BP神经网络和D-S证据理论的目标识别

目标识别是指挥自动化系统的一个重要组成部分,针对现代战争对抗手段不断增强的特点,运用BP神经网络和D-S证据理论探索作战飞机机型的识别方法.前端采用3层BP神经网络结构,以传感器接收数据为输入,以神经网络输出作为证据,后端对不同传感器的证据按D-S理论进行融合,得到待识别目标的识别概率.经由MATLAB编程对国内外几种主要机型的识别进行仿真研究,与现行目标识别方法相比较,能够更快速、准确、可靠地识别飞机目标,较好地满足了空战中作战指挥系统对飞机机型识别的需求.     

一种新的MIMO非线性系统动态解耦控制方法

提出了一种基于回归小波网络(recurrent wavelet networks)的多输入多输出系统(multi-input multi-output)动态解耦控制的新方法.该方法为分散式控制结构,采用回归小波网络作为解耦辨识器(decoupling identifier),在线动态辨识、回馈对应输入输出的灵敏度信息(sensitivity information),PID神经网络控制器根据回馈信息实现自适应分散独立控制.小波函数的紧支性、波动性以及回归网络较强的动态非线性映射能力使得回归小波网络具有较好的综合性能.仿真结果表明,用该方法构成的控制系统解耦效果好,收敛速度快,且具有较好的鲁棒性.     

Critical interfaces in body armour systems

The ballistic performance, and behaviour, of an armour system is governed by two major sets of variables, geometrical and material. Of these, the consistency of performance, especially against small arms ammunition, will depend upon the consistency of the properties of the constituent materials. In a body armour system for example, fibre diameter, areal density of woven fabric, and bulk density of ceramic are examples of critical parameters and monitoring such parameters will form the backbone of associated quality control procedures. What is often overlooked, because it can fall into the User’s domain, are the interfaces that exist between the various products; the carrier, the Soft Armour Insert (SAI), and the one or two hard armour plates (HAP1 and HAP2). This is especially true if the various products are sourced from different suppliers.There are between 30 and 150 individual layers within a typical body armour system, and each of the interfaces between each of those layers will, in some way or another, contribute to the ballistic performance of the system. For example, consider the following interfaces/interlayers: (i) the frictional, sliding, inter-ply surfaces within a soft armour pack, and also between the pack and the carrier, (ii) the air-gaps that may develop within the soft armour pack, (iii) the interconnecting space between the soft armour pack and the hard armour plate, (iv) the nature of the interfaces between adjacent plies of a multiplied backing laminate, even in a highly compressed Ultra High Molecular Weight Polyethylene (UHMWPE) variant, (v) the interlayer between the ceramic and its substrate, within a HAP, and (vi) the geometrical fit between two hard armour plates within a stacked body armour system. This paper will provide a User-friendly overview of all such interfaces and provide unique guidance as to their criticality and influence.     

A new energy efficient management approach for wireless sensor networks in target tracking

This paper mainly studied the problem of energy conserving in wireless sensor networks for target tracking in defensing combats. Firstly, the structures of wireless sensor nodes and networks were illustrated; Secondly, the analysis of existing energy consuming in the sensing layer and its calculation method were provided to build the energy conserving objective function; What's more, the other two indicators in target tracking, including target detection probability and tracking accuracy, were combined to be regarded as the constraints of the energy conserving objective function. Fourthly, the three energy conserving approaches, containing optimizing the management scheme, prolonging the time interval between two adjacent observations, and transmitting the observations selectively, were introduced; In addition, the improved lion algorithm combined with the Logistic chaos sequence was proposed to obtain sensor management schemes. Finally, simulations had been made to prove the effectiveness of the proposed methods and algorithm.     

基于神经网络的弹丸强度可靠性分析

构造了一个基于神经网络的弹丸强度分析模型,通过对以往实际发生数据的训练与推理,设计并构造了一种自适应变步长自构型神经网络。对影响弹丸强度的诸多因素进行了综合的非线性分析。并可以利用该模型进行强度预测,减少实际打弹的次数,经济效益明显。     

直接网络中的自适应路由算法分析

互连网络是大规模并行计算机的重要组成部分，路由算法是其中决定网络性能的重要因素，本文在直接网络结构基础上对路由算法进行讨论，给出了一种分类方法，并着重对采用虫孔路由开关技术的自适应路由算法进行分析，为进一步的评价和设计新的算法提供了参考。     

基于神经网络的非线性控制系统自组织辨识

本文首先将自组织神经网络算法向一般化情形引伸，接着把自组织过程应用到一般非线性系统的动态过程分类，使得整个非线性系统能够按照输入输出样本空间的概率密度自组织，成为许多具有不同分类核心和感受野的线性子空间逼近。在此基础上，我们采用通用最小二乘算法，以子空间的非线性问题线性化误差作为依据，并进一步运用自组织神经网络的合作与竞争思想，最终得到一般情形的非线性系统的最小二乘辨识。仿真结果表明了本方法的可行性与优越性。     

神经网络的函数逼近理论

分析了将函数逼近理论与方法引入神经网络研究的必要性；从经典函数逼近与统计分析两方面详细地讨论了多层前馈网（ＭＬＰ）逼近能力分析的基本方法及结论；分析了正则理论观点下的径向基函数网络（ＲＢＦ）的逼近能力；讨论了ＲＢＦ网与多层前馈网在最佳逼近特性上的差异。文末指出了神经网络函数逼近的发展方向。     

扩展卡尔曼滤波的有向传感器网络移动目标跟踪算法

针对传感器网络中跟踪目标需要大量的节点协同工作,还需要实时处理和传输大量数据,提出一种基于扩展卡尔曼滤波的有向传感器网络目标跟踪算法(EK-MTDC),重点研究了传感器网络中的扇区数量对节点间数据传输与目标跟踪精度的影响,根据对目标状态的分析,通过压缩参与监测的节点个数,选择激活网络中节点相交区域内的节点对跟踪目标进行监测。仿真结果表明,该算法能在不降低跟踪效果的前提下,降低网络能耗,延长其使用寿命。     

Analysis of production lines with Coxian service times and no intermediate buffers

This paper uses the holding time model (HTM) method to derive an approximate analytic formula for the calculation of the mean throughput of a K-station production line with no buffers between any two successive stations. Service times follow the two-stage Coxian (C²) distribution at all stations. The paper provides a formula that relates the third moment of the service completion (or virtual service) time with the respective parameters of the service time, the repair time and the time to breakdown (the latter is assumed to follow the exponential distribution). In this way, it concludes that under certain conditions the two-stage Coxian distribution can be used to approximate any general distribution matching the first three moments of the service completion time distribution. The mean holding times (consisting of the service and blocking periods) of all stations of the line are obtained in an analytical form. Numerical results are provided for the mean throughput of lines with up to 20 stations. These results are shown to have a good accuracy compared against results obtained from the Markovian state method (for short lines) and results from simulation (for longer lines). © 1998 John Wiley & Sons, Inc. Naval Research Logistics 45: 669–685, 1998