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。     

Controlled output variance based diagnosis tree for feedforward/feedback control systems

A diagnosis tree based on the controlled output variance is proposed to assess a feedforward/feedback control performance. It is used for diagnosing and removing its fault causes. Based on the controlled output, the current output variance of the feedback/feedforward system is contributed by the feedback-only effect and the combination of feedback with feedforward effects, respectively. The feedback loop variance can be further expressed as the sum of the feedback invariant (FBI) term and the feedback-dependent (FBD) term. The feedforward loop variance can also be decomposed into the feedback/feedforward invariant (FBI/FFI) term, the feedback-invariant/feedforward-dependent (FBI/FFD) term and the feedback/feedforward-dependent (FBD/FFD) term. These effect variations are systematically conducted by a sequence of the statistic hypothesis testing procedures and the isolation strategy to compare the current control performance and the achievable benchmark operating one. Without the traditional complex physical model and/or any external input to change the current operating process, the diagnosis tree with hierarchical structure is constructed. The capability of the proposal is illustrated through two simulation cases with multiple faults.     

Facile synthesis of graphene oxide-wrapped CNFs as high-performance microwave absorber

Graphene oxide/carbon nanofibers hierarchical structures have been successfully synthesized through a modified Hummers method. Owing to the harsh chemical exfoliation and oxidation, graphene oxide (GO) appears on the outer walls of carbon nanofibers (CNFs) with the preservation of the 3D fibrous network. By adjusting the oxidation time, the obtained sample exhibited excellent electromagnetic (EM) attenuation performance with a maximum reflection loss of −49.82 dB at a thickness of 1.5 mm. Meanwhile, an effective bandwidth of 2.48 GHz was also investigated. The superior EM absorbing performance of GO/CNFs is ascribed to the hierarchical structure. While the inner carbon skeleton endows the material with desirable conductive network, GO exhibits a larger surface area with abundant functional groups and defects that give rise to multiple polarizations and relaxation processes. Moreover, the resistance-capacitance coupled circuits formed in the GO/CNFs network are beneficial for dissipating the incident waves. Prospectively, the synthetic strategy applied in this research can be extended to assemble GO on carbonaceous materials to fabricate novel microwave absorbers.     

Adaptive partitioning PCA model for improving fault detection and isolation☆

In chemical process, a large number of measured and manipulated variables are highly correlated. Principal com-ponent analysis (PCA) is widely applied as a dimension reduction technique for capturing strong correlation un-derlying in the process measurements. However, it is difficult for PCA based fault detection results to be interpreted physical y and to provide support for isolation. Some approaches incorporating process knowledge are developed, but the information is always shortage and deficient in practice. Therefore, this work proposes an adaptive partitioning PCA algorithm entirely based on operation data. The process feature space is partitioned into several sub-feature spaces. Constructed sub-block models can not only reflect the local behavior of process change, namely to grasp the intrinsic local information underlying the process changes, but also improve the fault detection and isolation through the combination of local fault detection results and reduction of smearing effect. The method is demonstrated in TE process, and the results show that the new method is much better in fault detection and isolation compared to conventional PCA method.     

Chemical process fault diagnosis based on a combined deep learning method

The study on fault detection and diagnosis (FDD) of chemical processes has always been the top priority of the chemical process safety. In this paper, a fault diagnosis method combining the deep convolutional with the recurrent neural network (DCRNN) is proposed. In this method, the data from chemical processes are input to the deep convolutional neural network (DCNN) to extract features in spatial domains, and then, the features are fused into the bidirectional recurrent neural network (BRNN). Due to the powerful capabilities of DCNN to extract features in spatial domains and the sensitivity to time series of RNN, the combined method can adaptively learn the dynamic information of the raw data in both spatial and temporal domains and has unique advantages in multivariate chemical processes. The application of the DCRNN model in the Tennessee Eastman (TE) process demonstrates the high accuracy of this proposal in identifying abnormal conditions for the chemical process, compared with the traditional fault identification algorithms of deep learning.     

A process fault diagnosis method using multi-time scale dynamic feature extraction based on convolutional neural network

Unlike many other techniques used in process control, which are widely applied in practice and play significant roles, abnormal situation management (ASM) still relies heavily on human experience, not least because the problem of fault detection and diagnosis (FDD) has not been well addressed. In this paper, a process fault diagnosis method using multi-time scale dynamic feature extraction based on convolutional neural network (CNN) consisting of similarity measurement, variable ranking, and multi-time scale dynamic feature extraction is proposed. The CNN-based model containing the fixed multiple sampling (FMS) layer can extract dynamic characteristics of process data at different time scales. The benchmark Tennessee Eastman (TE) process is used to verify the performance of the proposed method.     

Decentralized Fault Isolation by a Combination of Transfer Entropy and Classification Methods

Early fault detection and isolation in industrial systems is vitally necessary to prevent any potential product damage. The paper proposes a new decentralized multi-unit fault isolation methodology in which all the known process faults with similar time signatures are grouped into appropriate categories. An innovative genetic algorithm-based method is introduced to explore for optimum plant zones in a large-scale plant wide search to appropriately configure each architectural unit, having less reliance on excess process variables with redundant and uncorrelated diagnostic information. The methodology employs a set of Bayes and radial basis function neural network classifiers to properly isolate the most usual known faults. A new idea based on transfer entropy algorithm has been integrated in the decentralized configuration to be triggered for isolation of novel faults which have been left unrecognized by the set of maintained classifiers. Experimental results clearly demonstrate that the proposed methods are considerably superior to the conventional centralized methods.     

基于多动态核聚类的间歇过程在线监控

针对传统的多元统计监测方法不能有效检测工业过程中由于初始条件波动较大所引发的弱故障问题,提出一种基于多动态核聚类的核主元分析(DKCPCA)监控策略,实现多阶段间歇过程的弱故障在线监控.该方法首先针对过程中各阶段每一批次数据结合自回归移动平均时间序列模型(ARMAX)和核主成分分析(KPCA)方法分别建立动态核PCA模型,然后根据各批次模型间载荷的相似性采用分层次聚类方法进行聚类,最后将聚在一起的批次数据进行展开重新再建立动态核PCA模型,随着聚类数目的不同从而建立多个类模型.当在线应用时给出了多模型选择策略,以提高监测精度.将此方法应用于青霉素发酵过程的监控中,监测结果表明此方法取得了比DKPCA和MKPCA更好的监测性能.     

基于半监督密集阶梯网络的工业故障识别

针对工业过程故障识别的需要和实际工业数据小比例有标签、大比例无标签的特点,研究了基于深度学习的半监督故障分类方法。在半监督阶梯网络的基础上,通过对网络结构和损失函数的改进,提出了半监督密集阶梯网络算法。该算法改进了原始的网络结构,添加了各层之间的密集连接,尝试最大化阶梯网络内部的数据信息流,使得各编码解码层之间的特征得以传递和复用。针对损失函数的特点,添加了无噪声编码层的预测输出损失,确保训练目标与模型输出一致。实验结果证明了所提出的新方法能在工业过程的小比例有标签数据情况下,获得理想的分类效果。     

Distributed process monitoring framework based on decomposed modified partial least squares

With the growing complexity of industrial processes, the scale of production processes tends to be large. The significant amount of measurement data in large‐scale processes poses challenges in data collection, management, and storage. In order to perform effective process monitoring in large‐scale processes, the distributed process monitoring strategy is widely applied. Meanwhile, product quality is an important indicator for industrial production. Therefore, a novel quality‐based distributed process monitoring scheme is proposed. Firstly, the Girvan‐Newman (GN) algorithm in complex network divides process variables into multiple sub‐blocks. Secondly, greedy algorithm‐based high‐dimensional mutual information (HDMI) is used to extract quality‐related variables in each sub‐block, through which the irrelevant and redundant variables are eliminated. Thirdly, the decomposed modified partial least squares (DMPLS) approach is used to detect whether a fault is quality‐related or not in each sub‐block. Finally, the Bayesian inference strategy is adopted to combine the detection results of all sub‐blocks. The effectiveness of the distributed DMPLS approach is illustrated through a numerical simulation and the Tennessee Eastman (TE) process. The results show the superiority of our proposed monitoring scheme.     

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     

基于支持向量数据描述的非高斯过程故障重构与诊断

提出一种基于支持向量描述（SVDD）的统计过程监控与故障重构及诊断算法,避免了PCA、PLS等传统统计过程监控方法假设过程数据服从高斯分布的不足。鲁棒故障重构算法通过迭代保证重构后的数据对应的SVDD监控统计量最小化。诊断算法根据故障集中的不同故障重构后监控统计量是否恢复正常,确定实际发生的过程故障。CSTR过程的仿真研究表明了所提出方法的有效性。     

An Extension Sample Classification‐Based Extreme Learning Machine Ensemble Method for Process Fault Diagnosis

In order to achieve higher accuracy and faster response in complex process fault diagnosis, an extension sample classification‐based extreme learning machine ensemble (ESC‐ELME) method is proposed. In the realization process, the extension sample classification is used to divide the fault types. For each fault type, a specific extreme learning machine (ELM) is established and trained independently. Then, all specific ELMs are integrated to determine which fault is happened by the majority voting method. The proposed ESC‐ELME method is compared with the traditional ELM and a duty‐oriented hierarchical artificial neural network in fault diagnosis of the Tennessee Eastman process. The results demonstrate that the proposed method provides higher diagnosis accuracy and faster response.     

复杂故障判定的基于结构化残差的多层次分析法

In industrial processes,there exist faults that have complex effect on process variables.Complex and simple faults are defined according to their effect dimensions.The conventional approaches based on structured residuals cannot isolate complex faults.This paper presents a multi-level strategy for complex fault isolation.An extraction procedure is employed to reduce the complex faults to simple ones and assign them to several levels.On each level,faults are isolated by their different responses in the structured residuals.Each residual is obtained insensitive to one fault but more sensitive to others.The faults on different levels are verified to have different residual responses and will not be confused.An entire incidence matrix containing residual response characteristics of all faults is obtained,based on which faults can be isolated.The proposed method is applied in the Tennessee Eastman process example,and the effectiveness and advantage are demonstrated.     

基于改进差别矩阵属性约简的聚合釜粗糙集-神经网络故障诊断

引言 聚氯乙烯树脂(PVC)是重要的有机合成材料,其产品具有良好的物理性能和化学性能,广泛应用于工业、建筑、农业、电力、公用事业等领域.聚合釜则是聚氯乙烯生产装置的关键设备,聚合釜能否稳定运行直接关系到整个聚氯乙烯生产装置的运行状况.     

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.     

基于数据复杂网络理论的系统故障检测方法

化工过程系统结构的大型化和复杂性,通过单独的机理模型进行故障检测已越来越困难.提出一种基于数据复杂网络理论的过程故障检测方法,利用偏相关系数确定复杂变量间的邻接矩阵,生成过程系统数据变量之间的网络模型,从网络拓扑结构出发,计算系统复杂网络的特征参数,通过对故障模型与非故障模型之间网络特征参数的差异判断系统是否发生故障,进而找到故障点.以TE过程为应用对象,验证了该方法的有效性.     

Synthetic Modular Antibody Construction by Using the SpyTag/SpyCatcher Protein-Ligase System

Efforts to engineer recombinant antibodies for specific diagnostic and therapy applications are time consuming and expensive, as each new recombinant antibody needs to be optimized for expression, stability, bio-distribution, and pharmacokinetics. We have developed a new way to construct recombinant antibody-like “devices” by using a bottom-up approach to build them from well-behaved discrete recombinant antibody domains or “parts”. Studies on antibody structure and function have identified antibody constant and variable domains with specific functions that can be expressed in isolation. We used the SpyTag/SpyCatcher protein ligase to join these parts together, thereby creating devices with desired properties based on summed properties of parts and in configurations that cannot be obtained by using genetic engineering. This strategy will create optimized recombinant antibody devices at reduced costs and with shortened development times.     

Hierarchical domain structures in (Pb,La)(Zr,Sn, Ti)O3 antiferroelectric ceramics

(Pb, La)(Zr, Sn, Ti)O₃ (PLZST) ceramic is one of the most prospective antiferroelectric (AFE) materials for variety of functional applications including energy storage and converter. Systematic structural investigation of domain structures should be of fundamental importance for understanding the structure-property relationship in AFE ceramics. In this study, the hierarchical domain structures and modulated structures correlated to the compositional variation in (Pb_0.97La_0.02) (Zr_0.50Sn_xTi_0.50-x)O₃ (x = 0.375, 0.45 and 0.50) were observed and investigated in details by transmission electron microscopy. The PLZST ceramics show exclusively incommensurate modulated structures (IMS) whose modulation period changed from 9.37 to 6.15 and to 4.04 with increasing of the x value. The hierarchical domain structures include, in decreasing scales, AFE domains, incommensurate domains and nanodomains. The elementary domains in PLZST ceramics are pinstriped nanodomains which were formed based on IMS configuration but by frequent modulation of IMS periodicity and formation of faults. Nanodomains accumulated and then dissociated into incommensurate domains and AFE domains successively. The presently revealed structural characteristics in antiferroelectric PLZST may stimulate future researches on the evolution of IMS-based hierarchical domains under external physical fields, e.g. thermal or electrical, and their correlation to the physical performance.     

Multivariate time delay analysis based local KPCA fault prognosis approach for nonlinear processes☆

Currently, some fault prognosis technology occasionally has relatively unsatisfied performance especially for in-cipient faults in nonlinear processes duo to their large time delay and complex internal connection. To overcome this deficiency, multivariate time delay analysis is incorporated into the high sensitive local kernel principal com-ponent analysis. In this approach, mutual information estimation and Bayesian information criterion (BIC) are separately used to acquire the correlation degree and time delay of the process variables. Moreover, in order to achieve prediction, time series prediction by back propagation (BP) network is applied whose input is multivar-iate correlated time series other than the original time series. Then the multivariate time delayed series and future values obtained by time series prediction are combined to construct the input of local kernel principal component analysis (LKPCA) model for incipient fault prognosis. The new method has been exemplified in a sim-ple nonlinear process and the complicated Tennessee Eastman (TE) benchmark process. The results indicate that the new method has superiority in the fault prognosis sensitivity over other traditional fault prognosis methods. ? 2016 The Chemical Industry and Engineering Society of China, and Chemical Industry Press. Al rights reserved.