| Title |
Machine Learning-based Screening Algorithmfor Energy Storage System Using Retired Lithium-ion Batteries |
| Authors |
Eui-Seong Han ; Je-Yeong Lim ; Hyeon-Ho Lee ; Dong-Hwan Kim ; Tae-Won Noh ; Byoung-Kuk Lee |
| DOI |
https://doi.org/10.6113/TKPE.2022.27.3.265 |
| Keywords |
ESS (Energy Storage System); Retired battery; Secondary usage; Clustering method |
| Abstract |
This paper proposes a machine learning-based screening algorithm to build the retired battery pack of the energy storage system. The proposed algorithm creates the dataset of various performance parameters of the retired battery, and this dataset is preprocessed through a principal component analysis to reduce the overfitting problem. The retried batteries with a large deviation are excluded in the dataset through a density-based spatial clustering of applications with noise, and the K-means clustering method is formulated to select the group of the retired batteries to satisfy the deviation requirement conditions. The performance of the proposed algorithm is verified based on NASA and Oxford datasets. |