构.算法采用群智能蚁群优化机理进行设计:首先通过构造基于流量的能量有效性权将网络划分为不同的功能区域,使得路由的选择过程能够低延时地自适应网内不均衡性的能耗状况;然后,设计了新颖的启发式因子和信息素更新规则,赋予人工蚂蚁代理感知网络局域能量状况和逼近理论优化树的能力,从而提高路由构建的自适应性和能量有效性.仿真实验结果表明,本文提出的路由机制能够在数据收集的应用背景下,有效提高收集质量和降低传输时延,并在健壮性和节能效果方面优于许多经典的传感器网络路由算法.     

飞机故障排除专家辅助系统的设计与开发

简要介绍了飞机故障排除的专家辅助系统设计与开发,该系统以飞机专家在维护飞机过程中所积累的经验知识为例,结合故障隔离手册的内容,通过建立数据库的形式,依据人工智能的理论,使其具有查询功能,自动优选排故方法以及对故障内容的添加、修改、删除功能。