RUBoost-Based Ensemble Machine Learning for Electrode Quality Classification in Li-ion Battery Manufacturing

As a typical mechatronics system, the battery manufacturing chain becomes a hot research topic because it directly determines electrode quality, further affecting manufactured battery performance. Due to the complexity of battery manufacturing, an effective sensitivity analysis solution that could quantify variable importance or correlations and explore impact variables toward resulting the electrode quality is urgently needed. This article scrutinizes the effects of component parameters from the mixing stage on the manufactured results of Li-ion battery electrode via classification modeling. Specifically, an effective RUBoost-based ensemble learning framework is proposed to compensate for class imbalance issue and well classify three key quality indicators including the electronic conductivity, thickness, and half-cell capacity for both LiFePO <formula><tex>$_4$</tex></formula>- and Li<formula><tex>$_4$</tex></formula> Ti<formula><tex>$_5$</tex></formula>O<formula><tex>$_{12}$</tex></formula>-based electrode. Experimental results reveal that the proposed models could well handle the class imbalance issues and accurately classify/predict the qualities of the manufactured electrode. Moreover, the importance weights of variables and the correlations of variable pairs could be effectively quantified. Due to the superiority in terms of accuracy, interpretability, and data-driven nature, the proposed ensemble learning approach could not only help to conduct reliable multiclassification of manufactured electrode but also benefit smarter battery manufacturing.