基于AMFNN的非线性噪声消除器

提出基于加乘性模糊神经网络(AMFNN)的非线性噪声消除器，讨论了AMFNN模型和学习算法及其通用逼近性．该消除器利用AMFNN逼近噪声，然后从测量信号中消去噪声即得到有用信号．该噪声消除器具有神经网络分布式并行信息处理能力、较好的容错性和鲁棒性以及除噪性能．     

铁路枢纽作业轮廓计划优化模型及算法

本文给出铁路枢纽日常运输组织工作轮廓计划多商品时空网络流模型及算法，对次日枢纽内大小车流、机车应用配合我纽内各站装、卸、排空计划作出合理安排。揭示枢纽内各站次日工作的重点与关键。为进一步编制日班计划及阶段计划提供指导及辅助决策基础。     

神经网络在车辆半主动控制中的应用

针对车辆半主动悬挂模型的非线性特性，研究了采用神经网络的自适应控制在车辆悬挂半主动控制中的应用，设计了采用前馈神经网络的辩识器和控制器，对控制器网络采用的学习规则进行了分析。仿真计算表明，采用神经网络自适应控制方法能有效改善车辆的平稳性，采用的神经网络辩识器和控制器的改进BP算法是有效的。     

IP ADDRESS AUTOCONFIGURATION FOR WIRELESS AD HOC NETWORKS

IntroductionWireless ad hoc networks are gaining increas-ing popularity in recent years because of their easeof deployment. No wired base station or infras-tructure is supported,and each hostcommunicatesone anothervia packetradios. In ad hoc networks,routing protocols are challenged with establishingand maintaining multihop routes in the face of mo-bility,bandwidth limitation and power con-straints. In ad hoc networks,each node( host)acts as a router since routes are mostly multihop.Nodes in …     

Practicability study on the suitability of artificial,neural networks for the approximation of unknown steering torques

For steer-by-wire systems, the steering feedback must be generated artificially due to the system characteristics. Classical control concepts require operating-point driven optimisations as well as increased calibration efforts in order to adequately simulate the steering torque in all driving states. Artificial neural networks (ANNs) are an innovative control concept; they are capable of learning arbitrary non-linear correlations without complex knowledge of physical dependencies. The present study investigates the suitability of neural networks for approximating unknown steering torques. To ensure robust processing of arbitrary data, network training with a sufficient volume of training data is required, that represents the relation between the input and target values in a wide range. The data were recorded in the course of various test drives. In this research, a variety of network topologies were trained, analysed and evaluated. Though the fundamental suitability of ANNs for the present control task was demonstrated.     

一种基于神经网络的馈线自适应继电保护技术

针对常规保护的自适应能力及检测某些复杂故障方面存在一定局限性,利用前馈神经网络,导出了常规保护与神经网络参数间的显式关系,证明了神经网络继电保护可实现常规馈线保护的功能。     

接触网检测车振动补偿研究

针对接触检测车实际工况,分析了检测车车体振动的动力学特性,建立了基于运动规律的数学模型,论述了训练样本得出检测车拉出值振动补偿函数的原理和方法。     

模糊神经网络系统在滩海铺管敷缆船中的应用设计

针对滩海铺管敷船数学模型过于复杂,难以用传统控制进行建模的特点,提出了用模糊神经网络进行智能化控制的方案,并采用了一种较为简单实用的全局最优算法简化计算过程。实验证明,此控制系统具有较强的自适应性与自学习能力,表明了该方案的正确性与实用性。     

Reliable routing algorithm in marine ad hoc networks

A routing algorithm called DNH for increasing efficiency of mobile ad hoe network is presented, which is based on a new cflteflon called TSS (Temporarily Steady State), combining with wireless transmission theory that makes networks topology correspondingly stabilization. Also the DNH algorithm has the characteristics of giving up queuing in a node, but selecting another idle node instead of the node for forwarding data packets if the node has a full throughput. Simulation evaluation shows that selecting another node is better than queuing in a full throughout node if some conditions are satisfied, especially during a sea battle, every warship in ad hoe network wants to contest time and increase propagation reliability. The DNH algorithm can help decrease routing time, and raise efficiency of marine ad hoe networks.     

改进的BP神经网络在船舶与海洋工程中的应用研究

人工神经网络作为一个具有高度非线性映射能力的计算模型,在工程中具有广泛的应用前景.在数值预测方面,它不需要预选确定样本的数学模型,仅通过学习样本数据即可以进行预测.文章介绍了BP神经网络,并针对实际应用中收敛速度慢,平台效应等问题对网络进行了改进并优化,详尽地给出了改进的三层BP神经网络数值预测算法.为测试该算法.选用了著名的XOR(异或)问题和和一个高度非线性的0-1矩阵预测问题对其进行了验证.计算结果表明文中算法能给出令人满意的精度.最后结合船舶与海洋工程的两个实际问题,探讨了利用改进的BP神经网络进行数值预测的方法和应该注意的问题,并给出了一些有益的建议.实践表明,文中给出的改进的BP神经网络数值预测算法值得在船舶与海洋工程中加以应用并推广.