深空探测用低温推进剂贮箱热力排气系统研究

Cryogenic propellant usually experiences long term on orbit storage. The pressure increase in cryogenic storage tank is faced by most of space missions. The thermodynamic vent system (TVS) is treated as the promising method to control the increase of the tank pressure by scholars both at home and abroad. Based on the investigation conducted by different research agencies, literature review and management are conducted to reflect the recent research statue on TVS. The development profile of the experimental research on the pressure control performance of TVS is specially summarized. The condition setting and performance difference of TVS conducted by different agencies are compared and analyzed. The key technique and related conclusion are refined during the operation of TVS. Finally, based on the requirement of the large scale using of cryogenic propellant in deep space exploration in China, the development plan is proposed on the aspect of TVS pressure control on cryogenic storage tanks.     

弱模型依赖通用智能姿态控制技术

超高速跨域飞行、敏捷机动等是新一代飞行器发展方向,而长时高速飞行产生的气动外形变化带来的气动参数大范围改变等问题,都对控制系统设计提出了更高的要求。为提高飞行器对模型不确定性的适应能力及控制方法对不同外形、复合执行机构的通用性,深入研究了弱模型依赖的通用智能姿态控制技术,分层次地开展了基于深度学习(DL)的自适应姿态控制、基于深度确定性策略梯度算法(DDPG)的通用姿态控制、弱模型依赖的多维复合控制等技术研究,显著提高了控制系统的鲁棒性和通用性,对人工智能技术在飞行器姿态控制中的应用具有一定的指导意义。     

高校师德建设实践探索——以西安航空学院为例

师德建设是高校师资建设的重要内容。以西安航空学院已开展的工作为基础,从加强思想理论建设,建立完善各项相关规章制度,创建学习型组织等方面出发,探索构建高校师德建设的长效机制,推进高校师德建设向纵深方向发展。     

浅论戏剧在外语教学中的应用

探讨了将戏剧教学应用于外语课堂教学的具体实施步骤与方法,并结合实际教学效果阐述了戏剧表演在外语课堂教学中的潜在功能。实践证明戏剧教学不仅有利于学生对语言知识的深度学习和可理解输入,而且可以提高学生学习的自主性和交际能力。它是第二语言掌握的有效方法之一。     

Extrasolar space exploration by a solar sail accelerated via thermal desorption of coating

For extrasolar space exploration it might be very convenient to take advantage of space environmental effects such as solar radiation heating to accelerate a solar sail coated by materials that undergo thermal desorption at a particular temperature. Thermal desorption can provide additional thrust as heating liberates atoms, embedded on the surface of the solar sail. We are considering orbital dynamics of a solar sail coated with materials that undergo thermal desorption at a specific temperature, as a result of heating by solar radiation at a particular heliocentric distance, and focus on two scenarios that only differ in the way the sail approaches the Sun. For each scenario once the perihelion is reached, the sail coat undergoes thermal desorption. When the desorption process ends, the sail then escapes the Solar System having the conventional acceleration due to solar radiation pressure. We study the dependence of a cruise speed of a solar sail on perihelion of the orbit where the solar sail is deployed. The following scenarios are considered and analyzed: (1) Hohmann transfer plus thermal desorption. In this scenario the sail would be carried as a payload to the perihelion with a conventional propulsion system by a Hohmann transfer from Earth’s orbit to an orbit very close to the Sun and then be deployed. Our calculations show that the cruise speed of the solar sail varies from 173?km/s to 325?km/s that corresponds to perihelion 0.3?AU and 0.1 AU, respectively. (2) Elliptical transfer plus Slingshot plus thermal desorption. In this scenario the transfer occurs from Earth’s orbit to Jupiter’s orbit; then a Jupiter’s fly-by leads to the orbit close to the Sun, where the sail is deployed and thermal desorption comes active. In this case the cruise speed of the solar sail varies from 187?km/s to 331?km/s depending on the perihelion of the orbit. Our study analyses and compares the different scenarios in which thermal desorption comes beside traditional propulsion systems for extrasolar space exploration.     

Adaptive level of autonomy for human-UAVs collaborative surveillance using situated fuzzy cognitive maps

Collaborating with a squad of Unmanned Aerial Vehicles (UAVs) is challenging for a human operator in a cooperative surveillance task. In this paper, we propose a cognitive model that can dynamically adjust the Levels of Autonomy (LOA) of the human-UAVs team according to the changes in task complexity and human cognitive states. Specifically, we use the Situated Fuzzy Cognitive Map (SiFCM) to model the relations among tasks, situations, human states and LOA. A recurrent structure has been used to learn the strategy of adjusting the LOA, while the collaboration task is separated into a perception routine and a control routine. Experiment results have shown that the workload of the human operator is well balanced with the task efficiency.     

Deep reinforcement learning for six degree-of-freedom planetary landing

This work develops a deep reinforcement learning based approach for Six Degree-of-Freedom (DOF) planetary powered descent and landing. Future Mars missions will require advanced guidance, navigation, and control algorithms for the powered descent phase to target specific surface locations and achieve pinpoint accuracy (landing error ellipse <5 m radius). This requires both a navigation system capable of estimating the lander’s state in real-time and a guidance and control system that can map the estimated lander state to a commanded thrust for each lander engine. In this paper, we present a novel integrated guidance and control algorithm designed by applying the principles of reinforcement learning theory. The latter is used to learn a policy mapping the lander’s estimated state directly to a commanded thrust for each engine, resulting in accurate and almost fuel-optimal trajectories over a realistic deployment ellipse. Specifically, we use proximal policy optimization, a policy gradient method, to learn the policy. Another contribution of this paper is the use of different discount rates for terminal and shaping rewards, which significantly enhances optimization performance. We present simulation results demonstrating the guidance and control system’s performance in a 6-DOF simulation environment and demonstrate robustness to noise and system parameter uncertainty.     

论领导干部的表达力

领导干部的表达力,不仅是个人的人力资本,更是组织的宝贵财富。其现实表现具有策略性。通过个人的学习和组织的文化引领,可以实现角色转换、认同、超越,进而改善和提高表达力。     

面向卫星电源系统的一种新颖异常检测方法

面向卫星电源高维周期性时序遥测数据，提出了一种新颖的代表性特征自编码器（RFAE）模型，并用于无监督的异常检测。RFAE采用改进的堆叠自编码器损失函数和训练算法，从而使模型可以学习到相位相同样本的代表性特征；然后根据代表性特征重构样本，根据重构误差来判断样本是否异常。在试验部分首先通过模拟数据校验了RFAE算法能够有效地检测出高维周期性时序数据的异常，然后又采用某卫星电源系统2014年1~12月真实遥测数据进行试验，RFAE异常检测准确率达到99%，检测效果明显优于目前的其他异常检测算法，具有较高应用价值。     

基于局部线性嵌入的高光谱影像特征提取算法

特征提取能够消除冗余信息,提高高光谱数据处理的精度和计算效率,是分类等分析必要的预处理手段.传统特征提取算法基于线性变换,无法准确描述高、低维特征空间的关系,因此采用一种新型非线性特征提取算法,即局部线性嵌入(LLE,Locally Linear Em-bedding),挖掘高光谱影像的本征信息.针对分类问题,使用训练样本类别属性修正距离矩阵,并借鉴LLE计算未知样本低维映射的方法求解测试样本的特征向量,实现监督局部线性嵌入(SLLE,Supervised Locally Linear Embedding).使用机载可见光/红外成像光谱仪数据,与3种分类算法结合进行测试,实验结果表明:SLLE优于线性特征提取算法,能够解决高光谱影像的小样本分类问题.