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 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     

Quality‐relevant and process‐relevant fault monitoring with concurrent projection to latent structures

This paper proposes a new concurrent projection to latent structures is proposed in this paper for the monitoring of output‐relevant faults that affect the quality and input‐relevant process faults. The input and output data spaces are concurrently projected to five subspaces, a joint input‐output subspace that captures covariations between input and output, an output‐principal subspace, an output‐residual subspace, an input‐principal subspace, and an input‐residual subspace. Fault detection indices are developed based on these subspaces for various fault detection alarms. The proposed monitoring method offers complete monitoring of faults that happen in the predictable output subspace and the unpredictable output residual subspace, as well as faults that affect the input spaces only. Numerical simulation examples and the Tennessee Eastman challenge problem are used to illustrate the effectiveness of the proposed method. © 2012 American Institute of Chemical Engineers AIChE J, 59: 496–504, 2013     

基于统计信号重构的传感器故障诊断

主元分析、偏最小二层等数据驱动的多元统计监控方法由于不依赖于精确的数学模型,在化工过程监控与故障检测方面取得了广泛应用.通过研究基于统计信号重构的传感器故障诊断算法,给出了统计信号重构算法的一般形式,并推导了基于统计信号重构算法进行传感器故障诊断的可检测与可分离性条件,定义了模型空间和余差空间的故障识别指标.通过CSTR仿真对象的应用比较了不同统计信号重构算法间的差异,验证了故障诊断算法的有效性.     

Active fault isolation of nonlinear process systems

This work considers the problem of designing an active fault‐isolation scheme for nonlinear process systems subject to uncertainty. The faults under consideration include bounded actuator faults and process disturbances. The key idea of the proposed method is to exploit the nonlinear way that faults affect the process evolution through supervisory feedback control. To this end, a dedicated fault‐isolation residual and its time‐varying threshold are generated for each fault by treating other faults as disturbances. A fault is isolated when the corresponding residual breaches its threshold. These residuals, however, may not be sensitive to faults in the operating region under nominal operation. To make these residuals sensitive to faults, a switching rule is designed to drive the process states, upon detection of a fault, to move toward an operating point that, for any given fault, results in the reduction of the effect of other faults on the evolution of the same process state. This idea is then generalized to sequentially operate the process at multiple operating points that facilitate isolation of different faults for the case where the residuals are not simultaneously sensitive to faults at a single operating point. The effectiveness of the proposed active fault‐isolation scheme is illustrated using a chemical reactor example and demonstrated through application to a solution copolymerization of methyl methacrylate and vinyl acetate. © 2013 American Institute of Chemical Engineers AIChE J, 59: 2435–2453, 2013     

Siamese DeNPE network framework for fault detection of batch process

In batch processes, it is crucial to ensure safe production by fault detection. However, the long batch duration, limited runs, and strong nonlinearity of the data pose challenges. Incipient faults with small amplitudes further complicate the detection process. To achieve safe production, motivated by deep learning strategies, we propose a new fault detection method of batch process called Siamese deep neighbourhood preserving embedding network (SDeNPE). First, the DeNPE network is constructed by means of NPE and kernel functions, which utilizes the different types of kernel functions in the kernel mapping layer to extract diverse deep nonlinear features and overcome strong nonlinearity in the process data. Then, the Siamese network is used to obtain the different features between the data and improve the recognition of incipient faults. In addition, the deep extraction and Siamese network allow for batches of training data reduction without diminishing the performance of fault detection. Finally, we utilize monitoring statistics to complete the fault detection process. Two batch process cases involving the penicillin fermentation process and the semiconductor etching process demonstrate the superior fault detection performance of the proposed SDeNPE over the other comparison methods.     

Robust fault detection and monitoring of hybrid process systems with uncertain mode transitions

A methodology for fault detection and monitoring of a class of hybrid process systems modeled by switched nonlinear systems with control actuator faults, uncertain continuous dynamics, and uncertain mode transitions is presented. A robust hybrid monitoring scheme that distinguishes reliably between faults, mode transitions, and uncertainty is developed using tools from unknown input observer theory and results from Lyapunov stability theory. The monitoring scheme consists of (1) a family of dedicated mode observers that locate the active operating mode at any given time and detect mode switches, (2) a family of robust Lyapunov‐based fault detection schemes that detect the faults within the continuous modes, and (3) a supervisor that synchronizes the switching between different controllers and different fault detectors as the process transitions from one mode to another. A key idea of the developed framework is to design the mode observers in a way that facilitates the identification of the active mode without information from the controllers and renders the residuals insensitive to the faults and uncertainties in the constituent subsystems. The implementation of the developed monitoring scheme is demonstrated using a simulated model of a chemical reactor that switches between multiple operating modes. © 2010 American Institute of Chemical Engineers AIChE J, 2011     

基于加权互信息主元分析算法的质量相关故障检测

质量相关的故障检测已成为近几年研究热点,它的目标是在过程监测中,对质量相关的故障检测率更高,对质量无关的故障少报警或不报警。传统主元分析算法的故障检测会对所有故障均报警,不能达到上述要求。另外,在实际工业生产中,质量变量通常难以实时获得,需要后续分析或延时得到。为此,提出一种融合贝叶斯推断与互信息的加权互信息主元分析算法。首先利用贝叶斯推断的加权方法将度量过程变量和质量变量之间相关关系的互信息进行融合,选出包含质量变量信息量最大的一组过程变量。然后对过程变量利用主元分析（principal component analysis,PCA）进行统计建模,再次根据加权互信息选出包含质量变量信息量最大的主元,建立统计量进行故障检测。最后,通过实验验证该方法的可行性和有效性。     

Dynamic models and fault diagnosis‐based triggers for closed‐loop scheduling

Establishing an explicit feedback connection between production management and process control decisions is a key requirement for more nimble and cost effective process operations in today's variable market conditions. Past research efforts focused on embedding dynamic process information in the production scheduling problem. In this article, we propose a novel framework for closing the scheduling loop, based on considering the process‐level events and disturbances that impact the implementation of scheduling decisions. We emphasize the role of a comprehensive fault detection, isolation and reconstruction mechanism as a trigger for rescheduling decisions and for reflecting the process capabilities altered by these events in the rescheduling problem formulation. Our framework is agnostic to the process type, and we present two (continuous process, sequential batch process) case studies to demonstrate its applicability. © 2016 American Institute of Chemical Engineers AIChE J, 63: 1959–1973, 2017     

A geometric framework for monitoring and fault detection for periodic processes

Although cyclical operation systems are relatively widespread in practice (notably in the realm of physical separations, for example, pressure‐swing adsorption and chromatography), the development of specific fault detection mechanisms has received little attention compared to the extensive efforts dedicated to continuous or batch processes. Here, a novel geometric approach for process fault detection is proposed. Specifically, a time‐explicit multivariable representation of data collected from the process, which provides a natural framework for defining “normal” operation and the corresponding confidence regions is developed. On this basis, a two‐step fault detection approach is proposed, based on detecting intercycle variations to locate a faulty cycle, and intracycle changes to determine the exact timing of a fault. The theoretical developments are illustrated with two simulation case studies. © 2017 American Institute of Chemical Engineers AIChE J, 63: 2719–2730, 2017     

基于加权深度支持向量数据描述的工业过程故障检测

传统支持向量数据描述（SVDD）方法本质上采用浅层学习框架,难以有效监控非线性工业过程的复杂故障。针对此问题,提出一种基于加权深度支持向量数据描述（WDSVDD）的故障检测方法。该方法一方面在深度学习框架下重新定义SVDD优化目标函数,构建基于深度特征的深度SVDD监控模型（DSVDD）,并利用核密度估计法计算监控指标的统计控制限;另一方面,考虑到深度特征的故障敏感度差异特性,在DSVDD监控模型中设计特征加权层,分别从静态和动态信息分析角度给出权重因子的计算方法,利用权重因子突出故障敏感特征的影响以提高故障检测率。应用于一个典型化工过程的测试结果表明,所研究的方法能够比传统SVDD方法更有效地监控过程中复杂故障的发生。     

基于主元分析法的冷水机组传感器故障检测效率分析

冷水机组是一个高度非线性的复杂系统,其自控系统传感器故障会导致冷水机组的运行偏离正常状态和能耗浪费。采用冷水机组正常运行数据,通过多元统计方法中的主元分析法建立训练矩阵,利用平方预测误差进行故障分析工作。引入不同程度故障,分析主元分析法的检测效率。结果表明,主元分析法故障检测效果明显,但对于不同传感器的不同程度故障,故障检测的误判率存在一定的差异。     

Reconstruction in integrating fault spaces for fault identification with kernel independent component analysis

In the original fault identification methods, contribution plots are popular. However, it is not accurate because of the smearing effect. In addition, traditional contribution plots cannot be applied to nonlinear process because there seems no way to accurately calculate variable contributions. As a comparison, the reconstruction method is widely used in fault identification for finding the root causes of the fault. For fault detection and identification of actual industrial process with nonlinear and non-Gaussian features, a new reconstruction-based fault identification method with kernel independent component analysis (KICA) is developed in this article. The proposed method, reconstruction in integrating fault spaces (RIFSs), extends the classic reconstruction-based fault identification approach to KICA for the first time, and develops the reconstruction method from unidimensional faults to multidimensional ones for nonlinear cases. Furthermore, the number of reconstruction is effectively reduced on the basis of the integrating fault spaces (IFSs) which are composed of fault subspaces satisfying orthogonal to each other from the known fault set. In addition, fault magnitude, indicating the adjustment magnitude of a fault sample back to normal range, is used as index to identify faults, and it makes the fault identification problem become more straightforward than with the existing fault identification index, such as ratio (index I) or the reconstructed statistics (index II). Finally, the proposed method is applied to the fault detection and identification on cyanide leaching of gold, which shows its feasibility and efficiency for both sensor faults and complex process faults.     

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.     

Multi-linear model-based fault detection during process transitions

Process transitions due to startup, shutdown, product slate changes, and feedstock changes are frequent in the process industry. Experienced operators usually execute transitions in the manual mode as transitions may involve unusual conditions and nonlinear process behavior. Processes are therefore more prone to faults as well as inadvertent operator errors during transitions. Fault detection during transition is critical as faults can lead to abnormal situations and even cause accidents. This paper proposes a model-based fault detection scheme that involves decomposition of nonlinear transient systems into multiple linear modeling regimes. Kalman filters and open-loop observers are used for state estimation and residual generation based on the resulting linear models. Analysis of residuals using thresholds, faults tags, and logic charts enables on-line detection and isolation of faults. The multi-linear model-based fault detection technique has been implemented using Matlab and successfully tested to detect process faults and operator errors during the startup transition of highly nonlinear pH neutralization reactor in the laboratory.     

基于MAF的传感器故障检测与诊断

针对工业控制系统中变量之间既存在线性相关性,且在时间结构上呈现自相关的特点,提出了一种基于最小/最大自相关因子(min/max autocorrelation factors, MAF)分析的传感器故障检测与诊断方法。首先,利用正常工况下的历史数据进行自相关因子分析,获得强自相关因子和弱自相关因子;在此基础上构造故障检测统计量,由核密度估计方法获得故障检测控制限,根据贡献图进行传感器故障定位。将所提出的方法应用于连续反应釜仿真过程的传感器故障检测与诊断,与经典的多变量统计方法——主元分析方法相比,所提出的方法能避免虚警,更快地检测缓变故障,并能更好地诊断和解释复杂故障。     

基于SVDD的冷水机组传感器故障检测及效率分析

传感器是制冷空调系统的重要组成部分,起着测量数据和监控状态的作用。传感器故障,尤其是输出偏差会引起测量值不准,影响控制策略,导致系统能耗增加。依据模式识别理论,故障检测可处理为一种单分类问题。据此采用一种单分类模式识别工具——支持向量数据描述(SVDD),针对冷水机组进行了偏差故障条件下的传感器故障检测工作。收集冷水机组实测正常运行数据,基于训练集建立SVDD模型,进行冷水机组传感器故障检测;在测试集中引入不同幅值水平的偏差故障,分析检测效率。结果表明:基于SVDD的冷水机组传感器故障检测效果明显,但对于不同传感器的不同幅值偏差故障,故障识别程度并不一致。     

Reducing smearing effect in contribution plots and improving fault detection via polynomial approximated isomap embeddings

Dimension reduction is an essential method used in multivariate statistical process monitoring for fault detection and diagnosis. Principal component analysis (PCA) and independent component analysis (ICA) are the most frequently used linear dimensional reduction tools, and the contribution plot is the most popular fault isolation method in the absence of any prior information on the faults. These methods, however, come with their shortcomings. The fault detection capability of linear methods may not be sufficient for non-linear processes, and smearing effect is known to deteriorate the diagnostics obtained from contribution plots. While the fault detection rate may be increased by kernelized methods or deep artificial neural network models, tuning data-dependent hyperparameter(s) and network structure with limited historical data is not an easy task. Furthermore, the resulting non-linear models often do not directly possess fault isolation capability. In the current study, we aim to devise a novel method named ICA_pIso-PCA, which offers non-linear fault detection and isolation in a rather straightforward manner. The rationale of ICA_pIso-PCA mainly involves building a non-linear scores matrix, composed of principal component scores and high-order polynomial approximated isomap embeddings, followed by implementation of the ICA-PCA algorithm on this matrix. Applications on a toy dataset and the Tennessee Eastman plant show that the I² index from ICA_pIso-PCA yields a high fault detection rate and offers accurate contribution plots with diminished smearing effects compared to those from traditional monitoring methods. Easy implementation and the potential for future research are further advantages of the proposed method.     

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     

Quality-relevant and process-relevant fault monitoring based on GNPER and the fault quantification index for industrial processes

Traditional quality-relevant fault monitoring methods focus on extracting the relationship between the global structural features of the process and quality variables but ignore the local features. At the same time, they lack the quantification of quality-relevant faults. To solve these problems, a quality-relevant and process-relevant fault monitoring method and its fault quantification index based on global neighbourhood preserving embedding regression (GNPER) are proposed. First, by seeking the direction of maximum global variance, the global objective function is applied to neighbourhood preserving embedding algorithm, and the global neighbourhood preserving embedding (GNPE) model is established to fully extract the global and local information of process data. Second, on the basis of GNPE, through the idea of projection regression, the GNPER model is established to obtain mapping relationships among process variables and quality variables, and quality-relevant subspace and process-relevant subspace are extracted, the corresponding subspace statistics are established for fault monitoring. Finally, the fault quantification index is established for the faults in the two subspaces, which can provide more meaningful fault monitoring results. A numerical example, the hot rolling mill and the Tennessee Eastman (TE) process, verify the superiority and accuracy of the proposed method.