一种基于神经网络的彩色图像分割方法

提出了适于彩色图像分割的加强型径向基函数网络方法,采用在线自适应聚类学习算法确定隐层节点的数目、激活函数中心值;通过Hebb学习算法迅速将隐层节点中心值分为目标颜色聚类中心和背景颜色聚类中心两类;输出层用竞争规则将目标与背景分开。通过对多幅彩色图像进行分割处理验证了该方法的有效性。     

Network design for time‐constrained delivery

To meet customer demand, delivery companies are offering an increasing number of time‐definite services. In this article, we examine the strategic design of delivery networks which can efficiently provide these services. Because of the high cost of direct connections, we focus on tree‐structured networks. As it may not be possible to identify a tree‐structured network that satisfies all of the delivery guarantees, we allow these guarantees to be violated but seek to minimize the sum of the violations. We establish the complexity of the problem and exploit an empirically identified solution structure to create new neighborhoods which improve solution values over more general neighborhood structures. © 2008 Wiley Periodicals, Inc. Naval Research Logistics, 2008     

基于神经网络的内燃机燃烧过程的辨识

发动机燃烧过程的数值计算精度是计算有害排放物和发动机结构优化的基础。跳出基于零维模型、准维模型和多维模型的数值计算方法,基于利用神经网络对燃烧过程进行辨识,并给出了仿真结果。     

Strategic capacity decision‐making in a stochastic manufacturing environment using real‐time approximate dynamic programming

In this study, we illustrate a real‐time approximate dynamic programming (RTADP) method for solving multistage capacity decision problems in a stochastic manufacturing environment, by using an exemplary three‐stage manufacturing system with recycle. The system is a moderate size queuing network, which experiences stochastic variations in demand and product yield. The dynamic capacity decision problem is formulated as a Markov decision process (MDP). The proposed RTADP method starts with a set of heuristics and learns a superior quality solution by interacting with the stochastic system via simulation. The curse‐of‐dimensionality associated with DP methods is alleviated by the adoption of several notions including “evolving set of relevant states,” for which the value function table is built and updated, “adaptive action set” for keeping track of attractive action candidates, and “nonparametric k nearest neighbor averager” for value function approximation. The performance of the learned solution is evaluated against (1) an “ideal” solution derived using a mixed integer programming (MIP) formulation, which assumes full knowledge of future realized values of the stochastic variables (2) a myopic heuristic solution, and (3) a sample path based rolling horizon MIP solution. The policy learned through the RTADP method turned out to be superior to polices of 2 and 3. © 2010 Wiley Periodicals, Inc. Naval Research Logistics 2010     

稳定自组织网络结构中单点突变对网络稳定性影响

从战场恶劣环境通信设备无法正常通信的条件下,介绍了一种自组织网络稳定度的模型。通过比较自组织网络结构中微结构和巨结构的优缺点,动态地描述了结构间的聚合和裂解。基于结构分析,考虑单点突变对网络稳定性的影响,从时间因素策略方面,提出了一个基于预测最稳定链路生存时间的一种分布式成群策略。通过合理建模以及优化路由算法,尽可能地维护网络结构的稳定。     

自适应神经模糊推理系统(ANFIS)及其仿真

自适应神经网络模糊推理系统ANF IS是模糊控制与神经网络控制结合的产物。讨论了ANF IS的结构及其特点,并利用M ATLAB的专用工具箱进行了仿真研究,取得满意的效果。     

基于复杂网络的作战描述模型研究

针对传统作战模型重点关注兵力的毁伤,不能充分地反映信息时代作战的特点,提出了一个基于复杂网络的作战描述模型,把作战单元抽象成节点,把各单元之间的相互作用抽象成有向边,将战场描述为一个由传感器、决策器、影响器、目标四类节点组成的有向网络图。定义了网络模型的若干特征参数,把作战环看成是反映作战能力的指标,并区别分析了标准作战环和广义作战环,能更好地反映信息时代作战的特点。最后实例研究了传统作战条件下决策器连通程度的变化给作战能力带来的影响。     

基于BP网络的某型火控雷达角跟踪系统故障诊断

在介绍BP网络基本结构原理及其学习算法的基础上,结合某型火控雷达的特点,以角跟踪系统作为被诊断对象,运用BP神经网络的数学模型及学习算法对其进行故障诊断。诊断结果表明BP网络能够准确地诊断出样本的故障,提高了某型火控雷达角跟踪系统的一线维修效率,为提高火控雷达故障诊断效率提供了一种新的途径。     

二维弹道修正弹及其制导控制技术综述

针对二维弹道修正弹这类具有广泛应用前景的智能弹药,综述了二维弹道修正弹的发展、主要修正机构方案及其制导控制技术.对二维弹道修正弹的研制历程进行总结,梳理发展脉络揭示其发展规律,分析二维修正弹的打击任务.对几种主流修正方案进行讨论,分析各机构的作用特点及研究难点.基于二维弹道修正弹打击任务需求,从气动辨识及状态估计算法、...     

基于神经网络的舰船目标识别研究

为了实现对水下目标的识别,在现有特征提取方法的基础上,提出了一种从DEMON谱线谱和DEMON谱连续谱提取的特征方法,并设计了一个基于BP神经网络和多神经网络分类识别器的舰船目标识别系统。通过对实际舰船噪声目标进行识别,识别效果比较满意。这对舰船目标识别的发展具有一定的参考价值。