Fault detection properties of global, local and time evolving models for batch process monitoring

Ramaker, Henk‐Jan; Sprang, E.N.M. van; Westerhuis, Johan A.; Smilde, Age K.

doi:10.1016/j.jprocont.2005.02.001

Cited by 60 publications

(64 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Local models [20] are the simplest example of this approach, where the submodel associated to a sampling time is computed from the data collected at that sampling time alone. Data are split according to Equation (7).…”

Section: K-models Approachmentioning

confidence: 99%

“…Nonetheless, the inclusion of the dynamics of the process can be crucial for a good modelling performance. A straightforward alternative to local modelling is evolving modelling [20], where all the possible LMVs are included in a sub-model as additional variables (8).…”

Section: K-models Approachmentioning

confidence: 99%

“…The multi-model approach is traditionally based on the generation of a bilinear model for every sampling time of the batch duration [19][20][21]. This is referred here as the K-models approach (Figure 1(d)).…”

Section: Introductionmentioning

confidence: 99%

“…If each sub-model includes only the data of a sampling time, then it is called a local model. If each sub-model incorporates the measurements from the beginning of the batch to a sampling time, then it is called an evolving model [20]. Hierarchical models [19] follow the latter method but giving different weight to the current measurements of the variables.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Bilinear modelling of batch processes. Part I: theoretical discussion

Camacho

Picó

Ferrer

2008

Journal of Chemometrics

View full text Add to dashboard Cite

When studying the principal component analysis (PCA) or partial least squares (PLS) modelling of batch process data, one realizes that there is a wide range of approaches. In many cases, new modelling approaches are presented just because they work properly for a particular application, for example, on-line monitoring and a given number of processes. A clear understanding of why these approaches perform successfully and which are the advantages and disadvantages in front of the others is seldom supplied. Why does modelling after batch-wise unfolding capture changing dynamics? What are the consequences of variable-wise unfolding? Is there any best unfolding method? When should several models for a single process be used? In this paper, it is shown how these and other related questions can be answered by properly analyzing the dynamic covariance structures of the various approaches.

show abstract

Section: K-models Approachmentioning

confidence: 99%

Section: K-models Approachmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Bilinear modelling of batch processes. Part I: theoretical discussion

Camacho

Picó

Ferrer

2008

Journal of Chemometrics

View full text Add to dashboard Cite

show abstract

“…Nonetheless, the use of a single model in an on-line application, for instance in a monitoring system, presents some drawbacks [7,8]. An alternative way to model a batch process is to fit a bilinear model for every single sampling time of the process [9][10][11]. This is referred here as the K-model approach, which principal drawback is the large number of models to deal with.…”

Section: Introductionmentioning

confidence: 99%

Bilinear modelling of batch processes. Part II: a comparison of PLS soft‐sensors

Camacho

Picó

Ferrer

2008

Journal of Chemometrics

View full text Add to dashboard Cite

The on-line monitoring of batch processes based on principal component analysis (PCA) has been widely studied. Nonetheless, researchers have not paid so much attention to the on-line application of partial least squares (PLS). In this paper, the influence of several issues in the predictive power of a PLS model for the on-line estimation of key variables in a batch process is studied. Some of the conclusions can help to better understand the capabilities of the proposals presented for on-line PCA-based monitoring. Issues like the convenience of batch-wise or variable-wise unfolding, the method for the imputation of future measurements and the use of several sub-models are addressed. This is the first time that the adaptive hierarchical (or multi-block) approach is extended to the PLS modelling. Also, the formulation of the so-called trimmed scores regression (TSR), a powerful imputation method defined for PCA, is extended for its application with PLS modelling. Data from two processes, one simulated and one real, are used to illustrate the results.

show abstract

Multivariate Statistical Process Control

Yao

Gao

2013

Computer Modeling for Injection Molding

View full text Add to dashboard Cite

Fault detection properties of global, local and time evolving models for batch process monitoring

Cited by 60 publications

References 23 publications

Bilinear modelling of batch processes. Part I: theoretical discussion

Bilinear modelling of batch processes. Part I: theoretical discussion

Bilinear modelling of batch processes. Part II: a comparison of PLS soft‐sensors

Multivariate Statistical Process Control

Contact Info

Product

Resources

About