| Title |
A Method of Battery State-of-health (SOH) Estimation based on Distributional Features of Time Series |
| Authors |
정우진(Woojin Jeong) ; 박용주(Yongju Park) ; 박진욱(Jinuk Park) |
| DOI |
https://doi.org/10.5573/ieie.2025.62.3.87 |
| Keywords |
State-of-health; Battery states; Machine learning; Time series; Feature extraction |
| Abstract |
Lithium-ion batteries, with their advantages of long lifespan and high energy density, have become a widely utilized energy source across various industries, including electric vehicles. However, as the adoption of lithium-ion batteries increases, incidents caused by battery degradation or failure are also rising, underscoring the need for models capable of analyzing battery conditions and detecting anomalies in advance. In this study, a model was developed to predict the state of health (SOH) and detect anomalies during charging processes by utilizing open-source battery charge-discharge cycle data, including voltage, current, and temperature measurements. |