A novel dynamic bayesian network‐based networked process monitoring approach for fault detection,propagation identification,and root cause diagnosis

A novel networked process monitoring, fault propagation identification, and root cause diagnosis approach is developed in this study. First, process network structure is determined from prior process knowledge and analysis. The network model parameters including the conditional probability density functions of different nodes are then estimated from process operating data to characterize the causal relationships among the monitored variables. Subsequently, the Bayesian inference‐based abnormality likelihood index is proposed to detect abnormal events in chemical processes. After the process fault is detected, the novel dynamic Bayesian probability and contribution indices are further developed from the transitional probabilities of monitored variables to identify the major faulty effect variables with significant upsets. With the dynamic Bayesian contribution index, the statistical inference rules are, thus, designed to search for the fault propagation pathways from the downstream backwards to the upstream process. In this way, the ending nodes in the identified propagation pathways can be captured as the root cause variables of process faults. Meanwhile, the identified fault propagation sequence provides an in‐depth understanding as to the interactive effects of faults throughout the processes. The proposed approach is demonstrated using the illustrative continuous stirred tank reactor system and the Tennessee Eastman chemical process with the fault propagation identification results compared against those of the transfer entropy‐based monitoring method. The results show that the novel networked process monitoring and diagnosis approach can accurately detect abnormal events, identify the fault propagation pathways, and diagnose the root cause variables. © 2013 American Institute of Chemical Engineers AIChE J, 59: 2348–2365, 2013     

Systematic rationalization approach for multivariate correlated alarms based on interpretive structural modeling and Likert scale

Alarmflood is one of themain problems in the alarmsystems of industrial process. Alarmroot-cause analysis and alarmprioritization are good for alarmflood reduction. This paper proposes a systematic rationalization method for multivariate correlated alarms to realize the root cause analysis and alarm prioritization. An information fusion based interpretive structural model is constructed according to the data-driven partial correlation coefficient calculation and process knowledge modification. This hierarchical multi-layer model is helpful in abnormality propagation path identification and root-cause analysis. Revised Likert scale method is adopted to determine the alarmpriority and reduce the blindness of alarmhandling. As a case study, the Tennessee Eastman process is utilized to showthe effectiveness and validity of proposed approach. Alarmsystem performance comparison shows that our rationalization methodology can reduce the alarmflood to some extent and improve the performance.     

过程工业报警系统可视化监控技术及应用

合理有效的可视化监控技术及工具有助于操作员及时理解报警信息并采取响应措施。针对现有可视化技术存在的缺点及不足, 如资源利用不充分、报警等级划分不明确、报警根源分析不彻底等, 构建了4种新型可视化工具:基于信息融合的解释结构模型(静态和动态)、层次高密度报警图、层次优先级色彩图、性能水平趋势图, 分别实现了过程递阶模型建立、报警根源分析、滋扰报警识别、报警优先级划分、报警系统性能常规评估等目的。以TE仿真模型为例, 阐明了上述可视化技术及工具的实用性和有效性, 不仅可以展示报警全貌原始信息, 还可快速识别报警根源、关键报警、滋扰报警以及报警系统性能水平, 实现了高效监控,从一定程度上解决了报警泛滥问题。     

基于数据驱动的化工过程参数报警阈值优化

为了提高化工过程报警系统的性能,需要对过程参数的报警阈值进行优化设置。针对传统阈值方法存在的问题,采用核密度估计方法、基于历史数据对过程报警状态进行估计,从最小化误报警和漏报警概率的角度建立了优化过程报警阈值的目标函数,并采用数值优化的方法进行求解。应用于TE过程的仿真结果表明,此方法能够有效地减少过程误报警的次数,并且对漏报警的次数进行抑制。     

Multiway discrete hidden Markov model‐based approach for dynamic batch process monitoring and fault classification

A new multiway discrete hidden Markov model (MDHMM)‐based approach is proposed in this article for fault detection and classification in complex batch or semibatch process with inherent dynamics and system uncertainty. The probabilistic inference along the state transitions in MDHMM can effectively extract the dynamic and stochastic patterns in the process operation. Furthermore, the used multiway analysis is able to transform the three‐dimensional (3‐D) data matrices into 2‐D measurement‐state data sets for hidden Markov model estimation and state path optimization. The proposed MDHMM approach is applied to fed‐batch penicillin fermentation process and compared to the conventional multiway principal component analysis (MPCA) and multiway dynamic principal component analysis (MDPCA) methods in three faulty scenarios. The monitoring results demonstrate that the MDHMM approach is superior to both the MPCA and MDPCA methods in terms of fault detection and false alarm rates. In addition, the supervised MDHMM approach is able to classify different types of process faults with high fidelity. © 2011 American Institute of Chemical Engineers AIChE J, 2012     

一种新的模糊聚类-分级算法及其在流程报警管理中的应用

1 INTRODUCTION Normally, operating management experience of in- dustrial process indicates that the probability one ig- nores alarm is 10-4 after handling one alarm signal and the probability one takes no direct action is 10-5 after hearing one alarm. Experiences also indicate that the probability one ignores alarm will increase to 10-3 from 10-4 if one alarm isn't handled within one minute[1]. Therefore, when the second alarm is appearing the probability which it can't be identified is 10…     

Real-time analysis of process plant alarms using a mini-computer

Many process plants are equipped with alarm systems. In most cases the operator is left to perform an overall diagnosis from a pattern of alarms. He is expected to perform this analysis in real time, while under considerable stress, even though the fault sequence which has caused the pattern of alarms may be one which he has never seen before. The objective of the work reported here is to investigate the use of a digital computer to assist the operator in diagnosing the basic fault from a pattern of alarms.     

面向系统层级的复杂工业过程全息故障诊断

复杂工业过程具有长流程、系统层级多、故障潜在分布空间范围较广的特点，是当前故障诊断领域的热门研究方向。首先，对主流故障诊断技术进行了分类和概述；其次，采用定量与定性相结合思路，提出了面向系统层级的复杂工业过程全息故障诊断框架，为复杂工业全流程的过程监测提供一整套技术和解决方案。相比于目前的故障诊断方法，该框架不仅包括故障检测和故障辨识，还包括故障根源诊断、故障传播路径识别、故障的定量诊断与评估，可有效解决复杂工业过程系统的综合故障诊断问题，实用性强，能够有效地减少或避免故障发生、保证产品的质量、提高企业的生产效率与生产安全；最后对故障诊断技术的发展趋势和亟待解决的问题进行了展望。     

A method of alarm system analysis for process plants

The design and improvement of alarm systems in process plants has been given considerable attention recently. A methodology is presented in this paper which can be used as an aid in the design of new alarm systems or in the improvement of existing alarm systems. The methodology is incorporated in computer software into which expert knowledge of a given process plant can be entered and used to select alarm systems.

Scope—Alarm systems play a very important role in process plants. They aid the operator in his primary tasks of detecting and interrupting progression of a failure, and diagnosing and providing corrective actions for fault conditions. There are, however, operator difficulties in handling alarms. A particular alarm system design can significantly affect the operator's success likelihood in receiving and processing alarms.

Several factors are important in the design or improvement of a given system. Human likelihood of success using a given alarm system under a given fault condition is one obvious factor. Economical aspects of selecting alarm systems, given probable types and frequencies of fault conditions, should also be considered in the design or improvement of alarm systems. A systematic approach is necessary to consider the effects of all these factors in evaluating a set of proposed alarm systems and in selecting the most appropriate alarm system. The purpose of this paper is to provide a method for determining the worth of a given alarm system by considering all factors which influence that worth.

In complex process plants, applications of the methodology presented in this paper can be very difficult without the aid of a computer. Therefore, a computer program is also described to carry out the methodology. Information regarding the process plant is entered into the program using the goal-tree concept. The goal tree contains the expert knowledge of the process which in turn is used in the design or modification of alarm systems.

Conclusions and Significance—A methodology has been presented to perform systematic evaluation of alarm systems. The methodology is based on the goal-tree concept through which process plants can be modeled.

Goal trees excellent tools for cause-consequence determination. The methodology makes use of decision trees which are constructed in parallel to goal trees to show all operator action(s) required to achieve each goal, and to show the consequences of operator's failure to achieve each goal. The decision trees can also model the progression of an initiating fault condition. The operator's likelihood of success of achieving each goal for a given alarm system design or alarm system modification can be estimated and used in the decision tree to estimate anticipated consequences of a given alarm design or modification. Anticipated consequence is defined as the probability of not achieving a goal times the consequence of not achieving that goal. Finally, alarm system designs or modifications with a low anticipated consequence and low implementation cost can be identified for further evaluation as potential alarm systems for the process.

The methodology has been modeled in a system of computer codes called UMPIRE-I. Process knowledge is entered into the computer through a goal tree coupled with human success likelihoods. The rest of the analysis is performed by UMPIRE-I. The code is user-friendly and can be used with minimal training. An example is provided in the paper to further clarify the methodology.

This method has been applied to several limited-scale engineering processes with rather significant success.     

基于复杂网络边负载分配理论的化工过程级联故障风险传播路径

依据复杂网络边负载分配相关理论,建立化工过程级联故障传播理论模型,用于解决化工过程中日益突出的级联故障传播问题。本文首先将化工生产系统抽象成网络模型,对网络中的节点进行重要性排序;其次对网络进行随机攻击并对重要性靠前的节点进行蓄意攻击,求解两种攻击方式下的最高风险传播路径;最后假设其发生边负载故障,根据风险传播路径故障概率对两种攻击方式下的最高风险传播路径进行评估,确定危险性较大的风险传播路径。经案例验证分析表明：该方法可有效确定生产过程中故障发生后的故障传播路径以及风险性较大的路径,为预防化工生产过程中故障传播提供一定的理论依据和决策支持。     

基于Hopfield网络的时滞分析故障诊断策略

振荡是化工过程中常见的对全流程运行性能有显著影响的故障类型,仅基于数据幅值域知识的故障诊断方法对这一类故障诊断性能不佳。时滞分析基于数据信号时域知识,根据波形相关性分析变量之间因果关系,通过得到的因果模型确定故障完整传播路径,可进一步识别出扰动发生的根本原因。将Hopfield网络与时滞分析相结合,解决了时滞分析当变量数众多时,从变量对的因果关系难以得到故障传播路径的问题,并同时讨论了时滞分析数据窗选取、对称时滞确立等的原则,提升了故障传播路径建立的准确度,建立了基于时滞分析的完备的故障诊断策略,最后通过TE模型验证了方法的优越性。     

过程参数滋扰报警的一类自适应管理策略

滋扰报警是过程工业报警系统的主要问题,然而,目前报警优化方法一般敏感度低、可靠性差,根据报警变量之间的时间间隔和报警持续时间确定滋扰报警的形式,提出了自适应报警死区和报警延时器的计算方法,利用时间序列ARMA模型预测报警死区来处理高频报警,并利用报警间隔时间更新报警延时器参数n来处理低频报警。通过工业实例数据验证表明,所提出的方法能够有效减少滋扰报警的数量、提高报警系统的性能。     

基于Logistic和ARMA模型的过程报警预测

提出了一种基于Logistic回归模型和ARMA模型相结合的过程报警事件预测方法,从历史数据中提取过程报警事件序列,并分解成报警状态及报警状态的持续时间,对应建立Logistic回归模型和ARMA模型分别对其进行预测,最终实现对过程报警事件的预测。通过数值实例分析和工业过程数据进行了验证,表明该方法能够准确地预测过程报警事件。     

Multiway independent component analysis mixture model and mutual information based fault detection and diagnosis approach of multiphase batch processes

Batch process monitoring is a challenging task, because conventional methods are not well suited to handle the inherent multiphase operation. In this study, a novel multiway independent component analysis (MICA) mixture model and mutual information based fault detection and diagnosis approach is proposed. The multiple operating phases in batch processes are characterized by non‐Gaussian independent component mixture models. Then, the posterior probability of the monitored sample is maximized to identify the operating phase that the sample belongs to, and, thus, the localized MICA model is developed for process fault detection. Moreover, the detected faulty samples are projected onto the residual subspace, and the mutual information based non‐Gaussian contribution index is established to evaluate the statistical dependency between the projection and the measurement along each process variable. Such contribution index is used to diagnose the major faulty variables responsible for process abnormalities. The effectiveness of the proposed approach is demonstrated using the fed‐batch penicillin fermentation process, and the results are compared to those of the multiway principal component analysis mixture model and regular MICA method. The case study demonstrates that the proposed approach is able to detect the abnormal events over different phases as well as diagnose the faulty variables with high accuracy. © 2013 American Institute of Chemical Engineers AIChE J, 59: 2761–2779, 2013     

基于仿射传播聚类子集主元分析的间歇过程监测方法

针对间歇过程固有的多阶段特性,也为了克服传统阶段划分方法严格按照物理时刻顺序将采样点硬性分割而不能使其寻找数据特征最为相近的聚类中心的严重缺陷,提出基于仿射传播聚类(AP)的子集多向主元分析(subset-MPCA)监测新方法:采用全新的乱序聚类思想,将时间片矩阵打乱用AP进行无约束乱序聚类,使样本突破时间顺序的约束自由找寻与其特征最为相近的聚类中心,获得聚类子集,建立精确的子集MPCA监控模型。在线监控时,引入信息度传递实现实时采样点的阶段归属判断,解决阶段不等长批次的最佳模型选择问题。对青霉素仿真数据的实验表明,该方法较传统方法可有效降低故障的漏报和误报,有着更加可靠的监控性能。     

Quantification of alarm chatter based on run length distributions

In the process industry, alarms are configured on the control system to provide indication of abnormal events to the control room operators. In the presence of improper design of alarm generating algorithm or lack of appropriate tuning, alarms are announced more frequently than what is typically sufficient to alert the operator, a condition commonly known as ‘alarm chatter’. Chattering alarms are the most common form of nuisance alarms. The concept of run length is introduced in the alarm management context to study alarm chatter and an index is proposed to quantify the degree of alarm chatter based on run length distributions obtained exclusively from readily available historical alarm data. Chatter index hence plays a crucial role in routine assessment of industrial alarm systems. Prominent features of the proposed chatter index and its variant are demonstrated using industrial data.     

Petri-net models for comprehensive hazard analysis of MOCVD processes

Reducing contamination level is of primary importance for the safety and efficiency of a MOCVD process. Off-line fault identification is one of the basic tasks that must be performed in hazard analysis to identify potential operational problems. For illustration convenience, the scope of present study is limited to the purge-gas purifier of the process. A systematic step-by-step procedure is proposed in this paper to construct Petri nets for modeling the purification system. Efficient hazard assessment studies have been performed by simulating the fault propagation behaviors on the basis of the system model. A comprehensive list of possible fault origins has been thoroughly examined to demonstrate the effectiveness of the proposed approach.     

基于多级流建模的间歇过程故障定位方法

针对间歇性供水系统故障定位问题的复杂性,提出了一种扩展多级流模型( MFM)的建模、故障警报分析和故障定位新方法.利用多级流模型和Petri网复合的方法,扩展了多级流模型以适应间歇过程的连续变化和离散变化,实现了分布式复杂系统的故障根源搜索和定位.     

炼化装置故障链式效应定量安全预警方法

炼化装置故障及其故障链式效应对油气生产和人民生命安全所造成的危害严重。从故障链角度进行事故风险研究,提出炼化装置故障链式效应定量安全预警方法。首先分析炼化装置故障链式关系结构,基于目标树成功树-动态主逻辑图（GTST-DMLD）建立其故障链式效应关系模型,揭示炼化装置故障链式效应行为规律和关联本质,从而评价装置异常工况下的安全状态。进一步以马尔可夫过程为理论基础,建立故障链式效应预测模型,预测故障传播的后果和方向,并计算各后果的发生概率,为现场操作人员进行主动维修或应急处置提供依据。案例分析中通过对某化工厂常压塔装置、减压炉装置为研究对象进行应用与验证,结果表明该方法可以准确地对系统故障发生后的状态进行评价和预测,方法有效、可行,便于操作人员在处置已有故障的同时,注意预防其他异常工况的发生,降低油气生产加工过程中的整体风险。     

基于约翰逊转换的鲁棒化工过程监控方法

化工厂中一个小故障可能导致大事故,从而造成生命财产损失和环境破坏。为了防止小故障演变成大事故,化学工业需要有效的过程监控来及时检测故障和诊断故障原因。传统化工过程监控方法主元分析法(Principal Component Analysis, PCA)假设数据服从高斯分布,实践中有时并不满足该条件。此外,其使用方差、协方差捕捉数据非线性变化时,鲁棒性较差。本工作提出一种改进的主元分析法—基于约翰逊转换的鲁棒过程监控方法。首先引入约翰逊正态转换(Johnson Transformation)使过程数据服从高斯分布;其次使用鲁棒性强的斯皮尔曼相关系数(Spearman Correlation Coefficient)矩阵代替传统主元分析法的协方差矩阵提取特征向量,构造特征空间;最后将过程数据投影到特征空间,使用T2和SPE统计量实施过程监控。将此方法应用于TE过程故障案例,并与PCA和核主元分析法(Kernel Principal Component Analysis, KPCA)对比,验证了此方法的有效性。