基于ARIMA和PF的锂电池剩余使用寿命预测方法

有效的电池剩余使用寿命(RUL)预测方法能够极大地提高系统的可靠性。提出一种基于自回归集成滑动平均模型(ARIMA)和粒子滤波(PF)融合预测框架,该框架由ARIMA方法和PF方法构成，ARIMA 应用于短期预测，而粒子滤波应用于长期预测。首先在线对锂离子电池进行监测，然后根据短期预测或长期预测要求执行相应的算法,得出横纵坐标分别为周期和容量的 RUL 预测图。实验结果表明，该预测框架能够快速准确地预测锂离子电池 RUL。

Remaining Useful Life prediction for lithium battery based on ARIMA and Particle Filter

An efficient method for battery Remaining Useful Life(RUL) prediction would greatly improve the reliability of systems. A novel Autoregressive Integrated Moving Average Model-Particle Filter(ARIMA-PF) fusion prognostic framework is developed to improve the performance of battery RUL prediction. It is composed of ARIMA algorithm and PF algorithm. ARIMA is employed for short-term estimation of system state, while Particle Filter for long-term estimation of system state. Firstly, the lithium ion battery is monitored online; then the corresponding algorithms are employed according to short-term forecasts or long-term forecasts requirements; the forecast maps are obtained with the transverse and longitudinal coordinates standing for the cycle and capacity respectively. The experimental results indicate that the proposed prognostic framework can predict lithium ion battery RUL accurately and fast.