Skip navigation
Please use this identifier to cite or link to this item: https://repository.esi-sba.dz/jspui/handle/123456789/579
Full metadata record
DC FieldValueLanguage
dc.contributor.authorKERMALI, ABdelfatah-
dc.date.accessioned2023-10-22T07:28:46Z-
dc.date.available2023-10-22T07:28:46Z-
dc.date.issued2023-
dc.identifier.urihttps://repository.esi-sba.dz/jspui/handle/123456789/579-
dc.descriptionEncadreur : M. Soleyman Chaib / Co-Encadreur : M. BEZOUI Madani / M. OUCHANI Samiren_US
dc.description.abstractAbstract : The evolving paradigm of Reconfigurable Manufacturing System (RMS) stands as a promising response to the rapidly changing requirements of both the market and the manufacturing systems. Characterised by its inherent flexibility, scalability and adaptability, RMS has received considerable attention in recent years. This thesis provides a comprehensive review of RMS, including a thorough exploration of their theoretical foundations, practical implementations, and emerging optimisation methods.Furthermore, this thesis presents a novel Deep Reinforcement Learning (DRL) solution for scheduling, reconfiguration, and balancing RMS problems. It highlights its potential to improve system performance and adaptability.Ultimately, this work aims to stimulate further research and development in this field and to serve as a valuable resource for researchers and practitioners seeking to harness the transformative power of RMS in modern manufacturing.*** Résumé : Le modèle évolutif des systèmes de fabrication reconfigurables (RMS) constitue une réponse prometteuse à l’évolution rapide des exigences du marché et des systèmes de fabrication. Cette thèse fournit un examen complet des RMS, y compris une exploration approfondie de leurs fondements théoriques, de leurs implémentations pratiques et des méthodes d’optimisation émergentes. En fin de compte, ce travail vise à stimuler la recherche et le développement dans le domaine des RMS et à servir de ressource précieuse pour les chercheurs et les praticiens qui cherchent à exploiter le pouvoir de transformation des RMS dans la fabrication moderne.en_US
dc.language.isoenen_US
dc.subjectReconfigurable Manufacturing Systemen_US
dc.subjectComprehensive Reviewen_US
dc.subjectRMS Analysisen_US
dc.subjectDeep Reinforcement Learningen_US
dc.subjectHierachcical Systemsen_US
dc.subjectMulti-Agent Systemsen_US
dc.titleReconfigurable Manufacturing Systems: A Comprehensive Review and A Deep Reinforcement Learning Frameworken_US
dc.typeThesisen_US
Appears in Collections:Ingénieur

Files in This Item:
File Description SizeFormat 
PFE_THESIS (1)-1-1.pdf85,87 kBAdobe PDFView/Open
Show simple item record


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.