Machine learning-based assessment of the impact of the manufacturing process on battery electrode heterogeneity

Abstract

Electrode manufacturing process strongly impacts lithium-ion battery characteristics. The electrode slurry properties and the coating parameters are among the main factors influencing the electrode heterogeneity which impacts the battery cell performance and lifetime. However, the analysis of the impact of electrode manufacturing parameters on the electrode heterogeneity is difficult to be quantified and automatized due to the large number of parameters that can be adjusted in the process. In this work, a data-driven methodology was developed for automatic assessment of the impact of parameters such as the formulation and liquid-to-solid ratio in the slurry, and the gap used for its coating on the current collector, on the electrodes heterogeneity. A dataset generated by experimental measurements was used for training and testing a Machine Learning (ML) classifier namely Gaussian Naives Bayes algorithm, for predicting if an electrode is homogeneous or heterogeneous depending on the manufacturing parameters. Lastly, through a 2D representation, the impact of the manufacturing parameters on the electrode heterogeneity was assessed in detail, paving the way towards a powerful tool for the optimization of next generation of battery electrodes.

Keywords

• Machine learning
• Electrode manufacturing
• Battery
• Heterogeneity
• Data analysis