PCA-based multivariate statistical network monitoring for anomaly detection

Process Fault Diagnosis Method Based on MSPC and LiNGAM and its Application to Tennessee Eastman Process

A multivariate approach for evaluation and monitoring of water quality in mining and minerals processing industry

Combined Multivariate Statistical Process Control

Process modeling and control applied to real-time monitoring of distillation processes by near-infrared spectroscopy

Chemometric quality control of chromatographic purity

Multivariate monitoring and control schemes based on latent variable methods have been receiving increasing attention by industrial practitioners in the last 15 years. Several companies have enthusiastically adopted the methods and have reported many success stories. Applications have been reported where multivariate statistical process control, fault detection and diagnosis is achieved by utilizing the latent variable space, for continuous and batch processes, as well as, for process transitions as for example start ups and re‐starts. This paper gives an overview of the latest developments in multivariate statistical process control (MSPC) and its application for fault detection and isolation (FDI) in industrial processes. It provides a critical review of the methodology and describes how it is transferred to the industrial environment. Recent applications of latent variable methods to process control as well as to image analysis for monitoring and feedback control are discussed. Finally it is emphasized that the multivariate nature of the data should be preserved when data compression and data preprocessing is applied. It is shown that univariate data compression and reconstruction may hinder the validity of multivariate analysis by introducing spurious correlations. Copyright © 2005 John Wiley & Sons, Ltd.

This paper presents a new knowledge discovery assistance method to improve wastewater treatment plant (WWTP) operation based on multivariate statistical process control (MSPC). The proposed method combines with MSPC by principal component analysis (PCA-MSPC) and monitoring of a pre-defined performance index for efficient and stable plant operation. Fault detection and isolation (FDI) related to the performance index is selectively performed by monitoring the time series data of the performance index wherein the sample points violating the control limit of Q statistic or that of T2 statistic in PCA-MSPC are indicated. Hidden patterns of probable cause variables to deteriorate the performance index are discovered from the FDI by observing the time series data of the isolated variables. Applications of the proposed method to real WWTPs illustrate the effectiveness of the proposed method by showing possible improvement for energy-saving operation and stable plant operation.

Multivariate Statistical Process Control (MSPC) methods are used commonly to detect and identify shifts in multivariate industrial processes. However, these methods are limited by assumptions and complexities. In this study, a new two-stage MSPC approach based on independent component analysis is proposed. The proposed method aims to provide solutions to both the determination and the identification of the shift in the mean vector of a multivariate process. In the first step of this new method, independent components extracted by ICA were used as monitoring statistics in the MSPC chart to detect the shift in the process. The second step of the method started to deal with the problem of identifying the source of this shift by decomposing the monitoring statistics. The simulation results show the superiority of the new method over traditional methods in both determining and identifying the shift in the process mean vector.

Datasets with missing values arising from causes such as sensor failure, inconsistent sampling rates, and merging data from different systems are common in the process industry. Methods for handling missing data typically operate during data pre-processing, but can also occur during model building. This article considers missing data within the context of principal component analysis (PCA), which is a method originally developed for complete data that has widespread industrial application in multivariate statistical process control. Due to the prevalence of missing data and the success of PCA for handling complete data, several PCA algorithms that can act on incomplete data have been proposed. Here, algorithms for applying PCA to datasets with missing values are reviewed. A case study is presented to demonstrate the performance of the algorithms and suggestions are made with respect to choosing which algorithm is most appropriate for particular settings. An alternating algorithm based on the singular value decomposition achieved the best results in the majority of test cases involving process datasets.

At the first stage of our work, the theoretical knowledge needed to use the multivariate statistical process control (MSPC) was explored. Last year, we clarified the sometimes confused concepts, equations, and formulas [1]. At the se­cond stage, R project simulation studies and some food industrial practical model investigations are carried out for con­firming the MSPC advantages compared with the univariate ones. Furthermore, we analyse, using principal component analysis (PCA), what could cause the outlying values. Moreover, we will demonstrate how to use the MYT-decomposition.

Experiences with industrial applications of projection methods for multivariate statistical process control

In this paper, we propose an ensemble method based on bagging and decision tree to resolve the problem of diagnosing out-of-control signals in multivariate statistical process control. To classify the out-of-control signals, we obtain a series of classifiers through ensemble learning on decision tree. Then we will integrate the classification results of multiple classifiers to determine the final classification. The experimental results show that our method could improve the accuracy of classification and is superior to other methods in terms of diagnosing out-of-control signals in multivariate statistical process control.

In this paper, we propose an ensemble method based on bagging and decision tree to resolve the problem of diagnosing out-of-control signals in multivariate statistical process control. To classify the out-of-control signals, we obtain a series of classifiers through ensemble learning on decision tree. Then we will integrate the classification results of multiple classifiers to determine the final classification. The experimental results show that our method could improve the accuracy of classification and is superior to other methods in terms of diagnosing out-of-control signals in multivariate statistical process control.

PurposeThe purpose of this paper is to develop a new easy-to-implement distribution-free integrated multivariate statistical process control (MSPC) approach with an ability to recognize out-of-control points, identify the key influential variable for the out-of-control state, and determine necessary changes to achieve the state of statistical control.Design/methodology/approachThe proposed approach integrates the control chart technique, the Mahalanobis-Taguchi System concept, the Andrews function plot, and nonlinear optimization for multivariate process control. Mahalanobis distance, Taguchi’s orthogonal array, and the main effect plot concept are used to identify the key influential variable responsible for the out-of-control situation. The Andrews function plot and nonlinear optimization help to identify direction and necessary correction to regain the state of statistical control. Finally, two different real life case studies illustrate the suitability of the approach.FindingsThe case studies illustrate the potential of the proposed integrated multivariate process control approach for easy implementation in varied manufacturing and process industries. In addition, the case studies also reveal that the multivariate out-of-control state is primarily contributed by a single influential variable.Research limitations/implicationsThe approach is limited to the situation in which a single influential variable contributes to out-of-control situation. The number and type of cases used are also limited and thus generalization may not be debated. Further research is necessary with varied case situations to refine the approach and prove its extensive applicability.Practical implicationsThe proposed approach does not require multivariate normality assumption and thus provides greater flexibility for the industry practitioners. The approach is also easy to implement and requires minimal programming effort. A simple application Microsoft Excel is suitable for online implementation of this approach.Originality/valueThe key steps of the MSPC approach are identifying the out-of-control point, diagnosing the out-of-control point, identifying the “influential” variable responsible for the out-of-control state, and determining the necessary direction and the amount of adjustment required to achieve the state of control. Most of the approaches reported in open literature are focused only until identifying influencing variable, with many restrictive assumptions. This paper addresses all key steps in a single integrated distribution-free approach, which is easy to implement in real time.

Process fault detection and diagnosis plays a very important role in the production security and the product quality. In this paper, in order to improve the accuracy for fault detection and diagnosis, a new method based on principal component analysis (PCA) is proposed in low pressure lost foam casting process. PCA method reduces the dimensionality of the original dataset by the projection of the dataset onto a smaller subspace defined by the principal components. The aim of this method is to establish the normal statistical correlation among the coefficients of the dataset to detect and diagnose the faults. The process faults are detected and diagnosed using multivariate statistical process control (MSPC) parameters such as: Hotelling’s T 2 -statistic, Q-statistic or squared prediction error (SPE) and Q-residual contribution. The monitoring results indicates that the proposed method can detect and diagnose the abnormal change of the process.