逻辑阀概述

对逻辑阀的特性、参数进行了总结,介绍了逻辑阀的使用方法和注意事项。     

Application of particle swarm optimization blind source separation technology in fault diagnosis of gearbox

Blind source separation (BBS) technology was applied to vibration signal processing of gearbox for separating different fault vibration sources and enhancing fault information. An improved BSS algorithm based on particle swarm optimization (PSO) was proposed. It can change the traditional fault-enhancing thought based on de-noising. And it can also solve the practical difficult problem of fault location and low fault diagnosis rate in early stage. It was applied to the vibration signal of gearbox under three working states. The result proves that the BSS greatly enhances fault information and supplies technological method for diagnosis of weak fault.     

确定最佳起爆点的磁探测仪研究

雷的作战效果取决于雷体起爆时距离目标的远近程度,为了改善现存部分库存雷没有确定最佳起爆点这一现状,在此设计了确定最佳起爆点的磁探测仪.本探测仪采用磁阻传感器探测目标,目标信号经过后续的放大电路,微分电路处理,确定最佳起爆点,并在最佳起爆点时输出触发信号,引爆雷体.本设计还为以后智能雷的发展提供了一些研究思路.     

一种基于YOLOv4-TIA的林业害虫实时检测方法

针对现有基于深度学习的林业昆虫图像检测方法存在检测精度低和检测速度慢的问题,提出一种结合改进PANet结构与三分支注意力机制的目标检测方法YOLOv4-TIA。通过对样本数量较少的昆虫类别进行数据增强,实现样本均衡分布。利用三分支注意力机制改进YOLOv4中的CSPDarkNet53骨干网络,同时通过旋转操作和残差变换建立维度间的依存关系,以提高有效的特征通道权重,在PANet结构上增加将跳跃连接与跨尺度连接相结合的特征融合方式,从而获取更丰富的语义信息和位置信息。在此基础上,采用Focal loss函数优化分类损失,解决正负样本不均衡的问题。实验结果表明,该方法的精确率和召回率分别达到85.9%和91.2%,相比SSD、Faster R-CNN、YOLOv4方法,其在保证检测速度的同时,能够有效提高检测精度,且实现对林业害虫的实时精确监测。     

机房IC卡管理系统设计

介绍了某机房的ＩＣ卡自动化管理系统的设计,以Ｖｉｓｕａｌ Ｃ＋＋５．０编程平台和ＡＣＣＥＳＳ数据库平台进行软件设计,为机房的智能化管理手段提供了一种思路。     

不等厚薄壁筒焊缝超声板波检测技术研究

针对不等厚薄壁筒焊缝缺陷提出了一种超声检测技术,利用声场正交超声探头组对焊缝进行扫描检测,可较好解决不等厚薄壁筒焊缝缺陷的在线自动无损检测。     

基于RBF神经网络的磁探测引信系统研究

通过对比BP神经网络、径向基函数（RBF）神经网络在信号处理中的优缺点，详细分析了RBF神经网络的模型结构并应用于多模磁探测引信系统中，通过计算机仿真和实际测试效果较好。     

基于盲信号处理的传动箱状态监测与故障诊断

将盲信号处理技术应用到基于振动分析的传动箱故障诊断中,作为信号预处理与故障特征提取的主要工具,可极大增强故障信息,改变传统的以降噪为主的故障信息增强思想,提高诊断精度,解决实际中故障定位难、早期故障诊断率低的难题.     

Reformative multicast routing protocol based on Ad Hoc

Mobile Ad Hoc networks has been widely applied to military field, emergency management, public service and so on. Because it is uncertain on network and communication, a great deal of energy will be consumed with nodes increasing and creating routing each other. The reformative on-demand multicast routing protocol was putted forward by researching the energy consuming of multicast routing protocol in Ad Hoc. It will decrease consumption in a big multicast flooding through studying the relaying group net structure based on map or wormhole. The energy consumption is reduced 30% by creating the two kinds of routing principles: minimization of energy consumption and minimization of maximum nodes energy consumption. The simulation result indicates that the reformative RODMRP is effective to reduce the energy consuming while routing protocol built.     

基于BP分类的粒子群QoS路由算法研究

随机优化的粒子群算法（PSO）在解决待优化问题时,仅利用适应度函数对单个粒子所找到解的优劣进行判断,缺乏对种群总体状态的评估,导致算法经过一定次数的迭代后陷入局部收敛。改进算法BPPSO利用BP神经网络对种群进行状态划分,并根据划分结果对种群实施相应的扰动操作,从种群的角度对算法进行改进。仿真实验表明,改进算法能够增加种群多样性,提高优化精度,较好地解决了Ad Hoc网络的QoS路由问题,从而验证了所提算法的可行性和有效性。