Documents disponibles écrits par cet auteur

General framework for latent variable model inversion for the design and manufacturing of new products / Emanuele Tomba in Industrial & engineering chemistry research, Vol. 51 N° 39 (Octobre 2012) 

Public ISBD [article]  in Industrial & engineering chemistry research > Vol. 51 N° 39 (Octobre 2012) . - pp. 12886-12900 Titre : General framework for latent variable model inversion for the design and manufacturing of new products Type de document : texte imprimé Auteurs : Emanuele Tomba, Auteur ; Massimiliano Barolo, Auteur ; Salvador García-Muñoz, Auteur Année de publication : 2012 Article en page(s) : pp. 12886-12900 Note générale : Industrial chemistry Langues : Anglais (eng) Mots-clés : Manufacturing  Design  Modeling Résumé : Latent variable regression model (LVRM) inversion is a useful tool to support the development of new products and their manufacturing conditions. The objective of the model inversion exercise is that ot finding the best combination of regressors (e.g., raw material properties, process parameters) that are needed to obtain a desired response (e.g., product quality) from the model. Each of the published applications where model inversion has been applied utilizes a tailored approach to achieve the inversion, given the specific objectives and needs. These approaches range from the direct inversion of the LVRM to the formulation of an objective function that is optimized using nonlinear programming. In this paper we present a framework that aims to give a holistic view of the optimization formulations that can arise from the need to invert an LVRM. The different sets of equations that become relevant (either as a term within the objective function or as a constraint) are discussed, and an example of these scenarios is also provided. Additional to the formulation of the different scenarios and their objective functions, this work proposes a new metric (the P2 statistic) to cross-validate the ability of the model to reconstruct the regressor vector (analogous to the Q2 statistic aimed at the predictability of the response). This new metric comes from the need to not only predict the response from the regressor, but to also reconstruct the regressors from the scores values. In this context, a discussion is provided on the effect of uncertainty in the reconstruction of the regressor (the actual design) as these values are normally given upstream as targets to the supplier of materials, or as set points to the process. ISSN : 0888-5885 En ligne : http://cat.inist.fr/?aModele=afficheN&cpsidt=26419245 [article] General framework for latent variable model inversion for the design and manufacturing of new products [texte imprimé] / Emanuele Tomba, Auteur ; Massimiliano Barolo, Auteur ; Salvador García-Muñoz, Auteur . - 2012 . - pp. 12886-12900. Industrial chemistry Langues : Anglais (eng) in Industrial & engineering chemistry research > Vol. 51 N° 39 (Octobre 2012) . - pp. 12886-12900 Mots-clés : Manufacturing  Design  Modeling Résumé : Latent variable regression model (LVRM) inversion is a useful tool to support the development of new products and their manufacturing conditions. The objective of the model inversion exercise is that ot finding the best combination of regressors (e.g., raw material properties, process parameters) that are needed to obtain a desired response (e.g., product quality) from the model. Each of the published applications where model inversion has been applied utilizes a tailored approach to achieve the inversion, given the specific objectives and needs. These approaches range from the direct inversion of the LVRM to the formulation of an objective function that is optimized using nonlinear programming. In this paper we present a framework that aims to give a holistic view of the optimization formulations that can arise from the need to invert an LVRM. The different sets of equations that become relevant (either as a term within the objective function or as a constraint) are discussed, and an example of these scenarios is also provided. Additional to the formulation of the different scenarios and their objective functions, this work proposes a new metric (the P2 statistic) to cross-validate the ability of the model to reconstruct the regressor vector (analogous to the Q2 statistic aimed at the predictability of the response). This new metric comes from the need to not only predict the response from the regressor, but to also reconstruct the regressors from the scores values. In this context, a discussion is provided on the effect of uncertainty in the reconstruction of the regressor (the actual design) as these values are normally given upstream as targets to the supplier of materials, or as set points to the process. ISSN : 0888-5885 En ligne : http://cat.inist.fr/?aModele=afficheN&cpsidt=26419245

Nearest-neighbor method for the automatic maintenance of multivariate statistical soft sensors in batch processing / Pierantonio Facco in Industrial & engineering chemistry research, Vol. 49 N° 5 (Mars 2010) 

Public ISBD [article]  in Industrial & engineering chemistry research > Vol. 49 N° 5 (Mars 2010) . - pp. 2336–2347 Titre : Nearest-neighbor method for the automatic maintenance of multivariate statistical soft sensors in batch processing Type de document : texte imprimé Auteurs : Pierantonio Facco, Auteur ; Fabrizio Bezzo, Auteur ; Massimiliano Barolo, Auteur Année de publication : 2010 Article en page(s) : pp. 2336–2347 Note générale : Industrial Chemistry Langues : Anglais (eng) Mots-clés : Multivariate  Statistical;  Soft  sensors;  Batch  polymerization Résumé : Soft sensors based on multivariate statistical models are used very frequently for the monitoring of batch processes. From the moment of model calibration onward, the model is usually assumed to be time-invariant. Unfortunately, batch process conditions are subject to several events that make the correlation structure between batches change with respect to that of the original model. This can determine a decay of the soft sensor performance, unless periodic maintenance (i.e., updating) of the model is carried out. This article proposes a methodology for the automatic maintenance of PLS soft sensors in batch processing. Whereas the adaptation scheme usually follows chronological order in classical recursive updating, the proposed strategy defines the reference data set for model recalibration as the set of batches (nearest neighbors) that are most similar to the currently running batch. The nearest neighbors to a running batch are identified during the initial evolution of the batch following a concept of proximity in the latent space of principal components. In this way, for any new batch to be run, a model can be tailored on the running batch itself. The effectiveness of the proposed updating methodology is evaluated in two case studies related to the development of adaptive soft sensors for real-time product quality monitoring: a simulated fed-batch process for the production of penicillin and an industrial batch polymerization process for the production of a resin. Note de contenu : Bibliogr. ISSN : 0888-5885 En ligne : http://pubs.acs.org/doi/abs/10.1021/ie9013919 [article] Nearest-neighbor method for the automatic maintenance of multivariate statistical soft sensors in batch processing [texte imprimé] / Pierantonio Facco, Auteur ; Fabrizio Bezzo, Auteur ; Massimiliano Barolo, Auteur . - 2010 . - pp. 2336–2347. Industrial Chemistry Langues : Anglais (eng) in Industrial & engineering chemistry research > Vol. 49 N° 5 (Mars 2010) . - pp. 2336–2347 Mots-clés : Multivariate  Statistical;  Soft  sensors;  Batch  polymerization Résumé : Soft sensors based on multivariate statistical models are used very frequently for the monitoring of batch processes. From the moment of model calibration onward, the model is usually assumed to be time-invariant. Unfortunately, batch process conditions are subject to several events that make the correlation structure between batches change with respect to that of the original model. This can determine a decay of the soft sensor performance, unless periodic maintenance (i.e., updating) of the model is carried out. This article proposes a methodology for the automatic maintenance of PLS soft sensors in batch processing. Whereas the adaptation scheme usually follows chronological order in classical recursive updating, the proposed strategy defines the reference data set for model recalibration as the set of batches (nearest neighbors) that are most similar to the currently running batch. The nearest neighbors to a running batch are identified during the initial evolution of the batch following a concept of proximity in the latent space of principal components. In this way, for any new batch to be run, a model can be tailored on the running batch itself. The effectiveness of the proposed updating methodology is evaluated in two case studies related to the development of adaptive soft sensors for real-time product quality monitoring: a simulated fed-batch process for the production of penicillin and an industrial batch polymerization process for the production of a resin. Note de contenu : Bibliogr. ISSN : 0888-5885 En ligne : http://pubs.acs.org/doi/abs/10.1021/ie9013919

Online model-based redesign of experiments for parameter estimation in dynamic systems / Federico Galvanin in Industrial & engineering chemistry research, Vol. 48 N° 9 (Mai 2009) 

Public ISBD [article]  in Industrial & engineering chemistry research > Vol. 48 N° 9 (Mai 2009) . - pp. 4415–4427 Titre : Online model-based redesign of experiments for parameter estimation in dynamic systems Type de document : texte imprimé Auteurs : Federico Galvanin, Auteur ; Massimiliano Barolo, Auteur ; Fabrizio Bezzo, Auteur Année de publication : 2009 Article en page(s) : pp. 4415–4427 Note générale : Chemical engineering Langues : Anglais (eng) Mots-clés : Dynamic  systems  Online  model-based Résumé : The optimal model-based design of experiments aims at designing a set of dynamic experiments yielding the most informative process data to be used for the estimation of the parameters of a first-principles dynamic process model. According to the usual procedure for parameter estimation, the experiment is first designed offline; then, the experiment is carried out in the plant, and process measurements are collected; and finally, parameters are estimated after completion of the experiment. Therefore, the information gathered during the evolution of the experiment is analyzed only at the end of the experiment itself. Since the experiment is designed on the basis of the parameter estimates available before the experiment is started, the progressive increase of the information resulting from the progress of the experiment is not exploited by the designer until the end of that experiment. In this paper, a strategy for the online model-based redesign of experiments is proposed to exploit the information as soon as it is generated from the execution of an experiment, and its performance is compared to that of a standard optimal experiment design approach. Intermediate parameter estimations are carried out while the experiment is running, and by exploiting the information obtained, the experiment is partially redesigned before its termination, with the purpose of updating the experimental settings to generate more valuable information for subsequent analysis. This enables us to reduce the number of experimental trials that are needed to reach a statistically sound estimation of the model parameters and results in a reduction of experimental time, raw materials needs, number of samples to be analyzed, control effort, and labor. Two simulated case studies of increasing level of complexity are used to demonstrate the benefits of the proposed approach with respect to a state-of-the-art sequential model-based experiment design. En ligne : http://pubs.acs.org/doi/abs/10.1021/ie8018356 [article] Online model-based redesign of experiments for parameter estimation in dynamic systems [texte imprimé] / Federico Galvanin, Auteur ; Massimiliano Barolo, Auteur ; Fabrizio Bezzo, Auteur . - 2009 . - pp. 4415–4427. Chemical engineering Langues : Anglais (eng) in Industrial & engineering chemistry research > Vol. 48 N° 9 (Mai 2009) . - pp. 4415–4427 Mots-clés : Dynamic  systems  Online  model-based Résumé : The optimal model-based design of experiments aims at designing a set of dynamic experiments yielding the most informative process data to be used for the estimation of the parameters of a first-principles dynamic process model. According to the usual procedure for parameter estimation, the experiment is first designed offline; then, the experiment is carried out in the plant, and process measurements are collected; and finally, parameters are estimated after completion of the experiment. Therefore, the information gathered during the evolution of the experiment is analyzed only at the end of the experiment itself. Since the experiment is designed on the basis of the parameter estimates available before the experiment is started, the progressive increase of the information resulting from the progress of the experiment is not exploited by the designer until the end of that experiment. In this paper, a strategy for the online model-based redesign of experiments is proposed to exploit the information as soon as it is generated from the execution of an experiment, and its performance is compared to that of a standard optimal experiment design approach. Intermediate parameter estimations are carried out while the experiment is running, and by exploiting the information obtained, the experiment is partially redesigned before its termination, with the purpose of updating the experimental settings to generate more valuable information for subsequent analysis. This enables us to reduce the number of experimental trials that are needed to reach a statistically sound estimation of the model parameters and results in a reduction of experimental time, raw materials needs, number of samples to be analyzed, control effort, and labor. Two simulated case studies of increasing level of complexity are used to demonstrate the benefits of the proposed approach with respect to a state-of-the-art sequential model-based experiment design. En ligne : http://pubs.acs.org/doi/abs/10.1021/ie8018356

Optimal design of clinical tests for the identification of physiological models of type 1 diabetes mellitus / Federico Galvanin in Industrial & engineering chemistry research, Vol. 48 N°4 (Février 2009) 

Public ISBD [article]  in Industrial & engineering chemistry research > Vol. 48 N°4 (Février 2009) . - pp. 1989–2002 Titre : Optimal design of clinical tests for the identification of physiological models of type 1 diabetes mellitus Type de document : texte imprimé Auteurs : Federico Galvanin, Auteur ; Massimiliano Barolo, Auteur ; Sandro Macchietto, Auteur Année de publication : 2009 Article en page(s) : pp. 1989–2002 Note générale : Chemical engineering Langues : Anglais (eng) Mots-clés : Type  1  diabetes  mellitus  Artificial  pancreas  Dynamic  simulation  model  Glucose-insulin  system Résumé : Type 1 diabetes mellitus is a disease affecting millions of people worldwide and causing the expenditure of millions of euros every year for health care. One of the most promising therapies derives from the use of an artificial pancreas, based on a control system able to maintain the normoglycaemia in the subject affected by diabetes. A dynamic simulation model of the glucose−insulin system can be useful in several circumstances for diabetes care, including testing of glucose sensors, insulin infusion algorithms, and decision support systems for diabetes. This paper considers the problem of the identification of single individual parameters in detailed dynamic models of glucose homeostasis. Optimal model-based design of experiment techniques are used to design a set of clinical tests that allow the model parameters to be estimated in a statistically sound way, while meeting constraints related to safety of the subject and ease of implementation. The model with the estimated set of parameters represents a specific subject and can thus be used for customized diabetes care solutions. Simulated results demonstrate how such an approach can improve the effectiveness of clinical tests and serve as a tool to devise safer and more efficient clinical protocols, thus providing a contribution to the development of an artificial pancreas. En ligne : http://pubs.acs.org/doi/abs/10.1021/ie801209g [article] Optimal design of clinical tests for the identification of physiological models of type 1 diabetes mellitus [texte imprimé] / Federico Galvanin, Auteur ; Massimiliano Barolo, Auteur ; Sandro Macchietto, Auteur . - 2009 . - pp. 1989–2002. Chemical engineering Langues : Anglais (eng) in Industrial & engineering chemistry research > Vol. 48 N°4 (Février 2009) . - pp. 1989–2002 Mots-clés : Type  1  diabetes  mellitus  Artificial  pancreas  Dynamic  simulation  model  Glucose-insulin  system Résumé : Type 1 diabetes mellitus is a disease affecting millions of people worldwide and causing the expenditure of millions of euros every year for health care. One of the most promising therapies derives from the use of an artificial pancreas, based on a control system able to maintain the normoglycaemia in the subject affected by diabetes. A dynamic simulation model of the glucose−insulin system can be useful in several circumstances for diabetes care, including testing of glucose sensors, insulin infusion algorithms, and decision support systems for diabetes. This paper considers the problem of the identification of single individual parameters in detailed dynamic models of glucose homeostasis. Optimal model-based design of experiment techniques are used to design a set of clinical tests that allow the model parameters to be estimated in a statistically sound way, while meeting constraints related to safety of the subject and ease of implementation. The model with the estimated set of parameters represents a specific subject and can thus be used for customized diabetes care solutions. Simulated results demonstrate how such an approach can improve the effectiveness of clinical tests and serve as a tool to devise safer and more efficient clinical protocols, thus providing a contribution to the development of an artificial pancreas. En ligne : http://pubs.acs.org/doi/abs/10.1021/ie801209g