BatCAT deliverable 5.1: Cellular neural networks and multicriteria optimization
This deliverable reports on the development and results of advanced battery health optimization and performance within T5.1 of the project. The work focuses on creating a self-supervised cellular neural network predictor to provide real-time and adaptable battery state of health by leveraging a student-teacher learning framework. Additionally, the deliverable covers T5.2, i.e., the implementation of multicriteria optimization for dynamic, staged constant-current charging protocols, which enables optimized balance charging speed, safety, and battery longevity.
Authors
- Marco Baldan (ORCID: https://orcid.org/0000-0002-5803-3150)
- Fadi Al Machot
- Peter Klein
- Aditya Dey
Institutions
- Fraunhofer Institute for Industrial Mathematics (DE)
- Fraunhofer Institute for Industrial Engineering (DE)
- Norwegian University of Life Sciences (NO)
Publication Details
- Journal
- Zenodo (CERN European Organization for Nuclear Research)
- Published
- 2025-06-29
- DOI
- https://doi.org/10.5281/zenodo.18063373
- Primary Topic
- Advanced Battery Technologies Research
- Type
- article
- Field-Weighted Citation Impact
- 0.00