Hasselwander, Samuel und Rettich, Julian und Schmid, Stephan und Siefkes, Tjark (2025) How will future BEV models develop? Market potential of different battery technologies assessed by a ML-based manufacturer agent. Journal of Energy Storage, 131 (A). Elsevier. doi: 10.1016/j.est.2025.117195. ISSN 2352-152X.
![]() |
PDF
- Verlagsversion (veröffentlichte Fassung)
2MB |
Offizielle URL: https://www.sciencedirect.com/science/article/pii/S2352152X25019085
Kurzfassung
The ramp up of battery electric vehicles is already in full swing, with multiple countries having implemented regulations to defossilize their vehicle fleets. This is leading to a growing number of vehicle models that are becoming increasingly diverse, with even fundamental differences in battery chemistry. However, it is important to understand which energy storage technology will be used in future vehicles in order to recognize and avoid dependencies on raw materials or supply chains at an early stage. By developing a machine learning based manufacturer agent trained on historic vehicle data from models available in Germany and a comprehensive technology and component database, we show that it is possible to predict the market potential of bottom-up calculated future battery electric vehicle models. Our findings align with the current trend towards diversifying vehicle models through the adoption of various cell chemistries. The results indicate that vehicles equipped with lithium iron phosphate or even sodium-ion batteries, particularly those utilizing cell-to-pack technology, demonstrate significant market potential in the near future, especially for small vehicles.
elib-URL des Eintrags: | https://elib.dlr.de/215600/ | ||||||||||||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Dokumentart: | Zeitschriftenbeitrag | ||||||||||||||||||||
Titel: | How will future BEV models develop? Market potential of different battery technologies assessed by a ML-based manufacturer agent | ||||||||||||||||||||
Autoren: |
| ||||||||||||||||||||
Datum: | 20 September 2025 | ||||||||||||||||||||
Erschienen in: | Journal of Energy Storage | ||||||||||||||||||||
Referierte Publikation: | Ja | ||||||||||||||||||||
Open Access: | Ja | ||||||||||||||||||||
Gold Open Access: | Nein | ||||||||||||||||||||
In SCOPUS: | Ja | ||||||||||||||||||||
In ISI Web of Science: | Ja | ||||||||||||||||||||
Band: | 131 | ||||||||||||||||||||
DOI: | 10.1016/j.est.2025.117195 | ||||||||||||||||||||
Herausgeber: |
| ||||||||||||||||||||
Verlag: | Elsevier | ||||||||||||||||||||
ISSN: | 2352-152X | ||||||||||||||||||||
Status: | veröffentlicht | ||||||||||||||||||||
Stichwörter: | Battery electric vehicle; Market potential; Technology assessment;Machine learning; Neural network | ||||||||||||||||||||
HGF - Forschungsbereich: | Luftfahrt, Raumfahrt und Verkehr | ||||||||||||||||||||
HGF - Programm: | Verkehr | ||||||||||||||||||||
HGF - Programmthema: | Verkehrssystem | ||||||||||||||||||||
DLR - Schwerpunkt: | Verkehr | ||||||||||||||||||||
DLR - Forschungsgebiet: | V VS - Verkehrssystem | ||||||||||||||||||||
DLR - Teilgebiet (Projekt, Vorhaben): | V - MoDa - Models and Data for Future Mobility_Supporting Services | ||||||||||||||||||||
Standort: | Stuttgart | ||||||||||||||||||||
Institute & Einrichtungen: | Institut für Fahrzeugkonzepte > Fahrzeugsysteme und Technologiebewertung | ||||||||||||||||||||
Hinterlegt von: | Hasselwander, Samuel | ||||||||||||||||||||
Hinterlegt am: | 13 Aug 2025 11:06 | ||||||||||||||||||||
Letzte Änderung: | 13 Aug 2025 11:06 |
Nur für Mitarbeiter des Archivs: Kontrollseite des Eintrags