Proof of concept for a new battery sorting method based on deep learning image classification
| dc.contributor.author | Blum, Fridolin | |
| dc.contributor.author | Wieczorek, Nils | |
| dc.contributor.author | Stelldinger, Peer | |
| dc.contributor.editor | Wohlgemuth, Volker | |
| dc.contributor.editor | Kranzlmüller, Dieter | |
| dc.contributor.editor | Höb, Maximilian | |
| dc.date.accessioned | 2023-12-15T09:22:25Z | |
| dc.date.available | 2023-12-15T09:22:25Z | |
| dc.date.issued | 2023 | |
| dc.description.abstract | Battery recycling requires efficient sorting based on chemical composition. Traditional methods like X-Ray or Electromagnetic Sensors lack automation, with X-Ray sorting 26 batteries and electromagnetic sorting only 6 batteries per second. We propose using deep learning image classification to detect battery manufacturer and product series. Our prototype includes a conveyor belt, webcam, ring light, and Nvidia Jetson AGX Orin. With a dataset of 9 battery series, we achieved over 99% validation accuracy using a pretrained MobileNetV2 model. The model can classify 50 images per second with limited hardware. This approach offers potential for automated sorting, significantly improving recycling throughput and efficiency. Further research should expand the dataset and explore applicability to other battery types, optimizing the model and hardware configuration. | en |
| dc.identifier.doi | 10.18420/env2023-003 | |
| dc.identifier.isbn | 978-3-88579-736-4 | |
| dc.identifier.pissn | 1617-5468 | |
| dc.identifier.uri | https://dl.gi.de/handle/20.500.12116/43351 | |
| dc.language.iso | en | |
| dc.publisher | Gesellschaft für Informatik e.V. | |
| dc.relation.ispartof | EnviroInfo 2023 | |
| dc.relation.ispartofseries | Lecture Notes in Informatics (LNI) - Proceedings, Volume P-342 | |
| dc.subject | battery recycling; deep learning; image classification | |
| dc.title | Proof of concept for a new battery sorting method based on deep learning image classification | en |
| dc.type | Text/Conference Paper | |
| gi.citation.endPage | 44 | |
| gi.citation.publisherPlace | Bonn | |
| gi.citation.startPage | 35 | |
| gi.conference.date | 11.-13. Oktober 2023 | |
| gi.conference.location | Garching, Germany | |
| gi.conference.review | full | |
| gi.conference.sessiontitle | EnvironmentalMonitoringandSensingTechnologies |
Dateien
Originalbündel
1 - 1 von 1
Vorschaubild nicht verfügbar
- Name:
- GI_Proceedings_342_Digital_Paper_3.pdf
- Größe:
- 350.13 KB
- Format:
- Adobe Portable Document Format