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...     

基于数据扩充和特征增强的雷达回波无人机检测

针对基于雷达无人机目标识别难度高、精确度低、适应性差等问题，本文提出了利用深度学习的方法，对雷达回波进行无人机检测。首先，利用相参累积的方法生成雷达回波的距离-多普勒图像，增强目标特征并提高信噪比;其次，采用生成对抗模型对距离-多普勒图像进行数据扩充，以获得充足的图像数据减小网络的过拟合并提高网络鲁棒性;最后，使用基于位置感知的卷积神经网络增强特征，通过构建基于距离-多普勒图像的感知模块，实现对目标距离和运动速度的检测。通过在雷达回波序列中弱小飞机目标检测跟踪数据集上验证的结果表明:最终检测结果在召回率89%的情况下达到了91%的准确率。相比于基准方法，本文提出的方案具有更高的检测精度和更好的网络运行效率。     

星箭分离减冲击环结构优化设计

针对星箭分离过程，建立了减冲击环结构模型，并分析了该结构的减冲原理。利用冲击响应谱的时域合成算法计算获得符合冲击谱规范的时域载荷，并以此作为结构优化设计中动力学模型的输入载荷工况。以减冲击环的连续层数、单层支撑块数、连续层厚度、支撑块层高度以及环的外半径和内半径6个结构参数为设计变量，以减冲效果和结构强度、刚度为约束，以质量最轻为目标，建立减冲击环的结构优化设计模型，这是一包含离散变量和连续变量的混合优化问题。为了在跨平台下求解该混合优化问题，采用代理模型策略和自适应模拟退火算法求解，并在最优点处开展结构性能对设计变量的敏度计算，对计算结果进行了分析评估。本研究对强冲击动力学环境下的航天器结构分析与设计有一定的指导意义。     

基于空间分布特性多层RX高光谱点目标检测

针对目前高光谱图像异常点目标检测过程中准确率低和虚警率高的问题,本文结合目标的空间分布特性,提出了一种多层级RX检测方法。通过计算被检测区域图像谱向相似性响应图,采用非线性抑制的方法,突出点目标并抑制背景。为进一步提高检测算法的表达能力和泛化性能,采用多级检测器级联的方式,逐层级增强异常点处的相对能量,削弱背景的影响,从而达到较高的检测性能。在外场挂飞试验数据集上进行验证,结果表明:该方法 AUC值达到0.988 1,明显优于CEM算法的0.962 6和传统RX算法的0.939 2。     

Interaction tonal noise generated by contra-rotating open rotors

Fast and accurate prediction of sound radiation of Contra-Rotating Open Rotors(CRORs) is an essential element of design methods of low-noise open rotor propulsion systems.In the present work, a previous frequency-domain model is extended to predict CROR noise. It builds explicitly the relationship between harmonic loadings and corresponding tonal noise, by which the influential parameters to noise generation can be clearly understood. The real distributions of steady and unsteady blade loadings ...     

基于几何设计法的航空发动机内外机匣减振控制新方法

航空发动机在运行过程中，由于其结构的复杂性和外部气流的不稳定性，不可避免地会产生大量的振动问题。针对航空发动机整机振动问题，首先根据航空发动机的实际结构并结合经验总结，建立了一种通用的转子-支承-机匣振动传递动力学模型，并从航空发动机内外机匣减振控制问题出发，利用一种新型的控制算法（几何设计法），在有限频域内来设计减振控制器，在传感器和执行机构受限的情况下，尝试对多个输出量（即航空发动机的内机匣和外机匣）进行减振控制，并与经典控制理论法比例、微分、积分（Proportional integral derivative,PID）设计的减振控制器进行减振效果对比，最后通过Matlab/Simulink搭建仿真模型并进行仿真验证。结果表明，几何设计法在有限频域内可以直观地获得最优控制器的存在性、唯一性、最优性，对于主控对象的减振控制最优可高达25 dB，相较于传统控制方法形成明显优势。     

锯切圆柱形42CrMoA的声发射监测试验

针对锯切加工中的带锯条磨损状态未知、锯切质量下降等问题，本文研究了新试制的FTCUT双金属带锯条锯切圆柱形42CrMoA合金结构钢过程中锯切行为的变化，探讨了声发射信号与单刀锯切过程、锯齿磨损和锯切表面质量变化的关联。研究表明：锯切圆柱材料时随着锯切深度的变化，参与齿数先增大后减小，带锯条约束条件不断变化，进而影响着声发射信号幅值和锯切表面质量；基于时域分析可知锯齿磨损过程分为磨合磨损、快速磨损、稳定磨损三个阶段；基于FFT频域分析发现当频谱图出现多个主频，且第一主频幅值下降时，表明声发射信号来源比较分散，即可认定带锯条失效；基于小波包频域分析发现第7频段信号占比最高，最能反映工件表面质量的变化，其波动情况与锯切表面的微纹和波纹情况可建立一定的联系。因此，可基于声发射信号时域和频域分析判断锯齿磨损和锯切表面恶化情况，为锯齿磨损和锯切表面质量的在线监测提供一定的思路。     

顾及动态物体感知的增强型视觉SLAM系统

传统的同步定位与制图（Simultaneous localization and mapping, SLAM）系统在复杂环境下工作时，无法分辨环境中的物体是否存在运动状态，图像中运动的物体可能导致特征关联错误，引起定位的不准确和地图构建的偏差。为了提高SLAM系统在动态环境下的鲁棒性和可靠性，本文提出了一种顾及动态物体感知的增强型视觉SLAM系统。首先，使用深度学习网络对每一帧图像的动态物体进行初始检测，然后使用多视图几何方法更加精细地判断目标检测无法确定的动态物体区域。通过剔除属于动态物体上的特征跟踪点，提高系统的鲁棒性。本文方法在公共数据集TUM和KITTI上进行了测试，结果表明在动态场景中定位结果的准确度有了明显提升，尤其在高动态序列中相对于原始算法的精度提升在92%以上。与其他顾及动态场景的SLAM系统相比，本文方法在保持精度优势的同时，提高了运行结果的稳定性和时间效率。     

Source free unsupervised domain adaptation for electro-mechanical actuator fault diagnosis

A common necessity for prior unsupervised domain adaptation methods that can improve the domain adaptation in unlabeled target domain dataset is access to source domain dataset and target domain dataset simultaneously. However, data privacy makes it not always possible to access source domain dataset and target domain dataset in actual industrial equipment simultaneously, especially for aviation component like Electro-Mechanical Actuator (EMA) whose dataset are often not shareable due to the data copyright and confidentiality. To address this problem, this paper proposes a source free unsupervised domain adaptation framework for EMA fault diagnosis. The proposed framework is a combination of feature network and classifier. Firstly, source domain datasets are only applied to train a source model. Secondly, the well-trained source model is transferred to target domain and classifier is frozen based on source domain hypothesis. Thirdly, nearest centroid filtering is introduced to filter the reliable pseudo labels for unlabeled target domain dataset, and finally, supervised learning and pseudo label clustering are applied to fine-tune the transferred model. In comparison with several traditional unsupervised domain adaptation methods, case studies based on low- and high-frequency monitoring signals on EMA indicate the effectiveness of the proposed method.     

A Robotic TeleoperationSystem for Precise Robotic Manipulation by Human-Machine Interaction

Teleoperation is of great importance in the area of robotics， especially when people are unavailable in the robot workshop. It provides a way for people to control robots remotely using human intelligence. In this paper， a robotic teleoperation system for precise robotic manipulation is established. The data glove and the 7-degrees of freedom (DOFs) force feedback controller are used for the remote control interaction. The control system and the monitor system are designed for the remote precise manipulation. The monitor system contains an image acquisition system and a human-machine interaction module， and aims to simulate and detect the robot running state. Besides，a visual object tracking algorithm is developed to estimate the states of the dynamic system from noisy observations. The established robotic teleoperation systemis applied to a series of experiments， and high-precision results are obtained， showing the effectiveness of the physical system.