Remaining Useful Life Prediction of Lithium-Ion Batteries Using Neural Network and Bat-Based Particle Filter

Yi Wu, Wei Li, Youren Wang, Kai Zhang
2019 IEEE Access  
Predicting the remaining useful life (RUL) is an effective way to indicate the health of lithium-ion batteries, which can help to improve the reliability and safety of battery-powered systems. To predict the RUL, the line of research focuses on using the empirical degradation model followed by the particle filter (PF) algorithm, which is used for online updating the model's parameters. However, this works well for specific batteries under specific discharge conditions. When the degradation
more » ... s cannot be presented by the chosen empirical model or the standard PF encounters impoverishment and degeneracy problem, the RUL prediction would be inaccurate. To improve the RUL prediction accuracy, we propose a novel approach by enhancing the existing method from two aspects. First, we introduce a neural network (NN) to model battery degradation trends under various operation conditions. As NN's generalization and nonlinear representing ability, it outperforms the typical empirical degradation model. Second, the NN model's parameters are recursively updated by the bat-based particle filter. The bat algorithm is used to move the particles to the high likelihood regions, which optimizes the particle distribution and thus reduces the degeneracy and impoverishment of PF. In this paper, quantitative evaluation is presented using two datasets with different batteries under different aging conditions. The results indicate that the proposed the approach can achieve higher RUL prediction accuracy than conventional empirical model and standard PF. INDEX TERMS Lithium-ion batteries, neural network, capacity degradation, remaining useful life prediction, bat algorithm, particle filter. The associate editor coordinating the review of this manuscript and approving it for publication was Dong Wang. can effectively indicate lithium-ion batteries' health, which could help to provide maintenance plans to ensure the reliability and safety of the systems [2], [3]. Many approaches have been proposed to predict the RUL of lithium-ion batteries [4] , which can be generally grouped into two families, the fully data-driven methods and the model-based methods. Note that hybrid approaches fused data-driven and model-based methods also gain lots of research interests recently [5]- [7] . Regarding the fully data-driven methods, the degradation features are extracted from the historical data such as voltage, current, and temperature. Then the machine learning algorithms are used to predict the degradation and estimate the RUL of the batteries. Typical data-driven approaches used for battery RUL prediction include auto regressive integrated moving average (ARIMA) model [8] , Gaussian process regression (GPR) [9], long short-term memory recurrent neural
doi:10.1109/access.2019.2913163 fatcat:xgyxdvbnnngujbk3ldgzugf7gu