摘要
提出了一种基于贝叶斯最小二乘支持向量回归(LS-SVR)的锂电池剩余寿命在线概率性预测方法。首先,通过滚动窗方法选取锂电池历史健康退化数据,并根据相空间重构原理建立训练样本,其中最小嵌入维数使用Cao氏方法计算获得。然后,运用贝叶斯3层推理训练LS-SVR预测模型,在迭代预测阶段,采用蒙特卡罗方法来表示和管理多步预测中的不确定性及其传递,即用一群离散粒子来近似连续分布,结合"退化轨迹不相交"原则和高斯过程假设,预测出锂电池健康状态未来时刻的发展趋势。最后结合给定的失效阈值,通过统计穿越阈值的粒子数目得到剩余寿命的概率分布。使用美国国家航空航天局阿姆斯研究中心公开的电池数据集与高斯过程回归(GPR)方法进行对比实验,多项预测性能指标结果表明贝叶斯LS-SVR方法具有更高的预测准确度和置信度。
An online probabilistic prediction approach for the residual life of a lithium-ion battery is proposed by using the Bayesian least squares support vector regression （LS-SVR）. First, historical degradation data of the lithium-ion battery are selected through a sliding window. Then the selected data are formed into training samples by the phase space reconstruc- tion theory, with the minimum embedding dimension calculated by Oao＇s method. Secondly, a predicting model based on least squares support vector regression is trained by a three level Bayesian inference framework. Then in the iterative pre- diction stage, Monte Carlo method is applied to manage the uncertainty and its propagation in the multi-step prediction, which is achieved by approximating the continuous distribution with a group of discrete particles and predicting the future health status of the battery based on the principle of ＂non intersecting degradation trajectories＂ and the Gaussian process as- sumption. Finally, by counting the number of particles which pass through the predetermined failure threshold, the probability distribution of the battery residual life can therefore be estimated. Comparative experiments are conducted between Bayes- ian LS-SVR and Gaussian process regression （GPR） using the public battery data sets provided by National Aeronautics and Space Administration Ames Research Center. The results demonstrate that the Bayesian LS-SVR method has higher predic- tion accuracy and confidence.
出处
《航空学报》
EI
CAS
CSCD
北大核心
2013年第9期2219-2229,共11页
Acta Aeronautica et Astronautica Sinica
基金
航空科学基金(20100751010
2010ZD11007)~~
