Remaining Useful Life Prediction of Lithium-Ion Batteries Based on Health Indicator and Gaussian Process Regression Model

Authors:
Open Access
Publisher website
Google Scholar
Abstract
Achieving accurate and reliable remaining useful life (RUL) prediction of lithium-ion batteries is very vital for normal operation of battery system. The direct RUL prediction based on capacity largely depends on laboratory condition. A novel method which combines indirect health indicator (HI) and multiple Gaussian process regression (GPR) model is presented for RUL forecast to solve the capacity unmeasurable problem of operating battery in this paper. Firstly, three measurable HIs are extracted in constant current and constant voltage charge process. Both Pearson and Spearman rank correlation analytical approaches show that the correlations between the HIs and the capacity are good. Then, the GPR model is optimized with combined kernel functions to improve the ability of predicting the capacity regeneration. Next, based on the measurable HI versus cycle number data, three GPR models are built and the HIs prognosis results are achieved at single point. The HIs prediction results are added in the multidimensional GPR model which is accomplished by using the HIs and capacity as input and output, respectively. The predicted capacity is used to compare with the threshold to acquire RUL prediction result. The approach is validated by the two different life-cycle test datasets. The results indicate that an accurate and reliable RUL forecast of lithium-ion batteries can be realized by using the proposed approach.
Funding Information
  • National Natural Science Foundation of China (51677119)

This publication has 36 references indexed in Scilit: