【摘要】 针对锂离子电池寿命在线预测时直接测量困难及容量再生的现象,提出一种基于等压差充电时间和改进高斯过程回归模型的电池寿命预测方法.建立了具备不确定性表达能力的高斯过程回归模型,并采用组合核函数与粒子群算法进行了模型优化.在恒流充电过程中提取等压差充电时间参数,将其作为健康因子建立了广义线性回归模型,通过预测等压差充电时间进行电池容量估计与寿命预测,根据电池充放电循环数据进行实验验证.结果表明:基于等压差充电时间的高斯过程回归模型预测方法可以预测容量非线性退化轨迹,具备较高的锂离子电池寿命预测精度及在线预测能力.更多还原

【Abstract】 In order to solve the difficulty in measuring capacity directly and capacity regeneration during online remaining useful life(RUL) prediction for lithium-ion batteries, a new method is proposed based on time interval of equal charging voltage difference and optimized Gaussian process regression(GPR) model. Firstly, the GPR model with uncertainty expression is established and optimized by using combined kernel functions and particle swarm optimization. The time interval of equal charging voltage difference is extracted during the constant current charging process of lithium-ion batteries. The relationship between the time interval of equal charging voltage difference and capacity is analyzed by a generalized linear regression model. The time interval of equal charging voltage difference can act as a health indicator for RUL prediction of lithium-ion batteries. According to the data sets of charge/discharge tests of lithium-ion batteries, the verification experiments are carried out. The results show that the proposed method can predict nonlinear degradation of capacity well and have high prediction accuracy and online RUL prediction ability for lithium-ion batteries.更多还原