Fault detection and isolation in hybrid process systems using a combined data‐driven and observer‐design methodology

A combined data‐driven and observer‐design methodology for fault detection and isolation (FDI) in hybrid process systems with switching operating modes is proposed. The main contribution is to construct a unified framework for FDI by integrating Gaussian mixture models (GMM), subspace model identification (SMI), and results from unknown input observer (UIO) theory. Initially, a GMM is built to identify and describe the multimodality of hybrid systems using the recorded input/output process data. A state‐space model is then obtained for each specific operating mode based on SMI if the system matrices are unknown. An UIO is designed to estimate the system states robustly, based on which the fault detection is laid out through a multivariate analysis of the residuals. Finally, by designing a set of unknown input matrices for specific fault scenarios, fault isolation is performed through the disturbance‐decoupling principle from the UIO theory. A significant benefit of the developed framework is to overcome some of the limitations associated with individual model‐based and data‐based approaches in dealing with the problem of FDI in hybrid systems. Finally, the validity and effectiveness of the proposed monitoring framework are demonstrated using a numerical example, a simulated continuous stirred tank heater process, and the Tennessee Eastman benchmark process. © 2014 American Institute of Chemical Engineers AIChE J, 60: 2805–2814, 2014     

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     

基于多阶段多向核熵成分分析的间歇过程故障检测方法

针对间歇过程的非线性、多阶段特性,提出一种基于多阶段多向核熵成分分析（multistage-MKECA,MsMKECA）的故障检测方法。针对间歇过程的多阶段特性,建立一种时序核熵主元关联度的矩阵相似性阶段划分方法,实现对间歇生产过程的多阶段划分;针对传统批次展开方式在线监控需要预估批次未来值的缺陷,进一步引入一种批次-变量三维数据展开方式建立每个阶段的MKECA非线性统计模型,实现对间歇过程的分阶段监控。最后对盘尼西林发酵过程开展仿真研究,结果表明所提方法能够比传统MKECA方法更为快速地进行故障检测。     

Input reconstruction for statistical‐based fault detection and isolation

In this work, an input reconstruction scheme for detecting and isolating sensor, actuator, and process faults is proposed. The scheme uses model‐based and statistical‐based FDI methods, which yields an improved analysis of abnormal operation conditions in chemical processes. The main advantage of the proposed approach over existing works lies in the reconstruction of system inputs and the subsequent estimation of fault signatures. This advantage is demonstrated through simulation examples and the analysis of recorded process data from a reactive batch distillation column. © 2011 American Institute of Chemical Engineers AIChE J, 2012     

基于LECA的多工况过程故障检测方法

针对工业过程监控中的多工况复杂分布数据,提出一种基于局部熵成分分析(LECA)的故障检测方法。为处理数据的多模态分布问题,LECA首先采用KNN-Parzen窗方法估计变量的局部概率密度,进一步构造局部相对概率密度函数降低对窗参数选择的敏感性。为有效挖掘非高斯分布数据中的特征信息,利用信息熵理论计算过程数据的局部信息熵,并采用独立元分析(ICA)方法建立局部熵成分统计模型,实时检测过程故障。在数值例子和连续搅拌反应釜(CSTR)上的仿真结果表明,该方法在故障检测过程中能够获得较好的监控性能。     

基于双近邻标准化和PCA的多阶段过程故障检测

现代工业产品的生产往往需要多个生产阶段,多阶段生产过程的故障检测成为一个重要问题。多阶段过程数据具有多中心、各工序数据结构不同等特征。针对多阶段过程数据的特征,提出了基于双近邻标准化和主元分析的故障检测方法（DLNS-PCA）。首先寻找样本的双层局部近邻集;其次使用双层局部近邻集的信息标准化样本,得到标准样本;最后在标准样本集上使用主元分析方法进行故障检测。双局部近邻标准化能够将各阶段数据的中心平移到同一点,并且调整各阶段数据的离散程度,使之近似相等,从而将多阶段过程数据融合为服从单一多元高斯分布的数据。进行了青霉素发酵过程故障检测实验,实验结果表明DLNS-PCA方法相对于PCA、KPCA、FDkNN等方法对多阶段过程故障具有更高的检测率。DLNS-PCA方法提高了多阶段过程故障检测能力。     

基于代价敏感主动学习的氧化铝蒸发过程故障检测

针对氧化铝蒸发过程故障检测中标注者不切实际的假设和控制参数难以确定问题,提出改进的代价敏感主动学习方法。给出了代价敏感主动学习形式化描述和放松了标注者不切实际的假设。为了提高分类精度和减少标注代价,该方法结合粒子群优化和代价敏感主动学习。利用连续的粒子群优化代价敏感主动学习的控制参数,该参数用于最大化未标注样本的信息度和最小化标注代价。将所提出的方法应用于氧化铝蒸发过程故障检测,实验结果表明,该方法能正确地选择控制参数,有效地减少了误分类代价和标注代价,提高了故障检测率。     

基于故障判别增强KECA算法的故障检测

基于核熵主成分分析方法的统计模型仅利用正常工况下数据进行建模,而忽略了监控系统数据库中一些已知类别的先前故障数据。为了利用先前故障数据中包含的故障信息来增强故障检测性能,提出了一种故障判别增强KECA (fault discriminant enhanced kernel entropy component analysis, FDKECA)算法。该法通过采用无监督学习和监督学习方法建立模型,同时监测非线性核熵主成分(kernel entropy component, KEC)和故障判别成分(fault discriminant component, FDC)两类数据特征。此外,利用贝叶斯推理将相应的监视统计信息转换为故障概率,并通过加权两个子模型的结果来构建基于总体概率的监视统计量。通过数值仿真和田纳西伊斯曼(Tennessee Eastman, TE)过程仿真实验,证明和传统KECA相比,FDKECA算法能够有效利用故障数据提高故障检测率。     

Tensor sequence component analysis for fault detection in dynamic process

For dynamic processes, using sequence information to augment the data can improve fault detection performance. Traditional approaches transform raw data into augmented vectors, which leads to losses in structural information in the variables and increases the data dimension. This paper proposes a novel data dimension reduction algorithm called tensor sequence component analysis (TSCA) and applies it to dynamic process fault detection. The algorithm extends each sample into a matrix comprising current and past process data, and simultaneously reduces the dimensions of time delay and the variables for feature extraction, solving the problem of the curse of dimensionality. For the dimension reduction of time delay, in order to extract similar information from the samples, each sample is reconstructed with time neighbourhoods. For the dimension reduction of the variables, considering the information of different variables variance information of the latent variables is maximized for feature extraction. Finally, a numerical example and the Tennessee Eastman process are used to demonstrate the efficacy of the proposed method.     

A novel fault detection scheme for a nonlinear dynamic process based on generalized non-negative matrix projection-maximum mean discrepancy: Application on the DAMADICS benchmark process

In order to address the issue of minor fault detection in nonlinear dynamic processes, this paper proposes a fault detection method based on generalized non-negative matrix projection-maximum mean discrepancy (GNMP-MMD). Firstly, the GNMP is employed to acquire the residual scores of the samples. Subsequently, a sliding window approach is integrated with MMD for real-time monitoring of sample status within the residual subspace. In this study, GNMP is utilized to mitigate the impact of non-Gaussianity in data distribution, while MMD serves to alleviate autocorrelation among samples. A numerical case and experimental data collected from the DAMADICS process are utilized to simulate and validate the proposed method. Compared to traditional principal component analysis (PCA), dynamic principal component analysis (DPCA), dynamic kernel principal component analysis (DKPCA), non-negative matrix factorization (NMF), GNMP, and MMD, the experiment results clearly illustrate the feasibility of the proposed method.     

层次变分高斯混合模型与主多项式分析的故障检测策略

针对多模态工业过程中模态数量难以确定问题,提出一种层次变分高斯混合模型（hierarchical variational Gaussian mixture model, HVGMM）。在此基础上,使用主多项式分析（principal polynomial analysis, PPA）用于多模态非线性过程故障检测。首先,变分贝叶斯高斯混合模型（variational Bayesian Gaussian mixture model, VBGMM）作为初始模型用于分解过程数据得到工作模态的初始数量,将过程按初始数量分解为多个子块;其次,应用包含多个局部模型的VBGMM将各子块分解为附属子块,并利用附属子块的均值、精度等信息对VBGMM进行重构;然后,将重构后的VBGMM作为初始模型再次用于分解原始过程数据,重复上述步骤直至重构VBGMM无法分解各子块时停止;最后,分别在各附属子块中建立局部PPA模型,并在每个局部模型中计算T²和SPE统计量进行故障检测。将该方法应用于数值例子和Tennessee Eastman（TE）化工过程,并将仿真结果与主元分析（principal component analysis, PCA）、PPA进行对比,验证了所提出方法的有效性。     

Community detection based process decomposition and distributed monitoring for large-scale processes

Distributed architectures wherein multiple decision-making units are employed to coordinate their decision-making/actions based on real-time communication have become increasingly important for monitoring processes that have large scales and complex structures. Typically, the development of a distributed monitoring scheme involves two key steps, that is, the decomposition of the process into subsystems, and the design of local monitors based on the configured subsystem models. In this article, we propose a distributed process monitoring approach that tackles both steps for large-scale processes. A data-driven process decomposition approach is proposed by leveraging community structure detection to divide variables into subsystems optimally via finding a maximal value of the metric of modularity. A two-layer distributed monitoring scheme is developed where local monitors are designed based on the configured subsystems of variables using canonical correlation analysis. Inner-subsystem interactions and inter-subsystem interactions are tackled by the two layers separately, such that the sensitivity of this monitoring scheme to certain types of faults is improved. We utilize a numerical example to illustrate the effectiveness and superiority of the proposed method. It is then applied to a simulated wastewater treatment process.     

变量加权型主元分析算法及其在故障检测中的应用

传统主成分分析（PCA）算法旨在挖掘训练数据各变量间的相关性特征,已在数据驱动的故障检测领域得到了广泛的研究与应用。然而,传统PCA方法在建模过程中通常认为各个测量变量的重要性是一致的,因此不能有效而全面地描述出变量间相关性的差异。为此,提出一种变量加权型PCA（VWPCA）算法并将之应用于故障检测。首先,通过对训练数据进行加权处理,使处理后的数据能够充分体现出变量间相关性的差异。然后,在此基础上建立分布式的PCA故障检测模型。在线实施故障检测时,则通过贝叶斯准则将多组监测结果融合为一组概率指标。VWPCA方法通过相关性大小为各变量赋予不同的权值,从而将相关性差异考虑进了PCA的建模过程中,相应模型对训练数据特征的描述也就更全面。最后,通过在TE过程上的测试验证VWPCA方法用于故障检测的优越性。     

基于加权统计特征KICA的故障检测与诊断方法

针对核独立元分析（kernel independent component analysis, KICA）在非线性动态过程中对微小故障检测率低的问题,提出一种基于加权统计特征KICA（weighted statistical feature KICA, WSFKICA）的故障检测与诊断方法。首先,利用KICA从原始数据中捕获独立元数据和残差数据;然后,通过加权统计特征和滑动窗口获取改进统计特征数据集,并由此数据集构建统计量进行故障检测;最后,利用基于变量贡献图的方法进行过程故障诊断。与传统KICA统计量相比,所提方法的统计量对非线性动态过程中的微小故障具有更高的故障检测性能。应用该方法对一个数值例子和田纳西-伊斯曼（Tennessee-Eastman, TE）过程进行仿真测试,仿真结果显示出所提方法相对于独立元分析（ICA）、KICA、核主成分分析（kernel principal component analysis, KPCA）和统计局部核主成分分析（statistical local kernel principal component analysis, SLKPCA）检测的优势。     

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.     

基于深度学习的化工过程故障检测与诊断研究综述

化工过程的故障检测与诊断对于现代化工系统的可靠性和安全性具有重要意义.深度学习作为一项新兴的技术,引起了学术界和工业界的广泛关注.从方法的角度出发,将基于深度学习的化工过程故障检测与诊断技术分为:基于自动编码器的方法、基于深度置信网络的方法、基于卷积神经网络的方法和基于循环神经网络的方法,并分别对4种方法的最新研究进展...     

基于变量分组DTW-MCVA的不等长间歇过程故障检测方法

针对不等长间歇过程监控中批次数据同步化未能充分挖掘局部信息的问题,提出一种基于变量分组DTW-MCVA（VGDTW-CVA）的不等长间歇过程故障检测方法。首先,利用互信息矩阵描述不等长间歇过程测量变量之间的相关性,并基于互信息矩阵进行变量分组。然后利用DTW算法对各个变量组分别进行同步化,并将同步化后的变量组整合为完整的三维数据集。最后,利用MCVA方法建立动态监控模型实现对间歇生产过程的在线监控。盘尼西林发酵过程的仿真结果表明,VGDTW-MCVA能够比基本的DTW-MCVA方法更好地监控间歇过程故障。     

基于KECA的非线性工业过程故障检测与诊断新方法

提出了一种基于核熵成分分析(kernel entropy component analysis,KECA)的非线性过程故障检测与诊断新方法。该方法首先利用KECA获取过程数据的得分向量及非线性特征子空间;然后鉴于KECA可以以角结构的方式揭示数据中潜在的集群结构,设计了基于角度的监测指标VoA。该指标通过各得分向量之间的角度方差来描述变换后数据间的结构差异,并根据角度方差的变化情况实现故障检测;接着,为了在检测到故障后有效地进行故障识别,构建了KECA相似度因子来度量特征子空间的相似程度以识别故障模式;最后,以非线性数值案例及Tennessee Eastman过程进行仿真测试研究,结果验证了所提方法的可行性及有效性。