民航卫星通信网可视通信图像压缩编码方法研究

对民航卫星通信网进行可视通信图像压缩编码方法进行了研究。通过在多媒体计算机上进行模拟实验表明，将视频信息及语音信息压缩为64kbps通过TES卫星网传输方案是可行的。     

CAN总线在电液伺服阀性能测试系统中的应用

伺服阀性能测试系统中，测控电路和计算机间的模拟信号传输易受外界干扰，而把信号以数码形式通过CAN总线传输的方法，可以彻底消除外界干扰问题，还能提高系统的性能和可靠性。介绍了CAN总线硬件电路、程序设计及CANopen通讯协议的实现，讨论了CAN总线在测试系统上的实际应用。     

网络实时录播系统在网络课程库建设中的应用

不改变传统教学方式 ,利用网络实时录播系统可以有效地发挥传统电教设备的作用 ,轻松实现网上直播、实时记录和点播 ,构建网络课程库     

电长度测量方法探究

从电长度的概念出发，主要介绍了使用网络分析仪来实现电长度测量的三种方法，分别是频域电延迟法、时域反射法和时域传输法；针对三种不同方法分别做了试验。     

基于分布式管理架构的应用型网管系统的设计与研究

根据当前IT应用的普及情况,分析了大中型企业中网络资源管理存在的问题,研究了网管软件的相关技术并设计了一套符合当前应用需求的分布式管理架构的应用型网管系统。该系统不但可监测各类操作系统的性能,还可对数据库、WEB服务等应用服务器的性能进行监控。结合网管软件的发展动态,展示了该应用型网管系统的工程应用价值。     

Using the radial basis function neural network to predict ionospheric critical frequency of F2 layer over Wuhan

Neural networks (NNs) have been applied to ionospheric predictions recently. This paper uses radial basis function neural network (RBF-NN) to forecast hourly values of the ionospheric F₂ layer critical frequency(f_oF₂), over Wuhan (30.5N, 114.3E), China. The false nearest neighbor method is used to determine the embedding dimension, and the principal component analysis (PCA) is used to reduce noise and dimension. The whole study is based on a sample of about 26,000 observations of f_oF₂ with 1-h time resolution, derived during the period from January 1981 to December 1983. The performance of RBF-NN is estimated by calculating the normalized root-mean-squared (NRMSE) error, and its results show that short-term predictions of f_oF₂ are improved.     

An artificial neural network approach for aerodynamic performance retention in airframe noise reduction design of a 3D swept wing model

With the progress of high-bypass turbofan and the innovation of silencing nacelle in engine noise reduction, airframe noise has now become another important sound source besides the engine noise. Thus, reducing airframe noise makes a great contribution to the overall noise reduction of a civil aircraft. However, reducing airframe noise often leads to aerodynamic perfor-mance loss in the meantime. In this case, an approach based on artificial neural network is intro-duced. An established database serves as a basis and the training sample of a back propagation (BP) artificial neural network, which uses confidence coefficient reasoning method for optimization later on. Then the most satisfactory configuration is selected for validating computations through the trained BP network. On the basis of the artificial neural network approach, an optimization pro-cess of slat cove filler (SCF) for high lift devices (HLD) on the Trap Wing is presented. Aerody-namic performance of both the baseline and optimized configurations is investigated through unsteady detached eddy simulations (DES), and a hybrid method, which combines unsteady DES method with acoustic analogy theory, is employed to validate the noise reduction effect. The numerical results indicate not merely a significant airframe noise reduction effect but also excel-lent aerodynamic performance retention simultaneously.     

用神经网络法编程加工轮毂上特殊曲面的探讨

根据轮毂上曲面的特殊性,提出了采用神经网络方法进行编程,实现数控加工,以取代传统的加工方法的设想。     

基于单代号网络的银行家算法

通过对银行家算法的分析,提出单代号网络的进程安全状态序列的改进算法-基于单代号网络的银行家算法,并通过具体的示例实现此算法。     

人工神经元网络在变压器分接头实时控制中的应用

本文提出了一种利用人工神经元网络实时控制变压器分接头的新方法。研究结果表明该方法具有快速准确等优点，适应电力系统高度自动化的要求，并为变压器分接头实时控制开辟了一条新途径。