武器装备智能保障系统建模与效能分析

为实现信息化作战保障条件下的装备保障能力建设和提升，面向装备OODA闭环提出装备智能保障系统，建立基于DoDAF的智能保障系统结构模型，并基于网络分析法对装备智能保障系统和传统装备保障系统的效能进行了对比评估。在总结当前装备效能评估领域国内外研究现状的基础上，以OODA全流程闭环为目标，分析装备保障的现存问题和装备智能保障模式的特点，并构建武器装备智能保障系统模型。通过系统高层概念、能力、任务活动等要素建模，构建武器装备智能保障系统效能模型并基于网络分析法开展效能评估，通过装备训练保障、维修保障、信息支援和行动支持等维度对比了传统装备保障系统与智能保障系统的效能差异，提出智能保障技术的发展建议，为装备保障的智能化发展提供理论参考。     

基于改进SSD算法的航拍目标检测算法研究

研究基于深度学习技术的无人机航拍图像目标检测算法，首先介绍目标检测算法SSD（Single Shot MultiBox Detector），并对其特征提取网络进行改进，采用稠密特征提取网络替换原网络的主干特征提取网络，提高算法的特征提取能力，从而提升了算法的检测精度。针对网络实时性问题，在算法中引入分组卷积，极大地减少了网络参数量，提升了网络推理速度。为解决训练中出现的正负样本不均衡问题，利用焦点损失（Focal Loss）改进了原算法的损失函数，进一步提升了网络的收敛速度和精度。最后，通过仿真验证了改进算法在目标检测精度上的优越性。     

Finite time non-singular sliding mode control for spinning tether system with prescribed performance under artificial gravity mission

In this paper, the spinning tether system (STS) is applied to produce the artificial gravity overload with a proposed spin-up scheme in elliptical transfer orbits. To improve the comfort of the astronauts during spinning, the combined control scheme with tension and thrust is designed for spin-up. Then, based on the novel performance function and sliding mode technology, a finite time prescribed performance controller is proposed to track angular velocity for the desired artificial gravity overload. Compared with the existing works, the tracking error is controlled within the preset transient performance and converged to the origin within finite time even in the presence of unknown external disturbance. The stability of closed-loop tracking system is proved by Lyapunov theorem. Finally, the numerical simulations are given to demonstrate the effectiveness and robustness of the proposed controllers in the artificial gravity mission.     

增强神经网络辨识模型泛化能力的研究

神经网络(Artificial Neural Network,ANN)辨识模型的泛化能力是其最主要的性能之一,增强ANN模型的泛化能力也是近年来国内外有关专家学者研究的重点问题。大量研究表明,ANN模型泛化能力的改善与很多因素相关联,其中恰当的性能指标函数设计是一个重要影响因素。文中在分析常见的基于均方误差最小原则的性能指标函数基础上,通过加入ANN辨识模型权值间的延迟信息,进而获得一种改进型性能指标函数。通过仿真,验证了所设计的改进型性能指标函数对增强ANN辨识模型的泛化能力是有效的。     

Surrogate role of machine learning in motor-drive optimization for more-electric aircraft applications

Motor drives form an essential part of the electric compressors, pumps, braking and actuation systems in the More-Electric Aircraft (MEA). In this paper, the application of Machine Learning (ML) in motor-drive design and optimization process is investigated. The general idea of using ML is to train surrogate models for the optimization. This training process is based on sample data collected from detailed simulation or experiment of motor drives. However, the Surrogate Role (SR) of ML may vary for different applications. This paper first introduces the principles of ML and then proposes two SRs (direct mapping approach and correction approach) of the ML in a motor-drive optimization process. Two different cases are given for the method comparison and validation of ML SRs. The first case is using the sample data from experiments to train the ML surrogate models. For the second case, the joint-simulation data is utilized for a multi-objective motor-drive optimization problem. It is found that both surrogate roles of ML can provide a good mapping model for the cases and in the second case, three feasible design schemes of ML are proposed and validated for the two SRs. Regarding the time consumption in optimizaiton, the proposed ML models can give one motor-drive design point up to 0.044 s while it takes more than 1.5 mins for the used simulation-based models.     

Orbital error propagation considering atmospheric density uncertainty

Due to the influence of various errors, the orbital uncertainty propagation of artificial celestial objects while orbit prediction is required, especially in some applications such as conjunction analysis. In the orbital error propagation of artificial celestial objects in low Earth orbits (LEOs), atmospheric density uncertainty is one of the important factors that require special attention. In this paper, on the basis of considering the uncertainties of position and velocity, the atmospheric density uncertainty is also taken into account to further investigate the orbital error propagation of artificial celestial objects in LEOs. Artificial intelligence algorithms are introduced, the MC Dropout neural network and the heteroscedastic loss function are used to realize the correction of the empirical atmospheric density model, as well as to provide the quantification of model uncertainty and input uncertainty for the corrected atmospheric densities. It is shown that the neural network we built achieves good results in atmospheric density correction, and the uncertainty quantization obtained from the neural network is also reasonable. Moreover, using the Gaussian mixture model - unscented transform (GMM-UT) method, the atmospheric density uncertainty is taken into account in the orbital uncertainty propagation, by adding a sampled random term to the corrected atmospheric density when calculating atmospheric density. The feasibility of the GMM-UT method considering atmospheric density uncertainty is proved by the further comparison of abundant sampling points and GMM-UT results (with and without considering atmospheric density uncertainty).     

遥感场景分类的批处理协方差神经网络方法

针对卫星遥感图像场景分类数据集中存在的局部区域特征异常问题，提出一种采用批处理协方差层的神经网络(CovNN)模型进行遥感场景分类的方法。该方法通过计算全输入通道的局部区域均值实现一种3D批处理协方差算法，能够有效消除局部区域均值的影响，从而更好地处理局部光照过强和局部区域存在无关特征的问题。将其应用于存在局部光照异常和局部无关特征问题的卫星采集AID数据集和NWPU RESISC45数据集中，实验表明CovNN在两个数据集上均取得了超过现有卷积神经网络(CNN)的召回率，可有效降低图像局部区域特征异常的不利影响。     

基于时空数据模型的障碍物数据集数据查询与应用研究

障碍物数据集是国际民航组织在航空情报管理（AIM）体系下提出的一种基于航空信息交换模型（AIXM）规范的航空情报数据集，该数据集中障碍物的查询将直接影响机场净空评估与飞行程序设计。在分析障碍物数据集的时间与空间属性基础上，利用时空数据模型与航空信息交换模型规范，提出一种基于时间点和空间位置的障碍物数据集查询方法， 用于解决障碍物数据集的查询问题；构建障碍物查询与可视化系统，并通过设计随机实验和实例应用对该方法的可行性和可靠性进行验证。结果表明：该障碍物数据集查询方法能够提取出对机场净空与飞行程序设计有影响的障碍物，增强了飞行程序设计人员对机场障碍物分布的情景意识。