基于FMECA知识的故障诊断贝叶斯网络建模研究

为了构建具有较完备知识的贝叶斯网络诊断模型,提出了一种基于FMECA知识的故障诊断贝叶斯网络建模方法,该方法根据产品FMECA分析所得故障模式、故障原因、故障影响之间的因果关系构建贝叶斯网络拓扑结构,通过历史数据确定网络各节点的先验概率和条件概率分布,进而利用建立的贝叶斯网络进行故障诊断推理决策,最后通过某型飞机平视显示器的故障诊断贝叶斯网络建模及诊断实例,验证了方法的正确性及可行性。     

贝叶斯网络数据细化的柴油发电机故障诊断

针对传统故障诊断方法在不确定问题诊断方面的不足,提出了基于贝叶斯网络的数据细化的柴油发电机故障诊断法。对柴油发电机转子的某些特定故障,结合专家知识确定转子特定状态下故障与振动频率、幅值及相关描述的依存关系,将获取的观测数据细化处理,利用结构学习,构建了基于贝叶斯网络的柴油发电机故障诊断模型,通过参数学习确定各节点的条件概率。实验结果表明,在已知信息具有模糊性和不完备性时,基于贝叶斯网络数据细化的故障诊断技术可明显提高诊断正确率。     

基于故障分析模型的贝叶斯网络构建及应用

为快速、准确地构建具有较完备知识的贝叶斯网络诊断模型,提出了基于故障模式、影响(及危害性)分析知识模型的贝叶斯网络自动构建方法.在该方法中,借助影响(及危害性)知识模型中的产品结构层次关系,将产品各层零部件的故障模式加以关联,形成贝叶斯网络结构;并以影响(及危害性)知识模型中的概率知识为依据,确定贝叶斯网络中节点的先验概率和条件概率.以列车自动门为应用对象,实现贝叶斯网络诊断模型的自动构建,并开发了相应的诊断系统,解决了列车自动门的诊断系统开发、应用跟不上维护的难题.最后,通过列车自动门的故障诊断实例,证明了所构建的贝叶斯网络的有效性.     

Exploiting Bayesian networks for fault isolation: A diagnostic case study of diesel fuel injection system

Fault isolation is known to be a challenging problem in machinery troubleshooting. It is not only because the isolation of multiple faults contains considerable number of uncertainties due to the strong correlation and coupling between different faults, but often massive prior knowledge is needed as well. This paper presents a Bayesian network-based approach for fault isolation in the presence of the uncertainties. Various faults and symptoms are parameterized using state variables, or the so-called nodes in Bayesian networks (BNs). Probabilistically causality between a fault and a symptom and its quantization are described respectively by a directed edge and conditional probability. To reduce the qualitative and quantitative knowledge needed, particular considerations are given to the simplification of Bayesian networks structures and conditional probability expressions using rough sets and noisy-OR/MAX model, respectively. By adopting the simplified approach, symptoms under multiple-fault are decoupled into the ones under every single fault, while the quantity of the conditional probabilities is simplified into the linear form of the faults quantity. Prior knowledge needed in Bayesian network-based diagnostic model is reduced significantly, which decreases the complexity in establishing and applying this diagnosis model. The computational efficiency is improved accordingly in the simplified BN model, after eliminating the redundant symptoms. The fault isolation methodology is illustrated through an example of diesel engine fuel injection system to verify the developed model.     

MapReduce Based Parallel Bayesian Network for Manufacturing Quality Control

Increasing complexity of industrial products and manufacturing processes have challenged conventional statistics based quality management approaches in the circumstances of dynamic production. A Bayesian network and big data analytics integrated approach for manufacturing process quality analysis and control is proposed. Based on Hadoop distributed architecture and MapReduce parallel computing model, big volume and variety quality related data generated during the manufacturing process could be dealt with. Artificial intelligent algorithms, including Bayesian network learning, classification and reasoning, are embedded into the Reduce process. Relying on the ability of the Bayesian network in dealing with dynamic and uncertain problem and the parallel computing power of MapReduce, Bayesian network of impact factors on quality are built based on prior probability distribution and modified with posterior probability distribution. A case study on hull segment manufacturing precision management for ship and offshore platform building shows that computing speed accelerates almost directly proportionally to the increase of computing nodes. It is also proved that the proposed model is feasible for locating and reasoning of root causes, forecasting of manufacturing outcome, and intelligent decision for precision problem solving. The integration of bigdata analytics and BN method offers a whole new perspective in manufacturing quality control.     

基于贝叶斯网络的多状态系统可靠性建模与评估

利用贝叶斯网络(Bayesian network, BN)的不确定性推理和图形化表达的优势,提出一种基于BN的多状态系统可靠性建模与评估的新方法,确定BN的结点及系统各元件的多个状态,并给出各状态的概率,进而用概率分布表(Conditional probability distributing, CPD)描述元件各状态之间的关系来表达关联结点的状态,建立多状态系统BN模型.该模型表达直观,能够清晰地表示系统和元件的多种状态以及状态概率,并能够根据元件多种状态概率直接计算系统可靠度,对多状态系统可靠性进行定性分析和定量评估.实例分析表明了应用BN方法进行多状态系统可靠性评估的有效性.     

Fault detection in roller bearing operating at low speed and varying loads using Bayesian robust new hidden Markov model

This paper uses Bayesian robust new hidden Markov modeling (BRNHMM) for bearing fault detection and diagnosis based on its acoustic emission signal. A variational Bayesian approach is used that simultaneously approximates the distribution over the hidden states and parameters with simpler distribution hence using Bayesian inference for the estimation of the posterior HMM hyperparameters. This allows for online detection as small data sets can be used. Also, the Kullback-Leibler (KL) divergence is effectively used to access the divergence of the probability function of the BRNHMM, to find its lower bound approximation and by applying a linear transform to the maximum output probability parameter generation (MOPPG). The training set result obtained from BRNHMM is then compared to the result from artificial neural network (ANN) fault detection for same complex system of low speed and varying load conditions which are difficult from a diagnostic perspective, as found in rolling mills.     

基于贝叶斯网络的磨煤机过程异常工况诊断 模型实时更新方法

磨煤机作为火电厂制粉系统的核心设备,依靠新磨煤机投入使用后仅有的少量异常工况数据,建立其异常工况诊断模型,对整体系统安全运行有着重要的意义。本文首先针对磨煤机三个典型异常工况建立异常工况诊断模型,并提出新的基于节点辨识的贝叶斯网络模型实时更新方法。将已有磨煤机成熟的异常工况诊断模型作为源域模型,利用目标域磨煤机仅有的少量新数据信息,搜索源域模型与新数据信息不匹配的节点。在保留源域模型有用信息的前提下,通过局部更新,依据新的数据信息完成目标域模型的更新补足。为了验证方法的有效性,将所提方法应用于磨煤机异常工况诊断过程,实验结果表明,更新得到的模型具有良好的性能,平均诊断正确率超过98%。     

基于贝叶斯网的制造工艺质量建模方法

针对多品种小批量制造模式下,工艺质量建模面临的模型维度高、数据稀疏的问题,提出了基于贝叶斯网的工艺质量建模方法.该方法以工艺机理知识为基础构建贝叶斯网结构,在构建时采用删除法保证结构的完备性与简洁性.设计实验获得均衡分布的实验数据,并通过实验数据的学习获得条件概率表.在应用中,模型利用生产线的数据更新条件概率表,来体现生产过程中不确定性因素的影响.以印刷线路板微小孔钻孔工艺为例进行了建模方法的应用与对比,结果验证了该方法对多品种小批量制造工艺的质量建模具有适用性,并且能够获得更高的模型精度.     

基于贝叶斯网络的复杂系统故障诊断

系统结构和部件关系复杂、试验费用昂贵是小样本下基于不确定性信息的决策问题。针对其特点，建立了基于贝叶斯网络的复杂系统故障诊断模型，并提出采用Leaky Noisy-OR模型来降低数据需求量和计算复杂度。经研究表明，这种方法能综合利用各种来源信息，具有知识表达明确、样本需求量小、故障诊断准确度高等特点，可为复杂系统故障诊断提供决策支持。     

Method of Judging Potential Failure States of Electronic Instruments

Potential failures of electronic instrument are very common in the engineering practice.In this paper,potential failure state model is analyzed based on dynamic characteristics of electronic instrument at work and a comprehensive method of judging multi-state reliability is put forward.Then,a multi-state electronic instrument reliability analysis model is built based on Bayesian Networks(BN).Considering the failure-potential failure-normal work states,the model is built to estimate reliability of the system and the conditional probability of the elements.Finally,the model is proved corrective and effective by examples.     

A hybrid approach of rough set theory and genetic algorithm for fault diagnosis

This paper proposes an integrated intelligent system that builds a fault diagnosis inference model based on the advantage of rough set theory and genetic algorithms (GAs). Rough set theory is a novel data mining approach that deals with vagueness and can be used to find hidden patterns in data sets. Based on this approach, minimal condition variable subsets and induction rules are established and illustrated using an application for motherboard electromagnetic interference (EMI) test fault diagnosis. This integrated system successfully integrated the rough set theory for handling uncertainty with a robust search engine, GA. The result shows that the proposed method can reduce the number of conditional attributes used in motherboard EMI fault diagnosis and maintain acceptable classification accuracy. The average diagnostic accuracy of 80% shows that this hybrid model is a promising approach to EMI diagnostic support systems .     

基于信息熵属性约简的航空发动机故障诊断

针对不协调信息条件下的航空发动机故障诊断问题,研究了基于信息熵属性约简的故障诊断方法。首先定义了故障诊断信息系统来描述不协调故障样本数据,针对基本粗糙集模型分类能力不足的问题,引入变精度粗糙集模型处理不协调诊断信息系统;然后针对现有条件熵不能区分不确定性规则的缺陷,提出了变精度条件熵作为属性重要度的度量标准,设计了启发式属性约简算法,提取故障诊断规则。将该方法用于航空发动机故障诊断,验证了该方法可有效处理不协调信息,显著提高了航空发动机故障诊断的准确率。     

应用扩展贝叶斯进化算法求解混流装配调度问题

为求解复杂混流装配线调度的问题,提出一种基于贝叶斯进化算法的优化方法,给出了基于同机工序和工艺相关工序关联分析的贝叶斯进化算法求解框架.在贝叶斯进化算法基本建模方法的基础上,引入有效解模式表征指标,以增强对有效解变量取值关系的表征和进化能力.同时,引入模式扩展关联机制,将变量层次的关联关系拓展到变量取值层次,进一步提高算法的进化搜索效率.最后,给出了算法实现过程中的小概率解模式保留策略,以避免优化信息的缺失.通过对混流装配调度算例及标准benchmark算例的仿真验证表明,在较大规模的问题求解中,本文算法与遗传算法和一般贝叶斯进化算法相比,优化效率得到了明显的提高.     

Sensor fault diagnosis with a probabilistic decision process

In this paper a probabilistic approach to sensor fault diagnosis is presented. The proposed method is applicable to systems whose dynamic can be approximated with only few active states, especially in process control where we usually have a relatively slow dynamics. Unlike most existing probabilistic approaches to fault diagnosis, which are based on Bayesian Belief Networks, in this approach the probabilistic model is directly extracted from a parity equation. The relevant parity equation can be found using a model of the system or through principal component analysis of data measured from the system. In addition, a sensor detectability index is introduced that specifies the level of detectability of sensor faults in a set of analytically redundant sensors. This index depends only on the internal relationships of the variables of the system and noise level. The method is tested on a model of the Tennessee Eastman process and the result shows a fast and reliable prediction of fault in the detectable sensors.     

基于优化分簇贝叶斯网的转子振动故障诊断

针对柴油发动机的充电发电机结构及振动的复杂性导致其转子振动故障具有多层次性、耦合性和随机性,以及故障信息不完整性等特点,提出了一种基于振动频谱分析和贝叶斯网络的转子振动故障诊断方法。该方法将故障源和故障现象根据专家经验数值化表示并离散化,运用改进的优化分簇算法,构建特定振动故障类型的贝叶斯诊断网络,利用贝叶斯网络推理算法诊断出故障概率分布,并利用具体的故障证据、设定值对该方法进行验证。仿真及实验结果表明,该方法能在故障信息不完整情况下,依据不完整证据信息更新各网络节点的概率状态,实现对不确定信息的推理和估计,得到较好的诊断结果,提高了转子振动故障的诊断准确度。     

CS-PSO算法在贝叶斯网络结构学习中的应用

针对传统的贝叶斯网络(Bayesian network, BN)结构学习算法运行效率低、算法易早熟、学习效果不理想等缺点,选取布谷鸟(Cuckoo search, CS)和粒子群(Particle swarm optimization, PSO)智能算法,结合BN结构特点,提出了一种CS-PSO的BN结构学习算法。首先,对CS算法从以下三个方面进行改进:利用最大支撑树来指导CS算法的初始化方向,利用解的适应度来调节解的寻优及舍弃过程,利用PSO算法来进行CS算法的位置更新。其次根据BN的结构特征,将CS-PSO算法应用于BN的结构学习。最后采用chest clinic、 credit和car diagnosis三种经典网络作为仿真模型,进行贪婪算法、 K2算法、 CS算法和CS-PSO算法的建模和仿真比较。结果表明, CS-PSO算法在BN的结构学习中,收敛速度快、收敛精度高且稳定性好,可以更快、更优地得到精确的贝叶斯网络结构模型。     

自适应Laplace统计模型下的量子降噪算法

受量子理论启发,提出自适应Laplace统计模型下的量子降噪算法,并将其成功应用于机械故障诊断。建立起带自适应参数的Laplace概率密度函数模型,提高统计模型的适用性;结合贝叶斯估计理论,推导出小波系数收缩函数;利用父-子代小波系数的相关性,提出量子叠加态信号与噪声出现概率,并推导出基于量子叠加态参数估计的方差公式,实现小波系数的非线性收缩。通过仿真试验和轴承故障诊断实例分别对此算法进行分析和验证,结果表明,该算法均具有良好的降噪效果,可以有效地对机械振动信号进行降噪。     

A probabilistic approach to variation propagation control for straight build in mechanical assembly

Random component variations have a significant influence on the quality of assembled products, and variation propagation control is one of the procedures used to improve product quality in the manufacturing assembly process. This paper considers straight-build assemblies composed of axi-symmetric components and proposes a novel variation propagation control method in which individual components are re-orientated on a stage-by-stage basis to optimise the table-axis error for the final component in the assembly. Mathematical modelling methods are developed to predict the statistical variations present in the complete assembly. Three straight-build assembly strategies are considered: (a) direct build, (b) best build and (c) worst build assembly. Analytical expressions are determined for the probability density function of the table-axis error for the final component in the assembly, and comparisons are made against Monte Carlo simulations for the purposes of validation. The results show that the proposed variation propagation control method offers good accuracy and efficiency, compared to the Monte Carlo simulations. The probability density functions are used to calculate the probability that the eccentricity will exceed a particular value and are useful for industrial applications and academic research in tolerance assignment and assembly process design. The proposed method is used to analyse the influence of different component tolerances on the build quality of an example originating in aero-engine sub-assembly.     

隐性函数S-压缩贝叶斯故障识别方法

支持矢量机(Support vector machines,SVM)已经在小样本故障识别中得到了广泛应用。与之对比,由于先验知识获取和非线性识别较难实现,基于贝叶斯概率的故障识别方法应用较少。针对上述问题,提出隐性函数S-压缩贝叶斯故障识别方法(LS-BFR)。LS-BFR以高斯随机过程和贝叶斯概率为基础,以高斯回归作为隐性函数,通过S-压缩对回归输出进行变换使其具有概率意义,利用贝叶斯概率实现故障识别。为提高LS-BFR非线性故障识别效果,引入核函数方法在高维空间进行隐性高斯过程回归,并给出基于贝叶斯参数估计的核函数参数选择方法。在转子试验台上模拟了不对中和不平衡故障,并利用LS-BFR进行故障识别。试验结果表明,基于隐性函数和S-压缩的LS-BFR方法能有效地进行小样本故障识别,且识别效果优于SVM。