Impact of Data Partitioning to Improve Prediction Accuracy for Remaining Useful Life of Li-Ion Batteries

Predicting the remaining useful life (RUL) of a battery is critical to ensure the safe management of its manufacture and operation. In this study, a comprehensive investigation of the effect of data partitioning methods on RUL prediction was performed. To confirm the generality and transferability, the charge-discharge information of cathode materials with different chemical elements was adopted from previous research, including lithium iron phosphate, lithium nickel cobalt aluminum oxide, and lithium nickel cobalt manganese oxide cells. Among the partitioning procedures, the method of adding predicted data from the surrogate model to the training set exhibited the best accuracy, with an average mean absolute error (MAE) of 47 cycles. In contrast, the slide BOX method, which only used certain cycles before the test set as the training set, exhibited the worst MAE value of 60 cycles. In conclusion, the proposed data partitioning method could be implemented to predict the RUL of batteries to develop next-generation cathode materials with improved performance and stability, shorten the quality assessment time, and achieve stable predictive maintenance.

Automated summary

This study investigated the impact of data partitioning methods on predicting the remaining useful life (RUL) of batteries. Results showed that the method of adding predicted data from a surrogate model to the training set had the highest accuracy, with an average mean absolute error (MAE) of 47 cycles. In contrast, the slide BOX method, which used only certain cycles before the test set as the training set, had the worst MAE value of 60 cycles. Therefore, this data partitioning method can be implemented to predict the RUL of batteries and aid in the development of next-generation cathode materials with improved performance and stability, as well as achieve reliable predictive maintenance.