基于改进SUSAN算法的红外目标边缘检测

从3个方面改进了传统的SUSAN算法:①自适应选取阈值,以提高算法自动化程度:②使用双几何阈值,增强算法的抗噪性;③加入目标点判断因子,减少计算时间.利用改进的算法进行了红外目标边缘检测,结果表明,改进算法比传统的SUSAN算法有更强的噪声抑制能力,更快的边缘检测速度,显示出更加优良的性能.对对比度比较低的红外图像,改进算法可以减少40%以上的计算时间,而对对比度较高的红外图像,改进算法可以减少70%以上的计算时间.     

基于UKF-SOFNN的近距机动目标跟踪滤波算法

对于多目标杂波环境中的机动目标跟踪,由于目标集群中各个目标间的空间距离可能小于探测器的空间分辨率,因而可能出现误跟、诱饵欺骗与杂波虚警等一系列严重后果。对此,提出一种综合运用UKF(不敏卡尔曼滤波)和SOFNN(自组织模糊神经网络)的UKF-SOFNN滤波跟踪算法,将机动目标模型视作严格的非线性系统,利用UKF-SOFNN对非线性参数的辨识能力提高对锁定机动目标的跟踪能力。仿真实例表明,该算法能有效地辨识目标群中的目标,并进行可靠的跟踪。     

空天防御发射技术发展研究

在世界新军事变革形势下,随着空天攻防技术不断发展,空天防御的发射技术也得到了发展与完善.以国内外典型空天防御产品为例,开展了发射技术的未来发展趋势综合技术研究,提出了空天防御体系中发射技术将向通用化、网络化和功能扁平化等方向发展的观点,并为此展开了详细论述.     

基于模糊Petri网的航材供应链冲突诊断建模与分析

结合航材供应链特点,建立航材供应链冲突诊断指标体系,并将节点问协作指标引入体系之中。通过模糊产生式规则,建立航材供应链冲突诊断模型,进行诊断推理,找出引起冲突的关键因素,并提出航材供应链冲突的防范对策。     

基于模糊控制的军用铅酸蓄电池充电控制技术

针对建立蓄电池精确模型存在的困难,采用了基于模糊控制算法的充电控制技术。以控制经验数据为依据,介绍了模糊控制器的设计、硬件实现及软件编程。经试验验证,模糊充电系统能使充电电流根据蓄电池本身可接受电流的大小实时改变,符合快速充电的要求,同时避免了蓄电池的过充电和欠充电。     

复杂目标毁伤效果评估的模糊专家系统框架研究

分析了复杂目标毁伤效果评估的特点和要求,提出能够满足毁伤效果评估要求的模糊专家系统方法。对模糊专家系统的基本结构、开发步骤进行了研究,建立了对复杂目标进行毁伤效果评估的模糊专家系统框架。以评估某电厂目标的毁伤效果为例,对模糊专家系统的建模步骤和关键技术进行了介绍。最后指出了模型的优缺点。     

IETM在通信装备保障中的应用

交互式电子技术手册(IETM)是实现通信装备保障信息化的关键技术之一。文章简要介绍了IETM的标准和规范、IETM的分类和技术特点,介绍了应用于通信装备保障的交互式电子技术手册实现的技术途径。     

A reusable planar triggered spark-gap switch batched-fabricated with PCB technology for medium-and low-voltage pulse power systems

Triggered spark-gap switch is a popular discharge switch for pulse power systems. Previous studies have focused on planarizing this switch using thin film techniques in order to meet the requirements of compact size in the systems. Such switches are one-shot due to electrodes being too thin to sufficiently resist spark-erosion. Additionally, these switches did not employ any structures in securing internal gas composition, resulting in inconsistent performance under harsh atmospheres. In this work, a novel planar triggered spark-gap switch (PTS) with a hermetically sealed cavity was batched-prepared with printed circuit board (PCB) technology, to achieve reusability with low cost. The proposed PTS was inspected by micro-computed tomography to ensure PCB techniques meet the requirements of machining precision. The results from electrical experiments demonstrated that PCB PTS were consistent and reusable with lifespan over 20 times. The calculated switch voltage and circuit current were consistent with those derived from real-world measurements. Finally, PCB PTS was used to introduce hexanitrostilbene (HNS) pellets in a pulse power system to verify its performance.     

Multi-scale traffic vehicle detection based on faster R-CNN with NAS optimization and feature enrichment

It well known that vehicle detection is an important component of the field of object detection. However, the environment of vehicle detection is particularly sophisticated in practical processes. It is compara-tively difficult to detect vehicles of various scales in traffic scene images, because the vehicles partially obscured by green belts, roadblocks or other vehicles, as well as influence of some low illumination weather. In this paper, we present a model based on Faster R-CNN with NAS optimization and feature enrichment to realize the effective detection of multi-scale vehicle targets in traffic scenes. First, we proposed a Retinex-based image adaptive correction algorithm (RIAC) to enhance the traffic images in the dataset to reduce the influence of shadow and illumination, and improve the image quality. Second, in order to improve the feature expression of the backbone network, we conducted Neural Architecture Search (NAS) on the backbone network used for feature extraction of Faster R-CNN to generate the optimal cross-layer connection to extract multi-layer features more effectively. Third, we used the object Feature Enrichment that combines the multi-layer feature information and the context information of the last layer after cross-layer connection to enrich the information of vehicle targets, and improve the robustness of the model for challenging targets such as small scale and severe occlusion. In the imple-mentation of the model, K-means clustering algorithm was used to select the suitable anchor size for our dataset to improve the convergence speed of the model. Our model has been trained and tested on the UN-DETRAC dataset, and the obtained results indicate that our method has art-of-state detection performance.     

基于AHP模糊综合评判的军工电子产品质量评价研究

采用基于AHP模糊综合评判的方法,针对军工电子产品的自身特点建立了其质量评价数学模型.运用该模型对某型号军用电子产品的质量进行评价,证明了评价方法的可行性.