一种星-箭连接动态界面力的深度学习反演方法

针对于星-箭连接动态界面力无法通过力传感器直接测量,且典型时域动载反演方法难以准确计算界面力的时域变化等难点,提出了基于长短时记忆(LSTM)神经网络的星-箭界面力深度学习反演方法。首先通过卫星地面测试试验得到数据依据,以卫星主体结构的加速度测量数据为输入层,以星-箭界面力测量数据为输出层,利用LSTM神经网络建立输入和输出间的反演映射关系模型,实现卫星在发射过程中较高精度的界面力反演。进而,设计并开展了某典型卫星结构的正弦扫频和随机振动实验,测试LSTM界面力反演方法的可行性。结果分析可知,所提出的基于LSTM深度学习反演方法能够精确地获得动态界面力时程数据,两项性能指标均优于目前典型的载荷反演方法。     

改进PointNetLK的点云智能配准与位姿图优化方法

针对空间在轨服务任务中的非合作目标相对位姿测量问题,提出一种目标可测部位点云的智能配准方法。首先,通过Straight Through滤波算法对半物理仿真平台采集得到的点云进行目标提取,以消除背景数据等杂乱信息;其次,改进PointNetLK神经网络点云配准算法,将提取后的点云数据作为输入,从而获得初步配准结果,解决非合作目标先验信息缺失导致的无法配准问题;最后,建立基于位姿图的优化模型,以降低配准误差,提高配准精度。实验结果表明,与传统迭代最近点(ICP)算法相比,配准综合误差从6.3598降低到1.7291,精度提高约 72.81% 单次耗时从33.16 s降低到4.2 s,效率提升约87.33%,与当前SM ICP等其他算法相比,也具有一定的优势。     

Atmospheric response to a Hot SST Event in November 2006 as observed by the AIRS instrument

Using Atmospheric Infrared Sounder (AIRS) products of atmospheric temperature and geopotential height, we investigate the atmospheric response to HE0611, which was found and investigated by [Qin, H., Kawamura, H., Sakaida, F., Ando, K. A case study of the tropical Hot Event in November 2006 (HE0611) using a geostationary meteorological satellite and the TAO/TRITON mooring array. J. Geophys. Res. 113, C08045, doi: 10.1029/2007JC004640, 2008]. HE0611 was formed by connecting two very high SST areas, HE0611-East and HE0611-West. The period-mean atmosphere temperatures at levels of 925 and 850 hPa in HE0611-West are higher, by about 0.5 K, than those in WE0611-East while the atmospheric temperatures at middle to high levels (700–300 hPa) are higher in HE0611-East. The period-mean geopotential heights HE0611-East are much lower than those in HE0611-West for the levels from the surface to 400 hPa. The mean geopotential heights from 400 hPa to 200 hPa are higher in HE0611-East. In the middle and high layers over HE0611-West, the atmosphere temperatures gradually decrease from 7th to 17th, and then increase significantly. The increase in HE0611-East starts from 15th November, which is earlier than that of HE0611-West. The geopotential heights in the high layer of both the areas also show corresponding behaviors. The lagged atmospheric response in the western part is confirmed by the correlation analysis. It emerges that the atmospheric response to HE0611 is well organized and associated with deep convention in HE0611-East and subsidence in HE0611-West. These are also consistent with the HE0611 features and evolution revealed by earlier HE studies.     

期望状态序列导向的深空探测器规划修复方法

Aiming at the challenges caused by the persistence, concurrency and energy consumption of probe actions, a plan repair method of deep space probe based on the expected state sequence is proposed. In this method, the expected state sequence is formed of the expected effect of the unfinished action and the expected precondition of the unexecuted action in the pre designed plan, according to the execution status of the action. The expected state sequence is an ordered set of states with mixed logic and energy, providing subgoals for plan repair and also transforming the plan repair problem into the state transition path searching problem. During the search, the plan repair strategy with energy supply priority is proposed, which separates the logic repair from energy repair to reduce the difficulty of solving the problem. And this method enables the probe to recover from plan failure autonomously. Finally, the effectiveness and rationality of the proposed method are verified through simulation by taking the Mars Orbiter as an example.     

月球表层采样样品智能确认方法

表层采样是月球采样探测的重要方式，样品智能确认有助于提升工作效率与复杂问题处理能力。结合月球表层采样铲挖工作过程，分析了铲挖过程中臂载相机图像的特点，模仿有人参与识别过程，提出了层次解耦的月球样品智能识别流程，利用深度学习方法构建了一类深度卷积识别网络，完整地描述了图像、特征、标记在网络中的正反传递关系，并在月球表层采样地面试验中进行了验证，结果表明该方法对不同光照、不同背景、不同过程、不同形态的样品，具有较好的泛化识别能力，误识别率优于8.1%，平均单幅识别时间约0.7 s。     

Application of a PCA-DBN-based surrogate model to robust aerodynamic design optimization

An efficient method employing a Principal Component Analysis (PCA)-Deep Belief Network (DBN)-based surrogate model is developed for robust aerodynamic design optimization in this study. In order to reduce the number of design variables for aerodynamic optimizations, the PCA technique is implemented to the geometric parameters obtained by parameterization method. For the purpose of predicting aerodynamic parameters, the DBN model is established with the reduced design variables as input and the aerodynamic parameters as output, and it is trained using the k-step contrastive divergence algorithm. The established PCA-DBN-based surrogate model is validated through predicting lift-to-drag ratios of a set of airfoils, and the results indicate that the PCA-DBN-based surrogate model is reliable and obtains more accurate predictions than three other surrogate models. Then the efficient optimization method is established by embedding the PCA-DBN-based surrogate model into an improved Particle Swarm Optimization (PSO) framework, and applied to the robust aerodynamic design optimizations of Natural Laminar Flow (NLF) airfoil and transonic wing. The optimization results indicate that the PCA-DBN-based surrogate model works very well as a prediction model in the robust optimization processes of both NLF airfoil and transonic wing. By employing the PCA-DBN-based surrogate model, the developed efficient method improves the optimization efficiency obviously.     

Stall flutter prediction based on multi-layer GRU neural network

The modeling of dynamic stall aerodynamics is essential to stall flutter, due to the flow separation in a large-amplitude pitching oscillation process. A newly neural network based Reduced Order Model (ROM) framework for predicting the aerodynamic forces of an airfoil undergoing large-amplitude pitching oscillation at various velocities is presented in this work. First, the dynamic stall aerodynamics is calculated by solving RANS equations and the transitional SST-γ model. Afterwards, the stall flutter bifurcation behavior is calculated by the above CFD solver coupled with structural dynamic equation. The critical flutter speed and limit-cycle oscillation amplitudes are consistent with those obtained by experiments. A newly multi-layer Gated Recurrent Unit (GRU) neural network based ROM is constructed to accelerate the calculation of aerodynamic forces. The training and validation process are carried out upon the unsteady aerodynamic data obtained by the proposed CFD method. The well-trained ROM is then coupled with the structure equation at a specific velocity, the Limit-Cycle Oscillation (LCO) of stall flutter under this flow condition is predicted precisely and more quickly. In order to predict both the critical flutter velocity and LCO amplitudes after bifurcation at different velocities, a new ROM with GRU neural network considering the variation of flow velocities is developed. The stall flutter results predicted by ROM agree well with the CFD ones at different velocities. Finally, a brief sensitivity analysis of two structural parameters of ROM is carried out. It infers the potential of the presented modeling method to depict the nonlinearity of dynamic stall and stall flutter phenomenon.     

Collaborative image compression and classification with multi-task learning for visual Internet of Things

Widespread deployment of the Internet of Things(Io T) has changed the way that network services are developed, deployed, and operated. Most onboard advanced Io T devices are equipped with visual sensors that form the so-called visual Io T. Typically, the sender would compress images, and then through the communication network, the receiver would decode images, and then analyze the images for applications. However, image compression and semantic inference are generally conducted separately, and t...     

脉冲展宽对深空激光通信的影响与补偿研究

深空激光通信系统下行链路的脉冲位置调制PPM（Pulse Position Modulation）信号在经过大气信道传输和单光子探测器接收时,将出现脉冲展宽效应,引起通信系统性能下降。分析了大气信道中的淡积云云层散射、大气湍流与气溶胶散射和单光子探测器的抖动特性所引起的脉冲展宽效应。在此基础上,仿真分析了淡积云云层物理厚度对不同PPM调制阶数下通信速率的影响,并研究了单光子探测器引起的脉冲展宽产生的抖动损失。为补偿脉冲展宽的影响,提出了一种基于时隙似然比解调的补偿方法,通过仿真验证了该方法能够有效降低深空PPM激光通信链路中脉冲展宽对通信误码率的影响。该研究对分析和提升深空PPM激光通信系统的链路性能具有一定的参考意义。     

Relevant experience learning: A deep reinforcement learning method for UAV autonomous motion planning in complex unknown environments

Unmanned Aerial Vehicles (UAVs) play a vital role in military warfare. In a variety of battlefield mission scenarios, UAVs are required to safely fly to designated locations without human intervention. Therefore, finding a suitable method to solve the UAV Autonomous Motion Planning (AMP) problem can improve the success rate of UAV missions to a certain extent. In recent years, many studies have used Deep Reinforcement Learning (DRL) methods to address the AMP problem and have achieved good results. From the perspective of sampling, this paper designs a sampling method with double-screening, combines it with the Deep Deterministic Policy Gradient (DDPG) algorithm, and proposes the Relevant Experience Learning-DDPG (REL-DDPG) algorithm. The REL-DDPG algorithm uses a Prioritized Experience Replay (PER) mechanism to break the correlation of continuous experiences in the experience pool, finds the experiences most similar to the current state to learn according to the theory in human education, and expands the influence of the learning process on action selection at the current state. All experiments are applied in a complex unknown simulation environment constructed based on the parameters of a real UAV. The training experiments show that REL-DDPG improves the convergence speed and the convergence result compared to the state-of-the-art DDPG algorithm, while the testing experiments show the applicability of the algorithm and investigate the performance under different parameter conditions.