Lithium-Ion Cell Screening With Convolutional Neural Networks Based on Two-Step Time-Series Clustering and Hybrid Resampling for Imbalanced Data

Due to the material variations of lithium-ion cells and fluctuations in their manufacturing precision, differences exist in electrochemical characteristics of cells, which inevitably lead to a reduction in the available capacity and premature failure of a battery pack with multiple cells configured in series, parallel, and series parallel. Screening cells that have similar electrochemical characteristics to overcome the inconsistency among cells in a battery pack is a challenging problem. This paper proposes an approach for lithium-ion cell screening using convolutional neural networks (CNNs) based on two-step time-series clustering (TTSC) and hybrid resampling for imbalanced data, which takes into account the dynamic characteristics of lithium-ion cells, thus ensuring that the screened cells have similar electrochemical characteristics. In this approach, we propose the TTSC to label the raw samples and propose the hybrid resampling method to solve the sample imbalance issue, thereby obtaining labeled and balanced datasets and establishing the CNN model for online cell screening. Finally, industrial applications verify the effectiveness of the proposed approach and the inconsistency rate of the screened cells drops by 91.08%.