Topological Deep Learning for Graph‑Structured EV Battery Monitoring:  Persistence-Based Features with Transformers

Ghouse Bhasa Batlapadu, Gholam Mursalin Ansari

Topological Deep Learning for Graph‑Structured EV Battery Monitoring: Persistence-Based Features with Transformers

Authors

Ghouse Bhasa Batlapadu, Gholam Mursalin Ansari

Keywords:

EV batteries, SOH prediction, shallow cycles, self-supervised learning, attention mechanism.

Abstract

Electric vehicle (EV) battery monitoring plays a major role in keeping the system efficient, safe, andlong-lasting. Many existing solutions miss deeper structural signals when battery data is collected inthe form of graphs. These solutions usually rely on local or linear patterns and are unable to capturethe full behavior of battery

References

Y. Liu, J. He, and X. Zhang, Electric vehicle battery monitoring: Challenges and solutions, IEEE Transactions on Industrial Electronics, vol. 67, no. 12, pp. 10353–10361, 2020.

J. Li, B. Liu, and S. Wang, Data-driven battery health monitoring: A review, Renewable and Sustainable Energy Reviews, vol. 113, p. 109254, 2019.

Downloads

Published

2024-11-20

How to Cite

Ghouse Bhasa Batlapadu, Gholam Mursalin Ansari. (2024). Topological Deep Learning for Graph‑Structured EV Battery Monitoring: Persistence-Based Features with Transformers . Journal of Computational Analysis and Applications (JoCAAA), 33(08), 5824–5835. Retrieved from https://eudoxuspress.com/index.php/pub/article/view/3429