Phase partition and KPI-related process monitoring for batch processes using a novel canonical correlation analysis strategy

Key performance indicators (KPI)-related process monitoring has been of great significance to ensure product quality and economic benefits for batch processes. Considering that different phases exhibit different characteristics, one of the key issues is how to partition the whole batch process into different phases and characterize them separately by multiple phase models. In order to model and monitor batch processes more accurately and efficiently, a novel canonical correlation analysis (CCA) strategy is proposed in this paper. The phase partition algorithm is designed based on the joint canonical variable matrix (JCVM). Different from previous methods, it considers the time sequence of operation phases and can distinguish the phase switches from dynamics anomalies. Using this algorithm, phases are separated in order from a KPI-related perspective, revealing high correlation among variables. After phase partition, a novel multi-phase local neighbourhood standardization CAA (MPLNSCCA) method focusing on KPI is set up for online monitoring, which could further address the misclassification problems. The advantages of the proposed method are illustrated by two case studies, a penicillin simulation platform and an industrial application of Escherichia coli fermentation, respectively.     

基于联合典型变量矩阵的多阶段发酵过程质量相关故障监测

为考虑发酵过程的质量变量和动态特征对于阶段划分的影响,提出了一种基于联合典型变量矩阵的多阶段发酵过程质量相关故障监测方法。首先,将历史三维数据沿批次方向展开,对每个时间片矩阵进行典型相关分析（canonical correlation analysis, CCA）,得到融合过程变量和质量变量信息的联合典型变量矩阵,对其进行K均值聚类,实现基于静态特征的第1步划分;然后采用慢特征分析（slow feature analysis, SFA）算法提取表征过程动态性的慢特征,对其进行聚类实现第2步划分。最后综合分析两步划分结果,将生产过程划分为不同的稳定阶段和过渡阶段,并在划分的子阶段中分别建立CCA监测模型进行质量相关故障监测。该方法通过静态和动态特征的变化实现两步划分,准确区分强动态变化与阶段切换,有效提高质量相关的故障监测模型精度。青霉素仿真平台与大肠杆菌实际生产数据验证了所提方法的可行性和有效性。     

Between‐phase‐based statistical analysis and modeling for transition monitoring in multiphase batch processes

Between‐phase transition analysis and monitoring are a critical problem in multiphase (MP) batch processes. An improved statistical analysis, modeling, and monitoring strategy are proposed for MP processes with between‐phase transition. It is realized that between‐phase transition may show complex “irregular dynamics” over different batches. That is, transition patterns may follow different trajectories with different durations and reveal different characteristics in different batch cycles. Phase centers are defined to capture the transition irregularity, and the relationship between two neighboring phase centers is analyzed by performing between‐phase analysis. Two different subspaces are thus separated in each phase, driven by the phase‐common and dependent correlations, respectively. The basic assumption is that despite their different operation patterns, the two neighboring phases share a certain common correlations immune to phase shift. Then, reconstruction‐based transition identification algorithm is designed, by which, between‐phase transition can be supervised automatically and dynamically without the need of transition model development. The proposed method captures the between‐phase transition from a new viewpoint. Its feasibility and performance are illustrated with a practical case. © 2011 American Institute of Chemical Engineers AIChE J, 2012     

Quality‐relevant fault diagnosis with concurrent phase partition and analysis of relative changes for multiphase batch processes

Multiplicity of phases as indicated by changes of process characteristics is an inherent nature of many batch processes for both normal and fault cases. To more efficiently perform online fault diagnosis via reconstruction for multiphase batch processes, the phase nature and the relationship between normal and fault cases within each phase should be deeply addressed. This article proposes a quality‐relevant fault diagnosis strategy with concurrent phase partition and analysis of relative changes for multiphase batch processes. First, a concurrent phase partition algorithm is developed. The basic idea is to track the changes of process characteristics at normal and fault statuses jointly so that multiple sequential modeling phases are identified simultaneously for both normal and fault cases. Then, the relative changes from the normal status to each fault case are analyzed in each phase to reveal the specific fault effects more efficiently. The fault effects are decomposed in two different monitoring subspaces, principal subspace, and residual subspace, by capturing their different roles in removing out‐of‐control signals. The significant increases relative to the normal case are judged to be responsible for the concerned alarm monitoring statistics in each phase. The others are composed of general variations that are deemed to still follow normal rules and thus insignificant to remove alarm monitoring statistics. Those alarm‐responsible fault deviations are then used to develop reconstruction models which can more efficiently recover the fault‐free part for online fault diagnosis. The proposed algorithm is illustrated with a typical multiphase batch process with one normal case and three fault cases. © 2014 American Institute of Chemical Engineers AIChE J, 60: 2048–2062, 2014     

基于奇异值识别的模式切换过程递归PCA监控

常规的PCA方法难于对发生模式变化的过程参数进行监控,为此,本文提出了一种基于奇异值识别递归PCA技术,用于解决多模式切换过程的监控问题。首先建立了在线奇异值识别算法,通过识别奇异值的变化可以准确判断过程发生模式切换的时间,然后采用递归PCA对过程的模式切换过渡阶段进行监控。将TE过程用于实例研究,验证了所提出方法的有效性。     

Multivariate statistical monitoring of multiphase batch processes with between‐phase transitions and uneven operation durations

In order to achieve satisfactory monitoring, multivariate statistical process models should well reflect process nature. In manufacturing systems, many batch processes are inherently multiphase. Usually, different phases have different characteristics, while gradual transitions are often observed between phases. Another important feature of batch processes is the unevenness of operation durations. Especially, in multiphase batch processes, the situation becomes more complicated. In this study, a batch process modelling and monitoring strategy is proposed based on Gaussian mixture model (GMM), which can automatically extract phase and transition information for uneven‐duration batch processes. The application results verify the effectiveness of the proposed method. © 2011 Canadian Society for Chemical Engineering     

Concurrent phase partition and between‐mode statistical analysis for multimode and multiphase batch process monitoring

The exiting automatic phase partition and phase‐based process monitoring strategies are in general limited to single‐mode multiphase batch processes. In this article, a concurrent phase partition and between‐mode statistical modeling strategy (CPPBM) is proposed for online monitoring of multimode multiphase batch processes. First, the time‐varying characteristics of batch processes are concurrently analyzed across modes so that multiple sequential phases are simultaneously identified for all modes. The feature is that both time‐wise dynamics and mode‐wise variations are considered to get the consistent phase boundaries. Then within each phase, between‐mode statistical analysis is performed where one mode is chosen for the development of reference monitoring system and the relative changes from the reference mode to each alternative mode are analyzed. From the between‐mode perspective, each of the original reference monitoring subspaces, including systematic subspace and residual subspace, are further decomposed into two monitoring subspaces for each alternative mode, which reveal two kinds of between‐mode relative variations. The part which shows significant increases represents the variations that will cause alarm signals if the reference models are used to monitor the alternative modes, whereas the part that shows no increases will not issue alarms. By modeling and monitoring different types of between‐mode relative variations, the proposed CPPBM method can not only efficiently detect faults but also offer enhanced process understanding. It is illustrated with a typical multiphase batch process with multiple modes. © 2013 American Institute of Chemical Engineers AIChE J 60: 559–573, 2014     

Density peaks clustering-based steady/transition mode identification and monitoring of multimode processes

Multimode is the characteristic of industrial manufacturing processes due to different production strategies and environments. For multimode process monitoring, it is a challenge to identify different steady modes and transition modes. In this paper, a k nearest neighbours (KNN)-based density peaks clustering (DPC) method is applied to identify different modes. First, the local density of each sample, which is obtained with a KNN constraint and its minimum distance to the higher local density points are calculated as two indicators of the DPC algorithm to find the cluster centres of the training data. Then, the transition modes are identified by combining the moving window strategy and the DPC algorithm, where an index called the local density-distance ratio (LDDR) is employed. Finally, the monitoring algorithm is used to detect the faults for each operation mode. The effectiveness and advantages of the proposed method are illustrated by a numerical example and a Tennessee Eastman (TE) benchmark process.     

基于时段过渡分析的多时段间歇过程质量预测(英文)

Batch processes are usually involved with multiple phases in the time domain and many researches on process monitoring as well as quality prediction have been done using phase information. However, few of them consider phase transitions, though they exit widely in batch processes and have non-ignorable impacts on product qualities. In the present work, a phase-based partial least squares (PLS) method utilizing transition information is proposed to give both online and offline quality predictions. First, batch processes are divided into several phases using regression parameters other than prior process knowledge. Then both steady phases and transitions which have great influences on qualities are identified as critical-to-quality phases using statistical methods. Finally, based on the analysis of different characteristics of transitions and steady phases, an integrated algorithm is developed for quality prediction. The application to an injection molding process shows the effectiveness of the proposed algorithm in comparison with the traditional MPLS method and the phase-based PLS method.     

Enhanced high-order information extraction for multiphase batch process fault monitoring

Conventional independent component analysis (ICA) monitoring methods extract the feature information of process data by selecting more important independent components (ICs), which discard a small part of ICs that may contain useful information for faults, leading to unsatisfactory monitoring results. However, when the number of sampling points is greater than that of process variables, the ICA monitoring model does not work well. To address the aforementioned problems, a novel monitoring method, multiphase enhanced high-order information extraction (MEHOIE), is proposed in this paper. The entire production process was first divided into several steady phases and transition phases by the affinity propagation (AP) phase partitioning method. The enhanced high-order information extraction (EHOIE) model was then built in each phase for fault monitoring. Finally, the algorithm was applied in the penicillin simulation platform and industrial microbial pharmaceutical process. The flexibility and superiority of this algorithm were verified by comparing it with other conventional methods.     

An improved artificial bee colony algorithm for steelmaking–refining–continuous casting scheduling problem

Steelmaking–refining–Continuous Casting(SCC) scheduling is a worldwide problem, which is NP-hard. Effective SCC scheduling algorithms can help to enhance productivity, and thus make significant monetary savings. This paper develops an Improved Artificial Bee Colony(IABC) algorithm for the SCC scheduling. In the proposed IABC, charge permutation is employed to represent the solutions. In the population initialization, several solutions with certain quality are produced by a heuristic while others are generated randomly. Two variable neighborhood search neighborhood operators are devised to generate new high-quality solutions for the employed bee and onlooker bee phases, respectively. Meanwhile, in order to enhance the exploitation ability, a control parameter is introduced to conduct the search of onlooker bee phase. Moreover, to enhance the exploration ability,the new generated solutions are accepted with a control acceptance criterion. In the scout bee phase, the solution corresponding to a scout bee is updated by performing three swap operators and three insert operators with equal probability. Computational comparisons against several recent algorithms and a state-of-the-art SCC scheduling algorithm have demonstrated the strength and superiority of the IABC.     

Between‐phase calibration modeling and transition analysis for phase‐based quality interpretation and prediction

The quality‐concerned between‐phase transition analysis is performed and an improved calibration modeling strategy is designed for quality prediction and interpretation in multiphase batch processes. From the between‐phase viewpoint, the quality‐related phase behaviors are decomposed and two subspaces are separated. In common subspace, the underlying quality‐relevant variation stays invariable between the neighboring phases, showing the common contribution to quality. The other part changes with the alternation of phases and has the different influences on quality interpretation, termed specific subspace here. Based on subspace separation, between‐phase transition regions are distinguished from steady phases. Different models are developed in steady phases and transition regions respectively for online quality prediction. Offline quality analyses are also conducted in two subspaces to explore the time cumulative effects. The proposed method gives an interesting insight into the phase behaviors and between‐phase transitions for quality prediction. The feasibility and performance of the proposed method are illustrated with a typical multiphase batch process. © 2012 American Institute of Chemical Engineers AIChE J, 59: 108–119, 2013     

Polymerizable oil‐in‐oil emulsions: poly(vinyl pyrrolidone) dispersions in reactive PDMS medium

The system N‐vinyl‐2‐pyrrolidone (VP)/polydimethylsiloxane diglycidylether (PDMS‐DGE) is a typical example of an oil‐in‐oil emulsion formed by two non‐miscible liquids, where both phases are polymerizable in a ‘one‐pot’ procedure by two distinct reaction mechanisms. These oil‐in‐oil emulsions were characterized by their stability and by the particle size of the dispersed VP phase. Non‐aqueous dispersions (NADs) are obtained in a first step by free radical polymerization of the dispersed VP phase. The reaction kinetics, studied as a function of the initiator type and concentration, show that the polymerization rate is mainly influenced by the partition coefficient of the initiator between both phases. The NAD particle size could be tailored from a micrometer to a nanometer range by in situ formation of PVP‐PDMS graft copolymer. Hydrophilic–hydrophobic two‐phase materials can be obtained by polycondensation, in the presence of polyamines, of the epoxy‐functionalized PDMS continuous NAD phase. Copyright © 2007 Society of Chemical Industry     

油水界面测量过程中自适应阈值聚类优化算法

精确检测原油储罐内油水界面及液位高度是保证净油外输含水率控制精度及联合站盘库系统计量精度的前提条件，是石油化工过程系统工程中的重要环节。鉴于油水界面测量过程中传统分类统计算法和经典K-means聚类算法存在依赖人工选取典型值和初始聚类质心、计算结果不确定性以及精度难于保证等问题，本文提出了一种改进的K-means自适应阈值聚类优化算法。该算法能自动获取最优初始阈值，并改进了油水界面测量传统分类统计算法和经典K-means聚类算法的思想，可实现最优数据分类。首先采用自适应阈值查找算法自动查找油水界面最优初始阈值，其次采用改进K-means聚类优化算法对油水界面数据进行最优划分，最后根据最优化聚类结果计算油水界面及液位高度。实验结果表明：相对于油水界面测量的传统分类统计算法和经典K-means聚类算法, 该算法无需人工选值、能够完全保证计算结果的准确性，且比经典K-means聚类算法和其他改进K-means聚类算法所需的迭代次数更少、运行时间更短。     

基于信息增量矩阵的多阶段间歇过程质量预测

针对间歇过程划分阶段方法很少考虑过程的时序性和动态特性,易将时间上不连续但具有相似特征的样本划分到同一阶段,影响建模精确性的问题,提出一种基于信息增量矩阵-偏最小二乘（information increment matrix-partial least square,ⅡMPLS）的多阶段间歇过程质量预测方法。将历史三维数据沿批次方向展开为二维数据,将其切分成融合质量变量的扩展时间片,依据扩展时间片的信息增量使用滑动窗划分阶段,对各个阶段内数据建立PLS模型进行质量预测。该方法考虑变量之间的相关关系沿采样时刻的变化,利用信息增量捕获系统的动态特性并时序地划分阶段。青霉素仿真平台与大肠杆菌实际生产数据验证了方法的可行性和有效性。     

Nonlinear quality prediction for multiphase batch processes

Typically, a multiphase batch process comprises several steady phases and transition periods. In steady phases, the data characteristics remain similar during the phase and have a significant repeatability from batch to batch; thus most data nonlinearities can be removed through the batch normalization step. In contrast, in each transition period, process observations vary with time and from batch to batch, so nonlinearities in the data may not be eliminated through batch normalization. To improve quality prediction performance, an efficient nonlinear modeling method—relevance vector machine (RVM) was introduced. RVMs were formulated for each transition period of the batch process, and for combining the results of different process phases. For process analysis, a phase contribution index and a variable contribution index are defined. Furthermore, detailed performance analyses on the prediction uncertainty and variation were also provided. The effectiveness of the proposed method is confirmed by an industrial example. © 2011 American Institute of Chemical Engineers AIChE J, 58: 1778–1787, 2012     

Separation of some metal ions by high performance centrifugal partition chromatography with di‐2‐methylnonylphosphoric acid

The separation of such metal ions as Cu(II), Mn(II), Co(II), Ni(II), Mg(II) and Ca(II) has been investigated by high performance centrifugal partition chromatography (HPCPC) employing di‐2‐methylnonylphosphoric acid/heptane as a stationary phase. The four transition metal ions have mutually been separated by the two‐step elution method, changing the pH of the chloroacetic acid mobile phase, and the two alkaline earth metal ions have been separated by an isocratic elution. The HPCPC system was operated with 2136 partition channels, at a rotation speed of 800 rpm, and at a flow rate of 2.0 cm³ min^?1. The elution curve was obtained by monitoring the absorbance of each metal complex post‐labeled with chromogenic compounds. Copyright © 2003 Society of Chemical Industry     

A QUASI-NEWTON ALGORITHM FOR SOLVING MULTIPHASE EQUILIBRIUM FLASH PROBLEMS

A new algorithm has been developed for solving the multicomponent vapor-liquid-liquid equilibrium Mash problem. The algorithm is an extension of the “inside-out” approach proposed by Boston and Britt for the vapor-liquid equilibrium flash problem.

Conventional flash algorithms use temperature, pressure, composition, and phase fraction as the problem independent variables, In the inside-out approach a new set of independent variables is introduced in place of the conventional variables. The new variables are chosen to be as independent as possible of the conventional variables and as free as possible of mutual interaction. Complex phase equilibrium models are used only to generate parameters for a simple equilibrium ratio model. These parameters become the problem independent variables. The Quasi-Newton method of Broyden is employed to promote convergence of these variables.

The algorithm first obtains a solution for the vapor-liquid equilibrium flash. By examining the liquid phase, a heuristic algorithm is employed which quickly locates a two liquid phase composition region of reduced total system free energy when the original liquid is unstable. The solution of the vapor-liquid-liquid equilibrium flash is initiated only when this occurs.

The performance of the algorithm is demonstrated by a number of problems which exhibit varying degrees of nonideality.     

A QUASI-NEWTON ALGORITHM FOR SOLVING MULTIPHASE EQUILIBRIUM FLASH PROBLEMS

A new algorithm has been developed for solving the multicomponent vapor-liquid-liquid equilibrium Mash problem. The algorithm is an extension of the “inside-out” approach proposed by Boston and Britt for the vapor-liquid equilibrium flash problem.

Conventional flash algorithms use temperature, pressure, composition, and phase fraction as the problem independent variables, In the inside-out approach a new set of independent variables is introduced in place of the conventional variables. The new variables are chosen to be as independent as possible of the conventional variables and as free as possible of mutual interaction. Complex phase equilibrium models are used only to generate parameters for a simple equilibrium ratio model. These parameters become the problem independent variables. The Quasi-Newton method of Broyden is employed to promote convergence of these variables.

The algorithm first obtains a solution for the vapor-liquid equilibrium flash. By examining the liquid phase, a heuristic algorithm is employed which quickly locates a two liquid phase composition region of reduced total system free energy when the original liquid is unstable. The solution of the vapor-liquid-liquid equilibrium flash is initiated only when this occurs.

The performance of the algorithm is demonstrated by a number of problems which exhibit varying degrees of nonideality.     

DNA Double Helix Based Hybrid GA for the Gasoline Blending Recipe Optimization Problem

A hybrid genetic algorithm is proposed for heavily nonlinear constrained optimization problems by utilizing the global exploration and local exploitation characteristics, and the convergence rate of the proposed algorithm is analyzed. In the global exploration phase, a DNA double helix structure is used to overcome Hamming cliffs and DNA computing based operators are applied to improve the global searching capability. When the feasible domains are located, the sequential quadratic programming (SQP) method is performed to quickly find the local optimum and improve the solution accuracy. The comparison results of typical numerical examples and the gasoline blend recipe optimization problem are employed to demonstrate the reliability and efficiency of the proposed algorithm.