基于单变量决策树的网络故障诊断方法

在网络故障诊断系统中,利用粗糙集理论约简反映网络信息的MIB变量,得出最有利于分类的变量集合.通过对约简结果构造单变量决策树的方法提取相应的决策规则,判断网络故障类型.实验结果表明,决策树构造方法简单,且提取出来的规则以决策树形式表示,规则易于理解、网络故障诊断效率较高.     

基于二叉树和四叉树综合表示环境的方法及智能路径规划的A*算法研究

通过比较利用四叉树和二叉树两种动态环境信息表示方法, 提出了移动机器人对多移动障碍物的智能路径规划的A^* 算法, 并在足球机器人系统中进行了动态避障的仿真, 得到了很好的效果.     

波长路由树形全光网中波长转换器配置算法

在波长路由全光网中,波长转换以及路由和波长分配算法（RWA）是降低网络阻塞率、改善网络性能的两个重要方法。研究了树形网络中波长转换器的配置问题,结合树形网络的特点,对影响波长转换器配置的主要因素进行了分析。综合路径长度、路径通信负荷以及节点的度,提出了基于网络直径的波长转换器配置算法和基于网络中心的波长转换器配置算法。通过算法演示和仿真,表明提出的两种算法各有优点。     

确定树求强规划解

定义了确定树,设计了求确定树的方法。基于该方法设计了求强规划解的算法,找到每个初始状态对应的确定树,在找到确定树之后,求强规划解不需要从目标状态一直搜索到初始状态,只需要从目标状态反向找到确定树的任意一个节点,再通过这个节点在确定树中反向搜索到初始状态从而得到一个强规划解。实验结果表明：所设计的算法比用反向搜索方法求强规划解的算法的效率高。     

Stochastic comparisons for rooted butterfly networks and tree networks, with random environments

Consider a rooted tree network, where the items enter at the system and they proceed away from the root until they reach their destination and exit the system, and they are served by a FIFO policy at each arc (server) of the network. The routing is defined by a discrete probability distribution with a given probability for each destination. For such systems, stochastic modelling of the departure times and the delay times is proposed, by the incorporation of random parameters of the inter-arrival times and of the service times, describing dynamic environments. A mixture model for the departure times is introduced. This mixture has an arbitrary mixing distribution defined by the environmental parameter distributions and the routing distribution. The main results provide conditions to compare stochastically the departure times (delay times) for two rooted tree networks characterized by different routing disciplines or by environmental and correlated random vectors of parameters. Furthermore, bounds for these measures are obtained from some well-known dependence concepts, as the PQD property, and ageing properties of the random environment. Similar results for butterfly networks, tree networks with possible failure during the service and other networks are provided. Within the computer networks, our framework and our results provide explorative tools to assess the design, the performance and the security of communication systems.     

树形全光网络中波长转换器配置算法

配置有限数量的波长转换器使网络阻塞率最低,是全光网络中需要解决的一个关键问题.通过考虑网络的直径、中心以及节点和链路的通信量,采用网络分解和迭代的方法,提出树形网络中基于赋权直径的波长转换器配置算法、基于节点加权中心的波长转换器配置算法,以及基于光路加权中心的波长转换器配置算法.算法演示表明,提出的3个算法总是将波长转换器放置在阻塞率较高的节点上,从而大大降低网络整体阻塞率.     

Planning grasps for industrial robotized applications using neural networks

The present paper proposes a computer-aided module for the detection of grasps of 3D objects by using artificial neural networks. This module considers the grasps performed by the most common classes of grippers used in industrial applications: two-jaw grippers, three-jaw grippers, magnetic grippers, vacuum grippers and expandable grippers. The neural networks are properly tailored and trained in order to evaluate and compare the different grasping alternatives according to geometrical and technological aspects of object surfaces. A case study is also discussed in order to point out the performances of this methodology.     

On the complexity of case-based planning

This paper analyses the computational complexity of problems related to case-based planning: planning when a plan for a similar instance is known, and planning from a library of plans. It is proven that planning from a single case has the same complexity than generative planning (i.e. planning ‘from scratch’); using an extended definition of cases, complexity is reduced if the domain stored in the case is similar to the one to search plans for. Planning from a library of cases is shown to have the same complexity. In both cases, the complexity of planning remains, in the worst case, PSPACE-complete.     

Quantization of the rolling-body problem with applications to motion planning

The problem of manipulation by low-complexity robot hands is a key issue since many years. The performance of simplified hardware manipulators relies on the exploitation of nonholonomic effects that occur in rolling. Beside this issue, more recently, the attention of the scientific community has been devoted to the problems of finite capacity communication channels and of constraints on the complexity of computation. Quantization of controls proved to be efficient for dealing with such kinds of limitations. With this in mind, we consider the rolling of a pair of smooth convex objects, one on top of the other, under quantized control. The analysis of the reachable set is performed by exploiting the geometric nature of the system which helps in reducing to the case of a group acting on a manifold. The cases of a plane, a sphere and a body of revolution rolling on an arbitrary surface are treated in detail.     

遗传算法在移动网络规划中的应用

本文通过采用遗传算法来优化移动网络规划中的基站布置。解决了基站覆盖率与经济效益之间的矛盾,并且采用实验向量的编码方式对遗传算子进行描述。在遗传操作中改进了选择算子和变异算子,加快了算法的收敛速度而不会陷入局部最优。实验结果证明了算法的有效性,比别的方法更加简单和更易于实现。     

Cooperative planning in express carrier networks — An empirical study on the effectiveness of a real-time Decision Support System

For small transportation firms cooperation in a carrier network is a proper mean to overcome the inefficiencies from deadheading. To be successful, such a network has to secure two different but equally important aspects: the partners have to be aware of specific consolidation potentials through order exchange which is an optimization and communication problem, and, the partners have to experience incentives to contribute actively to the network which is the problem of finding a fair cost/profit allocation schema for order exchanges. In this paper we discuss the experience with the development of a Decision Support System for a specific express carrier network. We illustrate how the consolidation potentials in such a network with autonomously planning carriers can be exploited and cost effectiveness can be improved substantially through the use of a suitable distributed Decision Support System if the two success factors awareness and fairness are addressed properly.     

基于生成树的无线传感器网络MAC协议

简要分析了无线传感器网络(W SNs)MAC层协议,针对MAC协议在节能和时延方面的不足,提出了一种基于生成树的MAC协议(ST-MAC)。以汇聚点为根节点,创建一个由网络中所有节点组成的生成树。ST-MAC采用TDMA接入方式,其固有的低工作周期提高了网络性能。性能分析和实验结果表明:相对S-MAC,ST-MAC在能量节省和时延方面有较好的效果。     

改进的快速扩展随机树路径规划算法

针对快速扩展随机树(RRT)路径规划算法缺乏稳定性和偏离最优解的问题,提出了一基于RRT的偏向性路径搜索算法(m-RRT).m-RRT采用生成随机点向量组的形式对随机点选取策略进行了优化,改善快速扩展随机树的不确定性,减少不必要的扩展,而加快向目标位置搜索的速度,且得到的路径优于RRT算法的结果.通过其在二维平面路径规划和三维机械臂路径规划的测试,表明其具有一定的应用价值.     

Intelligent setup planning in manufacturing by neural networks based approach

Setup planning is considered the most significant but also difficult activity in Computer Aided Process Planning (CAPP), and has a strong impact on manufacturability, product quality and production cost. Indeed, setup planning activity deserves much attention in CAPP. The setup planning in manufacturing consists mainly of three steps, namely, setup generation, operation sequence, and setup sequence. In this paper, the Kohonen self-organizing neural networks and Hopfield networks are adopted to solve such problems in setup planning efficiently. Kohonen self-organizing neural networks are utilized, according to the nature of the different steps in setup planning, to generate setups in terms of the constraints of fixtures/jigs, approach directions, feature precedence relationships, and tolerance relationships. The operation sequence problem and the setup sequence problem are mapped onto the traveling salesman problem, and are solved by Hopfield neural networks. This paper actually provides a complete research basis to solve the setup planning problem in CAPP, and also develops the most efficient neural networks based approaches to solve the setup planning problem in manufacturing. Indeed, the results of the proposed approaches work towards the optimal solution to the intelligent setup planning in manufacturing.     

实现机器人动态路径规划的仿真系统

针对机器人动态路径规划问题,提出了在动态环境中移动机器人的一种路径规划方法,适用于环境中同时存在已知和未知,静止和运动障碍物的复杂情况。采用栅格法建立机器人空间模型,整个系统由全局路径规划和局部避碰规划两部分组成。在全局路径规划中,用快速搜索随机树算法规划出初步全局优化路径,局部避碰规划是在全局优化路径的同时,通过基于滚动窗口的环境探测和碰撞规则,对动态障碍物实施有效的局部避碰策略,从而使机器人安全顺利地到达目的地。仿真实验结果说明该方法具有可行性。     

Acquiring,storing and utilizing process planning knowledge using neural networks

An approach is formulated for the automated acquisition of process selection and within-feature process sequencing knowledge from examples using neural networks. Network architecture, problem representation and performance issues are discussed.     

A practical algorithm for the minimum rectilinear steiner tree

An O(n^2) time approximation algorithm for the minimum rectilinear Steiner tree is proposed.The approximation ratio of the algorithm is strictly less than 1.5.The computing performances show the costs of the spanning trees produced by the algorithm are only 0.8% away from the optimal ones.     

A CAPWAP-based solution for frequency planning in large scale networks of WiFi Hot-Spots

We present the results of the experimental work we carried out to test a solution for frequency planning developed for the Provincia di Roma network of WiFi Hot-Spots. This work is both an example of how the Control And Provisioning of Wireless Access Points (CAPWAP) protocol may help in addressing the issues that arise in the deployment and control of large scale, possibly heterogeneous, wireless networks and a real-world test of our open source implementation of the CAPWAP protocol. Simulations and experimental tests confirm that the proposed technical solution is effective in improving network performance.     

制造资源计划中的物料清单系统

对制造资源计划(Manufacture Resource Planning,MRP Ⅱ)系统的物料清单(Bill of Materials,BOM)设计与实现过程中BOM的生成方法、多视图映射、数据结构及多层次通用件处理等关键问题进行深入研究.结合某机械加工厂的具体工作实例,给出单层BOM数据结构、多视图映射及低层码处理多层次通用件问题等方案,实现企业BOM管理的信息化,提高工作效率及质量.     

基于故障贝叶斯网的冷链物流系统可靠性分析

借鉴可靠性工程理论中系统可靠性的分析方法,将冷链物流系统运行故障这一抽象问题具体化处理,根据系统中各功能环节的运行特点及事件之间的因果关系,构建冷链物流系统的系统失效故障树;在此基础上生成贝叶斯网络,以综合评估冷链物流系统的运行可靠性,揭示系统故障产生的主要原因,为改进冷链物流系统的运行可靠性提供定量依据.将所提出方法用于某第三方冷链物流企业的运作管理中,取得了预期效果.