An infrared target intrusion detection method based on feature fusion and enhancement

Infrared target intrusion detection has significant applications in the fields of military defence and intelligent warning. In view of the characteristics of intrusion targets as well as inspection difficulties, an infrared target intrusion detection algorithm based on feature fusion and enhancement was proposed. This algorithm combines static target mode analysis and dynamic multi-frame correlation detection to extract infrared target features at different levels. Among them, LBP texture analysis can be used to effectively identify the posterior feature patterns which have been contained in the target library, while motion frame difference method can detect the moving regions of the image, improve the integrity of target regions such as camouflage, sheltering and deformation. In order to integrate the advantages of the two methods, the enhanced convolutional neural network was designed and the feature images obtained by the two methods were fused and enhanced. The enhancement module of the network strengthened and screened the targets, and realized the background suppression of infrared images. Based on the experiments, the effect of the proposed method and the comparison method on the background suppression and detection performance was evaluated, and the results showed that the SCRG and BSF values of the method in this paper had a better performance in multiple data sets, and it’s detection performance was far better than the comparison algorithm. The experiment results indicated that, compared with traditional infrared target detection methods, the proposed method could detect the infrared invasion target more accurately, and suppress the background noise more effectively.     

基于深度神经网络的无线覆盖预测算法*

为保证新一代移动无线网络能够根据实时覆盖情况动态地调节小区天线参数,需要实现高效且准确的无线覆盖预测。传统的求解方法通过精确的场强预测来判断天线参数的优劣,虽然精度很高但需要大量的计算资源,无法满足5G和后5G移动网络通过实时覆盖预测进行射频参数动态调整的实际需求。现采用基于深度神经网络的算法对给定天线参数的覆盖效果进行预测,以取代对目标区域的精确场强预测。数值结果表明,该方法能够在保持计算准确性的同时显著减少计算量,为5G动态网络规划提供基础性参考数据。     

电磁发射系统改进FAHP-神经网络健康评估方法

准确定量评估电磁发射系统发射前的健康状态意义重大。针对模糊层次分析方法(Fuzzy Analytic Hierarchy Process, FAHP)在评估电磁发射系统串行结构同级元素健康值时存在较大偏差,且无法适用系统非线性变权重需求的缺陷,提出改进FAHP-神经网络方法。通过在计算同级元素健康指数时构造能够满足串行结构健康评估的非线性函数进行计算,并在数学上证明该方法的有效性;通过引入神经网络系统,在已有的系统先验信息和测量数据的基础上训练模型解决系统健康评估非线性变权重需求。基于电磁发射系统脉冲成形网络系统建立健康评估模型,开展评估试验。结果表明,提出的方法健康评估精度较高,在各种系统健康状态下,评估结果均符合系统实际的健康状况;对比传统的FAHP,提出的改进方法评估精度大幅提升,且在评估试验中没有出现故障误报和漏报的情况,从而验证了提出方法的可行性和工程实用价值。     

从突发公共卫生事件角度思考新时代后勤保障工作

2019年年底,一场突如其来的新型冠状病毒肺炎疫情在全国爆发,中华民族的复兴之路和中国人民的幸福生活都面临着严峻的考验和挑战。这次疫情使人们对公共卫生突发事件有了更清醒的认识,完善重大疫情应急响应机制成为今后公共安全必须加强的一项重要工作。此次的公共卫生事件具有显著的突发性、广泛性和群体性,与战时后勤保障环境具有相似性,为深入研究后勤保障工作提供了经典的现实案例。本文借鉴抗击疫情经验教训分析军队后勤保障工作,结合大数据、物联网和人工智能等高新技术实践经验,从后勤指挥、战场感知、物资配送和网络通信等多个方面提出新时代后勤保障建设的思路和方法,对未来加强新时代后勤保障工作具有一定的借鉴及参考意义。     

Analysis on MAV/UAV cooperative combat based on complex network

A formation model of manned/unmanned aerial vehicle (MAV/UAV) collaborative combat can qualitatively and quantitatively analyze the synergistic effects. However, there is currently no effective and appropriate model construction method or theory, and research in the field of collaborative capability evaluation is basically nonexistent. According to the actual conditions of cooperative operations, a new MAV/UAV collaborative combat network model construction method based on a complex network is presented. By analyzing the characteristic parameters of the abstract network, the index system and complex network are combined. Then, a method for evaluating the synergistic effect of the cooperative combat network is developed. This method provides assistance for the verification and evaluation of MAV/UAV collaborative combat.     

变分自编码器结合聚类算法在空战态势评估问题上的应用

针对传统态势评估方法确定权值的主观性强、处理大数据能力弱、特征提取能力不足等问题,提出基于改进变分自编码器和聚类算法的无监督空战态势评估方法。根据态势变化连续性特点,提出基于时间段的空战态势分类方法,将敌我双方态势划分为四类。在变分自编码器的基础上,提出了VAE-WRBM-MDN特征提取模型,即使用混合密度网络优化变分自编码器的特征提取能力和生成数据的相似度,使用权值不确定限制玻尔兹曼机优化网络的初始权值。将提取的特征分别输入到两种典型的聚类算法中进行聚类,并结合态势函数和实际战场情况修正聚类结果,形成正确的态势分类标准。在实验部分,分别进行了最优参数调整、关键特征提取、聚类以及修正实验。实验结果表明,模型态势分类正确率和运行时间均满足应用需求,实例评估结果与客观态势一致性强,所提方法具有实际应用价值。     

基于深度学习的MPSK信号调制识别

为了有效实现信号调制方式的智能识别,提出基于深度学习的多进制相移键控(Multiple Phase Shift Keying, MPSK)信号调制识别方法。分析接收MPSK信号的循环谱,并通过提取MPSK信号循环谱的等高图获得二维特征信息,利用深度学习中的卷积神经网络对二维特征进行训练,使用测试样本对所设计的调制识别方法的有效性进行验证。仿真结果表明,所提方法具有良好的识别性能。     

干扰及机动条件下的比例导引智能调控策略

由于红外诱饵干扰样式复杂、目标机动形式多变导致传统比例导引律极易被干扰。为提高采用比例导引方法的导弹性能,提出一种利用径向基函数网络调控比例系数及导弹发射时机的智能导引律。以飞行时间及脱靶量为参考,通过构建加权型指标函数将求解最优比例系数及发射时机问题转化为单目标优化问题;引入量子粒子群算法求解最优决策参量,并以其作为网络输出,干扰样式作为网络输入,离线训练径向基函数网络;为提高训练效率,结合K-means及K最近邻算法初始化径向基函数网络。仿真结果表明,当存在红外诱饵干扰时,智能导引律性能优于扩展比例导引律及自适应滑模导引律。     

Optimizing the US Navy's combat logistics force

We study how changes to the composition and employment of the US Navy combat logistic force (CLF) influence our ability to supply our navy worldwide. The CLF consists of about 30 special transport ships that carry ship and aircraft fuel, ordnance, dry stores, and food, and deliver these to client combatant ships underway, making it possible for our naval forces to operate at sea for extended periods. We have modeled CLF operations to evaluate a number of transforming initiatives that simplify its operation while supporting an even larger number of client ships for a greater variety of missions. Our input is an employment schedule for navy battle groups of ships operating worldwide, extending over a planning horizon of 90–180 days. We show how we use optimization to advise how to sustain these ships. We have used this model to evaluate new CLF ship designs, advise what number of ships in a new ship class would be needed, test concepts for forward at‐sea logistics bases in lieu of conventional ports, demonstrate the effects of changes to operating policy, and generally try to show whether and how the CLF can support planned naval operations. Published 2008 Wiley Periodicals, Inc. Naval Research Logistics 2008