Prognostics of Lithium-Ion Batteries Based on Capacity Regeneration Analysis and Long Short-Term Memory Network

Abstract

The accurate prognostics of state of health (SOH) prediction of lithium-ion batteries is significant for manufacturers and consumers to determine the failure and optimize the usage in advance. This paper proposes a framework to decouple the capacity regeneration phenomena and the normal capacity degradation process to make predictions. The regeneration phenomena are automatically identified by clustering the time intervals of adjacent cycles and detecting the long time intervals. Then support vector regression is used to predict the capacity regeneration amplitude and the corresponding regeneration cycles. The complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) is utilized to decompose the normal degradation path into several intrinsic mode functions. The long short-term memory recurrent network is constructed to predict the components with the C-C method determining the appropriate model parameters. Ultimately, the prediction results are added to obtain the complete capacity degradation trajectory. The proposed framework is validated with five lithium-ion battery datasets from NASA Ames Prognostics Center of Excellence and Center for Advanced Life Cycle Engineering of the University of Maryland. The results demonstrate that the proposed method provides more accurate SOH prediction than the published methods.