针对锂离子电池在线剩余寿命预测时容量难以直接测量以及预测表达的不确定性等问题,提出一种利用锂离子电池充放电监测参数构建剩余寿命预测健康因子的方法框架,实现了锂电池健康状态的表征,同时利用高斯过程回归(Gaussian process regression,GPR)方法给出剩余寿命预测的不确定性区间,从而构建了锂离子电池在线剩余寿命预测的方法体系。基于NASA锂离子电池数据集和卫星锂离子试验数据的剩余寿命预测验证和评估实验,表明本文提出的方法框架可以很好地支撑电池在线剩余寿命预测的应用,具备较好的电池剩余寿命预测精度和不确定性管理能力。
As an important and necessary part in the intelligent battery management systems(BMS),the prognostics and remaining useful life(RUL)estimation for lithium-ion batteries attach more and more attractions.Especially,the data-driven approaches use only the monitoring data and historical data to model the performance degradation and assess the health status,that makes these methods flexible and applicable in actual lithium-ion battery applications.At first,the related concepts and definitions are introduced.And the degradation parameters identification and extraction is presented,as the health indicator and the foundation of RUL prediction for the lithium-ion batteries.Then,data-driven methods used for lithium-ion battery RUL estimation are summarized,in which several statistical and machine learning algorithms are involved.Finally,the future trend for battery prognostics and RUL estimation are forecasted.
