储能科学与技术2025，Vol.14Issue(6)：2498-2511,14.DOI:10.19799/j.cnki.2095-4239.2025.0021
基于白鹭群优化高斯过程回归的锂电池SOH估计方法
Lithium-ion batteries SOH estimation based on gaussian processed regression optimized by egret swarm optimization
摘要
Abstract
Accurate estimation of the state of health(SOH)of lithium-ion batteries is essential for ensuring the safety and reliability of battery systems and is a critical function of battery management systems.To address the limitations of existing data-driven SOH estimation methods—such as inadequate representation of uncertainty and insufficient decoupling of training and testing data—this study proposes a novel approach based on Gaussian process regression(GPR)optimized by the egret swarm optimization algorithm(ESOA).Health features related to battery aging are extracted from the charging voltage,current,and relaxation voltage data of similar batteries,and features with high correlation to capacity are selected using Pearson correlation analysis.A GPR model employing a squared exponential kernel is then used for SOH estimation,with its hyperparameters optimized via ESOA.The proposed method is validated using NCA and NCM battery datasets from Tongji University.Experimental results show that the method significantly improves estimation accuracy and robustness.For the tested batteries,the maximum root mean square error(RMSE)and mean absolute error(MAE)are 0.0028 and 0.22%,respectively,representing improvements of 58.82%and 57.69%over conventional GPR models.Additionally,the method enables SOH interval estimation,reducing the risk of safety hazards from overestimation.关键词
锂电池/健康状态/白鹭群优化算法/高斯过程回归/区间估计Key words
lithium-ion battery/state of health/egret swarm optimization algorithm/Gaussian process regression/interval estimation分类
信息技术与安全科学引用本文复制引用
巫春玲,王立顶,卢勇,耿莉敏,陈昊,孟锦豪..基于白鹭群优化高斯过程回归的锂电池SOH估计方法[J].储能科学与技术,2025,14(6):2498-2511,14.基金项目
国家重点研发计划项目(2021YFB2601300),陕西省重点研发计划(2022GY-193),陕西省教育厅服务地方专项科学研究计划项目(23JE021),陕西省创新能力支撑计划项目(2021TD-28,2022KXJ-144). （2021YFB2601300）
