- author = "Lorena {Silva Belisario}",
- title = "Contribution de l'apprentissage par simulation a l'auto-adaptation des systemes de production",
- title_anglais = "Simulation-based machine learning for the self-adaptation of manufacturing systems",
- school = "Universite Blaise Pascal",
- year = "2015",
- address = "Clermont-Ferrand 2, France",
- month = "12 " # nov,
- keywords = "genetic algorithms, genetic programming, microGP, linear genetic programming, Manufacturing systems, self-adaptation, decision support, knowledge extraction, machine learning, simulation, Fabrication, Systemes flexibles de -- Theses et ecrits academiques Programmation genetique (informatique) -- Theses et ecrits academiques Systemes de production Auto-adaptation Aide a la decision Extraction de connaissances Apprentissage automatique Simulation Programmation genetique lineaire",
- bibsource = "OAI-PMH server at api.archives-ouvertes.fr",
- contributor = "de Mod{\'e}lisation et d'optimisation des Syst{\`e}mes Laboratoire d'Informatique and Henri Pierreval",
- identifier = "NNT : 2015CLF22617; tel-01325229",
- language = "fr",
- oai = "oai:HAL:tel-01325229v1",
-
source = "Autre. Universit{\'e} Blaise Pascal - Clermont-Ferrand
II, 2015. Fran{\c c}ais.
", - URL = "
http://www.theses.fr/2015CLF22617",
- URL = "
http://www.sudoc.fr/191999954",
- URL = "
https://tel.archives-ouvertes.fr/tel-01325229",
- URL = "
https://tel.archives-ouvertes.fr/tel-01325229/document",
- URL = "
https://tel.archives-ouvertes.fr/tel-01325229/file/SILVA_BELISARIO_2015CLF22617.pdf",
- size = "260 pages",
- abstract = "Manufacturing systems must be able to continuously adapt their characteristics to cope with the different changes that occur along their life, in order to remain efficient and competitive. These changes can take the form of the evolution of customers demand for instance. It is essential for these systems to determine when and how to adapt (e.g., through changes in capacities). Unfortunately, such issues are known to be difficult. As manufacturing systems are complex, dynamic and specific in nature, their managers do not always have all the necessary expertise nor accurate enough forecasts on the evolution of their system. This thesis aims at studying the possible contributions of machine learning to the self-adaptation of manufacturing systems. We first study how the literature deals with self-adaptation and we propose a conceptual framework to facilitate the analysis and the formalization of the associated problems. Then, we study a learning strategy relying on models, which presents the advantage of not requiring any training set. We focus more precisely on a new approach based on linear genetic programming that iteratively extracts knowledge from a simulation model. Our approach is implemented using Arena and microGP. We show its benefits by applying it to increase/decrease the number of cards in a pull control system, to move machines or to change the inventory replenishment policy. The extracted knowledge is found to be relevant for continuously determining how each system can adapt to evolutions. It can therefore contribute to provide these systems with some intelligent capabilities. Moreover, this knowledge is expressed in the simple and understandable form of a decision tree, so that it can also be easily communicated to production managers in view of their everyday use. Our results thus show the interest of our approach while opening many research directions.",
- abstract = "Pour rester performants et competitifs, les systemes de production doivent etre capables de s'adapter pour faire face aux changements tels que l'evolution de la demande des clients. Il leur est essentiel de pouvoir determiner quand et comment s'adapter (capacites, etc.). Malheureusement, de tels problemes sont connus pour etre difficiles. Les systemes de production etant complexes, dynamiques et specifiques, leurs gestionnaires n'ont pas toujours l'expertise necessaire ni les previsions suffisantes concernant l'evolution de leur systeme. Cette these vise a etudier la contribution que peut apporter l'apprentissage automatique a l'auto-adaptation des systemes de production. Dans un premier temps, nous etudions la facon dont la litterature aborde ce domaine et en proposons un cadre conceptuel dans le but de faciliter l'analyse et la formalisation des problemes associes. Ensuite, nous etudions une strategie d'apprentissage a partir de modeles qui ne necessite pas d'ensemble d'apprentissage. Nous nous interessons plus precisement a une nouvelle approche basee sur la programmation genetique lineaire visant a extraire des connaissances iterativement a partir d'un modele de simulation pour determiner quand et quoi faire evoluer. Notre approche est implementee a l'aide d'Arena et uGP. Nous l'appliquons a differents exemples qui concernent l'ajout/retrait de cartes dans un systeme a flux tire, le demenagement de machines ou encore le changement de politique de reapprovisionnement. Les connaissances qui en sont extraites s'averent pertinentes et permettent de determiner en continu comment chaque systeme peut s'adapter a des evolutions. De ce fait, elles peuvent contribuer a doter un systeme d'une forme d'intelligence. Exprimees sous forme d'un arbre de decision, elles sont par ailleurs facilement communicables a un gestionnaire de production. Les resultats obtenus montrent ainsi l'interet de notre approche tout en ouvrant de nombreuses voies de recherche.",
- notes = "In French. Expected online June 2016.
Supervisor: Henri Pierreval
National Thesis number : 2015CLF22617 oai:HAL:tel-01325229v1
",
- URL = "
