A new multivariate statistical process monitoring method using principal component analysis

Kano, Manabu; Hasebe, Shinji; Hashimoto, Iori; Ohno, Hiromu

doi:10.1016/s0098-1354(01)00683-4

Cited by 189 publications

(95 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Schippers 134 proposed an integrated process control model using statistical process control, total productivity management and automated process control. Kano et al 135 proposed a novel statistical monitoring method which is based on PCA, called moving PCA, in order to improve process-monitoring performance. The aim of this method is to identify changes in the correlation structure.…”

Section: Pca and Autocorrelated Datamentioning

confidence: 99%

Multivariate statistical process control charts: an overview

Bersimis

Psarakis

Panaretos

2006

Quality & Reliability Eng

506

313

View full text Add to dashboard Cite

In this paper we discuss the basic procedures for the implementation of multivariate statistical process control via control charting. Furthermore, we review multivariate extensions for all kinds of univariate control charts, such as multivariate Shewharttype control charts, multivariate CUSUM control charts and multivariate EWMA control charts. In addition, we review unique procedures for the construction of multivariate control charts, based on multivariate statistical techniques such as principal components analysis (PCA) and partial least squares (PLS). Finally, we describe the most significant methods for the interpretation of an out-of-control signal.

show abstract

Section: Pca and Autocorrelated Datamentioning

confidence: 99%

Multivariate statistical process control charts: an overview

Bersimis

Psarakis

Panaretos

2006

Quality & Reliability Eng

506

313

View full text Add to dashboard Cite

show abstract

“…Las técnicas de monitoreo de procesos que han sido ampliamente empleadas tales como: el Análisis de Componentes Principales (PCA) y las Mínimos Cuadrados Parciales (PLS) [10], [11] caen en modelos estáticos, las cuales asumen que las observaciones son independientes del tiempo y siguen una distribución Gaussiana. Las extensiones al PCA y al PLS, también denominados DPCA y DPLS han estado desarrolladas a direccionar este problema.…”

Section: Perspectiva Del Uso Del Imeunclassified

Industrial Multivariate Explorer: A solution with Matlab for time series mining

Seisdedos¹,

Castillo²,

Martínez³

et al. 2015

ITEGAM- Journal of Engineering and Technology for Industrial Applications (ITEGAM-JETIA)

View full text Add to dashboard Cite

The design and features of a Matlab's application to support applied researches for serial time computing is presented. The input data can be from historical record coming from chemical and thermal processes and also it can be generated by simulation. Up to 8 signals, linearly normalized and distributed can be visualized on an axis Matlab's object. By means of two cursors, the user can choose short windows of recorded signals. On this serial time sections, in this version, statisticians are computed and they facilitate the static modeling. They can be saved into an Excel file. It is an opened software application permitting to include new features. The Windows between 2 cursors command facilities the dynamic modeling. Its applicability is exemplified by times series from industry (from a 250 MW thermal power plant) and generated by simulation.Keywords: process monitoring, data-driven modeling, quasi-stationary states, chemometric methods, steam generators. Multi-variable Industrial: Una solución con Matlab para minar series temporales RESUMENSe presenta el diseño y las prestaciones de una aplicación desarrollada en Matlab orientada a dar soporte de cómputo a la exploración y extracción de información a partir de series temporales. La data de entrada podrá ser de un registro histórico de un proceso químico y termo energético y aquellos generados de experimentación simulada. La visualización es de hasta 8 señales linealmente normalizadas y distribuidas a lo alto del objeto axis. El usuario podrá seleccionar ventanas cortas de registro mediante dos cursores. Sobre estas secciones de series temporales, en esta versión, se computan estadígrafos que facilitan el modelado estático. Estos podrán ser salvados en un fichero Excel. Es una aplicación abierta permitiendo la inclusión de nuevas prestaciones. El comando Windows entre dos cursores facilita el modelado dinámico. Su aplicabilidad se ejemplifica con series temporales de la industria (de una central térmica de 250 MW) y generadas por simulación.Palabras Claves: Monitoreo de procesos, modelado basado en datos, estados cuasi-estacionarios, métodos químico-métricos, generadores de vapor. INTRODUCCIÓNLa evolución de los sistemas de automatización hacia aquellos denominados de Control Distribuido (del inglés; DCS) y el software instalado en los computadores de supervisión [1], así como la facilidad de establecer compactos sistemas registradores de datos (del inglés; Data logger) conducen a la generación de grandes volúmenes de datos.La supervisión de procesos se encarga de observar continuamente las variables del proceso en busca de la detección de anormalidades que puedan representar un problema operativo o de calidad. A esta se le destinan como sub-tareas la detección y diagnóstico de fallos y el análisis de procesos. Dependiendo del horizonte de tiempo con el que se trabaja, la supervisión se puede aplicar a 2 niveles:A corto plazo: En este nivel las variables del proceso se observan continuamente. La meta es detectar cualquier desviación con respecto al esta...

show abstract

“…A baseline control system was reported by [24] and the simulation has been widely used for demonstration of advanced control schemes (e.g. [23,30,22,20,40]), and for testing of fault detection and diagnosis schemes, both data driven and model-based [19,12,5,[14][15][16]34]. The original code was written in Fortran, while [29] has made an implementation in Simulink available to other researchers.…”

Section: First Principles Modelsmentioning

confidence: 99%

A continuous stirred tank heater simulation model with applications

Thornhill

Patwardhan

Shah

2008

Journal of Process Control

193

109

View full text Add to dashboard Cite

This article presents a first principles simulation of a continuous stirred tank heater pilot plant at the University of Alberta. The model has heat and volumetric balances, and a very realistic feature is that instrument, actuator and process non-linearities have been carefully measured, for instance to take account of the volume occupied by heating coils in the tank. Experimental data from step testing and recordings of real disturbances are presented. The model in Simulink and the experimental data are available electronically, and some suggestions are given for their application in education, system identification, fault detection and diagnosis.

show abstract

A new multivariate statistical process monitoring method using principal component analysis

Cited by 189 publications

References 17 publications

Multivariate statistical process control charts: an overview

Multivariate statistical process control charts: an overview

Industrial Multivariate Explorer: A solution with Matlab for time series mining

A continuous stirred tank heater simulation model with applications

Contact Info

Product

Resources

About