Entwicklung einer Methode zum Einsatz von Reinforcement Learning für die dynamische Fertigungsdurchlaufsteuerung

This work aims to develop a method that can reschedule the matrix production in the case of a disruption. For this purpose, different artificial intelligence methods are combined in a novel way. The developed method is validated on a theoretical and a real scheduling case.

Bibliographic Details
Main Author: Lohse, Oliver
Format: eBook
Published: KIT Scientific Publishing 2023
Series:Reihe Informationsmanagement im Engineering Karlsruhe
Subjects:
Online Access:
Collection: Directory of Open Access Books - Collection details see MPG.ReNa
LEADER 01776nma a2200313 u 4500
001 EB002158897
003 EBX01000000000000001297012
005 00000000000000.0
007 cr|||||||||||||||||||||
008 230515 ||| deu
020 |a 1000156002 
100 1 |a Lohse, Oliver 
245 0 0 |a Entwicklung einer Methode zum Einsatz von Reinforcement Learning für die dynamische Fertigungsdurchlaufsteuerung  |h Elektronische Ressource 
260 |b KIT Scientific Publishing  |c 2023 
300 |a 1 electronic resource (208 p.) 
653 |a thema EDItEUR::T Technology, Engineering, Agriculture, Industrial processes::TG Mechanical engineering and materials 
653 |a Produktionssteuerung; Reinforcement Learning; Künstliche Intelligenz; Terminierung; Production control; artificial intelligence; scheduling 
041 0 7 |a deu  |2 ISO 639-2 
989 |b DOAB  |a Directory of Open Access Books 
490 0 |a Reihe Informationsmanagement im Engineering Karlsruhe 
500 |a Creative Commons (cc), https://creativecommons.org/licenses/by-sa/4.0/ 
024 8 |a 10.5445/KSP/1000156002 
856 4 2 |u https://directory.doabooks.org/handle/20.500.12854/99534  |z DOAB: description of the publication 
856 4 0 |u https://library.oapen.org/bitstream/20.500.12657/62536/1/entwicklung-einer-methode-zum-einsatz-von-reinforcement-learning-fur-die-dynamische-fertigungsdurchlaufsteuerung.pdf  |7 0  |x Verlag  |3 Volltext 
082 0 |a 630 
082 0 |a 700 
082 0 |a 600 
082 0 |a 620 
520 |a This work aims to develop a method that can reschedule the matrix production in the case of a disruption. For this purpose, different artificial intelligence methods are combined in a novel way. The developed method is validated on a theoretical and a real scheduling case.