基于贝叶斯网络的计算机网络设备级故障诊断

贝叶斯网络能够用图形化的方式表示对象间的依赖关系,并支持不确定推理。研究基于贝叶斯网络的计算机网络设备级故障诊断方法,描述故障诊断模型的构造方法,设计故障诊断算法,并通过仿真验证该方法的有效性。     

基于贝叶斯网络直升机操纵系统的故障诊断

该文针对直升机飞行操纵系统的故障诊断,讨论了故障树分析法和贝叶斯网络法的优缺点,提出一种基于贝叶斯网络的故障诊断方法。首先介绍了贝叶斯网络的基本原理,重点讲述了贝叶斯网络的构建方法和故障诊断流程,应用基于贝叶斯网络的故障诊断方法既可以通过操纵系统部件故障率推断系统总故障率,也可以分析操纵系统的薄弱环节,最后通过实例验证了贝叶斯网络法在直升机飞行操纵系统故障分析中的有效性。     

基于贝叶斯网络的设备故障诊断方法研究

贝叶斯网络的社别故障诊断方法使为更好解决其不完整性、不确定性而产生的,能够有效应用于关联性不强、设备内部构造更加复杂的诊断工作中,因而在许多方面都得到了较好应用。当前设备故障中的不确定性,主要是概率论与模糊逻辑等方法。本文主要研究了贝叶斯网络中设备故障的诊断方法,并说明这种诊断方法在设备故障中的应用优势,使其在故障诊断中的应用发展更加完善。     

一种针对水泥回转窑故障诊断的贝叶斯网络模型

为了实现水泥回转窑的故障诊断,采用贝叶斯网络建立了水泥回转窑故障智能诊断模型。在模型建立 过程中,提出了一种基于数据样本、不依赖先验知识的贝叶斯网络结构学习改进算法。在利用改进结构学习算法 建立诊断模型贝叶斯网络的基础上,利用MLE算法和变量消除法完成了模型的参数学习和诊断推理。为了验证 水泥回转窑故障诊断贝叶斯网络模型的准确率以及可行性,利用现场数据进行了大量的测试实验。     

基于LSTM的轴承故障诊断端到端方法

轴承是最为常见且重要的机械零部件之一,机械轴承的故障诊断方法一直被广泛关注和研究。近年来,越来越多的研究者利用深度学习方法对机械轴承进行故障检测与诊断,但为取得较好的轴承诊断结果,提出的复合诊断模型往往过于复杂,表现为多层次、多步骤、多算法集成。这导致泛化能力欠佳,只对特定场景下的轴承故障诊断有效,且计算量大,实时性欠佳。故提出一种基于长短时记忆网络的端到端故障诊断模型e2e-LSTM,可以直接利用时域振动信号对轴承的运行状态进行诊断。该模型包含3个LSTM层、2个全连接层、1个softmax层。实验结果表明,该模型能够以端到端模式一次性诊断多种轴承故障,并识别故障尺寸,即使在不同场景下,对轴承故障和尺寸的识别率仍然可以接近100%。     

基于贝叶斯网络的汽车故障诊断分析研究

贝叶斯（Bayes）网络是基于概率推理的图形化网络、数学模型,针对汽车故障的特点及类型,提出采用贝叶斯（Bayes）网络作为汽车故障诊断分析方法,为汽车故障提供准确和可靠的决策依据。     

基于贝叶斯网络的组合服务信任度评估方法

对组合服务信任度评估问题进行了研究。基于信任的不确定性和模糊性,给出了信任度的离散化表示方法;借助于贝叶斯网络的强大的推理能力,给出了组合服务的贝叶斯网络模型以及组合服务模型到贝叶斯网络的转换规则,利用贝叶斯网络的正向推理机制设计了基于贝叶斯网络模型的组合服务信任度评估方法。通过一个组合服务的买例,说明了组合服务的贝叶斯网络模型及其基于贝叶斯网络的组合服务信任度评估方法的使用方法。该评估方法基于信任的模糊性和不确定性,更符合信任的本质并易于实现。     

一种网络设备告警事件纵向关联方法的设计与实现

现有的网络事件关联系统主要存在以下不足：各被管设备感知的大量告警事件全部传送到管理端处理，会带来很多传输与事件管理问题；现有的网络事件关联方法很不成熟，一般只涉及底层协议告警事件的关联．在分析网络告警与故障关系的基础上，提出了一种在设备这一级驻留代理，采用贝叶斯网络推理技术完成包括应用层告警事件在内的本地告警事件纵向关联方法．并在描述协议栈各层协议实体模型的基础上，给出了利用AdventNet API和ebayes进行系统具体实现的方法．     

基于贝叶斯网络的VDT作业疲劳

在分析VDT作业中引起疲劳的各种影响因素时,提出利用贝叶斯网络分析疲劳的方法,建立疲劳先验贝叶斯网络,通过实证研究建立后验贝叶斯网络,利用Netica软件对后验贝叶斯网络模型进行数据分析解释及推理,以期找到影响疲劳的关键因素。     

基于Kohonen网络的轴系故障诊断研究

本文试从Kohonen神经网络在船舶铀系故障诊断中应用研究出发，提出了船舶轴系模拟试验台的结构和监测原理，通过数据采集系统和开发的软件系统，获得轴系振动倍号并求得其快速傅里叶变换(FFT)频谱，从频谱图中提取信号能量分布的特征矢量，用Kohonen神经网络对特征矢量进行识别，最终得到正确的故障诊断结果。介绍了Kohonen神经网络的学习和工作算法，并研究了在轴系故障诊断中的具体实施方法。实例验证表明，Kohonen网络是一种很有价值的轴系故障诊断手段。     

Rhombellanic networks

Rhombellanes are mathematical structures, proposed by us in 2017. The simplest rhombellanes, K_2.n, the complete bipartite graphs, are involved in construction of some important crystal networks, real or yet hypothetical ones. In this paper, a short insight on such triply periodic nanostructures, named here rhombellanic networks, is provided.     

Using neural networks to study networks of scientific journals

In this paper a new approach to study science dynamics is introduced. This approach is based in the use of Kohonen preserving topology maps, a kind of neural network. Four data set consisting in cross-citation matrix are studied using this approach. Relations maps and domains maps are computed for these data sets and interrelationships among journals are studied. This approach allow to stude both, hierarchical journal structure in a given time and evolution of relations among journals in a given time lag.     

水下无线传感器网络

水下无线传感器网络是一种包括声、磁场、静电场等的物理网络,它在海洋数据采集、污染预测、远洋开采、海洋监测等方面取得了广泛的应用,将在未来的海军作战中发挥重要的优势。描述了水下无线传感器网络的研究现状,给出了几种典型的水下无线传感器网络的体系结构,并针对水下应用的特点,分析了水下无线传感器网络设计中面临的节点定位、传感器网络能量、目标定位等诸多难题,最后根据应用需求提出了水下无线传感器网络研究的重点。     

Animal transportation networks

Many group-living animals construct transportation networks of trails, galleries and burrows by modifying the environment to facilitate faster, safer or more efficient movement. Animal transportation networks can have direct influences on the fitness of individuals, whereas the shape and structure of transportation networks can influence community dynamics by facilitating contacts between different individuals and species. In this review, we discuss three key areas in the study of animal transportation networks: the topological properties of networks, network morphogenesis and growth, and the behaviour of network users. We present a brief primer on elements of network theory, and then discuss the different ways in which animal groups deal with the fundamental trade-off between the competing network properties of travel efficiency, robustness and infrastructure cost. We consider how the behaviour of network users can impact network efficiency, and call for studies that integrate both network topology and user behaviour. We finish with a prospectus for future research.     

Enumeration of networks

The results of previous workers relating the number of internal and external vertices in a two-dimensional network to the number of elements of one given geometry are generalized to cover elements of any geometry (not necessarily convex) and any number of edge nodes, which may be vertex nodses of adjacent elements. It is shown that a relationship between the number of elements and number of vertices (nodes) alone exists only on a surface (plane or otherwise) and therefore cannot be extended to three-dimensional networks. In three-dimensions, the number of elements with any number of edges and vertices is related to the number of internal and external edges and vertices, is related to the number of internal and external edges and vertices, enclosed by a surface which may be non-simple, (i.e. of topological genus greater than zero).     

On bibliographic networks

In the paper we show that the bibliographic data can be transformed into a collection of compatible networks. Using network multiplication different interesting derived networks can be obtained. In defining them an appropriate normalization should be considered. The proposed approach can be applied also to other collections of compatible networks. The networks obtained from the bibliographic data bases can be large (hundreds of thousands of vertices). Fortunately they are sparse and can be still processed relatively fast. We answer the question when the multiplication of sparse networks preserves sparseness. The proposed approaches are illustrated with analyses of collection of networks on the topic "social network" obtained from the Web of Science. The works with large number of co-authors add large complete subgraphs to standard collaboration network thus bluring the collaboration structure. We show that using an appropriate normalization their effect can be neutralized. Among other, we propose a measure of collaborativness of authors with respect to a given bibliography and show how to compute the network of citations between authors and identify citation communities.