- Titel
- Charging strategies for AGVs using supervised learning
- Zitierfähige Url:
- https://nbn-resolving.org/urn:nbn:de:bsz:l189-qucosa2-943125
- Konferenz
- KI 2024 - 47th German Conference on Artificial Intelligence. Würzburg, 25.-27.09.2024
- Quellenangabe
- Workshop Proceedings AI in Production - 1
Herausgeber: Martin Krockert
Herausgeber: Torsten Munkelt
Erscheinungsort: Leipzig
Verlag: Hochschule für Technik, Wirtschaft und Kultur Leipzig
Erscheinungsjahr: 2024
Titel Schriftenreihe: AI in Production
Bandnummer Schriftenreihe: 1
Auflage: 1 - DOI
- https://doi.org/10.33968/2024.75
- Abstract (EN)
- This study introduces a method to optimize charging strategies for Automated Guided Vehicles in warehouses and logistics centers, aiming to enhance efficiency and reduce downtime. Using Tecnomatix Plant Simulation, a model with two vehicles and two charging stations was created to simulate realistic delivery scenarios, generating data on order duration, energy consumption, and vehicle charging times. This data was optimized with CPLEX to determine the best order sequences and loading schedules. The key challenge addressed is optimizing Automated Guided Vehicle charging strategies to maximize operational readiness and energy efficiency. A supervised learning approach was used, where a neural network predicts if an Automated Guided Vehicle should charge based on its State of Charge and current order backlog. The model was developed in Python, using an 80-20 split for training and testing. The study demonstrates the effectiveness of machine learning in improving Automated Guided Vehicle fleet management, providing a data-driven solution for real-time decision-making.
- Freie Schlagwörter (EN)
- Automated Guided Vehicles, Supervised Learning, Charging Strategies
- Herausgeber (Institution)
- Hochschule für Technik, Wirtschaft und Kultur Leipzig, Leipzig
- Version / Begutachtungsstatus
- publizierte Version / Verlagsversion
- URN Qucosa
- urn:nbn:de:bsz:l189-qucosa2-943125
- Veröffentlichungsdatum Qucosa
- 04.11.2024
- Dokumenttyp
- Konferenzbeitrag
- Sprache des Dokumentes
- Englisch
- Lizenz / Rechtehinweis
CC BY 4.0