Estimation of battery SOC using a combined approach of temporal convolutional networks and Unscented Kalman Filter
Huipin Lin, Xiaoying Chen, Lei Zhang, Zhengyi Bao, Sai Tang · 2026
Read Estimation of battery SOC using a combined approach of temporal convolutional networks and Unscented Kalman Filter by Huipin Lin, Xiaoying Chen, Lei Zhang, Zhengyi Bao, Sai Tang (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13235882.txt.
Description
Lin and colleagues offer a new way to estimate how much charge an electric vehicle battery holds. That figure, the state of charge, is a core reading in any battery management system. Guessing it wrong shortens range estimates and can harm the battery, so carmakers need methods that stay accurate as conditions change.
The team pairs a temporal convolutional network, a neural model built for time series, with an Unscented Kalman Filter. The network learns patterns in the battery's recent history; the filter then steadies the output and cuts its wobble. Tested on lithium-ion batteries, the combined method aims at accuracy with smooth, trustworthy readings a driver can rely on.
Catalog record
| CREATOR | Huipin Lin, Xiaoying Chen, Lei Zhang, Zhengyi Bao, Sai Tang |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 42 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |