Early-Stage end-of-Life prediction of lithium-Ion battery using empirical mode decomposition and particle filter

Abstract

The predictive maintenance is a major challenge for improving battery safety without compromising performance. Its main objective is to predict the end-of-life (EOL) and assess the associated prediction uncertainty. In this paper, we consider this issue and propose a hybrid method combining empirical mode decomposition (EMD) and particle filter (PF) to perform the battery early EOL prediction and its uncertainty assessment. The proposed approach is tested on the two most widely accessible public lithium-ion battery degradation datasets from the Prognostics Center of Excellence at NASA Ames and the Center for Advanced Life Cycle Engineering at the University of Maryland. To avoid the overfitting, a major constraint in the prediction phase, only the residual sequence obtained after EMD decomposition of the raw data is used as the measurement input for PF. Besides, the sum of standard deviation of all intrinsic mode functions (IMFs) is used to determine the noise characteristic for the PF algorithm. Extensive experiments are conducted to show the importance of uncertainty assessment for the early EOL prediction. Although the distance between the true EOL and the mean predicted EOL has no obvious decrease when more operation data is available, the results show a clear decreasing trend of EOL prediction uncertainty when the prediction starts from later operation cycles. Particularly, a strong experimental support is provided for filtering-based prediction methods in the early EOL prediction.