Rotating machinery fault detection and diagnosis based on deep domain adaptation: A survey

In practical mechanical fault detection and diagnosis, it is difficult and expensive to collect enough large-scale supervised data to train deep networks. Transfer learning can reuse the knowledge obtained from the source task to improve the performance of the target task, which performs well on small data and reduces the demand for high computation power. However, the detection performance is significantly reduced by the direct transfer due to the domain difference. Domain adaptation (DA) can transfer the distribution information from the source domain to the target domain and solve a series of problems caused by the distribution difference of data. In this survey, we review various current DA strategies combined with deep learning (DL) and analyze the principles, advantages, and disadvantages of each method. We also summarize the application of DA combined with DL in the field of fault diagnosis. This paper provides a summary of the research results and proposes future work based on analysis of the key technologies.     

多约束航迹规划与跟踪制导律

研究升力式飞行器多约束航迹规划与跟踪制导律设计。考虑到飞行器为满足任务需求规定了一定范围的禁飞区，为确保滑翔段末状态处于中末制导交班窗口内设置了严格的终端约束，导致传统基于最大升阻比、平衡滑翔策略的航迹规划不适用。针对飞行器在不同空域的动力学特性，结合飞行策略预划分手段分段提出不同状态下的攻角、倾侧角剖面，通过优化剖面构型参数将无穷维轨迹优化问题转化为有限维参数规划问题，完成多约束航迹规划。最后，考虑到气动不确定性带来的轨迹偏差，利用线性二次型调节器以位移加权误差最小为优化指标完成轨迹跟踪制导律设计，实现对规划航迹的在线纠偏，并通过仿真分析验证所提方法的有效性。     

横列式双倾转旋翼机控制系统研究CSCD

针对横列式双倾转旋翼机平飞加速过渡过程中的标称速度轨迹跟踪问题,提出了通过升力占比划分过渡阶段,实现标称轨迹的工程化设计。基于经典PID理论,分别设计了各过渡阶段各通道控制律和控制参数,提出了总距余弦分配的操纵分配方法,并解决了过渡过程中严重的纵垂向耦合问题。仿真结果表明,该纵向控制策略在强干扰下仍可以实现对象飞行器的平稳过渡。     

无人机蜂群轨迹预测研究

传统防空火控算法中的轨迹预测模型无法对复杂的无人机蜂群进行有效地轨迹预测，而现有针对无人机机动轨迹的预测研究通常只考虑单个无人机，且模型量级过大。为了准确且快速地预测无人机蜂群轨迹，本文提出一种面向蜂群的轨迹预测方法。在获得蜂群轨迹后，首先基于DBSCAN 对其进行聚类，判断出蜂群中各个无人机的类别；然后基于分形算法，判断无人机轨迹是简单轨迹还是复杂轨迹；最后，采用卡尔曼滤波进行简单轨迹的预测，用基于LSTM 网络的方法进行复杂轨迹的预测。结果表明：本文提出的无人机蜂群轨迹预测方法的预测误差远远小于纯采用卡尔曼滤波方法预测的误差，且预测时间小于仅采用LSTM 网络方法预测的时间，可以较为准确地预测蜂群中不同集群无人机的轨迹，为反无人机蜂群火控解算提供基础。     

A homogenization-planning-tracking method to solve cooperative autonomous motion control for heterogeneous carrier dispatch systems

Taxiing aircraft and towed aircraft with drawbar are two typical dispatch modes on the flight deck of aircraft carriers. In this paper, a novel hierarchical solution strategy, named as the Homogenization-Planning-Tracking (HPT) method, to solve cooperative autonomous motion control for heterogeneous carrier dispatch systems is developed. In the homogenization layer, any towed aircraft system involved in the sortie task is abstracted into a virtual taxiing aircraft. This layer transforms the heterogeneous systems into a homogeneous configuration. Then in the planning layer, a centralized optimal control problem is formulated for the homogeneous system. Compared with conducting the path planning directly with the original heterogeneous system, the homogenization layer contributes to reduce the dimension and nonlinearity of the formulated optimal control problem in the planning layer and consequently improves the robustness and efficiency of the solution process. Finally, in the tracking layer, a receding horizon controller is developed to track the reference trajectory obtained in the planning layer. To improve the tracking performance, multi-objective optimization techniques are implemented offline in advance to determine optimal weight parameters used in the tracking layer. Simulations demonstrate that smooth and collision-free cooperative trajectory can be generated efficiently in the planning phase. And robust trajectory tracking can be realized in the presence of external disturbances in the tracking phase. The developed HPT method provides a promising solution to the autonomous deck dispatch for unmanned carrier aircraft in the future.     

CCSDS统一空间数据链路协议应用分析

针对TM、TC、AOS、Proximity-1四种空间数据链路协议的应用局限性，对CCSDS（国际空间数据系统咨询委员会）提出的统一空间数据链路协议（Unified Space Data Link Protocol， USLP）规范进行分析，介绍了USLP传输帧主导头和数据域中各个字段的设计驱动，以及与其他空间数据链路协议的差异。对于服务数据单元信道复用传输需求，梳理了物理信道、主信道、虚拟信道、多路复用访问信道的服务类型，明确了数据传输服务、信道复用、信道标识、服务数据单元之间的关联关系。以遥测遥控数据空间链路传输为例，分析了USLP的适用性和推荐设置。     

脉冲展开式飞网质量分布与展开稳定性优化

针对脉冲展开式飞网的展开稳定性问题，从网面质量分布角度开展研究。首先基于传递矩阵方法、集中质量法和反比例函数推导建立了较优的网面质量分布模型。然后结合遗传算法优化得到了网面最优的质量分布状态，并通过大量数值仿真和回归分析得到了网面质量分布经验公式。提出的网面质量分布模型有效降低了网面质量分布问题中的优化变量个数，提升了网面质量分布最优解的求解效率。网面质量分布最优解所对应的网面展开稳定性得到大幅提升，网面质量分布经验公式对应的网面展开状态与最优解对应的网面展开状态基本一致。结果表明，将网面质量分布模型和网面质量分布经验公式应用到脉冲展开式飞网将有效提升飞网的展开稳定性。     

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%.     

Sea fog detection based on unsupervised domain adaptation

Sea fog detection with remote sensing images is a challenging task. Driven by the different image characteristics between fog and other types of clouds, such as textures and colors, it can be achieved by using image processing methods. Currently, most of the available methods are datadriven and relying on manual annotations. However, because few meteorological observations and buoys over the sea can be realized, obtaining visibility information to help the annotations is difficult. Considering t...     

Close relative motion on distant retrograde orbits

Distant Retrograde Orbits (DROs) in the Earth-Moon system have great potential to support varieties of missions due to the favorable stability and orbital positions. Thus, the close relative motion on DROs should be analyzed to design formations to assist or extend the DRO missions. However, as the reference DROs are obtained through numerical methods, the close relative motions on DROs are non-analytical, which severely limits the design of relative trajectories. In this paper, a novel approach is proposed to construct the analytical solution of bounded close relative motion on DROs. The linear dynamics of relative motion on DRO is established at first. The preliminary forms of the general solutions are obtained based on the Floquet theory. And the general solutions are classified as different modes depending on their periodic components. A new parameterization is applied to each mode, which allows us to explore the geometries of quasi-periodic modes in detail. In each mode, the solutions are integrated as a uniform expression and their periodic components are expanded as truncated Fourier series. In this way, the analytical bounded relative motion on DRO is obtained. Based on the analytical expression, the characteristics of different modes are comprehensively analyzed. The natural periodic mode is always located on the single side of the target spacecraft on DRO and is appropriate to be the parking orbits of the rendezvous and docking. On the basis of quasi-periodic modes, quasi-elliptical fly-around relative trajectories are designed with the assistance of only two impulses per period. The fly-around formation can support observations to targets on DRO from multiple viewing angles. And the fly-around formation is validated in a more practical ephemeris model.