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.
| Identifer | oai:union.ndltd.org:DRESDEN/oai:qucosa:de:qucosa:94312 |
| Date | 04 November 2024 |
| Creators | Jelibaghu, Mustafa, Eley, Michael, Rose, Oliver, Palatnik, Alexander, Rupp, Marius, Leontidou, Nikoleta |
| Contributors | Hochschule für Technik, Wirtschaft und Kultur Leipzig |
| Source Sets | Hochschulschriftenserver (HSSS) der SLUB Dresden |
| Language | English |
| Detected Language | English |
| Type | info:eu-repo/semantics/publishedVersion, doc-type:conferenceObject, info:eu-repo/semantics/conferenceObject, doc-type:Text |
| Rights | info:eu-repo/semantics/openAccess |
| Relation | urn:nbn:de:bsz:l189-qucosa2-941594, qucosa:94159 |
Page generated in 0.002 seconds