| Title |
Clustering Algorithm Considering Performance Deviation of Reusable Batteries Using DBSCAN and PCA method |
| Authors |
Je-Yeong Lim ; Jong-Hun Lim ; Dong-Hwan Kim ; Byoung-Kuk Lee |
| DOI |
https://doi.org/10.6113/TKPE.2023.28.4.299 |
| Keywords |
Reusable battery; Second use battery; Machine learning; Clustering algorithm |
| Abstract |
This study proposes a clustering algorithm that considers performance deviation in parameters and a data-preprocessing method for reusable batteries. The proposed method regroups battery cells by considering the density and performance deviation of a battery parameter dataset using the algorithm, which employs the density-based spatial clustering of applications with noise. The performance of the algorithm can be improved by data preprocessing using principal component analysis, which can prevent the performance degradation of the clustering algorithm. This study verifies the feasibility of the proposed algorithm by comparing it with general clustering algorithms such as k-means clustering and the Gaussian mixture model. |