High‑accuracy cell discrimination based on multiple regression combined with k‑means clustering algorithm for lithium‑ion rechargeable cells

Pyeong-Yeon Lee; Dongho Han; Jonghoon Kim

High‑accuracy cell discrimination based on multiple regression combined with k‑means clustering algorithm for lithium‑ion rechargeable cells

Pyeong-Yeon Lee

Dongho Han

Jonghoon Kim

Vol. 25, No. 4, pp. 709-723, Apr. 2025

10.1007/s43236-025-01012-6

Cell matching

Lithium-ion cell

multiple regression analysis

K-Means Clustering

Abstract

Inhomogeneity in battery pack unit cells significantly impacts their lifetime, performance, and safety. Consistent electrochemical characteristics are essential to mitigate this issue, and minimizing manufacturing tolerances is critical. This study introduces a novel approach that integrates multi-parameter screening with k-means clustering to enhance battery pack design. In contrast to traditional single-parameter sorting, which limits precision and increases performance inconsistencies, the proposed method considers a wider range of factors, including open-circuit voltage, voltage change, capacity, and partial capacity, ensuring more balanced and consistent performance while effectively addressing outliers. An analysis of 800 commercial batteries revealed high correlation factors via statistical methods. Multiple regression analysis was used to quantify their effects, and a clustering algorithm was employed to group cells with similar characteristics. The effectiveness of the proposed method was validated through electrical characteristic tests by comparing the designed battery packs.

Statistics

Show / Hide Statistics

Cumulative Counts from September 30th, 2019
Multiple requests among the same browser session are counted as one view. If you mouse over a chart, the values of data points will be shown.

Cite this article

[IEEE Style]

P. Lee, D. Han, J. Kim, "High‑accuracy cell discrimination based on multiple regression combined with k‑means clustering algorithm for lithium‑ion rechargeable cells," Journal of Power Electronics, vol. 25, no. 4, pp. 709-723, 2025. DOI: 10.1007/s43236-025-01012-6.

[ACM Style]

Pyeong-Yeon Lee, Dongho Han, and Jonghoon Kim. 2025. High‑accuracy cell discrimination based on multiple regression combined with k‑means clustering algorithm for lithium‑ion rechargeable cells. Journal of Power Electronics, 25, 4, (2025), 709-723. DOI: 10.1007/s43236-025-01012-6.