TY - GEN
T1 - Digital Twins of Production Systems Based on Discrete Simulation and Machine Learning Algorithms
AU - Krenczyk, Damian
N1 - Publisher Copyright:
© 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.
PY - 2023
Y1 - 2023
N2 - The implementation of the concept of a digital twin of a production system based on discrete-event simulation models, apart from the possibility of simulating the features, behavior, functioning and performance of a real counterpart, requires supplementing the model with analytical solutions. Such a solution will allow the digital twin to be included in the decision support process in the area of production management, and the obtained analysis results can be sent back to the executive elements of the production system or planning systems. The paper presents the concept and practical verification of the possibility of creating digital twins of production systems based on the integration of modern discrete simulation software with machine learning modules - reinforcement learning. This combination also gives the opportunity to effectively conduct optimization and adaptation activities and increase the level of autonomy and flexibility of production systems.
AB - The implementation of the concept of a digital twin of a production system based on discrete-event simulation models, apart from the possibility of simulating the features, behavior, functioning and performance of a real counterpart, requires supplementing the model with analytical solutions. Such a solution will allow the digital twin to be included in the decision support process in the area of production management, and the obtained analysis results can be sent back to the executive elements of the production system or planning systems. The paper presents the concept and practical verification of the possibility of creating digital twins of production systems based on the integration of modern discrete simulation software with machine learning modules - reinforcement learning. This combination also gives the opportunity to effectively conduct optimization and adaptation activities and increase the level of autonomy and flexibility of production systems.
KW - digital twin
KW - discrete-event simulation
KW - machine learning
KW - reinforcement learning
UR - https://www.scopus.com/pages/publications/85172721078
U2 - 10.1007/978-3-031-42536-3_6
DO - 10.1007/978-3-031-42536-3_6
M3 - Conference contribution
AN - SCOPUS:85172721078
SN - 9783031425356
T3 - Lecture Notes in Networks and Systems
SP - 57
EP - 66
BT - 18th International Conference on Soft Computing Models in Industrial and Environmental Applications (SOCO 2023), Proceedings
A2 - García Bringas, Pablo
A2 - Pérez García, Hilde
A2 - Martínez de Pisón, Francisco Javier
A2 - Martínez Álvarez, Francisco
A2 - Troncoso Lora, Alicia
A2 - Herrero, Álvaro
A2 - Calvo Rolle, José Luis
A2 - Quintián, Héctor
A2 - Corchado, Emilio
PB - Springer Science and Business Media Deutschland GmbH
T2 - 18th International Conference on Soft Computing Models in Industrial and Environmental Applications, SOCO 2023
Y2 - 5 September 2023 through 7 September 2023
ER -