Documents disponibles écrits par cet auteur

Data-derived analysis and inference for an industrial deethanizer / Francesco Corona in Industrial & engineering chemistry research, Vol. 51 N° 42 (Octobre 2012)

Public ISBD [article]  in Industrial & engineering chemistry research > Vol. 51 N° 42 (Octobre 2012) . - pp. 13732–13742 Titre : Data-derived analysis and inference for an industrial deethanizer Type de document : texte imprimé Auteurs : Francesco Corona, Auteur ; Michela Mulas, Auteur ; Roberto Baratti, Auteur Année de publication : 2012 Article en page(s) : pp. 13732–13742 Note générale : Industrial chemistry Langues : Anglais (eng) Résumé : This paper presents an application of data-derived approaches for analyzing and monitoring industrial processes. The discussed methods are used in visualizing process measurements, extracting operational information, and designing estimation models for primary process variables otherwise difficult to measure in real-time. Emphasis is given to the modeling of the data with two classical machine learning paradigms; the self-organizing map (SOM) and the multi-layer perceptron (MLP). The effectiveness of the proposed approach is validated on an industrial deethanizer, where the goal is to identify operational modes and most sensitive variables for this full-scale unit, as well as design an inferential model for a critical process variable, the bottom ethane concentration. The study led to the definition of a fully automated monitoring tool to be implemented online in the plant’s distributed control system. The results confirmed the potential of the data-derived approach, and based on the analysis, the existing control configuration of the unit could be redefined toward more consistent operations. Because it is general and modular by design, the tool can be easily used for other processes. [article] Data-derived analysis and inference for an industrial deethanizer [texte imprimé] / Francesco Corona, Auteur ; Michela Mulas, Auteur ; Roberto Baratti, Auteur . - 2012 . - pp. 13732–13742. Industrial chemistry Langues : Anglais (eng) in Industrial & engineering chemistry research > Vol. 51 N° 42 (Octobre 2012) . - pp. 13732–13742 Résumé : This paper presents an application of data-derived approaches for analyzing and monitoring industrial processes. The discussed methods are used in visualizing process measurements, extracting operational information, and designing estimation models for primary process variables otherwise difficult to measure in real-time. Emphasis is given to the modeling of the data with two classical machine learning paradigms; the self-organizing map (SOM) and the multi-layer perceptron (MLP). The effectiveness of the proposed approach is validated on an industrial deethanizer, where the goal is to identify operational modes and most sensitive variables for this full-scale unit, as well as design an inferential model for a critical process variable, the bottom ethane concentration. The study led to the definition of a fully automated monitoring tool to be implemented online in the plant’s distributed control system. The results confirmed the potential of the data-derived approach, and based on the analysis, the existing control configuration of the unit could be redefined toward more consistent operations. Because it is general and modular by design, the tool can be easily used for other processes.

Data-derived analysis and inference for an industrial deethanizer / Francesco Corona in Industrial & engineering chemistry research, Vol. 51 N° 42 (Octobre 2012) 

Public ISBD [article]  in Industrial & engineering chemistry research > Vol. 51 N° 42 (Octobre 2012) . - pp. 13732–13742 Titre : Data-derived analysis and inference for an industrial deethanizer Type de document : texte imprimé Auteurs : Francesco Corona, Auteur ; Michela Mulas, Auteur ; Roberto Baratti, Auteur Année de publication : 2012 Article en page(s) : pp. 13732–13742 Note générale : Industrial chemistry Langues : Anglais (eng) Mots-clés : Industrial  processes Résumé : This paper presents an application of data-derived approaches for analyzing and monitoring industrial processes. The discussed methods are used in visualizing process measurements, extracting operational information, and designing estimation models for primary process variables otherwise difficult to measure in real-time. Emphasis is given to the modeling of the data with two classical machine learning paradigms; the self-organizing map (SOM) and the multi-layer perceptron (MLP). The effectiveness of the proposed approach is validated on an industrial deethanizer, where the goal is to identify operational modes and most sensitive variables for this full-scale unit, as well as design an inferential model for a critical process variable, the bottom ethane concentration. The study led to the definition of a fully automated monitoring tool to be implemented online in the plant’s distributed control system. The results confirmed the potential of the data-derived approach, and based on the analysis, the existing control configuration of the unit could be redefined toward more consistent operations. Because it is general and modular by design, the tool can be easily used for other processes. ISSN : 0888-5885 En ligne : http://pubs.acs.org/doi/abs/10.1021/ie202854b [article] Data-derived analysis and inference for an industrial deethanizer [texte imprimé] / Francesco Corona, Auteur ; Michela Mulas, Auteur ; Roberto Baratti, Auteur . - 2012 . - pp. 13732–13742. Industrial chemistry Langues : Anglais (eng) in Industrial & engineering chemistry research > Vol. 51 N° 42 (Octobre 2012) . - pp. 13732–13742 Mots-clés : Industrial  processes Résumé : This paper presents an application of data-derived approaches for analyzing and monitoring industrial processes. The discussed methods are used in visualizing process measurements, extracting operational information, and designing estimation models for primary process variables otherwise difficult to measure in real-time. Emphasis is given to the modeling of the data with two classical machine learning paradigms; the self-organizing map (SOM) and the multi-layer perceptron (MLP). The effectiveness of the proposed approach is validated on an industrial deethanizer, where the goal is to identify operational modes and most sensitive variables for this full-scale unit, as well as design an inferential model for a critical process variable, the bottom ethane concentration. The study led to the definition of a fully automated monitoring tool to be implemented online in the plant’s distributed control system. The results confirmed the potential of the data-derived approach, and based on the analysis, the existing control configuration of the unit could be redefined toward more consistent operations. Because it is general and modular by design, the tool can be easily used for other processes. ISSN : 0888-5885 En ligne : http://pubs.acs.org/doi/abs/10.1021/ie202854b

Systematic approach to the design of operation and control policies in activated sludge systems / Antonio C. B. De Araujo in Industrial & engineering chemistry research, Vol. 50 N° 14 (Juillet 2011) 

Public ISBD [article]  in Industrial & engineering chemistry research > Vol. 50 N° 14 (Juillet 2011) . - pp. 8542–8557 Titre : Systematic approach to the design of operation and control policies in activated sludge systems Type de document : texte imprimé Auteurs : Antonio C. B. De Araujo, Auteur ; Simone Gallani, Auteur ; Michela Mulas, Auteur Année de publication : 2011 Article en page(s) : pp. 8542–8557 Note générale : Chimie industrielle Langues : Anglais (eng) Mots-clés : Biological  wastewater  treatment  process  Activated  sludge Résumé : This article describes the systematic design of a control structure for a biological wastewater treatment process as given by the test-bed Benchmark Simulation Model No. 1 (BSM1) and Activated Sludge Model No. 1 (ASM1). The objective of this work was to formalize and implement a systematic and yet simple procedure for the selection of control structures in wastewater treatment plants (WWTPs) and to show that the application of the proposed methodology agrees with the “empirical”’ findings regarding the operation of this process. The motivation underlying this endeavor was to search for a control configuration that leads to optimal economic operation while promptly rejecting disturbances at lower layers in the control hierarchy, thus avoiding violation of the more important regulatory constraints on effluent discharge. We started by optimizing a steady-state nonlinear model of the process for various important disturbances. The results confirmed that it is economically optimal to control the oxygen concentration in the aerobic basins and the nitrate in the second anoxic tank at their respective lower bounds, whereas the effluent ammonia from the bioreactors should be controlled at its upper limit. In addition, because it is good practice to operate with minimal manipulation, the wastage flow rate should be fixed at its nominal optimal set point. The proposed decentralized control configuration, consisting of simple PI controllers, is capable of maintaining the process well within the regulatory limits at a small cost when dynamic disturbances represented by three weather files affect the process, therefore suggesting that, according to the applied systematic methodology, more complex (multivariable) regulators are not necessary for the ASM1 process. DEWEY : 660 ISSN : 0888-5885 En ligne : http://pubs.acs.org/doi/abs/10.1021/ie101703s [article] Systematic approach to the design of operation and control policies in activated sludge systems [texte imprimé] / Antonio C. B. De Araujo, Auteur ; Simone Gallani, Auteur ; Michela Mulas, Auteur . - 2011 . - pp. 8542–8557. Chimie industrielle Langues : Anglais (eng) in Industrial & engineering chemistry research > Vol. 50 N° 14 (Juillet 2011) . - pp. 8542–8557 Mots-clés : Biological  wastewater  treatment  process  Activated  sludge Résumé : This article describes the systematic design of a control structure for a biological wastewater treatment process as given by the test-bed Benchmark Simulation Model No. 1 (BSM1) and Activated Sludge Model No. 1 (ASM1). The objective of this work was to formalize and implement a systematic and yet simple procedure for the selection of control structures in wastewater treatment plants (WWTPs) and to show that the application of the proposed methodology agrees with the “empirical”’ findings regarding the operation of this process. The motivation underlying this endeavor was to search for a control configuration that leads to optimal economic operation while promptly rejecting disturbances at lower layers in the control hierarchy, thus avoiding violation of the more important regulatory constraints on effluent discharge. We started by optimizing a steady-state nonlinear model of the process for various important disturbances. The results confirmed that it is economically optimal to control the oxygen concentration in the aerobic basins and the nitrate in the second anoxic tank at their respective lower bounds, whereas the effluent ammonia from the bioreactors should be controlled at its upper limit. In addition, because it is good practice to operate with minimal manipulation, the wastage flow rate should be fixed at its nominal optimal set point. The proposed decentralized control configuration, consisting of simple PI controllers, is capable of maintaining the process well within the regulatory limits at a small cost when dynamic disturbances represented by three weather files affect the process, therefore suggesting that, according to the applied systematic methodology, more complex (multivariable) regulators are not necessary for the ASM1 process. DEWEY : 660 ISSN : 0888-5885 En ligne : http://pubs.acs.org/doi/abs/10.1021/ie101703s