Fault Diagnosis of an Intelligent Building Facility Using Bayesian Networks

There is great significance to diagnose the fault of an intelligent building facility for fault controlling, repairing, eliminating and preventing. As an example, this paper established a Bayesian networks model f or fault diagnosis of the refrigeration system of an intelligent building facility, gave the networks parameters, and analyzed the reasoning mechanism. Based on the model, some data was analyzed and diagnosed by adopting Bayesian networks reasoning platform GeNIe. The result shows that the diagnosis effect is more comprehensive and reasonable than the other method.

Active Probing Based Method for Fault Diagnosis Using Bayesian Network

Fault diagnosis on large-scale and complex networks is a challenging task, as it requires efficient and accurate inference from huge data volumes. Active probing is a cost-efficient tool for fault diagnosis. However almost all existing probing-based techniques face the following problems: 1) performing inaccurately in noisy networks; 2) generating additional traffic to the network; 3) high cost computation. To address these problems, we propose an efficient probe selection algorithm for fault diagnosis based on Bayesian network. Moreover, two approaches which could significantly reduce the computational complexity of the probe selection process are provided. Finally, we implement the new proposed algorithm and a former representative probing-based algorithm (BPEA algorithm) on different settings of networks. The results show that, the new algorithm performs much faster than BPEA does without sacrificing the diagnostic quality, especially in large, noisy and multiple-fault networks.

The Diagnosis of Reciprocating Machinery by Bayesian Networks

A Bayesian Network is a reasoning tool based on probability theory and has many advantages that other reasoning tools do not have. This paper discusses the basic theory of Bayesian networks and studies the problems in constructing Bayesian networks. The paper also constructs a Bayesian diagnosis network of a reciprocating compressor. The example helps us to draw a conclusion that Bayesian diagnosis networks can diagnose reciprocating machinery effectively.

Method of Satellite Fault Diagnosis Based on Bayesian Network

Based on Bayesian network, a new method to diagnose satellite faults is presented. The Bayesian network model of physical processing of satellite is developed; the main ideas of Bayesian network model of satellite fault diagnosis are introduced; the method to make the symptom variables values into discrete forms is proposed; one example is given to illustrate the application of Bayesian network model for satellite fault diagnosis.

Decision Support System for Maintenance Management Using Bayesian Networks

The maintenance process has undergone several major developments that have led to proactive considerations and the transformation fiom the traditional ＂fail and fix＂ practice into the ＂predict and prevent＂ proactive maintenance methodology. The anticipation action, which characterizes this proactive maintenance strategy is mainly based on monitoring, diagnosis, prognosis and decision-making modules. Oil monitoring is a key component of a successful condition monitoring program. It can be used as a proactive tool to identify the wear modes of rubbing pans and diagnoses the faults in machinery. But diagnosis relying on oil analysis technology must deal with uncertain knowledge and fuzzy input data. Besides other methods, Bayesian Networks have been extensively applied to fault diagnosis with the advantages of uncertainty inference; however, in the area of oil monitoring, it is a new field. This paper presents an integrated Bayesian network based decision support for maintenance of diesel engines.

Exploiting structural similarity of log files in fault diagnosis for Web service composition

With increasing deployment of Web services, the research on the dependability and availability of Web service composition becomes more and more active. Since unexpected faults of Web service composition may occur in different levels at runtime, log analysis as a typical data- driven approach for fault diagnosis is more applicable and scalable in various architectures. Considering the trend that more and more service logs are represented using XML or JSON format which has good flexibility and interoperability, fault classification problem of semi-structured logs is considered as a challenging issue in this area. However, most existing approaches focus on the log content analysis but ignore the structural information and lead to poor performance. To improve the accuracy of fault classification, we exploit structural similarity of log files and propose a similarity based Bayesian learning approach for semi-structured logs in this paper. Our solution estimates degrees of similarity among structural elements from heterogeneous log data, constructs combined Bayesian network （CBN）, uses similarity based learning algorithm to compute probabilities in CBN, and classifies test log data into most probable fault categories based on the generated CBN. Experimental results show that our approach outperforms other learning approaches on structural log datasets.

Transformer Fault Analysis Based on Bayesian Networks and Importance Measures

Complex environment stresses bring many uncertainties to transformer fault. The Bayesian network(BN) can represent prior knowledge in the form of probability which makes it an effective tool to deal with the uncertain problems. This paper established a BN model for the transformer fault diagnosis with practical operation dataset and expert knowledge. Then importance measures are introduced to indentify the key attributes which affect the results of transformer diagnosis most. Moreover, a strategy was proposed to reduce the number of attribute in transformer fault detection and the resource cost was saved. At last, a diagnosis case of practical transformer was implemented to verify the effectiveness of this method.

Fault detection and diagnosis for data incomplete industrial systems with new Bayesian network approach

For the fault detection and diagnosis problem in largescale industrial systems, there are two important issues： the missing data samples and the non-Gaussian property of the data. However, most of the existing data-driven methods cannot be able to handle both of them. Thus, a new Bayesian network classifier based fault detection and diagnosis method is proposed. At first, a non-imputation method is presented to handle the data incomplete samples, with the property of the proposed Bayesian network classifier, and the missing values can be marginalized in an elegant manner. Furthermore, the Gaussian mixture model is used to approximate the non-Gaussian data with a linear combination of finite Gaussian mixtures, so that the Bayesian network can process the non-Gaussian data in an effective way. Therefore, the entire fault detection and diagnosis method can deal with the high-dimensional incomplete process samples in an efficient and robust way. The diagnosis results are expressed in the manner of probability with the reliability scores. The proposed approach is evaluated with a benchmark problem called the Tennessee Eastman process. The simulation results show the effectiveness and robustness of the proposed method in fault detection and diagnosis for large-scale systems with missing measurements.

基于AESL-GA的BN球磨机滚动轴承故障诊断方法

针对基于知识的贝叶斯网络(BN)构建方法存在不完全和不精确的缺点,提出一种基于知识引导和数据挖掘的BN结构构建方法。针对单一信号故障诊断结果不精确的问题和故障信息中存在的不确定性问题,将电流信号与振动信号融合建立BN的特征节点,分别提取2种信号的故障特征参数,利用区分度指标法进行特征筛选,将其作为BN结构特征层的节点。将专家知识构建的初始BN结构结合自适应精英结构遗传算法(AESL-GA)进行结构优化,通过自适应限制进化过程中的搜索空间,减少自由参数的数量,提高其全局搜索能力,得到最优BN结构。通过MQY5585溢流型球磨机滚动轴承实测数据和Paderborn University轴承数据集对所提方法进行验证,结果证明了所提方法的有效性。

改进贝叶斯网络在变压器故障诊断中的应用

针对变压器故障诊断精度低的问题,文中提出一种基于改进黏菌优化算法(Improved Slime Mould Algorithm,ISMA)优化贝叶斯网络(Bayesian Network,BN)的变压器故障诊断方法。通过爬山算法对定向最大支撑树搜索得到贝叶斯网络初始结构即初始种群,在改进黏菌优化算法中引入反向学习策略,增加种群多样性。添加正弦-余弦算法(Sine Cosine Algorithm,SCA),更新解的位置以避免种群陷入局部最优。根据改良的无编码比值法选取变压器故障状态的特征,利用改进黏菌优化算法优化贝叶斯网络结构,提高基于贝叶斯网络的变压器故障诊断的准确率,并利用不同种类的测试函数验证了改进黏菌优化算法具有收敛速度快、收敛精度高的优良性能。仿真结果表明,ISMA-BN诊断模型的训练集和测试集准确率分别为98.2%和97.14%,具有一定的研究价值。

一种用于变压器故障诊断的贝叶斯网络优化方法

针对变压器故障诊断效率低的问题,文中将油中溶解气体分析与人工智能方法相结合,提出了一种改进蝗虫优化算法优化贝叶斯网络的变压器故障诊断方法。利用差分进化算法和与模拟退火算法对蝗虫算法进行改进,提高了算法的优化能力。将改进蝗虫算法应用于贝叶斯网络结构来学习构建变压器故障诊断模型,利用所提方法对变压器进行故障诊断。实验结果表明,该方法诊断正确率达到了92.7%,与其他算法所构建的诊断模型相比具有更高的故障诊断准确率。

少量样本下基于PCA-BNs的多故障诊断

针对一些工业设备因有标签故障样本数据少而导致诊断准确率低的问题,提出了一种PCA-BNs主成分分析和斯网络(principal component analysis-Bayesian networks, PCA-BNs)结合的多故障网络模型的建模方法。通过PCA对时序信号进行降维,得到相互独立的故障特征,提高提取故障关键信息的能力;利用融合单故障贝叶斯网络构建多故障贝叶斯网络结构的方法,解决BN建模过程耗时的问题;通过高斯分布与极大似然估计结合的方法确定网络参数,提高少量数据BN建模的精度,实现在少量样本下的故障诊断。试验结果表明,基于PCA-BNs的故障诊断方法在少量样本条件下,能实现高精度的故障诊断,并且有效缩减了算法运行时间。

基于贝叶斯单源域领域泛化算法的天然气管道故障智能诊断

基于深度学习算法的故障智能诊断模型已被广泛应用于天然气管道运输安全领域,然而管道通常处于准稳态,使得训练集中的故障样本量受限。为此,针对天然气管道故障诊断中因训练集故障样本量有限,导致难以准确诊断的问题,提出了一种基于贝叶斯单源域领域泛化(BSDG)算法,部署了一种攻击防御策略,通过在攻击阶段明确伪目标域增强路径,并在防御阶段引导模型参数的后验分布向伪域样本得分更高的方向调整,增强模型在面对不同域扰动时的适应性和鲁棒性。研究结果表明:(1)基于贝叶斯网络建立的非定向攻击模型确保伪域样本既保留了与源域的相关性,又引入了足够的域差异来模拟潜在的目标域,由此提升了多源域和单源域设置下的领域泛化诊断准确率;(2)测试结果显示,BSDG算法在多源域泛化任务及两项单源域泛化任务中,相较于性能最优的对比算法,其准确率分别提高了9.79%、5.09%和27.98%;(3)裕度差异损失通过在学习决策边界的过程中引入不确定性,令分类器可以灵活且有效应对频繁的分布变化,显著性测试结果表明BSDG算法在多数场景下显著优于先进对比算法;(4)贝叶斯神经网络通过在权重上引入不确定性,有效提升了BSDG算法的泛化稳定性。结论认为,BSDG算法通过使用基于贝叶斯推理的攻击防御策略,有效扩展了源域模型的决策边界,解决了实际场景数据匮乏导致的深度神经网络泛化能力差的问题,为样本受限情形下的天然气管道故障诊断模型设计提供了理论支撑。

一种贝叶斯网络的卫星姿态系统故障诊断方法

姿态控制系统是卫星系统中重要的组成部分,由于其高昂的造价,发生故障会引发恶劣的影响。随着航天科技的发展,卫星姿态控制系统也逐渐复杂,其可能发生故障的概率也随之增大。针对传统神经网络故障诊断结果缺少置信度、鲁棒性较差以及易发生过拟合的缺点,在对贝叶斯统计和深度学习理论研究的基础上,提出了一种基于贝叶斯线性层与贝叶斯卷积层的Bayesian Le Net结合的网络模型。通过对卫星姿态控制系统飞轮部件的故障数据分析和处理,进而采用该模型对故障仿真,并与贝叶斯全连接神经网络与传统Le Net进行对比,实验结果表明:在飞轮可能发生的三种故障前提下,上述网络模型准确率较高,过拟合现象较轻。验证了上述网络模型的有效性。

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。

一种基于贝叶斯网络的燃气轮机故障诊断方法

本文针对现役电站燃气轮机故障样本少,以往的故障诊断方法依赖于海量的带有故障标签的数据,难以在实际生产中取得预期的诊断效果的现象,提出了一种通过利用贝叶斯网络进行反事实推理来识别燃气轮机故障原因的方法。本文首先介绍了贝叶斯网络的基本原理,然后将故障模式和影响分析及故障树技术应用于贝叶斯网络的搭建,最后通过实际案例分析,验证了这一方法的有效性。本文的故障诊断方法可以根据燃气轮机在运行中出现的异常现象分析出可能的故障和相应的故障原因,帮助运行及检修人员及时发现和排除故障,并且弥补了基于数据驱动的故障诊断方法缺少专业知识支撑的缺陷,为燃气轮机的故障诊断提供了一种灵活、高效、可靠的新选择。

基于Bayesian改进算法的回转窑故障诊断模型研究

贝叶斯网络是数据挖掘最有效和可靠的方法之一,而贝叶斯网络结构学习是贝叶斯网络研究的关键环节。针对现有经典结构学习算法——爬山算法易陷入局部最优、效率低的问题,通过计算互信息建立最大支撑树,并将最大支撑树与简化爬山算法相结合,提出了一种新的贝叶斯网络结构学习改进算法。通过与经典的爬山法和K2算法进行比较,结果表明该改进算法不仅能够得到较高准确率的模型,而且能够提高模型建立的效率。最后基于该改进算法,结合冀东水泥集团的水泥回转窑现场运行数据,建立了水泥回转窑故障诊断模型,实现了精确快速的故障诊断。

基于贝叶斯网络信息融合的直流配电网故障诊断方法

新型直流配电系统故障期间暂态特征复杂多变,继电保护存在拒动和误动情况。为了避免继电保护的不正确动作对故障诊断产生影响,提出一种基于贝叶斯网络信息融合的直流配电网故障诊断方法。首先,对传统继电保护贝叶斯网络模型进行改进,同时考虑直流配电网故障限流策略,分别构建保护动作信息、断路器动作信息和限流策略信息3种贝叶斯网络模型,对故障区域内各元件的故障概率进行初步评估。其次,利用D-S证据理论将各元件对应的故障概率信息进行融合,完成故障元件的判别。然后,应用故障元件对应的贝叶斯网络模型识别误动或拒动的保护装置与断路器,实现对直流配电网的故障诊断。最后,通过算例验证了所提故障诊断方法的可靠性以及准确性。

基于知识图谱和贝叶斯推理的断纸故障诊断模型

纸机断纸是制约造纸企业提高产品质量和生产效益的关键原因。造纸生产过程具有高维、非线性和多变量耦合的特点,对断纸故障的预防和诊断提出了挑战。数据驱动的方法基于断纸故障历史数据建模,对断纸故障的预防起到了一定的效果。但该方法忽略了造纸工业中隐藏的机理和经验知识,无法提供对断纸原因的追根溯源。知识图谱作为一种揭示实体间关系的语义网络,可以实现断纸故障数据与知识的集成。基于本体技术的断纸知识图谱为断纸故障诊断提供了全面、可扩展的关联知识库。在此基础上,结合贝叶斯网络开发了断纸故障诊断模型,通过对某生活用纸企业断纸故障的案例分析,验证了该模型在断纸故障推理方面的有效性,断纸预测的正确率达到了85%。

Probabilistic SDG model description and fault inference for large-scale complex systems

Large-scale complex systems have the feature of including large amount of variables that have complex relationships, for which signed directed graph （SDG） model could serve as a significant tool by describing the causal relationships among variables. Although qualitative SDG expresses the causing effects between variables easily and clearly, it has many disadvantages or limitations. Probabilistic SDG proposed in the article describes deliver relationships among faults and variables by conditional probabilities, which contains more information and performs more applicability. The article introduces the concepts and con- struction approaches of probabilistic SDG, and presents the inference approaches aiming at fault diagnosis in this framework, i.e. Bayesian inference with graph elimination or junction tree algorithms to compute fault probabilities. Finally, the probabilistic SDG of a typical example of 65t/h boiler system is given.