Self-organizing self-clustering network / Bharat Bhushan in Industrial & engineering chemistry research, Vol. 47 n°12 (Juin 2008)  

Public ISBD [article]  inIndustrial & engineering chemistry research > Vol. 47 n°12 (Juin 2008) . - p. 4209–4219 Titre : Self-organizing self-clustering network : a strategy for unsupervised pattern classification with its application to fault diagnosis Type de document : texte imprimé Auteurs : Bharat Bhushan, Auteur ; Jose A. Romagnoli, Auteur Année de publication : 2008 Article en page(s) : p. 4209–4219 Note générale : Bibliogr. p. 4219 Langues : Anglais (eng) Mots-clés : Unsupervised pattern classification  Self-organizing network  Self-clustering network Résumé : In this work, we propose a method for unsupervised pattern classification called self-organizing self-clustering network. This method incorporates the concept of fuzzy clustering into the learning strategy of the self-organizing map. The number of nodes in the network is determined incrementally during the training. The advantage of the proposed strategy over other existing clustering techniques is its ability to determine network size and the number of clusters in data sets automatically. Since the methodology is based on learning, it is computationally less expensive, and the result is not affected by the initial guess. A data set with Gaussian distribution is used to illustrate this method, and results are compared with fuzzy C-mean clustering. Furthermore, the proposed strategy is applied for the fault detection and diagnosis of a twin-continuous tank reactor virtual plant. The result shows that this strategy can be used as a process-monitoring tool in an industrial environment. En ligne : http://pubs.acs.org/doi/abs/10.1021/ie071549a [article] Self-organizing self-clustering network : a strategy for unsupervised pattern classification with its application to fault diagnosis [texte imprimé] / Bharat Bhushan, Auteur ; Jose A. Romagnoli, Auteur . - 2008 . - p. 4209–4219. Bibliogr. p. 4219 Langues : Anglais (eng) in Industrial & engineering chemistry research > Vol. 47 n°12 (Juin 2008) . - p. 4209–4219 Mots-clés : Unsupervised pattern classification  Self-organizing network  Self-clustering network Résumé : In this work, we propose a method for unsupervised pattern classification called self-organizing self-clustering network. This method incorporates the concept of fuzzy clustering into the learning strategy of the self-organizing map. The number of nodes in the network is determined incrementally during the training. The advantage of the proposed strategy over other existing clustering techniques is its ability to determine network size and the number of clusters in data sets automatically. Since the methodology is based on learning, it is computationally less expensive, and the result is not affected by the initial guess. A data set with Gaussian distribution is used to illustrate this method, and results are compared with fuzzy C-mean clustering. Furthermore, the proposed strategy is applied for the fault detection and diagnosis of a twin-continuous tank reactor virtual plant. The result shows that this strategy can be used as a process-monitoring tool in an industrial environment. En ligne : http://pubs.acs.org/doi/abs/10.1021/ie071549a

Exemplaires

Code-barres	Cote	Support	Localisation	Section	Disponibilité
aucun exemplaire

Use of predictive solubility models for isothermal antisolvent crystallization modeling and optimization / David J. Widenski in Industrial & engineering chemistry research, Vol. 50 N° 13 (Juillet 2011)  

Public ISBD [article]  inIndustrial & engineering chemistry research > Vol. 50 N° 13 (Juillet 2011) . - pp. 8304-8313 Titre : Use of predictive solubility models for isothermal antisolvent crystallization modeling and optimization Type de document : texte imprimé Auteurs : David J. Widenski, Auteur ; Ali Abbas, Auteur ; Jose A. Romagnoli, Auteur Année de publication : 2011 Article en page(s) : pp. 8304-8313 Note générale : Chimie industrielle Langues : Anglais (eng) Mots-clés : Optimization Crystallization Modeling Solubility Résumé : Predictive solubility models can be of great use for crystallization modeling and optimization, and can decrease the amount of experimental effort needed to create a robust crystallization model. In this study, predictive solubility models such as MOSCED, UNIFAC, NRTL-SAC, and the Jouyban-Acree model are compared against an empirical model for predicted solubility accuracy. The best models are subsequently compared against the empirical model for the antisolvent crystallization of acetaminophen in acetone, using water as the antisolvent. The effects of these solubility models on the predicted relative supersaturation, volume mean size, volume-percent crystal size distribution (CSD), and generated optimal antisolvent feed profiles are investigated. It was found that, for this system, only the NRTL-SAC and Jouyban-Acree solubility models were accurate enough to predict crystallization mean size and crystal size distributions. The Jouyban-Acree and NRTL-SAC solubility models respectively predicted end-volume mean-size differences up to 13% and 29% from the empirical model. When used to create optimal antisolvent feed profiles, the Jouyban-Acree and NRTL-SAC profiles produced results that varied up to 32% and 60%, respectively, from the desired objective. None of the predictive solubility models was accurate enough for the creation of optimal antisolvent feed profiles. DEWEY : 660 ISSN : 0888-5885 En ligne : http://cat.inist.fr/?aModele=afficheN&cpsidt=24332156 [article] Use of predictive solubility models for isothermal antisolvent crystallization modeling and optimization [texte imprimé] / David J. Widenski, Auteur ; Ali Abbas, Auteur ; Jose A. Romagnoli, Auteur . - 2011 . - pp. 8304-8313. Chimie industrielle Langues : Anglais (eng) in Industrial & engineering chemistry research > Vol. 50 N° 13 (Juillet 2011) . - pp. 8304-8313 Mots-clés : Optimization Crystallization Modeling Solubility Résumé : Predictive solubility models can be of great use for crystallization modeling and optimization, and can decrease the amount of experimental effort needed to create a robust crystallization model. In this study, predictive solubility models such as MOSCED, UNIFAC, NRTL-SAC, and the Jouyban-Acree model are compared against an empirical model for predicted solubility accuracy. The best models are subsequently compared against the empirical model for the antisolvent crystallization of acetaminophen in acetone, using water as the antisolvent. The effects of these solubility models on the predicted relative supersaturation, volume mean size, volume-percent crystal size distribution (CSD), and generated optimal antisolvent feed profiles are investigated. It was found that, for this system, only the NRTL-SAC and Jouyban-Acree solubility models were accurate enough to predict crystallization mean size and crystal size distributions. The Jouyban-Acree and NRTL-SAC solubility models respectively predicted end-volume mean-size differences up to 13% and 29% from the empirical model. When used to create optimal antisolvent feed profiles, the Jouyban-Acree and NRTL-SAC profiles produced results that varied up to 32% and 60%, respectively, from the desired objective. None of the predictive solubility models was accurate enough for the creation of optimal antisolvent feed profiles. DEWEY : 660 ISSN : 0888-5885 En ligne : http://cat.inist.fr/?aModele=afficheN&cpsidt=24332156

Exemplaires

Code-barres	Cote	Support	Localisation	Section	Disponibilité
aucun exemplaire