Integrated Multiscale Latent Variable Regression and Application to Distillation Columns
Proper control of distillation columns requires estimating some key variables that are challenging to measure online (such as compositions), which are usually estimated using inferential models. Commonly used inferential models include latent variable regression (LVR) techniques, such as principal c...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2013-01-01
|
| Series: | Modelling and Simulation in Engineering |
| Online Access: | http://dx.doi.org/10.1155/2013/730456 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832556603743666176 |
|---|---|
| author | Muddu Madakyaru Mohamed N. Nounou Hazem N. Nounou |
| author_facet | Muddu Madakyaru Mohamed N. Nounou Hazem N. Nounou |
| author_sort | Muddu Madakyaru |
| collection | DOAJ |
| description | Proper control of distillation columns requires estimating some key variables that are challenging to measure online (such as compositions), which are usually estimated using inferential models. Commonly used inferential models include latent variable regression (LVR) techniques, such as principal component regression (PCR), partial least squares (PLS), and regularized canonical correlation analysis (RCCA). Unfortunately, measured practical data are usually contaminated with errors, which degrade the prediction abilities of inferential models. Therefore, noisy measurements need to be filtered to enhance the prediction accuracy of these models. Multiscale filtering has been shown to be a powerful feature extraction tool. In this work, the advantages of multiscale filtering are utilized to enhance the prediction accuracy of LVR models by developing an integrated multiscale LVR (IMSLVR) modeling algorithm that integrates modeling and feature extraction. The idea behind the IMSLVR modeling algorithm is to filter the process data at different decomposition levels, model the filtered data from each level, and then select the LVR model that optimizes a model selection criterion. The performance of the developed IMSLVR algorithm is illustrated using three examples, one using synthetic data, one using simulated distillation column data, and one using experimental packed bed distillation column data. All examples clearly demonstrate the effectiveness of the IMSLVR algorithm over the conventional methods. |
| format | Article |
| id | doaj-art-374e56be59b94e83a144f6cbded10591 |
| institution | Kabale University |
| issn | 1687-5591 1687-5605 |
| language | English |
| publishDate | 2013-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Modelling and Simulation in Engineering |
| spelling | doaj-art-374e56be59b94e83a144f6cbded105912025-02-03T05:44:51ZengWileyModelling and Simulation in Engineering1687-55911687-56052013-01-01201310.1155/2013/730456730456Integrated Multiscale Latent Variable Regression and Application to Distillation ColumnsMuddu Madakyaru0Mohamed N. Nounou1Hazem N. Nounou2Chemical Engineering Program, Texas A&M University at Qatar, Doha, QatarChemical Engineering Program, Texas A&M University at Qatar, Doha, QatarElectrical and Computer Engineering Program, Texas A&M University at Qatar, Doha, QatarProper control of distillation columns requires estimating some key variables that are challenging to measure online (such as compositions), which are usually estimated using inferential models. Commonly used inferential models include latent variable regression (LVR) techniques, such as principal component regression (PCR), partial least squares (PLS), and regularized canonical correlation analysis (RCCA). Unfortunately, measured practical data are usually contaminated with errors, which degrade the prediction abilities of inferential models. Therefore, noisy measurements need to be filtered to enhance the prediction accuracy of these models. Multiscale filtering has been shown to be a powerful feature extraction tool. In this work, the advantages of multiscale filtering are utilized to enhance the prediction accuracy of LVR models by developing an integrated multiscale LVR (IMSLVR) modeling algorithm that integrates modeling and feature extraction. The idea behind the IMSLVR modeling algorithm is to filter the process data at different decomposition levels, model the filtered data from each level, and then select the LVR model that optimizes a model selection criterion. The performance of the developed IMSLVR algorithm is illustrated using three examples, one using synthetic data, one using simulated distillation column data, and one using experimental packed bed distillation column data. All examples clearly demonstrate the effectiveness of the IMSLVR algorithm over the conventional methods.http://dx.doi.org/10.1155/2013/730456 |
| spellingShingle | Muddu Madakyaru Mohamed N. Nounou Hazem N. Nounou Integrated Multiscale Latent Variable Regression and Application to Distillation Columns Modelling and Simulation in Engineering |
| title | Integrated Multiscale Latent Variable Regression and Application to Distillation Columns |
| title_full | Integrated Multiscale Latent Variable Regression and Application to Distillation Columns |
| title_fullStr | Integrated Multiscale Latent Variable Regression and Application to Distillation Columns |
| title_full_unstemmed | Integrated Multiscale Latent Variable Regression and Application to Distillation Columns |
| title_short | Integrated Multiscale Latent Variable Regression and Application to Distillation Columns |
| title_sort | integrated multiscale latent variable regression and application to distillation columns |
| url | http://dx.doi.org/10.1155/2013/730456 |
| work_keys_str_mv | AT muddumadakyaru integratedmultiscalelatentvariableregressionandapplicationtodistillationcolumns AT mohamednnounou integratedmultiscalelatentvariableregressionandapplicationtodistillationcolumns AT hazemnnounou integratedmultiscalelatentvariableregressionandapplicationtodistillationcolumns |