An on-line framework for monitoring nonlinear processes with multiple operating modes

A multivariate statistical process monitoring scheme should be able to describe multimodal data. Multimodality typically arises in process data due to varying production regimes. Moreover, multimodality may influence how easy it is for process operators to interpret the monitoring results. To address these challenges, this paper proposes an on-line monitoring framework for anomaly detection where an anomaly may either indicate a fault occurring and developing in the process or the process moving to a new operating mode. The framework incorporates the Dirichlet process, which is an unsupervised clustering method, and kernel principal component analysis with a new kernel specialized for multimode data. A monitoring model is trained using the data obtained from several healthy operating modes. When on-line, if a new healthy operating mode is confirmed by an operator, the monitoring model is updated using data collected in the new mode. Implementation issues of this framework, including the parameter tuning for the kernel and the selection of anomaly indicators, are also discussed. A bivariate numerical simulation is used to demonstrate the performance of anomaly detection of the monitoring model. The ability of this framework in model updating and anomaly detection in new operating modes is shown on data from an industrial-scale process using the PRONTO benchmark dataset. The examples will also demonstrate the industrial applicability of the proposed framework.     

Process pattern construction and multi-mode monitoring

A novel framework for process pattern construction and multi-mode monitoring is proposed. To identify process patterns, the framework utilizes a clustering method that consists of an ensemble moving window strategy along with an ensemble clustering solutions strategy. A new k-independent component analysis-principal component analysis (k-ICA-PCA) modeling method captures the relevant process patterns in corresponding clusters and facilitates the validation of ensemble solutions. Following pattern construction, the proposed framework offers an adjoined multi-ICA-PCA model for detection of faults under multiple operating modes. The Tennessee Eastman (TE) benchmark process is used as a case study to demonstrate the salient features of the method. Specifically, the proposed method is shown to have superior performance compared to the previously reported k-PCA models clustering approach.     

Real-time monitoring for a process with multiple operating modes

The real-time monitoring of a chemical process with multiple operating modes is a challenging problem. The frequent changes of operating modes require frequent updates of the monitoring models, which lead to frequent pauses in the real-time monitoring activities. This paper proposes a monitoring methodology for a process with multiple operating modes, based on hierarchical clustering and a super PCA model. The case studies show that the super PCA model performs better than a single PCA model for all operating modes, or local PCA models developed for each operating mode.     

多模态过程的全自动离线模态识别方法

多模态是复杂工业生产过程的普遍特性.不同模态具有不同的过程特性,需要建立不同的模型,因此离线建模数据的模态划分与识别是整个多模态过程建模的关键问题之一.目前,常用的聚类算法需要对其结果进行人工分析和后续处理,无法真正实现多模态过程的全自动模态识别.因此,本文提出一种全自动的多模态过程离线模态识别方法.首先通过宽度为H的大切割窗口对数据进行切割,利用改进的K-means聚类算法对窗口单元进行聚类;根据聚类结果,对稳定模态淹没现象进行处理,得到模态的初步划分结果;最终,利用小滑动窗口L,对稳定模态及过渡模态交接区域进行细划分,准确定位稳定模态与过渡模态的分割点.算法实现了多模态过程的全自动离线识别,并给出合理有效的识别结果.仿真分析表明此方法能够实现模态的自动识别,且识别结果准确.     

A new fault diagnosis method of multimode processes using Bayesian inference based Gaussian mixture contribution decomposition

This paper presents a novel Bayesian inference based Gaussian mixture contribution (BIGMC) method to isolate and diagnose the faulty variables in chemical processes with multiple operating modes. The statistical confidence intervals of traditional principal component analysis (PCA) based T² and SPE diagnostics rely upon the assumption that the operating data follow a multivariate Gaussian distribution approximately and therefore may not be able to determine the faulty variables in multimode non-Gaussian processes accurately. As an alternative solution, the proposed BIGMC method first identifies the multiple Gaussian modes corresponding to different operating conditions and then integrates the Mahalanobis distance based variable contributions across all the Gaussian clusters through Bayesian inference strategy. The derived BIGMC index is of probabilistic feature and includes all operation scenarios with posterior probabilities as weighting factors. The Tennessee Eastman process (TEP) is used to demonstrate the utility of the proposed BIGMC method for fault diagnosis of multimode processes. The comparison of the single-PCA and multi-PCA based contribution approaches shows that the BIGMC method can effectively identify the leading faulty variables with superior diagnosis capability.     

Performance monitoring of processes with multiple operating modes through multiple PLS models

Many industrial processes possess multiple operating modes in virtue of different manufacturing strategies or varying feedstock. Direct application of many of the current multivariate statistical process monitoring (MSPM) techniques such as PCA (principal component analysis) and PLS (projection to latent structures) to such a process tends to produce inferior performance. This can most be attributed to the adopted assumption by most MSPM methodologies of only one nominal operating region for the underlying process. It is therefore reasonable to develop separate models for different operating modes. In this paper, based on metrics in the form of principal angles to measure the similarities of any two models, a multiple PLS model based process monitoring scheme is proposed. Popular multivariate statistics such as SPE (squared prediction error) and T² can be incorporated in this framework straightforwardly. The proposed technique is assessed through application to the monitoring of an industrial pyrolysis furnace.     

Modeling and optimization method featuring multiple operating modes for improving carbon efficiency of iron ore sintering process

Iron ore sintering is one of the most energy-consuming processes in steelmaking. Since its main source of energy is the combustion of carbon, it is important to improve the carbon efficiency to save energy and to reduce undesired emissions. A modeling and optimization method based on the characteristics of the sintering process has been developed to do that. It features multiple operating modes and employs the comprehensive carbon ratio (CCR) as a measure of carbon efficiency. The method has two parts. The first part is the modeling of multiple operating modes of the sintering process. K-means clustering is used to identify the operating modes; and for each mode, a predictive model is built that contains two submodels, one for predicting the state parameters and one for predicting the CCR. The submodels are built using back-propagation neural networks (BPNNs). An analysis of material and energy flow, and correlation analyses of process data and the CCR, are used to determine the most appropriate inputs for the submodels. The second part of the method is optimization based on a determination of the optimal operating mode. The problem of how to reduce the CCR is formulated as a two-step optimization problem, and particle swarm optimization is used to solve it. Finally, verification of the modeling and optimization method based on actual process data shows that it improves the carbon efficiency of iron ore sintering.     

基于GMM的多工况过程监测方法

传统基于主元分析的故障检测方法大多假设工业过程只运行在1个稳定工况,数据服从单一的高斯分布。若这些方法直接用于多工况过程则将会产生大量的误检。为此,本文提出了1种基于高斯混合模型的多工况过程监测方法。首先利用PCA变换对过程数据集进行降维,在主元空间建立高斯混合模型对过程数据进行聚类,自动获取工况数和相关分布特性。然后对每个工况建立主元分析(principal component analysis,PCA)模型来描述整个运行过程数据分布的统计特性。最后在过程监测中,根据监测样本属于各个工况的概率构造综合统计量,实现对多工况过程的故障检测。TE过程的仿真结果表明,本文提出的方法与传统的PCA方法相比,能自动获取工况和精确估计各个工况的统计特性,从而能更准确及时地检测出多工况过程的各种故障。     

基于GMM的多模态过程模态识别与过程监测

多模态复杂过程的多变量、多工序、变量时变性以及模态转换时间不确定等多种原因, 导致面向多模态生产过程的监测问题十分复杂. 对此, 基于高斯混合模型的监测方法, 结合定性知识和定量知识, 解决了多模态过程监测中离线数据模态划分、稳定模态和过渡模态的监测模型建立以及在线数据的模态识别等关键问题, 最终实现了对多模态过程的监测.     

Phase analysis and statistical modeling with limited batches for multimode and multiphase process monitoring

For multimode batch processes, the conventional modeling methods in general require that sufficient batches should be available for every mode, which, however, cannot be guaranteed in practice. It may be impractical to conduct enough trial runs and wait until sufficient batches are available before development of monitoring models for each mode. Starting from limited batches, how to derive reliable process information and develop monitoring models has been an important question for successful online multimode batch process monitoring. To address this problem, this article proposes a phase analysis and statistical modeling strategy with limited batches. One mode which has obtained sufficient batches is chosen as the reference mode while the other modes which can only get limited batches work as alternative modes. Starting from limited batches, the proposed algorithm addresses two issues, concurrent phase partition and analysis of between-mode relative changes. First, for each alternative mode, generalized time-slices are constructed by combining several consecutive time-slices within a short time region to explore local process correlations. The time-varying characteristics are then concurrently analyzed across modes so that multiple sequential phases are identified simultaneously for all modes. Then phase-representative data units are arranged by variable-unfolding the conventional time-slices for the reference mode and the generalized time-slices for each alternative mode respectively. Between-mode statistical analysis is performed within each phase where the relative changes from the reference mode to each alternative mode are analyzed. From the between-mode perspective, different types of relative variations in each alternative mode are separated and modeled for online monitoring. Starting from limited batches, online batch process monitoring can be conducted, providing reliable fault detection performance. The proposed algorithm is illustrated with a typical multiphase batch process with multiple modes.     

基于工况识别的辊式淬火过程板形预报方法

板形是衡量淬火后钢板质量的重要指标之一,板形的预报对高质量钢板的持续稳定生产具有重要的指导意义.本文提出一种基于工况识别的辊式淬火过程板形预报方法,为淬火生产控制决策提供参考依据.首先对淬火过程进行特性分析;然后采用模糊C均值聚类算法对淬火过程进行工况识别,使用支持向量机建立各工况的板形预报模型,并运用改进的粒子群优化算法提高模型的精度;最后利用工业生产数据进行实验,结果验证了本文所提方法的可行性与有效性.     

Key principal components with recursive local outlier factor for multimode chemical process monitoring

Owing to various manufacturing strategies and demands of markets, chemical processes often involve multiple operating modes. How to identify mode from multimode process data collected under both stable and transitional modes is an important issue. This paper proposes a novel mode identification algorithm-recursive local outlier factor (RLOF) based on the sequential information in the time scale and the density information in the spatial scale. In this algorithm, not only the number of modes does not need to be determined in advance, but also details of mode switching can be acquired. In addition, the principal components (PCs) chosen by the variance of overall dataset in principal component analysis (PCA) cannot guarantee that all variables express information as completely as possible. Using the defined cumulative percent expression (CPE), this study chooses key PCs (KPCs) according to each variable. Moreover, fault diagnosis is realized via the contribution of every variable to key PCs. Finally, the monitoring performance is evaluated under the Tennessee Eastman (TE) benchmark and the continuous stirred tank reactor (CSTR) process.     

基于GMM和贝叶斯推理的多模态过程运行状态评价

为使综合经济效益最大化,生产过程应保持在最优运行状态等级.针对多模态过程运行状态等级优劣判断问题,提出一种运行状态等级评价方法.该方法对同一运行状态等级的多模态数据建立一个高斯混合模型(Gaussian mixture model,GMM),确保特征提取的准确性,避免模态划分问题.至于在线评价策略,本文采用贝叶斯推理,确定当前运行状态属于各等级的后验概率.并引入滑动窗口,判定当前运行状态等级,有效解决多模态过程运行状态在线评价问题.针对"非优"运行状态,本文提出一种基于变量偏导数的贡献计算方法,对导致过程运行状态等级"非优"的原因变量进行追溯.最后,通过田纳西–伊斯曼(Tennessee–Eastman,TE)过程验证所提方法的有效性.     

基于自适应高效递推规范变量分析的多模过程软传感器建模

由于多模过程中各模式间的均值和协方差发生了改变,多变量单模高斯分布的基本假设不再成立.基于递推方法的多模过程软传感器建模存在两点问题:其一,递推建模方法不能及时的跟踪多模过程的改变;其二,递推建模方法的在线计算负荷非常高.为了解决上述问题,本文提出了一种基于自适应高效递推规范变量分析的多模过程软传感器建模方法.首先,采用指数权重滑动平均来更新过去观测矢量的协方差矩阵;然后,利用基于模型输出误差范数的可变遗忘因子来跟踪多模过程的动态变化;最后,通过引入一阶干扰理论(firstorder perturbation,FOP)来实现递推奇异值分解,与常规奇异值分解相比递推奇异值算法的计算负荷显著降低.将提出的方法用于田纳西伊斯曼(tennessee eastman,TE)化工过程进行仿真验证,其结果表明了该方法的可行性和精确性.     

Multi-Model approach to discrete events systems: Application to operating mode management

In this paper, we propose a framework for designing suitable switching control decisions for discrete event systems (DES) whose structures change as they develop in different operating modes. Control decisions consist of either an event in a sequence to occur enabling an event or preventing the event from taking place disabling an event.

Our contribution enables to adopt different modeling approaches and ensures switching between all designed process models when there is commutation between the operating modes. Thus, in the context of supervisory control theory (SCT), we propose that each model automaton represents process functionning in a specific operating mode.

Specifications imposed on any operating mode could be conflicting. An attractive alternative is switching control, in which a different controller is applied to each operating mode [[2] and [15]]. Control of process functionning means that both process and specification models must be associated with one specific operating mode.

Based on supervisory control theory, our work focuses on operating mode management in particular when the process is subject to failure. The adopted approach (multi-model) assumes that only one attempted operating mode is activated at any one time, while the others are considered desactivated. The problem of commutation and tracking between all designed models (process and specification) is formalised by the proposed framework. In this context, several questions are raised. Is the process engaged in a state which is compatible with the atteined mode ? Are the specifications consistant with each starting state ?. Are the specification conflicting ? Can all defined states be reachable ?

To answer correctly these questions, a mode switching mechanism must be formalised.     

一种基于局部模型的非线性多工况过程监测方法

针对复杂工业过程中的非线性、非高斯特性以及多工况问题, 提出了一种基于局部模型的在线统计监测新方法. 首先利用局部最小二乘支持向量机回归 (Least square support vector regression, LSSVR) 模型对过程输出进行预测, 与真实的输出相比较构成残差序列. 然后利用 ICA-PCA 两步特征提取策略, 完整地提取残差的高斯和非高斯信息, 最后用三个统计量 (I2、T2 和 SPE) 对过程进行监测, 建立了一种具有非线性、非高斯特性的多工况过程在线监测算法. 通过对 TE (Tennessee Eastman) 过程的仿真研究, 验证提出的方法是可行、有效的, 并显示出了一定的故障检测能力.     

Control loop diagnosis with ambiguous historical operating modes: Part 1. A proportional parametrization approach

Control-loop performance assessment methods have been evolving over the past two decades, with many different monitor algorithms being used to single out specific problems and determine the operating mode. However, a change in operating mode may affect multiple monitors, resulting in the possibility of conflicting assessments. Data-driven Bayesian methods were previously proposed which use multiple monitors to yield probabilistic assessments; however, training data for Bayesian methods requires complete knowledge of underlying operational modes. This paper proposes an approach based on proportionality parameters θ to address the problem of incomplete mode information in the training data; values in θ can be used to fill in missing information, and by varying θ one can determine the boundaries on a probabilistic diagnosis. Two diagnostic approaches are considered: the first type is direct probability approach, which can only be applied when historical data on the operation mode is sufficient and representative. The second type is the likelihood approach which can be applied to more general cases, including when the historical data is too limited to adequately represent mode frequency. In order to represent mode frequency, the likelihood approach takes into account prior probabilities of operating modes. The proposed methods are evaluated in two simulated chemical processes.     

考虑销售方式和物流服务策略的运营模式研究

针对商家在进入大型电商平台面临的销售方式选择和物流服务策略问题,提出三种运营模式:a）转售模式,标记为A;b）代理+无平台物流模式,标记为B;c）代理+平台物流模式,标记为C。以一个电商平台和一个商家组成的分析框架为研究对象,构建两者之间的博弈模型。通过比较三种模式下的均衡结果,并结合企业的不同权力结构,发现当平台拥有绝对权力时,C模式对平台最优。当物流服务敏感系数和市场规模都较大时,B模式对拥有绝对权力的商家最优。此外,如果两者都没有绝对权力,只有当商家首先决定物流服务策略,然后平台决定销售方式时,B模式对双方最优;否则,A模式最优。本研究可为平台和商家运营模式的选择提供理论支持和决策指导。     

Multimode process monitoring with PCA mixture model

For multimode processes, Gaussian mixture model (GMM) has been applied to estimate the probability density function of the process data under normal-operational condition in last few years. However, learning GMM with the expectation maximization (EM) algorithm from process data can be difficult or even infeasible for high-dimensional and collinear process variables. To address this issue, a novel multimode process monitoring approach based on PCA mixture model is proposed. First, the PCA technique is directly applied to the covariance matrix of each Gaussian component to reduce the dimension of process variables and to obtain nonsingular covariance matrices. Then the Bayesian Ying-Yang incremental EM algorithm is adopted to automatically optimize the number of mixture components. With the obtained PCA mixture model, a novel process monitoring scheme is derived for fault detection of multimode processes. Three case studies are provided to evaluate the monitoring performance of the proposed method.