基于路径存储表的Hashgraph共识算法优化与实现

Hashgraph是一种数据采用有向无环图(DAG)结构的区块链共识算法,Hashgraph引入了虚拟投票的概念,允许节点在无额外通信开销的情况下并发出块,实现异步场景下的拜占庭容错。然而,Hashgraph提出的虚拟投票算法存在算法时间复杂度较高、共识运行逻辑过于复杂等问题。为此,提出一种基于路径存储表的Hashgraph优化方案。首先,提出一种基于顶点可达表的见证人判定方法,通过存储路径的方式实时记录生成事件与历史事件的可达关系,在轮次划分阶段,通过查询顶点事件的可达信息取代回溯算法,降低见证人判断算法的时间复杂度;其次,针对顶点可达表无法跨轮次判断事件关系的问题,提出一种基于历史可达表的知名见证人判定方法,历史可达表将存储见证人与历史事件之间的可达关系,通过查询历史可达表解决知名见证人判定阶段需要反复回溯视图的问题;最后,根据顶点可达表和历史可达表改进Hashgraph中复杂的共识计算,提升算法效率,加快事件确认速度。实验结果表明,所提优化方案与Hashgraph原共识算法相比,算法运行效率提升65.76%,在吞吐量方面平均提升41.27%。

Optimization of a dynamic uncertain causality graph for fault diagnosis in nuclear power plant

Fault diagnostics is important for safe operation of nuclear power plants(NPPs). In recent years, data-driven approaches have been proposed and implemented to tackle the problem, e.g., neural networks, fuzzy and neurofuzzy approaches, support vector machine, K-nearest neighbor classifiers and inference methodologies. Among these methods, dynamic uncertain causality graph(DUCG)has been proved effective in many practical cases. However, the causal graph construction behind the DUCG is complicate and, in many cases, results redundant on the symptoms needed to correctly classify the fault. In this paper, we propose a method to simplify causal graph construction in an automatic way. The method consists in transforming the expert knowledge-based DCUG into a fuzzy decision tree(FDT) by extracting from the DUCG a fuzzy rule base that resumes the used symptoms at the basis of the FDT. Genetic algorithm(GA) is, then, used for the optimization of the FDT, by performing a wrapper search around the FDT: the set of symptoms selected during the iterative search are taken as the best set of symptoms for the diagnosis of the faults that can occur in the system. The effectiveness of the approach is shown with respect to a DUCG model initially built to diagnose 23 faults originally using 262 symptoms of Unit-1 in the Ningde NPP of the China Guangdong Nuclear Power Corporation. The results show that the FDT, with GA-optimized symptoms and diagnosis strategy, can drive the construction of DUCG and lower the computational burden without loss of accuracy in diagnosis.

Enhanced graph-based fault diagnostic system for nuclear power plants

Scheduled maintenance and condition-based online monitoring are among the focal points of recent research to enhance nuclear plant safety.One of the most effective ways to monitor plant conditions is by implementing a full-scope,plant-wide fault diagnostic system.However,most of the proposed diagnostic techniques are perceived as unreliable by operators because they lack an explanation module,their implementation is complex,and their decision/inference path is unclear.Graphical formalism has been considered for fault diagnosis because of its clear decision and inference modules,and its ability to display the complex causal relationships between plant variables and reveal the propagation path used for fault localization in complex systems.However,in a graphbased approach,decision-making is slow because of rule explosion.In this paper,we present an enhanced signed directed graph that utilizes qualitative trend evaluation and a granular computing algorithm to improve the decision speed and increase the resolution of the graphical method.We integrate the attribute reduction capability of granular computing with the causal/fault propagation reasoning capability of the signed directed graph and comprehensive rules in a decision table to diagnose faults in a nuclear power plant.Qualitative trend analysis is used to solve the problems of fault diagnostic threshold selection and signed directed graph node state determination.The similarity reasoning and detection ability of the granular computing algorithm ensure a compact decision table and improve the decision result.The performance of the proposed enhanced system was evaluated on selected faults of the Chinese Fuqing 2 nuclear reactor.The proposed method offers improved diagnostic speed and efficient data processing.In addition,the result shows a considerable reduction in false positives,indicating that the method provides a reliable diagnostic system to support further intervention by operators.

The Dynamic-to-Static Conversion of Dynamic Fault Trees Using Stochastic Dependency Graphs and Stochastic Activity Networks

In this paper a new modeling framework for the dependability analysis of complex systems is presented and related to dynamic fault trees (DFTs). The methodology is based on a modular approach: two separate models are used to handle, the fault logic and the stochastic dependencies of the system. Thus, the fault schema, free of any dependency logic, can be easily evaluated, while the dependency schema allows the modeler to design new kind of non-trivial dependencies not easily caught by the traditional holistic methodologies. Moreover, the use of a dependency schema allows building a pure behavioral model that can be used for various kinds of dependability studies. In the paper is shown how to build and integrate the two modular models and convert them in a Stochastic Activity Network. Furthermore, based on the construction of the schema that embeds the stochastic dependencies, the procedure to convert DFTs into static fault trees is shown, allowing the resolution of DFTs in a very efficient way.

Sensor Configuration and Test for Fault Diagnoses of Subway Braking System Based on Signed Digraph Method

Fault diagnosis of various systems on rolling stock has drawn the attention of many researchers. However, obtaining an optimized sensor set of these systems, which is a prerequisite for fault diagnosis, remains a major challenge. Available literature suggests that the configuration of sensors in these systems is presently dependent on the knowledge and engineering experiences of designers, which may lead to insufficient or redundant development of various sensors. In this paper, the optimization of sensor sets is addressed by using the signed digraph （SDG） method. The method is modified for use in braking systems by the introduction of an effect-function method to replace the traditional quantitative methods. Two criteria are adopted to evaluate the capability of the sensor sets, namely, observability and resolution. The sensors configuration method of braking system is proposed. It consists of generating bipartite graphs from SDG models and then solving the set cover problem using a greedy algorithm. To demonstrate the improvement, the sensor configuration of the HP2008 braking system is investigated and fault diagnosis on a test bench is performed. The test results show that SDG algorithm can improve single-fault resolution from 6 faults to 10 faults, and with additional four brake cylinder pressure （BCP） sensors it can cover up to 67 double faults which were not considered by traditional fault diagnosis system. SDG methods are suitable for reducing redundant sensors and that the sensor sets thereby obtained are capable of detecting typical faults, such as the failure of a release valve. This study investigates the formal extension of the SDG method to the sensor configuration of braking system, as well as the adaptation supported by the effect-function method.

Fault Diagnosis Based on Graph Theory and Linear Discriminant Principle in Electric Power Network

In this paper, we adopt a novel topological approach to fault diagnosis. In our researches, global information will be introduced into electric power network, we are using mainly BFS of graph theory algorithms and linear discriminant principle to resolve fast and exact analysis of faulty components and faulty sections, and finally accomplish fault diagnosis. The results of BFS and linear discriminant are identical. The main technical contributions and innovations in this paper include, introducing global information into electric power network, developing a novel topological analysis to fault diagnosis. Graph theory algorithms can be used to model many different physical and abstract systems such as transportation and communication networks, models for business administration, political science, and psychology and so on. And the linear discriminant is a procedure used to classify an object into one of several a priori groupings dependent on the individual characteristics of the object. In the study of fault diagnosis in electric power network, graph theory algorithms and linear discriminant technology must also have a good prospect of application.

Multi-GAT:基于多度量衡构建图的故障诊断方法

基于图神经网络的故障诊断方法,通常需要根据度量衡确定样本之间的相似性,进而构建图的拓扑结构.然而,根据单一度量衡可能无法准确衡量数据样本之间的相似性,进而导致无法准确表征样本之间的关系.因此,选用不同的度量衡会极大地影响图神经网络的诊断性能.为了解决通过单一度量衡无法准确表征数据样本之间相关性的问题,本文提出了一种基于多度量衡构造图的故障诊断模型——Multi-GAT.通过结合3种度量衡的计算结果,从而判断数据样本之间相关性的强弱.本文改进了图注意力网络的评分函数,使其能够依据样本之间相关性的强弱更准确地确定数据样本之间的相似性.在本文基准数据集上的实验表明, Multi-GAT能够提升模型的诊断精度,且拥有较好的稳定性.

基于电子知识库的船舶故障诊断技术及应用

针对船舶电子设备故障的诊断问题,提出一种基于知识图谱的故障诊断系统。该系统不仅利用传统的故障维修日志库,还利用图书馆电子数据源提取和整合广泛的知识,建立起一个详尽的船舶设备故障知识图谱,为运维人员提供了一个全面的参考框架,并使用机器学习方法实现对电子设备故障的快速和准确诊断,显著提高了船舶故障处理的效率。

基于多层级时空图神经网络的风电机组在线异常检测

在风电场运营中,准确及时的故障检测是降低风电机组运行维护成本的关键。然而,现有检测方法未充分挖掘功能单元间的潜在时空关联,限制了检测准确性的提升。文中提出了一种基于多层级时空图神经网络的风电机组在线异常检测方法,以提高故障检测的准确性。该方法依据风电机组物理结构,将其功能单元划分为多个子图,从而构筑了一个多层级的时空图神经网络,通过图注意力机制和多头注意力机制全方位地分析风电机组各传感器节点与功能单元之间的关联强度。同时,针对数据采集与监控(SCADA)系统数据的时间关联,设计了动态图神经网络和时间注意力机制,使正常行为预测模型捕捉了SCADA系统数据的时间关联特性,实现了空间和时间特性的有效融合。最后,基于中国上海某风电场的实际数据验证了所提方法的显著有效性。

基于知识图谱与模糊贝叶斯推理的航空发动机故障诊断

针对航空发动机结构功能复杂,存在贝叶斯网络构建难、节点条件概率难以获得精确值的问题,提出基于知识图谱与模糊贝叶斯网络的故障推理诊断方法。首先,以历史故障数据为依据,构建航空发动机故障知识图谱;其次,提出“知识图谱-贝叶斯网络”的映射方法,用于快速构建贝叶斯网络;然后,引入模糊集合论,解决工程实际中概率参数的不确定性问题;最后,以航空发动机滑油系统故障进行实例验证,结果表明所提方法既能提高贝叶斯网络的构建效率,又能实现故障诊断的不确定性推理,可用于诊断策略优化和设备可靠性提升,具有较强的工程应用价值。

基于图半监督与多任务学习的配电网故障区段与类型统一辨识

为解决深度学习类配电网故障辨识方法在量测不足和标记率低时准确率不高的问题,提出了基于图半监督与多任务学习的故障区段与类型统一辨识方法。首先,设计了故障区段与类型统一辨识的图神经网络架构,在图嵌入层中融入网络拓扑和线路参数信息,以充分挖掘不同位置、类型的故障特征。其次,采用多任务注意力网络构建了故障区段定位和类型辨识两个任务,以提取故障的多重信息,实现不同任务间知识转移。再次,将图嵌入特征与无标签样本的编码压缩特征进行融合,得到新的多任务共享特征,以充分利用未标记数据,增强模型泛化能力。最后,通过算例测试表明,所提方法的故障辨识精度优于传统神经网络,且在实时量测少、标签率低及不同量测噪声条件下具有更好的鲁棒性。

基于图强化学习的配电网故障恢复决策

针对配电网拓扑变化时启发式等算法在配电网故障恢复决策中求解效果与适应性变差的问题,提出了一种基于图强化学习的故障恢复决策方法。首先,利用图数据表征故障恢复中的决策信息,包括配电网拓扑结构与电气特征信息。然后,在图强化学习模型中设置前置图神经网络接收图数据输入,应对故障恢复过程中配电网的拓扑变化。最后,由内嵌图神经网络的强化学习智能体输出最终故障恢复策略以提高决策速度。采用改进的PG&E 69节点配电网算例进行验证,结果表明所提算法求解速度达到毫秒级,较启发式和遗传算法在求解效率上提高了6%~7%,故障恢复策略的负荷恢复率也更高。

基于知识图谱的水电站设备故障根因分析方法

水电站设备故障成因复杂、关联性强,研究故障之间的成因关系及发生概率有助于快速确定故障原因和制定排查计划。根据专家经验与历史故障数据构建了水电站设备知识图谱,设计了基于知识图谱的智能故障诊断算法,利用Noisy Or模型实现一种近似推理算法,实现了根因的定量分析,并基于图推理分析相关现象和熵理论实现了排查建议的优化计算。该系统可给出全面、详细的建议和解释信息,允许用户自由交互,可以帮助用户快速开展排查故障。系统具有不依赖历史数据、准确性高、可解释性强、可动态更新等优点,为智慧水电站建设提供了先进平台。

域对抗图卷积注意力变工况故障研究

针对滚动轴承在变工况环境中网络特征提取能力不足的问题,提出了一种域对抗图卷积注意力迁移学习的故障诊断方法(DAGRESL)。首先,通过残差神经网络(residual network, Resnet)提取输入的轴承故障信息特征并通过Simam注意力模块增强Resnet的特征表达能力;其次,利用图生成层学习Resnet的特征数据并挖掘样本结构特征之间的关系来构造实例图;然后,利用图卷积网络(graph convolutional network, GCN)对实例图进行建模;最后,利用域判别器和局部最大平均差异(local maximum mean discrepancy, LMMD)对齐子域和全局域之间的分布并通过标签分类网络完成故障分类。通过在SQI-MFS轴承数据集的实验结果证明了所提出的DAGRESL模型能够精准地区分变工况轴承故障类型,有效解决了滚动轴承在变工况环境中网络特征提取能力不足的问题。

面向高速铁路道岔设备故障处置的知识图谱构建与应用

为了解决道岔设备故障处置过程中产生的大量知识难以存储应用,半结构化故障文本数据不能直接检索和推理等问题,提出一种高速铁路道岔设备故障处置知识图谱的构建方法。以少量人工标注故障文本数据为基础,采用基于强化学习的方法搭建BERT-BiLSTM-CRF*深度学习模型抽取实体;根据知识领域特点和数据结构设计关系匹配模板抽取各实体间的关系;针对实体冗余问题,采用文本相似度与结构相似度结合的方法进行故障实体融合;以我国各铁路局近3年的高速铁路道岔设备故障文本为研究对象,累计抽取实体807个且标注准确率在90%以上,构建实体关系2232条。基于以上知识图谱构建的高速铁路道岔设备故障处置知识图谱直观展示道岔设备故障关系,实现不同实体对象间的数据关联查询,挖掘隐含关系,辅助道岔维护人员进行故障处置决策,实现道岔设备预防性维护,延长设备寿命。

基于数据校核与图卷积神经网络的高容错配电网故障诊断方法

目前运用配电网中的多源故障遥信数据对配电网故障进行诊断的技术逐渐火热,但由于信息的误报、漏报使得诊断结果往往不尽如人意。针对配电网多源故障信息不健全的问题,本文提出了一种将数据校核操作与图卷积神经网络相结合的高容错性配电网故障诊断方法,旨在利用不健全故障信息对配电网进行故障诊断。首先,将多源故障遥信数据作归一化处理后再进行数据校核,从源头改善数据的不健全性;接着,根据配电网图模将多源故障数据转化为故障图数据;最后,将故障图数据送入图卷积神经网络进行学习训练,训练完毕的模型在部署后可实现对配电网的故障诊断。在Python 3.7平台进行实验,通过算例分析证明本文所提方法可有效提高配电网故障诊断的容错性。

AmazeMap:基于多层次影响图的微服务故障定位方法

微服务软件系统由于其具有大量复杂的服务依赖关系和组件化模块,一个服务发生故障往往造成与之相关的1个或多个服务发生故障,导致故障定位的难度不断提高.因此,如何有效地检测系统故障、快速而准确地定位故障根因问题,是当前微服务领域研究的重点.现有研究一般通过分析故障对服务、指标的作用关系来构建故障关系模型,但存在运维数据利用不充分、故障信息建模不全面、根因定位粒度粗等问题,因此提出了AmazeMap方法.该方法设计了多层次故障影响图建模方法以及基于多层次故障影响图的微服务故障定位方法.其中:多层次故障影响图建模方法通过挖掘系统运行时指标时序数据与链路数据,考虑不同层次间的相互关系,能够较全面地建模故障信息;基于多层次故障影响图的微服务故障定位方法通过缩小故障影响范围,从服务实例和指标两个方面发现根因,输出最有可能的故障根因节点和指标序列.基于开源基准微服务系统和AIOps挑战赛数据集,从有效性和效率两个方面设计了微服务软件故障定位实验,并与现有方法进行对比,实验结果验证了AmazeMap的有效性、准确性和效率.

变工况下动态卷积域对抗图神经网络故障诊断

针对基于无监督域自适应故障诊断方法忽略了域间数据结构信息、传统域对齐平均最大差异法全局泛化能力差等问题,本文提出一种基于无监督域自适应理论的动态卷积域对抗图神经网络故障诊断模型,分别通过对数据的类别标签、域标签和数据结构信息进行建模。通过分类器和域鉴别器分别建模类别标签和域标签,通过图神经网络将数据结构信息嵌入到实例图节点中,利用高斯Wasserstein距离来度量不同领域的实例图之间的差异。本文对比了不同工况下共14种迁移任务在各模型下故障识别的准确率。实验结果表明:基于动态卷积的域对抗图神经网络模型在变工况下的故障诊断效果均优于其他对比模型,且模型性能稳定。

卷积神经网络与知识图谱结合的轴承故障诊断

针对目前旋转机械故障诊断时,存在单一地利用振动数据、诊断结果模糊的问题,提出一种卷积神经网络(Convolutional Neural Network,CNN)与知识图谱结合的故障诊断方法。该方法以原始轴承数据和机理知识作为输入,然后进行实体抽取和数据标注,利用本文提出的端到端多尺度注意力机制神经网络模型进行故障诊断,最终构建知识图谱,实现故障信息的详细展示,进行辅助诊断。利用两份数据集进行实验验证,采用全新的数据处理方法,结果表明,所提出的算法在160种故障类型中加权F1值相比基准模型提高11.03%,并且利用传统故障诊断实验和其他算法对比充分证明本文提出的模型具有较强的稳定性和泛化性能。

基于产业链的电力设备智能故障诊断方法研究

电力设备故障是导致电网无法正常运行的重要原因。针对电力设备故障诊断机制因缺乏协同管理和知识共享导致的效率低下和技术更新受限问题,提出一种基于产业链的电力设备故障诊断方法。首先基于设备故障诊断历史数据,采用BERT-BiLSTM-ATT深度神经网络构建设备故障知识图谱;然后从上下游协同、虚实互补两个方面构建电力设备故障诊断跨时空信息联动模式。该方法解决了电力设备故障根源追溯、处理措施检索难题,有助于推动电力设备的智能化、可视化故障诊断。