2026/01/01 by Eunbin Noh, Haein Jeon, Jinseo Kim +6
Biochemistry, Genetics and Molecular Biology · Chemistry · Engineering · #Advanced Electron Microscopy Techniques and Applications #Advancements in Battery Materials #Electrochemical Analysis and Applications
paper · doi:10.1155/er/3779468
openalex publication_date 2026/01/01 · openalex created_date 2026/07/30 · openalex updated_date 2026/07/31
Calendering is a critical electrode fabrication process that significantly affects the microstructural and electrochemical properties of Ni‐rich lithium‐ion battery (LIB) cathodes, yet its influence on high‐rate performance remains insufficiently quantified. In this study, we investigate the impact of calendering conditions on the high‐rate performance of Ni‐rich cathodes through a combined experimental and scanning electron microscopy (SEM) image‐based machine‐learning approach. Electrochemical measurements reveal distinct performance variations at high C‐rates depending on the degree of calendering, which are correlated with structural and interfacial changes observed by X‐ray characterization. To capture calendering‐induced microstructural features, 474 SEM images obtained under four calendering conditions were analyzed using an ImageNet‐pretrained EfficientNet‐B0 classifier. The classifier distinguished the four calendering‐induced SEM‐image classes with an accuracy of 0.901 ± 0.015 and a macro‐F1 score of 0.900 ± 0.016. The SEM‐image classes correspond to calendering‐induced electrode states with different measured high‐rate behaviors. This work provides new insights into the relationship between electrode manufacturing conditions and battery performance and highlights the potential of image‐based machine learning for calendering optimization and advanced cathode design.