Documents disponibles écrits par cet auteur

A neural network and a genetic algorithm for multiobjective scheduling of semiconductor manufacturing plants / O. Baez Senties in Industrial & engineering chemistry research, Vol. 48 N° 21 (Novembre 2009) 

Public ISBD [article]  in Industrial & engineering chemistry research > Vol. 48 N° 21 (Novembre 2009) . - pp. 9546–9555 Titre : A neural network and a genetic algorithm for multiobjective scheduling of semiconductor manufacturing plants Type de document : texte imprimé Auteurs : O. Baez Senties, Auteur ; C. Azzaro-Pantel, Auteur ; L. Pibouleau, Auteur Année de publication : 2010 Article en page(s) : pp. 9546–9555 Note générale : Chemical engineering Langues : Anglais (eng) Mots-clés : Artificial  neural  network  technique  Multiobjective  genetic  algorithm  Semiconductor  manufacturing  plants Résumé : Scheduling of semiconductor wafer fabrication system is identified as a complex problem, involving multiple objectives to be satisfied simultaneously (maximization of workstation utilization and minimization of waiting time and storage, for instance). In this study, we propose a methodology based on an artificial neural network technique, for computing the various objective functions, embedded into a multiobjective genetic algorithm for multidecision scheduling problems in a semiconductor wafer fabrication environment. A discrete event simulator, developed and validated in our previous works, serves here to feed the neural network. Six criteria related to both equipment (facility average utilization) and products (average cycle time (ACT), standard deviation of ACT, average waiting time, work in process, and total storage) are chosen as significant performance indexes of the workshop. The optimization variables are the time between campaigns and the release time of batches into the plant. An industrial size example is taken as a test bench to validate the approach. En ligne : http://pubs.acs.org/doi/abs/10.1021/ie8018577 [article] A neural network and a genetic algorithm for multiobjective scheduling of semiconductor manufacturing plants [texte imprimé] / O. Baez Senties, Auteur ; C. Azzaro-Pantel, Auteur ; L. Pibouleau, Auteur . - 2010 . - pp. 9546–9555. Chemical engineering Langues : Anglais (eng) in Industrial & engineering chemistry research > Vol. 48 N° 21 (Novembre 2009) . - pp. 9546–9555 Mots-clés : Artificial  neural  network  technique  Multiobjective  genetic  algorithm  Semiconductor  manufacturing  plants Résumé : Scheduling of semiconductor wafer fabrication system is identified as a complex problem, involving multiple objectives to be satisfied simultaneously (maximization of workstation utilization and minimization of waiting time and storage, for instance). In this study, we propose a methodology based on an artificial neural network technique, for computing the various objective functions, embedded into a multiobjective genetic algorithm for multidecision scheduling problems in a semiconductor wafer fabrication environment. A discrete event simulator, developed and validated in our previous works, serves here to feed the neural network. Six criteria related to both equipment (facility average utilization) and products (average cycle time (ACT), standard deviation of ACT, average waiting time, work in process, and total storage) are chosen as significant performance indexes of the workshop. The optimization variables are the time between campaigns and the release time of batches into the plant. An industrial size example is taken as a test bench to validate the approach. En ligne : http://pubs.acs.org/doi/abs/10.1021/ie8018577

New product development with discrete event simulation / J. L. Perez-Escobedo in Industrial & engineering chemistry research, Vol. 50 N° 18 (Septembre 2011) 

Public ISBD [article]  in Industrial & engineering chemistry research > Vol. 50 N° 18 (Septembre 2011) . - pp. 10615-10629 Titre : New product development with discrete event simulation : application to portfolio management for the pharmaceutical industry Type de document : texte imprimé Auteurs : J. L. Perez-Escobedo, Auteur ; C. Azzaro-Pantel, Auteur ; L. Pibouleau, Auteur Année de publication : 2011 Article en page(s) : pp. 10615-10629 Note générale : Chimie industrielle Langues : Anglais (eng) Mots-clés : Pharmaceutical  industry  Product  development Résumé : New product development (NPD) constitutes a challenging problem in the pharmaceutical industry. Formally, the NPD problem can be stated as follows: Select a set of R&D projects from a pool of candidate projects to satisfy several criteria (e.g., economic profitability, time to market) while coping with the uncertain nature of the projects. More precisely, the recurrent key issues are to determine the projects to be developed, together with the order in which they enter the pipeline and the corresponding resource allocation. In this context, this work presents the development and implementation of a discrete event simulator for drug portfolio management based on object-oriented techniques and used as a tool for evaluating each drug or sequence of drugs. Evaluation methods based on bubble charts are used for selecting the best drugs according to the considered evaluation criteria. Imprecision modeling has been tackled in two ways: a classical probability approach and an interval-based one. Both approaches are illustrated by a numerical example, which shows that the tendencies obtained by the interval-based approach can be difficult to interpret for the decision maker, because of the growing uncertainty along the pipeline. In addition, the risk, which is taken into account through failure probability for some stages and which is strongly involved in the NPD process, must be an integral part of the modeling approach. The repetitive use of simulation with representative sampling turns out to be the most efficient strategy. DEWEY : 660 ISSN : 0888-5885 En ligne : http://cat.inist.fr/?aModele=afficheN&cpsidt=24523881 [article] New product development with discrete event simulation : application to portfolio management for the pharmaceutical industry [texte imprimé] / J. L. Perez-Escobedo, Auteur ; C. Azzaro-Pantel, Auteur ; L. Pibouleau, Auteur . - 2011 . - pp. 10615-10629. Chimie industrielle Langues : Anglais (eng) in Industrial & engineering chemistry research > Vol. 50 N° 18 (Septembre 2011) . - pp. 10615-10629 Mots-clés : Pharmaceutical  industry  Product  development Résumé : New product development (NPD) constitutes a challenging problem in the pharmaceutical industry. Formally, the NPD problem can be stated as follows: Select a set of R&D projects from a pool of candidate projects to satisfy several criteria (e.g., economic profitability, time to market) while coping with the uncertain nature of the projects. More precisely, the recurrent key issues are to determine the projects to be developed, together with the order in which they enter the pipeline and the corresponding resource allocation. In this context, this work presents the development and implementation of a discrete event simulator for drug portfolio management based on object-oriented techniques and used as a tool for evaluating each drug or sequence of drugs. Evaluation methods based on bubble charts are used for selecting the best drugs according to the considered evaluation criteria. Imprecision modeling has been tackled in two ways: a classical probability approach and an interval-based one. Both approaches are illustrated by a numerical example, which shows that the tendencies obtained by the interval-based approach can be difficult to interpret for the decision maker, because of the growing uncertainty along the pipeline. In addition, the risk, which is taken into account through failure probability for some stages and which is strongly involved in the NPD process, must be an integral part of the modeling approach. The repetitive use of simulation with representative sampling turns out to be the most efficient strategy. DEWEY : 660 ISSN : 0888-5885 En ligne : http://cat.inist.fr/?aModele=afficheN&cpsidt=24523881