Bidirectional parallel multi-branch convolution feature pyramid network for target detection in aerial images of swarm UAVs

In this paper, based on a bidirectional parallel multi-branch feature pyramid network (BPMFPN), a novel one-stage object detector called BPMFPN Det is proposed for real-time detection of ground multi-scale targets by swarm unmanned aerial vehicles (UAVs). First, the bidirectional parallel multi-branch convolution modules are used to construct the feature pyramid to enhance the feature expression abilities of different scale feature layers. Next, the feature pyramid is integrated into the single-stage object detection framework to ensure real-time performance. In order to validate the effectiveness of the proposed algorithm, experiments are conducted on four datasets. For the PASCAL VOC dataset, the proposed algorithm achieves the mean average precision (mAP) of 85.4 on the VOC 2007 test set. With regard to the detection in optical remote sensing (DIOR) dataset, the proposed algorithm achieves 73.9 mAP. For vehicle detection in aerial imagery (VEDAI) dataset, the detection accuracy of small land vehicle (slv) targets reaches 97.4 mAP. For unmanned aerial vehicle detection and tracking (UAVDT) dataset, the proposed BPMFPN Det achieves the mAP of 48.75. Compared with the previous state-of-the-art methods, the results obtained by the proposed algorithm are more competitive. The experimental results demonstrate that the proposed algorithm can effectively solve the problem of real-time detection of ground multi-scale targets in aerial images of swarm UAVs.     

Preparation and characterization of HMX/EVA/hBNNSs micro-composites with improved thermal stability and reduced sensitivity

Hexagonal boron nitride nanosheets(HBNNSs)have huge potential in the field of coating materials owing to their remarkable chemical stability,mechanical strength and thermal conductivity.Thin-layer hBNNSs were obtained by a liquid-phase exfoliation of h-BN powders and incorporated into EVA coatings for improving the safety performance of 1,3,5,7-tetranitro-1,3,5,7-tetrazocane(HMX).HBNNSs and ethylene-vinyl acetate copolymer(EVA)were introduced to HMX by a solvent-slurry process.For com-parison,the HMX/EVA and HMX/EVA/graphene(HMX/EVA/G)composites were also prepared by a similar process.The morphology,crystal form,surface element distribution,thermal decomposition property and impact sensitivity of HMX/EVA/hBNNSs composites were contrastively investigated.Results showed that as prepared HMX/EVA/hBNNSs composites were well coated with hBNNSs and EVA,and exhibited better thermal stability and lower impact sensitivity than that of HMX/EVA and HMX/EVA/G composites,suggesting superior performance of desensitization of hBNNSs in explosives.     

火灾场钢筋混凝土简支梁抗弯性能分析

通过对火灾中钢筋混凝土简支梁截面温度场和材料热力学性能分析,将混凝土分为弹性区和塑性区来分别计算其强度,建立了火灾场简支梁截面内混凝土应力和梁极限抗弯承载力的计算公式,通过具体算例分析了钢筋混凝土简支梁截面温度场和极限承载力的变化规律和原因。     

马尔科夫链扫雷效果评估模型可信度验证

目前基于马尔科夫链的扫雷作战效果评估模型从单链到多链,理论模型与算法设计已经架构完毕,但该模型的可信度还有待验证。文中利用误差分布拟合检验的方法,对模型可信度进行验证,计算表明,该模型可信度较好。     

编制实施三大规范推进企业技术进步——浅谈编制实施"某承制产品三大规范"的体会

“三大规范”是设计规范、工艺规范、试验规范的统称,是企业技术标准的核心组成部分。在某承制产品的设计、制造和试验等方面通过继承成熟的经验和技术诀窍,降低产品研制风险和提高质量,有利于新技术装备研制的一次成功,对加强企业技术标准体系建设,加快型号产品研制工作,做好武器装备研制具有非常重要和深远的意义。     

军工企业转型问题中的三个不等式

在当前鼓励民营资本进入军品市场,参与军工企业的改组改造这一政策背景下,分析了当前军工企业转型中的竞争与管制、姓"军"与姓"民"、法制与法治等三对辩证关系,澄清了对民营资本参与军工企业改组改造这一举措的模糊认识,对更好地推进优质民营企业参与军工建设有现实意义。     

基于B样条插值曲线直接筛选的EMD及其在机械振动信号处理中的应用

经典的经验模式分解(EMD)方法通过求解信号的上下2条三次样条包络曲线的均值曲线,实现对原始信号的分解.但是对于非平稳、非线性信号,包络平均无法代替真正的局部平均.另外,基于包络平均的分解方法还会引入极值过冲和欠冲问题.利用B样条的良好局部性质直接计算信号的局部均值插值曲线,克服了三次样条包络方法在EMD分解中的不足.通过对旋转机械故障振动信号的分解处理,表明基于B样条局部均值插值曲线的经验模式分解方法得到的固有模式函数更符合信号的真实物理意义,分解结果更好.     

基于ADAMS／Car与MATLAB的液压主动悬架平顺性仿真研究

利用ADAMS/Car建立了传统被动弹簧与液压缸串联的主动悬架模型,与其它子系统装配组成整车仿真模型,并在MATLAB/SIMULINK的环境下建立主动悬架的PID控制系统,实现了与整车机械模型的联合仿真。仿真结果表明,采用液压主动悬架系统后,车辆在通过路面凸起处时车体质心垂向加速度得到了有效抑制,从而提高了车辆的行驶平顺性和乘坐舒适性。     

核污染的危害及其去除方法

核污染已成为全球十大环境难题之一,成了人类摆脱不掉的阴影.论述了核污染设施的核污染去除方法如物理法、化学法、电化学法、物理-化学联用法、微生物清除法、焚烧、超级压缩法和土壤核污染去除方法如铲土去污、深翻客土、可剥离性膜、森林修复等,并分析了各种去除方法的优缺点,最后提出了加强管理削减核污染源、加强现有处理方法的联用、开发微生物处理新技术和开发基因工程修复植物的建议.     

海蛇神经毒素Erabutoxin（Eb）的基因在大肠杆菌中的表达研究

为满足科研和医学应用上的需要,用基因工程的方法制备海蛇神经毒素。首先人工合成海蛇神经毒素Erabutoxin（Eb）的基因,重组到T载体。通过PCR扩增Eb基因,用限制性内切酶把基因片段酶切成黏性末端,然后将目标基因插入表达载体pPET22b（＋）,电转重组质粒到宿主菌BL21（DE3）,在25℃0．5mmol／L IPTG诱导培养8h收获培养物,SDS-PAGE电泳检测目标蛋白大部分存在于包涵体中,用8mol／L尿素溶解后,利用C末端的His-6与Ni^2＋离子亲和层析纯化,得到单一的电泳蛋白带。