双三七自行高炮火控系统操作模拟器的设计

为解决部队的日常训练,设计了双三七自行高炮火控系统操作模拟器.由于其火控系统规模大,系统的多数功能是通过面板上繁多的开关、旋钮实现的,这为系统的仿真带来极大困难.本文介绍了通过综合利用数字仿真、数字检测、数字控制等技术,完成该系统仿真的设计.     

自组织特性图形的检测理论与应用

人工神经网络模型已研究多年,已使得在信息处理领域中具有类似人的性能,本文将Ｋｏｈｏｎｅｎ自组织特征映射的学习规则进行了修改,以降低拓扑邻域边界上的模糊性,而后,用它的联想存贮功能可以实现输入统计过程的特征存贮,以达到检测的目的。本文也讨论了多维检测的数学机理,作为它的一个结果,可以得出高精度的检测性能。     

具有分流型抑制机制的视网膜细胞神经网络模型及其应用

视觉细胞之间存在的侧抑制机制能够对接收到的视觉信息进行选择性的提取。运用数学方法模拟视觉细胞之间存在的这种生理机制,提出了一种具有分流型抑制机制的视网膜细胞神经网络模型(SIRCNN),分析了该模型的稳定性,给出了等价电路图,并且基于此模型提出了一种边缘检测算法。将该算法应用于图像边缘检测中,试验结果表明,这种以生物视觉感知机理为基础的神经计算方法可有效地增强图像反差,检测图像边缘。由于细胞神经网络具有高速并行运算、便于硬件实现等特点,因此这种方法在图像实时处理中也具有很大的潜力和应用前景。     

独立分量分析在液体火箭发动机故障检测中的应用

针对液体火箭发动机试车中,因噪声干扰、不同源信号之间的混叠而造成的信号信噪比低、信号分析和特征提取难度大的问题,提出采用独立分量分析(ICA)法对液体火箭发动机试车信号进行分离,以提高信号的信噪比,并能实时反映各子系统工作过程,为数据分析、特征提取和故障检测与诊断提供可靠的信号。通过对某型液体火箭发动机热试车压强信号进行实例分析,验证了该方法的有效性。     

基于并发式检测时序的几何级冲突检测策略研究

以三维CAD实时协同设计为背景,深入研究了实时协同设计中的数据冲突检测问题,提出了三维实时协同设计中的数据冲突本质上就是实体特征冲突的思想。在此基础上,探讨了基于特征的冲突检测方法,并针对其不足之处,提出了一种可行性较高的几何级冲突检测策略及其相应的检测时序方案,研究了其冲突检测数据结构、冲突检测规则。此冲突检测思想在PTC公司的Pro/Engineer平台上进行了算法验证,取得了较好的冲突检测效果。     

视频监控系统中的动目标检测新方法

在分析了现有算法在复杂背景下所存在的不足的基础上,提出了一种适用于视频监控系统的基于视频序列像素时空相关性检测的动目标检测方法.该方法首先用每一帧中像素的空间相关性检测出目标,再用序列图像中目标的时间相关性检验目标的真实性,从而最终确定是否有运动目标.试验表明,该方法能很好地检测出运动目标,并具有较强的抗干扰能力.     

结合YdUaVa颜色模型和改进MobileNetV3的视频烟雾检测方法

为降低视频烟雾检测中的虚警率和提升检测效率,提出Y^dU^aV^a颜色模型,该模型可以表征烟雾的空间域分布特性和时间域变化特性。利用该颜色模型快速筛选出疑似烟雾图像块,降低虚警率和提升运算效率。提出改进的MobileNetV3网络结构,用于提取图像深度特征并对疑似烟雾图像块进行分类识别,检测视频中是否存在烟雾。视频烟雾检测仿真结果表明:该方法准确率和检测帧率高,虚警率低。     

【专题】基于深度学习及FPGA的装备目标检测研究

本文应用深度学习技术实现海天背景下基于可见光、红外方式成像的舰船及角反、烟幕干扰的目标检测,这也是反舰导弹作战使用的关键技术之一。采集的可见光与红外成像目标检测数据集涵盖实施典型干扰下的态势场景,贴近实战;结合四种不同的目标检测机制,选取YOLOV3、Faster R-CNN、SSD及CenterNet四种典型模型分别进行训练与验证,通过对比分析进一步提高弱小目标、复杂干扰态势的的检测,可以实现端到端的高精度装备目标检测模型。在确保精度的前提下基于现场可编程门阵列（FPGA）进行软硬件协同设计,通过对比分析选定基于Vitis AI的实施方案,经过模型的量化、编译与优化,可在保证检测效率的前提下快速实现模型的小型化部署,便于进行装备移植。研究结果表明,该研究内容可有效提高现役反舰导弹目标检测的准确率。     

Theoretical design of new bridge-ring insensitive high energy compounds by selected normal Diels-Alder reactions between NH2-substituted oxazoles and NO2/NF2/NHNO2-substituted ethylenes/acetylenes

In this work, NH₂-substituted oxazoles and NO₂/NF₂/NHNO₂-substituted ethylenes/acetylenes were designed and used as dienes and dienophiles, respectively, in order to develop new bridge-ring insensitive high energy compounds through the Diels-Alder reaction between them. The reaction type, reaction feasibility and performance of reaction products were investigated in detail theoretically. The results showed that dienes most possibly react with dienophiles through the HOMO-diene controlled normal Diels-Alder reaction at relatively low energy barrier. Tetranitroethylene could react with the designed dienes much more easily than other dienophiles, and was employed to further design 29 new bridge-ring energetic compounds. Due to high heat of formation, density and oxygen balance, all designed bridge-ring energetic compounds have outstanding detonation performance, 16 of them have higher energy than HMX (1,3,5,7-tetranitro-1,3,5,7-tetrazocine) and 2 others even possess comparative energy with the representative of high energy compounds CL-20 (2,4,6,8,10,12-hexanitro-2,4,6,8,10,12-hexaazaisowurtzitane). The predicted average h₅₀ value of these bridge-ring energetic compounds is 83 cm, showing their low impact sensitivity. The NH₂ groups could obviously impel the proceeding of Diels-Alder reactions, but would slightly decrease the energy and sensitivity performance. In all, the new designed bridge-ring compounds have both high energy and low sensitivity, and may be produced through Diels-Alder reactions at relatively low energy barrier. This paper may be helpful for the theoretical design and experiment synthesis of new advanced insensitive high energy compounds.     

Hyperspectral imaging and remote trace detection of cis-1,3,4,6-tetranitrooctahydroimidazo-[4,5 d] imidazole (BCHMX) compared with traditional explosives using laser induced fluorescence

cis-1,3,4,6-Tetranitrooctahydroimidazo-[4,5 d] imidazole (BCHMX) is an advanced energetic compound that expected to spread worldwide in the near future. Since, no approved remote detection methods were reported in current literature for this material, we performed hyper-spectral imaging and laser induced fluorescence (LIF) to a BCHMX sample under low laser fluence for determining the optimum laser wavelength used in any future BCHMX-LIF based remote detection systems. For this purpose, an experimental setup consisted of a sun spectrum lamp and hyper-spectral camera was built to illuminate and image white powder samples of BCHMX in comparison with the traditional explosives, HMX (1,3,5,7-tetranitro-1,3,5,7-tetraazacyclooctane), RDX (1,3,5-trinitro-1,3,5-triazacyclohexane), PETN (2,2-Bis[(nitroxy)methyl]propane-1,3-diyldinitrate). The imaging reveals strong BCHMX sample absorption contrast among other samples at wavelength ranging from 400 to 410 nm. When light source was replaced by a 405 nm laser diode illuminator, a strong BCHMX sample LIF at the spectral range from 425 to 700 nm was observed under low laser fluence condition of 0.1 mJ/cm². Finally, we demonstrated successfully the ability of the 405 nm LIF and the hyperspectral imaging technique to detect finger print traces of BCHMX on white cellulose fabric from a distance of 15 m and a detection limit of 1 μg/cm².