Fault Detection and Diagnosis in a Food Pasteurization Process with Hidden Markov Models

Hidden Markov Models (HMM) are used to detect abnormal operation of dynamic processes and diagnose sensor and actuator faults. The method is illustrated by monitoring the operation of a pasteurization plant and diagnosing causes of abnormal operation. Process data collected under the influence of faults of different magnitude and duration in sensors and actuators are used to illustrate the use of HMM in the detection and diagnosis of process faults. Case studies with experimental data from a high‐temperature‐short‐time pasteurization system showed that HMM can diagnose the faults with certain characteristics such as fault duration and magnitude.     

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     

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 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     

Concurrent monitoring of operating condition deviations and process dynamics anomalies with slow feature analysis

Latent variable (LV) models have been widely used in multivariate statistical process monitoring. However, whatever deviation from nominal operating condition is detected, an alarm is triggered based on classical monitoring methods. Therefore, they fail to distinguish real faults incurring dynamics anomalies from normal deviations in operating conditions. A new process monitoring strategy based on slow feature analysis (SFA) is proposed for the concurrent monitoring of operating point deviations and process dynamics anomalies. Slow features as LVs are developed to describe slowly varying dynamics, yielding improved physical interpretation. In addition to classical statistics for monitoring deviation from design conditions, two novel indices are proposed to detect anomalies in process dynamics through the slowness of LVs. The proposed approach can distinguish whether the changes in operating conditions are normal or real faults occur. Two case studies show the validity of the SFA‐based process monitoring approach. © 2015 American Institute of Chemical Engineers AIChE J, 61: 3666–3682, 2015     

基于贝叶斯推理的PKPCAM的非线性多模态过程故障检测与诊断方法

针对一类非线性多模态的化工过程,提出一种基于概率核主元的混合模型(PKPCAM),并利用贝叶斯推理策略进行过程监控与故障诊断.在提出的模型中, 每个操作模态由一个局部化的概率核主元分量描述,从而构建的一系列分量对应了不同的操作模态.首先,将过程数据从原始的度量空间投影到高维特征空间;其次,在该特征空间建立概率主元混合模型,从概率角度刻画数据集的多个局部分量特征;最后,在提取的核主元分量内获得测试样本的后验概率,结合模态内的马氏距离贡献度,提出基于贝叶斯推理的全局概率指标进行故障检测,同时利用模态内变量的相对贡献度,基于全局贡献度指标进行故障诊断.利用TEP仿真平台,与基于k均值聚类的次级主元分析和核主元分析的方法进行了对比分析,验证了提出的贝叶斯推理的PKPCAM方法对非线性多模态过程进行故障检测与诊断的可行性和有效性.     

Multiway continuous hidden Markov model‐based approach for fault detection and diagnosis

A fault detection and classification scheme that uses probabilistic inference based on multiway continuous hidden Markov models (MCHMM) which is capable of capturing complex system dynamics and uncertainty is proposed. A set of observations from normal and faulty runs of the system was collected and used to generate the training dataset. The training data is assumed to follow a finite Gaussian mixture model. The number of mixture components and associated parameters for the optimal Gaussian mixture fit of the observed data was computed subsequently by clustering using the Figueiredo–Jain algorithm for unsupervised learning. The segmental k‐means algorithm was used to compute the HMM parameters. The applicability of the proposed scheme is investigated for the case of an inverted pendulum system and a fluidized catalytic cracker. The monitoring results for the above cases with the proposed scheme was found to be superior to the multiway discrete hidden Markov model (MDHMM) based scheme in terms of the accuracy of fault detection, especially in case of noisy observations. © 2014 American Institute of Chemical Engineers AIChE J, 60: 2035–2047, 2014     

Statistical root cause analysis of novel faults based on digraph models

This paper investigates the challenging problem of diagnosing novel faults whose fault mechanisms and relevant historical data are not available. Most existing fault diagnosis systems are incapable to explain root causes for unanticipated, novel faults, because they rely on either models or historical data of known faulty conditions. To address this issue we propose a new framework for novel fault diagnosis, which integrates causal reasoning on signed digraph models with multivariate statistical process monitoring. The prerequisites for our approach include historical data of normal process behavior and qualitative cause–effect relationships that can be derived from process flow diagrams. In this new approach, a set of candidate root nodes is identified first via qualitative reasoning on signed digraph; then quantitative local consistency tests are implemented for each candidate based on multivariate statistical process monitoring techniques; finally, using the resulting multiple local residuals, diagnosis is performed based on the exoneration principle. The cause–effect relationships in the digraph enable automatic variable selection and the local residual interpretations for statistical monitoring. The effectiveness of this new approach is demonstrated using numerical examples based on the Tennessee Eastman process data.     

Nonparametric manifold learning approach for improved process monitoring

A novel nonparametric method based on manifold learning is proposed for industrial process monitoring. In conventional algorithms, to preserve the global and local structure information of data, heat kernels containing two auxiliary parameters are introduced to define the global and local weight matrices, respectively. However, it is difficult to identify and choose these two parameters empirically. The inadequate selection of parameters can lead to one-sided and inappropriate global and local feature extractions, resulting in an inadequate fault detection performance. To resolve the above problems, a nonparametric strategy is used in this study to generate two nonparametric weight matrices to replace the heat kernel-based weight matrices. Consequently, the proposed method requires no auxiliary parameters in defining the weight matrices, making it more practical. Moreover, it automatically determines a good trade-off between global and local feature extractions. A process monitoring model based on the proposed method was developed. The feasibility and effectiveness of the new nonparametric method are evaluated using a synthetic example and the Tennessee Eastman chemical process.     

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。     

Orthogonal nonnegative matrix factorization based local hidden Markov model for multimode process monitoring

Traditional data driven fault detection methods assume that the process operates in a single mode so that they cannot perform well in processes with multiple operating modes. To monitor multimode processes effectively, this paper proposes a novel process monitoring scheme based on orthogonal nonnegative matrix factorization (ONMF) and hidden Markov model (HMM). The new clustering technique ONMF is employed to separate data fromdifferent processmodes. ThemultipleHMMs for various operating modes lead to highermodeling accuracy. The proposed approach does not presume the distribution of data in each mode because the process uncertainty and dynamics can bewell interpreted through the hidden Markov estimation. The HMM-based monitoring indication named negative log likelihood probability is utilized for fault detection. In order to assess the proposed monitoring strategy, a numerical example and the Tennessee Eastman process are used. The results demonstrate that this method provides efficient fault detection performance.     

Design and assessment of delay timer alarm systems for nonlinear chemical processes

In process and manufacturing industries, alarm systems play a critical role in ensuring safe and efficient operations. The objective of a standard industrial alarm system is to detect undesirable deviations in process variables as soon as they occur. Fault detection and diagnosis systems often need to be alerted by an industrial alarm system; however, poorly designed alarms often lead to alarm flooding and other undesirable events. In this article, we consider the problem of industrial alarm design for processes represented by stochastic nonlinear time‐series models. The alarm design for such complex processes faces three important challenges: (1) industrial processes exhibit highly nonlinear behavior; (2) state variables are not precisely known (modeling error); and (3) process signals are not necessarily Gaussian, stationary or uncorrelated. In this article, a procedure for designing a delay timer alarm configuration is proposed for the process states. The proposed design is based on minimization of the rate of false and missed alarm rates—two common performance measures for alarm systems. To ensure the alarm design is robust to any non‐stationary process behavior, an expected‐case and a worst‐case alarm designs are proposed. Finally, the efficacy of the proposed alarm design is illustrated on a non‐stationary chemical reactor problem. © 2017 American Institute of Chemical Engineers AIChE J, 63: 77–90, 2018     

A robust neural network model for fault detection in the presence of mislabelled data

Several data-driven methodologies for process monitoring and detection of faults or abnormalities have been developed for the safety of processing systems. The effectiveness of data-based models, however, is impacted by the volume and quality of training data. This work presents a robust neural network model for addressing the mislabelled and low-quality data in detecting faults and process abnormalities. The approach is based on harnessing data quality features along with supervisory labels in the network training. The data quality has been computed using the Mahalanobis distances and trusted centres of each class of data such as normal and faulty data. The method has been examined for detecting abnormalities in two case studies; a continuous stirred tank heater problem for detecting leaks and the Tennessee Eastman chemical process for detecting step and sticking faults. The performance of the proposed robust artificial neural networks (ANN) model is evaluated in terms of accuracy, fault detection rate, false alarm rate, and classification index at varying extents of mislabelling, namely, 1%, 5%, and 10% mislabelled data. The proposed model demonstrates higher detection performance, especially at increased labels of mislabelled data where the performance of the conventional ANN is severely impacted. The proposed methodology can be advantageous in handling mislabelled and low-quality data issues which are crucial in the data-driven modelling of processing systems.     

A time-varying process monitoring approach based on iterative-updated semi-supervised nonnegative matrix factorizations

This paper proposes a new time-varying process monitoring approach based on iterative-updated semi-supervised nonnegative matrix factorizations (ISNMFs). ISNMFs are a type of semi-supervised model that constructs a semi-nonnegative matrix factorization (SNMF) model of a process using both labelled and unlabelled samples. Compared with the existing nonnegative matrix factorizations (NMFs) where NMFs are referred to as matrix factorization algorithms that factorize a nonnegative matrix into two low-rank nonnegative matrices whose product can well approximate the original nonnegative matrix, ISNMFs have advantages in terms of the model update and the use of labelled samples. The ISNMFs-based process monitoring approach concerns fault detection and isolation and updates an SNMF model iteratively using the latest samples to capture the change of statistical property of time-varying processes. Moreover, the proposed fault detection and isolation approach is supported by the k-means algorithm in theory. At last, we demonstrate the superiority of ISNMFs over the existing NMFs in terms of fault detection and isolation through a case study on the penicillin fermentation process.     

基于广义隐马尔可夫模型的PM2.5浓度预测

近年来,以PM_2.5为主要污染物的重霾污染事件频频发生,给我国国民经济和居民健康造成了严重损失。在空气质量尚未得到根本性改善的情况下,对重霾污染的准确预警不仅能使公众合理回避污染危害,还能为政府实施应急管理提供时间裕量。针对影响PM_2.5浓度的前体物及气象因素的非高斯分布特点以及传统隐马尔可夫模型（hidden Markov model,HMM）必须已知隐含状态个数的缺点,采用广义隐马尔可夫模型（generalized hidden Markov model,GHMM）对北京市除去定陵外的11个国控站点2013年1月～2017年1月的PM_2.5浓度进行了预测。结果表明：GHMM对严重污染及以上PM_2.5样本浓度预测准确率显著高于传统连续HMM,但针对中度污染及以下PM_2.5样本浓度的预测准确率接近传统HMM。     

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.     

一种基于改进MPCA的间歇过程监控与故障诊断方法

针对基于不同展开方式的多向主元分析(MPCA)方法在线应用时各自存在的缺陷,提出一种改进的基于变量展开的MPCA方法,实现间歇过程的在线监控与故障诊断。该方法采用随时间更新的主元协方差代替固定的主元协方差进行T²统计量的计算,充分考虑了主元得分向量的动态特性;同时引入主元显著相关变量残差统计量,避免SPE统计量的保守性,且该统计量能提供更详细的过程变化信息,对正常工况改变或过程故障引起的T²监控图变化有一定的识别能力;最后提出一种随时间变化的贡献图计算方法用于在线故障诊断。该方法和MPCA方法的监控性能在一个青霉素发酵仿真系统上进行了比较。仿真结果表明：该方法具有较好的监控性能,能及时检测出过程存在的故障,且具有一定的故障识别和诊断能力。     

A support vector clustering‐based probabilistic method for unsupervised fault detection and classification of complex chemical processes using unlabeled data

A new support vector clustering (SVC)‐based probabilistic approach is developed for unsupervised chemical process monitoring and fault classification in this article. The spherical centers and radii of different clusters corresponding to normal and various kinds of faulty operations are estimated in the kernel feature space. Then the geometric distance of the monitored samples to different cluster centers and boundary support vectors are computed so that the distance–ratio–based probabilistic‐like index can be further defined. Thus, the most probable clusters can be assigned to the monitored samples for fault detection and classification. The proposed SVC monitoring approach is applied to two test scenarios in the Tennessee Eastman Chemical process and its results are compared to those of the conventional K‐nearest neighbor Fisher discriminant analysis (KNN‐FDA) and K‐nearest neighbor support vector machine (KNN‐SVM) methods. The result comparison demonstrates the superiority of the SVC‐based probabilistic approach over the traditional KNN‐FDA and KNN‐SVM methods in terms of fault detection and classification accuracies. © 2012 American Institute of Chemical Engineers AIChE J, 59: 407–419, 2013     

Operating condition diagnosis based on HMM with adaptive transition probabilities in presence of missing observations

A new approach for modeling and monitoring of the multivariate processes in presence of faulty and missing observations is introduced. It is assumed that operating modes of the process can transit to each other following a Markov chain model. Transition probabilities of the Markov chain are time varying as a function of the scheduling variable. Therefore, the transition probabilities will be able to vary adaptively according to different operating modes. In order to handle the problem of missing observations and unknown operating regimes, the expectation maximization algorithm is used to estimate the parameters. The proposed method is tested on two simulations and one industrial case studies. The industrial case study is the abnormal operating condition diagnosis in the primary separation vessel of oil‐sand processes. In comparison to the conventional methods, the proposed method shows superior performance in detection of different operating conditions of the process. © 2014 American Institute of Chemical Engineers AIChE J, 61: 477–493, 2015     

Combined generative topographic mapping and graph theory unsupervised approach for nonlinear fault identification

Identifying anomalies in chemical processes is highly desirable. Usually, one relies on previous knowledge of normal and faulty samples, excluding anomalies from model training and associating deviations to faults. How reliable is such knowledge, however, is questionable, especially during atypical scenarios. Unsupervised approaches, using no labels, provide an unbiased analysis. A generative topographic mapping (GTM) and graph theory combined approach, then, is proposed for unsupervised fault identification. GTM, given its probabilistic nature, highlights system features, reducing variable dimensionality. With this information, correlation between samples is calculated. Graph theory, then, generates a network, clustering similar samples. Two anomaly cases are analyzed: an artificial dataset and Tennessee Eastman Process. Principal component analysis (PCA) and Dynamic PCA indexes Q and T² along GTM and graph theory‐independent monitoring methodologies are used for comparison, considering supervised and unsupervised approaches. The proposed method performed similarly to all supervised methodologies, motivating its application and developments. © 2015 American Institute of Chemical Engineers AIChE J, 61: 1559–1571, 2015