[article]
Titre : |
Online monitoring of batch processes using IOHMM based MPLS |
Type de document : |
texte imprimé |
Auteurs : |
Junghui Chen, Auteur ; Che-Ming Song, Auteur ; Tong-Yang Hsu, Auteur |
Année de publication : |
2010 |
Article en page(s) : |
pp.2800–2811 |
Note générale : |
Industrial Chemistry |
Langues : |
Anglais (eng) |
Mots-clés : |
Online IOHMM MPLS collinearity dynamic information |
Résumé : |
Online monitoring of the batch process is extremely important to the health assessment of the batch operation; it ensures making products of consistent high quality. In this paper, an integrated framework called IOHMM-MPLS is proposed to monitor the performance of a batch process. It consists of the input−output hidden Markov model (IOHMM) and multiway partial least-squares (MPLS) method. The sequence of the process variables and the product quality variables are decomposed into linear outer relations, which can be handled by MPLS, and simple inner dynamic sequence relations, which can be coped with by a set of single-input−single-output IOHMM models. MPLS is used to solve the problem of high dimensionality and collinearity, while IOHMM is used to capture the transition probability of the dynamic information. The combined IOHMM-MPLS method requires a smaller computational load, converges faster, and encounters lesser occurrences of false detection. It utilizes output quality variables and within batch process variables to find the most likely state evolution. After extracting the essential features of the past operating information, subsequently, two simple monitoring charts are presented to track the progress of each batch run and monitor the occurrence of the observable upsets. The proposed model is successfully applied to two simulated problems. |
Note de contenu : |
Bibiogr. |
ISSN : |
0888-5885 |
En ligne : |
http://pubs.acs.org/doi/abs/10.1021/ie900536z |
in Industrial & engineering chemistry research > Vol. 49 N° 6 (Mars 2010) . - pp.2800–2811
[article] Online monitoring of batch processes using IOHMM based MPLS [texte imprimé] / Junghui Chen, Auteur ; Che-Ming Song, Auteur ; Tong-Yang Hsu, Auteur . - 2010 . - pp.2800–2811. Industrial Chemistry Langues : Anglais ( eng) in Industrial & engineering chemistry research > Vol. 49 N° 6 (Mars 2010) . - pp.2800–2811
Mots-clés : |
Online IOHMM MPLS collinearity dynamic information |
Résumé : |
Online monitoring of the batch process is extremely important to the health assessment of the batch operation; it ensures making products of consistent high quality. In this paper, an integrated framework called IOHMM-MPLS is proposed to monitor the performance of a batch process. It consists of the input−output hidden Markov model (IOHMM) and multiway partial least-squares (MPLS) method. The sequence of the process variables and the product quality variables are decomposed into linear outer relations, which can be handled by MPLS, and simple inner dynamic sequence relations, which can be coped with by a set of single-input−single-output IOHMM models. MPLS is used to solve the problem of high dimensionality and collinearity, while IOHMM is used to capture the transition probability of the dynamic information. The combined IOHMM-MPLS method requires a smaller computational load, converges faster, and encounters lesser occurrences of false detection. It utilizes output quality variables and within batch process variables to find the most likely state evolution. After extracting the essential features of the past operating information, subsequently, two simple monitoring charts are presented to track the progress of each batch run and monitor the occurrence of the observable upsets. The proposed model is successfully applied to two simulated problems. |
Note de contenu : |
Bibiogr. |
ISSN : |
0888-5885 |
En ligne : |
http://pubs.acs.org/doi/abs/10.1021/ie900536z |
|