PLS-based EWMA fault detection strategy for process monitoring

Fault detection (FD) and diagnosis in industrial processes is essential to ensure process safety and maintain product quality. Partial least squares (PLS) has been used successfully in process monitoring because it can effectively deal with highly correlated process variables. However, the conventional PLS-based detection metrics, such as the Hotelling's T² and the Q statistics are ill suited to detect small faults because they only use information from the most recent observations. Other univariate statistical monitoring methods, such as the exponentially weighted moving average (EWMA) control scheme, has shown better abilities to detect small faults. However, EWMA can only be used to monitor single variables. Therefore, the main objective of this paper is to combine the advantages of the univariate EWMA and PLS methods to enhance their performances and widen their applicability in practice. The performance of the proposed PLS-based EWMA FD method was compared with that of the conventional PLS FD method through two simulated examples, one using synthetic data and the other using simulated distillation column data. The simulation results clearly show the effectiveness of the proposed method over the conventional PLS, especially in the presence of faults with small magnitudes.     

A new fault detection method for non-Gaussian process based on robust independent component analysis

Conventional fault detection method based on fast independent component analysis (FastICA) is sensitive to outliers in the modeling data and thus may perform poorly under the adverse effects of outliers. To solve such problem, a new fault detection method for non-Gaussian process based on robust independent component analysis (RobustICA) is proposed in this paper. A RobustICA algorithm which can effectively reduce the effects of outliers is firstly developed to estimate the mixing matrix and extract non-Gaussian feature called independent components (ICs) by robust whitening and robust determination of the maximum non-Gaussian directions. Furthermore, a monitoring statistic for each extracted IC is constructed to detect process faults. Simulations on a simple example of the mixing matrix estimation and a fault detection example in the continuous stirred tank reactor system demonstrate that the RobustICA achieves much higher estimation accuracy for the mixing matrix and the ICs than the commonly used FastICA algorithm, and the RobustICA-based fault detection method outperforms the conventional FastICA-based fault detection method in terms of the fault detection time and fault detection rate.     

一种新的基于图模型的间歇过程故障监测方法

目前多元统计方法被广泛用于间歇过程故障监测并已经取得了比较好的效果。但是,统计模型的可解释性能比较差,很难直接利用操作人员积累的安全经验。为应对这些不足,提出了一种基于图模型的间歇过程故障监测方法。利用提出的定性建模方法,过程机理及操作人员的安全经验能够方便地表达。利用在线的过程变量数据和正向推理算法推断生产应处于的状态,利用安全知识及时地发现生产异常。当推断的结论与在线测得的结果矛盾或过程变量超过设定的安全限时,给出解释性输出。通过一个间歇反应案例,验证了提出的方法在模型的可解释性和利用安全经验方面的优势。     

A hybrid approach to faults detection and diagnosis in batch and semi-batch reactors by using EKF and neural network classifier

This work deals with a new hybrid approach for the detection and diagnosis of faults in different parts of fed-batch and batch reactors. In this paper, the fault detection method is based on the using of Extended Kalman Filter (EKF) and statistical test. The EKF is used to estimate on-line in added to the state of reactor the overall heat transfer coefficient (U). The diagnosis method is based on a probabilistic neural network classifier. The Inputs of the probabilistic classifier are the input–output measurements of reactor and the parameter U estimated by EKF, while the outputs of the classifier are fault types in reactor. This new approach is illustrated for simulated as well as experimental data sets using two cases of reactions: the first is the oxidation of sodium thiosulfate by hydrogen peroxide and the second is alkaline hydrolyse of ethyl benzoate in homogeneous hydro-alcoholic. Finally, the combination of the estimated parameter U using EKF and probabilistic neural network classifier provided the best results. These results show the performance of the proposed approach to monitoring the semi-batch and batch reactors.     

Model selection and fault detection approach based on Bayes decision theory: Application to changes detection problem in a distillation column

The fault detection of industrial processes is very important for increasing the safety, reliability and availability of the different components involved in the production scheme. In this paper, a fault detection (FD) method is developed for nonlinear systems. The main contribution consists in the design of this FD scheme through a combination of the Bayes theorem and a neural adaptive black-box identification for such systems. The performance of the proposed fault detection system has been tested on a real plant as a distillation column. The simplicity of the developed neural model of normal condition operation, under all regimes (i.e. steady-state and unsteady state), used in this case is realised by means of a NARX (Nonlinear Auto-Regressive with eXogenous input) model and by an experimental design. To show the effectiveness of proposed fault detection method, it was tested on a realistic fault of a distillation plant of laboratory scale.     

Simulation-based fault propagation analysis—Application on hydrogen production plant

Recently production of hydrogen from water through the Cu–Cl thermochemical cycle is developed as a new technology. The main advantages of this technology over existing ones are higher efficiency, lower costs, lower environmental impact and reduced greenhouse gas emissions. Considering these advantages, the usage of this technology in new industries such as nuclear and oil is increasingly developed. Due to hazards involved in hydrogen production, design and implementation of hydrogen plants require provisions for safety, reliability and risk assessment. However, very little research is done from safety point of view. This paper introduces fault semantic network (FSN) as a novel method for fault diagnosis and fault propagation analysis by using evolutionary techniques like genetic programming (GP) and neural networks (NN), to uncover process variables’ interactions. The effectiveness, feasibility and robustness of the proposed method are demonstrated on simulated data obtained from the simulation of hydrogen production process in Aspen HYSYS^®. The proposed method has successfully achieved reasonable detection and prediction of non-linear interaction patterns among process variables.     

Integration of techniques for early fault detection and diagnosis for improving process safety: Application to a Fluid Catalytic Cracking refinery process

In this paper we show the integration of techniques for early fault detection and diagnosis of operational faults in industrial processes, and we show an application example in a Fluid Catalytic Cracking refinery process. The early fault detection and diagnosis allow the operators in an industrial process to take the best actions during the real state of the process, avoiding incipient faults to scale to critical situations where there is risk of human lives and economical lost.     

基于随机森林的阻变型通风网络故障诊断方法*

为了在矿井通风网络发生阻变型故障时,能够快速准确判断出故障位置和故障量,提出1种基于随机森林的通风网络故障位置和故障量诊断方法。利用矿井通风仿真系统IMVS将唐安矿模拟故障生成空间数据集并进行数据预处理,构建基于随机森林的故障诊断模型,并利用该诊断模型对唐安矿矿井通风网络模拟故障位置和故障量进行判断和预测。引用多种方法对模型进行度量,通过唐安矿模拟实验验证基于随机森林的故障诊断模型的有效性。将随机森林和决策树的故障诊断准确率进行对比,研究结果表明:随机森林较决策树故障准确率有进一步的提高,并发现故障地点失误诊断多是相邻巷道,在一定程度上工作人员对故障地点的判断并不受其影响。     

基于模糊Petri网的有载分接开关故障诊断方法研究*

为解决分接开关故障诊断以主观经验、缺乏系统化流程以及诊断结果与分接开关实际发生故障存在偏差等问题,依据当前分接开关主要故障分类,提出基于模糊Petri网的有载分接开关故障诊断模型,并结合分接开关典型故障案例,验证模型有效性。研究结果表明:基于模糊Petri网的分接开关故障诊断模型能够有效处理故障概率中不确定性因素,具有容错性好、运行效率高等优势,研究结果可为提高分接开关故障诊断的准确性、保障电力系统安全稳定运行提供参考。     

Evaluation of EHS hazard and sustainability metrics during early process design stages using principal component analysis

A principal component analysis (PCA) based methodology accounting for EHS hazard and sustainability metrics has been recently proposed in literature (Srinivasan and Nhan, 2008) to deal with the subjective weighting problem of existing index-based methods. In this study we evaluate the potential use of the PCA-based method during early phases of process design in the problem of selection between various synthesis paths, also called chemical routes, for the production of chemical compounds. The study also focuses on the impact of the methodology settings on the obtained chemical route rankings and their interpretation. Two case studies have been performed regarding the production of 4-(2-methoxyethyl)-phenol (MEP) and methyl methacrylate (MMA) using fifteen different evaluation categories capturing various sustainability metrics. The PCA-based method identified the most promising chemical routes as well as the most important evaluation categories. The necessity for normalization of the raw data was demonstrated, without the method being very sensitive to the type of normalization. Moreover, the effect of the transition approach from chemical step to chemical route scores is discussed. The results of the PCA-based method are also compared with an index-based method (Koller et al., 2000) sharing the same evaluation categories, as well as with other index-based frameworks in order to reveal the extent of similarities.     

An integrated off-on line approach for increasing stability and effectiveness of automated controlled systems based on pump dependability—case study: Offshore industry

Automated controlled systems are vulnerable to faults. Faults can be amplified by the closed loop control systems and they can develop into malfunction of the loop. A control loop failure will easily cause production stop or malfunction at a petrochemical plant. A way to achieve a stable and effective automated system is to enhance equipment dependability. This paper presents a standard methodology for the analysis and improvement of pump performance to enhance total operational effectiveness and stability in offshore industry based on dependability. Furthermore, it is shown how a reliability–safety analysis can be conducted through equipment dependability indicators to facilitate the mitigation of hazard frequency in a plant. The main idea is to employ principle component analysis (PCA) and importance analysis (IA) to provide insight on the pumps performance. The pumps of offshore industries are considered according to OREDA classification. The approach identifies the critical pump and their fault through which the major hazards could initiate in the process. At first PCA is used for assessing the performance of the pumps and ranking them. IA is then performed for the worst pump which could have most impact on the overall system effectiveness to classify their components based on the component criticality measures (CCM). The analysis of the classified components can ferret out the leading causes and common-cause events to pave a way toward improving pump performance through design optimization and online fault detection which ultimately enhance overall operational effectiveness.     

基于迭代退火算法的高压变频器功率单元频繁故障诊断方法研究*

现有的变压器故障诊断方法较为复杂且计算冗余度较高,在高压变频器的功率单元频繁发生故障时难以高效地检测故障。为此,提出基于迭代退火算法的高压变频器功率单元频繁故障诊断方法。采用小波包分解方法提取高压变频器功率单元的电压信号特征熵,将该特征熵输入到支持向量机模型。使用迭代退火算法优化支持向量机的训练参数,并输出诊断结果。研究结果表明:该方法提取的高压变频器单元故障的平均冗余度最低至3.2%,平均诊断时间为15.1 ms,可实现高压变频器功率单元频繁故障的高效诊断。     

A sequential probability ratio test (SPRT) to detect changes and process safety monitoring

Detecting anomalies is an important problem that has been widely researched within diverse research areas and application domains. The early detection of faults may help avoid product deterioration, major damage to the machinery itself and damage to human health. This study proposes a robust fault detection method with an Artificial Neural Network-Multi-Layer Perceptron (ANN-MLP) and a statistical module based on Wald's sequential probability ratio test (SPRT). To detect a fault, this method uses the mean and the standard deviation of the residual noise obtained from applying a NARX (Nonlinear Auto-Regressive with eXogenous input) model. To develop the neural network model, the required training and testing data were generated at different operating conditions. To show the effectiveness of the proposed fault detection method, it was tested on a realistic fault of a distillation plant at the laboratory scale.     

基于KPLS数据重构的非线性过程监测与故障辨识

为适应快速变化的化工产品需求,过程工业逐步向柔性生产发展,使得间歇过程的应用日益广泛。这一类工艺过程具有动态和非线性的特征,过程故障带来的工艺波动和安全风险是较为突出的挑战。采用基于核函数的偏最小二乘方法,在高维特征空间提取特征变量,这些变量包含了生产过程的非线性结构特征,也反应了过程工况的模式特征。针对传统线性方法存在的故障漏报等问题,利用核函数技巧,在特征空间进行数据重构,进而计算统计监控指标SPE,并通过对SPE的在线监测实现更加有效地故障辨识。本方法针对标准非线性测试对象进行了过程监测,实现结果充分说明了方法的有效性。     

基于Petri网的750kV变电站故障恢复

对750 kV变电站可能发生的常见故障进行详细分类,并据此建立故障恢复推理模型,以便发生故障时能及时快速恢复供电。通过分析750 k V变电站拓扑结构,采用故障分类和基于Petri网建模的方法,将所有可能发生的常见故障分为母线、线路及变压器3类。变电站发生故障时,先根据变电站故障诊断结果,再从故障点隔离到恢复非故障失电区域并建立Petri网模型。故障恢复主要对开关进行操作,因此首先建立开关打开和关断的基本Petri网恢复模块,接着从变压器运行方式及裕量情况给出变压器故障恢复的Petri网模型,然后讨论母线和线路故障时不同情况下的故障恢复Petri网模型,最后根据模型推理过程中点火的变迁,将隔离故障点和恢复供电的断路器记录下来,按照Petri网运行的顺序即可给出最终的恢复方案。通过对750 k V变电站各类复杂故障的建模和推理及由此给出的恢复方案,能够及时给出恢复的操作顺序,方便运行人员快速检修。最后通过HPSim软件对代表性故障进行仿真运行,验证该方法正确、可行且及时。     

基于深度学习的输煤皮带故障视觉检测方法研究

为了更好地检测皮带跑偏、撕裂和异物干扰等严重影响皮带安全运行的故障状态,围绕相关问题产生的原因及检测方法开展深入研究,通过对纵/横向裂缝、异物的检测分析、实验,提高基于视觉的检测精度。提出基于Canny边缘检测算法的皮带跑偏检测算法;基于深度学习的横向与纵向撕裂检测,尤其对于裂缝与纵向纹理区分不明显情况,提出一种红光透射的判别方式;基于最小距离分类算法将识别异物转换为分类问题,利用机器学习的方法对样本进行训练并建立无异物阈值,通过提取特征,最后利用最小距离分类算法得到有无异物的结果。研究结果表明:提出的视觉检测系统可以实时高效地检测出输煤皮带常见的3种故障,可进一步保障运输系统安全运行。     

基于深度置信网络的管网泄漏故障诊断方法研究

针对当前管网系统数据量大不利于传统模型方法诊断故障的问题，设计了1种基于深度置信网络的管网故障诊断算法。首先，对管网数据结构以及管网系统运行状态进行分析，选取管网主要数据作为故障诊断网络的输入，确定相应运行状态作为诊断网络输出；其次，设计了基于多个受限制玻尔兹曼机与Softmax分类器级联的深度置信网络，并且利用对比散度算法和BP算法对模型进行预训练与调优，使模型参数达到全局最优；最后，通过实验测试确定所设计的深度置信网络的训练迭代次数与网络层数，使算法诊断准确率达到最优。研究结果表明:提出的基于深度置信网络的管网故障诊断算法对管网故障诊断可以达到良好的诊断结果，泄漏预测准确率在验证集样本上可达96.87%，在管网泄漏检测方面，相较于传统基于模型的方法优势明显。     

一种改进的CSCA+PCA化工过程异常检测技术

为了解决化工过程异常检测时因参数众多且数据庞杂而导致一些异常无法被有效检出的问题,在Brownlee的克隆选择分类算法（CSCA）基础上,通过引入主成分分析（PCA）技术,进行数据降维和数据重整,探讨了人工免疫算法在化工过程异常检测中的适用效果和技术方案,以TE过程数据作为样本进行异常检测和分类实验。结果表明,过程异常数据的规模、属性的数目对CSCA异常检测效果具有明显影响,而通过主成分分析进行数据降维之后,CSCA检测效果有所提高;进一步的数据重整之后,CSCA对过程异常分类辨识的准确率可提升到85%以上;基于CSCA+PCA的数据降维及重构之后的过程异常检测技术方案,可以获得较高的异常检测准确率,从而一定程度上为化工过程安全运行提供技术保障。     

Fault diagnosis of pipeline and pump unit systems using status coupling analysis

Earlier studies on fault diagnosis of the pipeline and pump unit systems (PPU) relied mainly on independent equipment analyses, which usually lead to false alarms because of the loss of information fusion. The aim of this study is to utilize the status coupling relationship to improve fault detection sensitivity and reduce false alarm rate. A real-time status identification of related equipment step is added between capturing abnormal signals and listing out diagnosis results. For example, when the pipeline pressure fluctuation is found abnormal, a status analysis of pump units is performed immediately, if the pump units are proven to be operational normally, then the pipeline leak alarm is acknowledged valid. The logical reasoning algorithm is used to capture abnormal conditions of pipeline pressures. The pump unit faults are captured by combining information from multiple sources. Field applications show that the proposed method significantly improves the PPU fault detection capability on fault detection sensitive and accuracy.     

A review on different pipeline fault detection methods

Pipeline faults like leakage and blockage always create problem for engineers. Detection of exact fault quantity and its location is necessary for smooth functioning of a plant or industry and safety of the environment. In this paper brief discussion is made on various pipeline fault detection methods viz. Vibration analysis, Pulse echo methodology, Acoustic techniques, Negative pressure wave based leak detection system, Support Vector Machine (SVM) based pipeline leakage detection, Interferometric fibre sensor based leak detection, Filter Diagonalization Method (FDM), etc. In this paper merit and demerits of all methods are discussed. It is found that these methods have been applied for specific fluids like oil, gas and water, for different layout patterns like straight and zigzag, for various lengths of pipeline like short and long and also depending on various operating conditions. Therefore, a comparison among all methods has been done based on their applicability. Among all fault detection methods, Acoustic reflectometry is found most suitable because of its proficiency to identify blockages and leakage in pipe as small as 1% of its diameter. Moreover this method is economical and applicable for straight, zigzag and long, short length pipes for low, medium and high density fluid.