Documents disponibles écrits par cet auteur

Enhanced process comprehension and statistical analysis for slow-varying batch processes / Zhao, Chunhui ; Wang, Fuli ; Gao, Furong in Industrial & engineering chemistry research, Vol. 47 n°24 (Décembre 2008) 

Public ISBD [article]  in Industrial & engineering chemistry research > Vol. 47 n°24 (Décembre 2008) . - p. 9996–10008 Titre : Enhanced process comprehension and statistical analysis for slow-varying batch processes Type de document : texte imprimé Auteurs : Zhao, Chunhui, Auteur ; Wang, Fuli, Auteur ; Gao, Furong, Auteur Année de publication : 2009 Article en page(s) : p. 9996–10008 Note générale : Industrial chemistry Langues : Anglais (eng) Mots-clés : Statistical  analysis Résumé : Under the influence of various exterior factors, batch processes commonly involve normal slow variations over batches, in which the changing underlying behaviors make their modeling and monitoring a greater challenge. Having realized the problems associated with the commonly adopted adaptive methods, in the present work, our biggest concern is how to minimize the efforts for long-term model updating adjustment and simultaneously maintain their validity as permanently as possible once the initial models are built. It is implemented from the viewpoint of between-batch relative changes, which are regular with process evolution and conform to certain evolving rule and statistical characteristics. First, difference subspace is constructed by calculating the between-batch difference trajectories, which represent the batchwise relative changes resulting from the slow-varying behaviors. Then their variability along batch direction is addressed and analyzed in the difference subspace using ICA-PCA two-step feature extraction, which reveals the evolving rule and statistical characteristics of slow variations. In this way, the mode of normal slow changes is extracted, trained, and modeled, which, thus, endows the initial monitoring system with adaptive competency to slow-varying behaviors. Therefore, it is less sensitive to normal slow variations, which eases the excessive dependency of monitoring performance on updating and, thus, decreases the risk of false adaptation to process disturbances. Despite the simplicity of the proposed idea and algorithm, the performance it achieves in the case studies indicates that it is smart and competitive as a feasible solution to analyze and monitor the regular slow-varying characteristics. En ligne : http://pubs.acs.org/doi/abs/10.1021/ie800643d [article] Enhanced process comprehension and statistical analysis for slow-varying batch processes [texte imprimé] / Zhao, Chunhui, Auteur ; Wang, Fuli, Auteur ; Gao, Furong, Auteur . - 2009 . - p. 9996–10008. Industrial chemistry Langues : Anglais (eng) in Industrial & engineering chemistry research > Vol. 47 n°24 (Décembre 2008) . - p. 9996–10008 Mots-clés : Statistical  analysis Résumé : Under the influence of various exterior factors, batch processes commonly involve normal slow variations over batches, in which the changing underlying behaviors make their modeling and monitoring a greater challenge. Having realized the problems associated with the commonly adopted adaptive methods, in the present work, our biggest concern is how to minimize the efforts for long-term model updating adjustment and simultaneously maintain their validity as permanently as possible once the initial models are built. It is implemented from the viewpoint of between-batch relative changes, which are regular with process evolution and conform to certain evolving rule and statistical characteristics. First, difference subspace is constructed by calculating the between-batch difference trajectories, which represent the batchwise relative changes resulting from the slow-varying behaviors. Then their variability along batch direction is addressed and analyzed in the difference subspace using ICA-PCA two-step feature extraction, which reveals the evolving rule and statistical characteristics of slow variations. In this way, the mode of normal slow changes is extracted, trained, and modeled, which, thus, endows the initial monitoring system with adaptive competency to slow-varying behaviors. Therefore, it is less sensitive to normal slow variations, which eases the excessive dependency of monitoring performance on updating and, thus, decreases the risk of false adaptation to process disturbances. Despite the simplicity of the proposed idea and algorithm, the performance it achieves in the case studies indicates that it is smart and competitive as a feasible solution to analyze and monitor the regular slow-varying characteristics. En ligne : http://pubs.acs.org/doi/abs/10.1021/ie800643d

Nonlinear batch process monitoring using phase-based kernel-independent component analysis−principal component analysis (KICA−PCA) / Zhao, Chunhui in Industrial & engineering chemistry research, Vol. 48 N° 20 (Octobre 2009) 

Public ISBD [article]  in Industrial & engineering chemistry research > Vol. 48 N° 20 (Octobre 2009) . - pp. 9163–9174 Titre : Nonlinear batch process monitoring using phase-based kernel-independent component analysis−principal component analysis (KICA−PCA) Type de document : texte imprimé Auteurs : Zhao, Chunhui, Auteur ; Gao, Furong, Auteur ; Wang, Fuli, Auteur Année de publication : 2010 Article en page(s) : pp. 9163–9174 Note générale : Chemical engineering Langues : Anglais (eng) Mots-clés : Nonlinear  batch  processes  Kernel  technique Résumé : In this article, the statistical modeling and online monitoring of nonlinear batch processes are addressed on the basis of the kernel technique. First, the article analyzes the conventional multiway kernel algorithms, which were just simple and conservative kernel extensions of the original multiway linear methods and thus inherited their drawbacks. Then, an improved nonlinear batch monitoring method is developed. This method captures the changes of the underlying nonlinear characteristics and accordingly divides the whole batch duration into different phases. Then, focusing on each subphase, both nonlinear Gaussian and non-Gaussian features are explored by a two-step modeling strategy usingkernel-independent component analysis−principal component analysis (KICA−PCA). Process monitoring and fault detection can be readily carried out online without requiring the estimation of future process data. Meanwhile, the dynamics of the data are preserved by exploring time-varying covariance structures. The idea and performance of the proposed method are illustrated using a real three-tank process and a benchmark simulation of fed-batch penicillin fermentation production. En ligne : http://pubs.acs.org/doi/abs/10.1021/ie8012874 [article] Nonlinear batch process monitoring using phase-based kernel-independent component analysis−principal component analysis (KICA−PCA) [texte imprimé] / Zhao, Chunhui, Auteur ; Gao, Furong, Auteur ; Wang, Fuli, Auteur . - 2010 . - pp. 9163–9174. Chemical engineering Langues : Anglais (eng) in Industrial & engineering chemistry research > Vol. 48 N° 20 (Octobre 2009) . - pp. 9163–9174 Mots-clés : Nonlinear  batch  processes  Kernel  technique Résumé : In this article, the statistical modeling and online monitoring of nonlinear batch processes are addressed on the basis of the kernel technique. First, the article analyzes the conventional multiway kernel algorithms, which were just simple and conservative kernel extensions of the original multiway linear methods and thus inherited their drawbacks. Then, an improved nonlinear batch monitoring method is developed. This method captures the changes of the underlying nonlinear characteristics and accordingly divides the whole batch duration into different phases. Then, focusing on each subphase, both nonlinear Gaussian and non-Gaussian features are explored by a two-step modeling strategy usingkernel-independent component analysis−principal component analysis (KICA−PCA). Process monitoring and fault detection can be readily carried out online without requiring the estimation of future process data. Meanwhile, the dynamics of the data are preserved by exploring time-varying covariance structures. The idea and performance of the proposed method are illustrated using a real three-tank process and a benchmark simulation of fed-batch penicillin fermentation production. En ligne : http://pubs.acs.org/doi/abs/10.1021/ie8012874

Phase-based joint modeling and spectroscopy analysis for batch processes monitoring / Zhao, Chunhui in Industrial & engineering chemistry research, Vol. 49 N° 2 (Janvier 2010) 

Public ISBD [article]  in Industrial & engineering chemistry research > Vol. 49 N° 2 (Janvier 2010) . - pp 669–681 Titre : Phase-based joint modeling and spectroscopy analysis for batch processes monitoring Type de document : texte imprimé Auteurs : Zhao, Chunhui, Auteur ; Gao, Furong, Auteur ; Wang, Fuli, Auteur Année de publication : 2010 Article en page(s) : pp 669–681 Note générale : Chimie industrielle Langues : Anglais (eng) Mots-clés : Spectroscopy  Processes  monitoring  Chemical  reactions. Résumé : Spectroscopy is a useful tool for analyzing chemical information in batch processes. However, conventional spectroscopic techniques can lead to complex model structures and difficult-to-interpret results because of the direct use of redundant wavelength variables. To solve this problem, the ICA technique has been used first to reveal the underlying independent sources from the observed mixtures and their mixing coefficients. This analysis associates the constituent species with their respective effects on the mixture spectra, which could make more sense for spectroscopy. In the following article, the use of mixing coefficients instead of redundant wavelength variables can provide a convenient modeling platform from which the phase-specific characteristics of chemical reactions are readily identified. Consequently, a phase-based joint modeling framework is formulated for process monitoring by combining different latent-variable- (LV-) based algorithms. It decomposes different types of systematic variations in spectral measurements (X) and then sets up different monitoring systems for them. Monitoring different parts of X can provide abundant process information about the status of the operation from a comprehensive viewpoint, thus benefitting process understanding and fault detection. The effectiveness of this approach is demonstrated by application to two case studies. DEWEY : 660 ISSN : 0888-5885 En ligne : http://pubs.acs.org/doi/abs/10.1021/ie9005996 [article] Phase-based joint modeling and spectroscopy analysis for batch processes monitoring [texte imprimé] / Zhao, Chunhui, Auteur ; Gao, Furong, Auteur ; Wang, Fuli, Auteur . - 2010 . - pp 669–681. Chimie industrielle Langues : Anglais (eng) in Industrial & engineering chemistry research > Vol. 49 N° 2 (Janvier 2010) . - pp 669–681 Mots-clés : Spectroscopy  Processes  monitoring  Chemical  reactions. Résumé : Spectroscopy is a useful tool for analyzing chemical information in batch processes. However, conventional spectroscopic techniques can lead to complex model structures and difficult-to-interpret results because of the direct use of redundant wavelength variables. To solve this problem, the ICA technique has been used first to reveal the underlying independent sources from the observed mixtures and their mixing coefficients. This analysis associates the constituent species with their respective effects on the mixture spectra, which could make more sense for spectroscopy. In the following article, the use of mixing coefficients instead of redundant wavelength variables can provide a convenient modeling platform from which the phase-specific characteristics of chemical reactions are readily identified. Consequently, a phase-based joint modeling framework is formulated for process monitoring by combining different latent-variable- (LV-) based algorithms. It decomposes different types of systematic variations in spectral measurements (X) and then sets up different monitoring systems for them. Monitoring different parts of X can provide abundant process information about the status of the operation from a comprehensive viewpoint, thus benefitting process understanding and fault detection. The effectiveness of this approach is demonstrated by application to two case studies. DEWEY : 660 ISSN : 0888-5885 En ligne : http://pubs.acs.org/doi/abs/10.1021/ie9005996