Multimode process monitoring based on mode identification / Shuai Tan in Industrial & engineering chemistry research, Vol. 51 N° 1 (Janvier 2012)  

Public ISBD [article]  inIndustrial & engineering chemistry research > Vol. 51 N° 1 (Janvier 2012) . - pp. 374–388 Titre : Multimode process monitoring based on mode identification Type de document : texte imprimé Auteurs : Shuai Tan, Auteur ; Fuli Wang, Auteur ; Jun Peng, Auteur Année de publication : 2012 Article en page(s) : pp. 374–388 Note générale : Chimie industrielle Langues : Anglais (eng) Mots-clés : Multimode process Résumé : Many industrial processes have multiple operation modes due to different manufacturing strategies or varying feedstock. Fault detection for a multimode process is a complex problem, as monitoring for both stable and transitional modes should be taken into consideration. In this paper, a novel method based on the similarity of data characteristics is proposed to realize mode identification for modeling data. Different models are developed to capture the major tendencies of process variables. Especially, the transitional regions between neighboring stable modes, which have their particular dynamic characteristics, are modeled, respectively. Online monitoring procedures are formulated on the basis of mode identification. It is more efficient than a model matching strategy using traversing method. At last, the efficacy of the proposed method is illustrated by applying it to a continuous annealing line process and the Tennessee Eastman process. Both results of real application and simulation clearly demonstrate the effectiveness and feasibility of the proposed method. DEWEY : 660 ISSN : 0888-5885 En ligne : http://pubs.acs.org/doi/abs/10.1021/ie102048f [article] Multimode process monitoring based on mode identification [texte imprimé] / Shuai Tan, Auteur ; Fuli Wang, Auteur ; Jun Peng, Auteur . - 2012 . - pp. 374–388. Chimie industrielle Langues : Anglais (eng) in Industrial & engineering chemistry research > Vol. 51 N° 1 (Janvier 2012) . - pp. 374–388 Mots-clés : Multimode process Résumé : Many industrial processes have multiple operation modes due to different manufacturing strategies or varying feedstock. Fault detection for a multimode process is a complex problem, as monitoring for both stable and transitional modes should be taken into consideration. In this paper, a novel method based on the similarity of data characteristics is proposed to realize mode identification for modeling data. Different models are developed to capture the major tendencies of process variables. Especially, the transitional regions between neighboring stable modes, which have their particular dynamic characteristics, are modeled, respectively. Online monitoring procedures are formulated on the basis of mode identification. It is more efficient than a model matching strategy using traversing method. At last, the efficacy of the proposed method is illustrated by applying it to a continuous annealing line process and the Tennessee Eastman process. Both results of real application and simulation clearly demonstrate the effectiveness and feasibility of the proposed method. DEWEY : 660 ISSN : 0888-5885 En ligne : http://pubs.acs.org/doi/abs/10.1021/ie102048f

Exemplaires

Code-barres	Cote	Support	Localisation	Section	Disponibilité
aucun exemplaire