Soft chemical analyzer development using adaptive least-squares support vector regression with selective pruning and variable moving window size / Yi Liu in Industrial & engineering chemistry research, Vol. 48 N° 12 (Juin 2009)  

Public ISBD [article]  inIndustrial & engineering chemistry research > Vol. 48 N° 12 (Juin 2009) . - pp. 5731–5741 Titre : Soft chemical analyzer development using adaptive least-squares support vector regression with selective pruning and variable moving window size Type de document : texte imprimé Auteurs : Yi Liu, Auteur ; Naiping Hu, Auteur ; Haiqing Wang, Auteur Année de publication : 2009 Article en page(s) : pp. 5731–5741 Note générale : Chemical engineering Langues : Anglais (eng) Mots-clés : Soft analyzers Adaptive least-squares support vector regression algorithm Nonlinear multi-input-multi-output process modeling Framework Time-varying dynamics Résumé : Soft analyzers have been increasingly accepted as an alternative to physical ones in the chemical industry to infer and improve the product quality. In this study, an adaptive least-squares support vector regression (ALSSVR) algorithm is proposed for the issue of nonlinear multi-input−multi-output process modeling and applied to soft chemical analyzer development. The ALSSVR algorithm adopts the moving window scheme and a two-stage recursive learning framework to trace the time-varying dynamics of a process. The useless sample (i.e., a node of analyzer model), while not the oldest one, is selectively deleted from the model topology, using the fast leave-one-out cross-validation criterion. Consequently, the updated model can exhibit good generalization ability and trace the process characteristics effectively. Besides, a variable moving window is proposed, so its size can be adaptively adjusted, relative to process changes. The ALSSVR-based soft analyzer is then applied to an industrial fluidized catalytic cracking unit to predict its three key product yields. The obtained results show that the presented ALSSVR method is superior to conventional recursive least-squares support vector regression (RLSSVR) approaches. The maximal root-mean-square error (RMSE) of all product yields is En ligne : http://pubs.acs.org/doi/abs/10.1021/ie8012709 [article] Soft chemical analyzer development using adaptive least-squares support vector regression with selective pruning and variable moving window size [texte imprimé] / Yi Liu, Auteur ; Naiping Hu, Auteur ; Haiqing Wang, Auteur . - 2009 . - pp. 5731–5741. Chemical engineering Langues : Anglais (eng) in Industrial & engineering chemistry research > Vol. 48 N° 12 (Juin 2009) . - pp. 5731–5741 Mots-clés : Soft analyzers Adaptive least-squares support vector regression algorithm Nonlinear multi-input-multi-output process modeling Framework Time-varying dynamics Résumé : Soft analyzers have been increasingly accepted as an alternative to physical ones in the chemical industry to infer and improve the product quality. In this study, an adaptive least-squares support vector regression (ALSSVR) algorithm is proposed for the issue of nonlinear multi-input−multi-output process modeling and applied to soft chemical analyzer development. The ALSSVR algorithm adopts the moving window scheme and a two-stage recursive learning framework to trace the time-varying dynamics of a process. The useless sample (i.e., a node of analyzer model), while not the oldest one, is selectively deleted from the model topology, using the fast leave-one-out cross-validation criterion. Consequently, the updated model can exhibit good generalization ability and trace the process characteristics effectively. Besides, a variable moving window is proposed, so its size can be adaptively adjusted, relative to process changes. The ALSSVR-based soft analyzer is then applied to an industrial fluidized catalytic cracking unit to predict its three key product yields. The obtained results show that the presented ALSSVR method is superior to conventional recursive least-squares support vector regression (RLSSVR) approaches. The maximal root-mean-square error (RMSE) of all product yields is En ligne : http://pubs.acs.org/doi/abs/10.1021/ie8012709

Exemplaires

Code-barres	Cote	Support	Localisation	Section	Disponibilité
aucun exemplaire