Documents disponibles écrits par cet auteur

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]  in Industrial & 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 <1.5 and the maximal relative prediction error (RE) is ∼7%, which can be acceptable in industrial practice for the intended objective of soft analyzers. 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 <1.5 and the maximal relative prediction error (RE) is ∼7%, which can be acceptable in industrial practice for the intended objective of soft analyzers. En ligne : http://pubs.acs.org/doi/abs/10.1021/ie8012709