Abstract
This short paper presents a recently reported dynamic data-driven method, Symbolic Dynamic Filtering (SDF), for real-time estimation of the state-of-health (SOH) and state-of-charge (SOC) in lead-acid batteries, as an alternative to model-based analysis techniques. In particular, SOC estimation relies on a k-NN regression algorithm while SOH estimation is obtained from the divergence between extracted features. The results show that the proposed data-driven method successfully distinguishes battery voltage responses under different SOC and SOH situations.
| Original language | English (US) |
|---|---|
| Pages (from-to) | 758-764 |
| Number of pages | 7 |
| Journal | Journal of Power Sources |
| Volume | 268 |
| DOIs | |
| State | Published - Dec 5 2014 |
All Science Journal Classification (ASJC) codes
- Renewable Energy, Sustainability and the Environment
- Energy Engineering and Power Technology
- Physical and Theoretical Chemistry
- Electrical and Electronic Engineering
