用神经网络控制器对小型帆船的航向控制

本文描述了一个简单的基于神经网络的小型帆船自适应舵的控制方案.该方案采用了两个简单的双层神经网络:一个使用在线的BP算法来学习未知的帆船动态;另一个则利用前一个所学到的知识来调整它的连接权系数和偏差权系数以产生控制信号.仿真结果表明,与仔细调整过的PID控制器相比较,神经网络控制器在航向保持上与PID近乎相同,但却具有好得多的鲁棒特性.     

基于模糊神经网络和数据融合的结构裂纹故障诊断

本文利用模糊神经网络和数据融合技术相结合,对铝板裂纹进行了故障诊断.在梁结构的振型斜率变化率的基础上,得到了板结构两个方向的振型斜率变化率裂纹诊断指标.通过对模糊神经网络诊断结果和模糊神经网络数据融合诊断结果的比较,证明模糊神经网络数据融合诊断方法对裂纹的检测、定位和性质刻画能够达到满意的精度,也证明了在所取五种裂纹诊断指标中,振型斜率变化率裂纹诊断指标对裂纹的诊断精度是最高的.     

A model to identify airport hubs and their importance to tourism in Brazil

Air transportation in Brazil has been recently liberalized and one of the consequences of this process is the concentration of flights in a few hubs. During the years 2006-2007 two fatal accidents created unprecedented chaos in both land and air sides of the system with harmful consequences to tourism in Brazil. The consequences were more airport congestion and many episodes of flight delays and cancellations that lasted for several months. We argue that, among other factors, this state of blackout was a result of the increase in the degree of concentration in few airports, particularly Congonhas (in São Paulo) and Brasília. Using data obtained from a survey with Brazilian experts, a comparison was made with two existing methods (the one used by the US Federal Aviation Administration and the usual Herfindahl-Hirschman method) in order to calculate the number of hubs in Brazil. Due to the huge discrepancy obtained between data from the survey and the other two methods considered, a new mathematical method based on the Herfindahl-Hirschman Index was proposed to identify the number of hubs in a given network. Drawing from the examples of what happened to tourist destinations during and after the air transport crisis in Brazil, the article concludes discussing the need for a more accurate tool to identify and to monitor the concentration of flights at the Brazilian air transportation network and its importance to tourism.     

输出端口编码的可扩展快速转发方法

提出了一种基于路由器端口编码的转发方法（OPCF）,该方法通过在通信源和目的间预先建立起面向连接的端口编码路径,可直接根据端口编码对数据包进行路由,避免了路由表查询开销,实现了基于显式路由的灵活快速转发,有助于网络服务质量的提高和流量工程的实现．由于不需要路由器存储和管理除路由表外的额外信息,OPCF可获得良好的扩展性．由于可隐藏数据包的IP地址信息,OPCF能有效增强网络通信的安全性．原型系统上的实验结果表明,该方法能实现比MPLS更低的端到端延时并能有效提高网络的吞吐量．     

Application of fuzzy neural network to the nuclear power plant in process fault diagnosis

The fuzzy logic and neural networks are combined in this paper, setting up the fuzzy neural network (FNN) ; meanwhile, the distinct differences and connections between the fuzzy logic and neural network are compared. Furthermore, the algorithm and structure of the FNN are introduced. In order to diagnose the faults of nuclear power plant, the FNN is applied to the nuclear power plant, and the intelligence fault diagnostic system of the nuclear power plant is built based on the FNN . The fault symptoms and the possibility of the inverted U-tube break accident of steam generator are discussed. In order to test the system‘ s validity, the inverted U-tube break accident of steam generator is used as an example and many simulation experiments are performed. The test result shows that the FNN can identify the fault.     

略论英汉航海专业词典的编写

科学技术的进步，其中包括科技图书的编辑出版工作。经过多年含辛茹苦的努力，作为重要文化工程的《英汉航海·航运·船舶大词典》已经面世。该文作者是《英汉航海·航运·船舶大词典》的主编和责任编辑，他们从编辑出版的全过程着重介绍了该词典具有的内容全、资料新、应用广、装帧美以及实用性、知识性、科学性和相对稳定性等特点。     

智能交通系统综合信息平台研究

分析了综合交通信息平台数据处理、交互平台和辅助决策等主要功能，在此基础上提出了以多种数据处理技术为核心的综合交通信息平台的分布式体系结构，探讨了综合交通信息平台建设的数据融合技术、数据压缩技术、数据标准、数据仓库技术以及数据挖掘技术等，该综合信息平台的具有实现交通运输系统的有效集成、交通运输服务内容的延伸等优越性。     

Traffic volume forecasting based on radial basis function neural network with the consideration of traffic flows at the adjacent intersections

The forecasting of short-term traffic flow is one of the key issues in the field of dynamic traffic control and management. Because of the uncertainty and nonlinearity, short-term traffic flow forecasting could be a challenging task. Artificial Neural Network (ANN) could be a good solution to this issue as it is possible to obtain a higher forecasting accuracy within relatively short time through this tool. Traditional methods for traffic flow forecasting generally based on a separated single point. However, it is found that traffic flows from adjacent intersections show a similar trend. It indicates that the vehicle accumulation and dissipation influence the traffic volumes of the adjacent intersections. This paper presents a novel method, which considers the travel flows of the adjacent intersections when forecasting the one of the middle. Computational experiments show that the proposed model is both effective and practical.