Batch process monitoring for consistent production

Martin, E.B.; Morris, A.J.; Papazoglou, M. C.; Kiparissides, Costas

doi:10.1016/0098-1354(96)00109-3

Cited by 53 publications

(20 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Two test statistics are derived from this model and both are monitored using control charts. Since its introduction, batch process monitoring has been successfully applied to many different processes and extensions have been suggested ( Martin et al. , 1996; Rannar , 1998; Wold et al.…”

Section: Introductionmentioning

confidence: 99%

Performance assessment and improvement of control charts for statistical batch process monitoring

Ramaker

Sprang

Westerhuis

et al. 2006

Statistica Neerlandica

View full text Add to dashboard Cite

This paper describes the concepts of statistical batch process monitoring and the associated problems. It starts with an introduction to process monitoring in general which is then extended to batch process monitoring. The performance of control charts for batch process monitoring is discussed by means of two performance indices: the overall type I error and the action signal time. Problems associated with the existing approach are discussed and highlighted. Improvements are suggested and checked with the performance indices. To evaluate the effect of the proposed improvements as well as to assess the performance of the existing approach, an industrial batch production process is used.

show abstract

Section: Introductionmentioning

confidence: 99%

Performance assessment and improvement of control charts for statistical batch process monitoring

Ramaker

Sprang

Westerhuis

et al. 2006

Statistica Neerlandica

View full text Add to dashboard Cite

show abstract

“…In PCA monitoring, the confidence limit is approximated by a specified distribution based upon the assumption that the latent variables follow a Gaussian distribution. However, the monitoring charts indicate many false alarms since this assumption is not valid in some cases (Martin et al, 1996). On the other hand, the independent components over some period do not conform to a multivariate Gaussian distribution; hence, the confidence limits of the I 2 , I e 2 and SPE statistics cannot be determined directly from a particular approximate distribution.…”

Section: Process Monitoring Statistics Of Icamentioning

confidence: 97%

On-line Batch Process Monitoring Using Different Unfolding Method and Independent Component Analysis.

Lee

2003

J. Chem. Eng. Japan

View full text Add to dashboard Cite

In many industries, the effective monitoring and control of batch processes is crucial to the production of high-quality materials. Several techniques using multivariate statistical analysis have been developed for monitoring and fault detection of batch processes. Multiway principal component analysis (MPCA) has shown a powerful monitoring performance in many industrial batch processes. However, it has shortcomings that all batch lengths should be equalized and future values of batches should be estimated for on-line monitoring. In order to overcome these drawbacks and obtain better monitoring performance, we propose a new statistical method for on-line batch process monitoring that uses different unfolding method and independent component analysis (ICA). If the measured data set contains non-Gaussian latent variables, the ICA solution can extract the original source signal to a much greater extent than the PCA solution since ICA involves higher-order statistics and is not based on the assumption that the latent variables follow a multivariate Gaussian distribution. The proposed monitoring method was applied to fault detection and identification in the simulation benchmark of the fed-batch penicillin production, which is characterized by some fault sources with non-Gaussian characteristics. The simulation results clearly show the power and advantages of the proposed method in comparison to MPCA.

show abstract

“…Neogi and Schlags580 applied multivariate statistical methods (multiway PCA and multiway PLS) to an industrial emulsion polymerization batch process. Martin et al581 reviewed the M 2 statistic (an alternative to the Hotelling T 2 statistic) and applied it to a batch MMA polymerization process. Other studies that have used multivariate statistical approaches were presented by Rannar et al,582 who used a multiblock PCA and PLS algorithm; Flores‐Cerrillo and MacGregor,583–586 who proposed multivariate approaches to predict particle size in emulsion polymerization reactors; Kumar et al587 for high‐pressure polymerization reactors; Albazzaz and Wang588 in the semi‐batch polymerization of polyol; Chen and Liu,589 who used dynamic PCA and PLS models; Duchesne et al590 who used PCA and PLS for the analysis and monitoring of process transitions (process start‐ups and restarts), and Sharmin et al544 who used PLS to develop a soft sensor to predict MFI.…”

Section: Other Topics Related To Sensorsmentioning

confidence: 99%

A Critical Overview of Sensors for Monitoring Polymerizations

Fonseca

Dubé

Penlidis

2009

Macro Reaction Engineering

View full text Add to dashboard Cite

The available on‐line and in‐line sensor technologies developed for polymerization reactors from 1990 until today are discussed and critically reviewed. About 600 references are included, which evidence the growth in sensor technology in the last two decades. Sensors for operational parameters in polymer reactors (i.e. temperature, pressure, level and flow) as well as sensors for polymer property monitoring (i.e. calorimetry, chromatography and spectroscopy, among others) are included. Complementary topics such as state estimation, multivariate statistical methods, fault diagnosis techniques and optimal sensor selection and location are briefly covered.

show abstract

Batch process monitoring for consistent production

Cited by 53 publications

References 7 publications

Performance assessment and improvement of control charts for statistical batch process monitoring

Performance assessment and improvement of control charts for statistical batch process monitoring

On-line Batch Process Monitoring Using Different Unfolding Method and Independent Component Analysis.

A Critical Overview of Sensors for Monitoring Polymerizations

Contact Info

Product

Resources

About