Depth analysis of battery performance based on a data-driven approach

Abstract

Capacity degradation remains a significant challenge in the current application of the cells. The disintegration mechanism is well known to be very complex across the system. Understanding this intricate process and accurately predicting it pose considerable challenges. Thus, the machine learning (ML) technology is employed to predict the specific capacity changes of the cell throughout the cycle and grasp this intricate procedure. In contrast to prior work, this study introduces the WOA-ELM model, achieving an impressive R2 = 0.9998, the key factors affecting the specific capacity of the battery are determined, and the defects in the machine learning black box are overcome by the interpretable model. Their connection with the structural damage of electrode materials and battery failure during battery cycling is comprehensively explained, revealing their essentiality to battery performance. These findings contribute to enhanced research on contemporary batteries and potential modifications.