Predict the Remaining Useful Life of Lithium Batteries Based on EWT-Elman
- 34 Downloads
The performance degradation process of a lithium battery is a nonlinear and non-stationary process. In order to accurately predict its remaining useful life (RUL), this paper combines empirical wavelet transform (EWT) and Elman neural network (ENN). First, the degraded signal of the lithium battery is decomposed by EWT, and the decomposed frequency sublayer signals are obtained. Secondly, the decomposition signal is predicted by ENN, and then, the predicted value of the decomposition signal is reconstructed to obtain the predicted lithium battery performance degradation signal. Finally, the RUL of the lithium battery is obtained by analyzing the failure threshold. It has been verified that the method proposed in this paper can effectively predict the RUL of lithium batteries.
KeywordsLithium battery Empirical wavelet transform Elman neural network Remaining useful life
This work was supported by the Fundamental Research Funds for the Central Universities (Project NO. 2018CDYJSY0055), was supported by the Open Research Fund of The Academy of Satellite Application under grant NO. JSKFJ201900011, was supported by the Natural Science Foundation of Chongqing City, China (cstc2016jcyjA0504).
- 1.Lipu MSH, Hannan MA, Hussain A, et al. A review of state of health and remaining useful life estimation methods for lithium-ion battery in electric vehicles: Challenges and recommendations. J Cleaner Prod; 2018.Google Scholar
- 3.Yang F, Song X, Dong G, et al. A coulombic efficiency-based model for prognostics and health estimation of lithium-ion batteries. Energy; 2019.Google Scholar