检索规则说明:AND代表“并且”;OR代表“或者”;NOT代表“不包含”;(注意必须大写,运算符两边需空一格)
检 索 范 例 :范例一: (K=图书馆学 OR K=情报学) AND A=范并思 范例二:J=计算机应用与软件 AND (U=C++ OR U=Basic) NOT M=Visual
作 者:陈洋 黄江东 余春雷 谢基 姜伟 CHEN Yang;HUANG Jiang-dong;YU Chun-lei;XIE Ji;JIANG Wei(School of Mechanical and Electrical Engineering,Guangzhou University,Guangzhou 510006,China;Guangzhou Customs Technology Centre,Guangzhou 510623,China)
机构地区:[1]广州大学机械与电气工程学院,广东广州510006 [2]广州海关技术中心,广东广州510623
出 处:《分析测试学报》2025年第3期402-410,共9页Journal of Instrumental Analysis
基 金:国家重点研发计划(2022YFF0607201);国家自然科学基金资助项目(52171331,51907082);广州市科技计划项目(2023A03J0646,2023A03J0120,2023A04J1013);海关总署课题(2022HK062)。
摘 要:该文提出了一种融合改进鲸鱼优化算法与支持向量回归(IWOA-SVR)的锂离子电池健康状态(SOH)检测评估方法。首先收集不同充放电策略下的充放电数据,并提取关键电池老化特征参数;然后运用皮尔逊相关性分析验证了特征参数与SOH间的强相关性,算法在传统鲸鱼优化算法中融入自适应权重调整机制与Levy飞行策略,有效克服了传统方法在线评估SOH时误差偏大的问题。最后,采用恒流恒压充电与恒流充电两种典型工况下的实验测试数据进行验证,结果表明IWOA-SVR检测方法具有更高的稳定性和准确性,最大误差可控制在1.4%以内。同时,在平均绝对百分比误差(MAPE)和均方根误差(RMSE)两项关键评估指标上,IWOA-SVR均显著优于对比算法,充分证明了其在锂离子电池SOH在线检测中的高精度与强鲁棒性。In this paper,a detection and evaluation method of lithium-ion battery state of health(SOH)is proposed by integrating the improved whale optimization algorithm and support vector regression(IWOA-SVR).Firstly,the charging/discharging data under different charging/discharging strategies are collected,and the critical battery aging characteristic parameters are extracted.Then Pearson correlation analysis is applied to verify the strong correlation between the parameters and the SOH,and the algorithm integrates the adaptive weight adjustment mechanism and Levy flight strategy into the traditional whale optimization algorithm,which effectively overcomes the problem of the large error of the traditional method when evaluating the SOH online.Finally,in order to verify the effectiveness of the algorithm,experimental test data under two typical operating conditions of constant-current and constant-voltage charging and constant-current charging are used for validation,and the results show that the IWOA-SVR detection method has higher stability and accuracy,and the maximal error can be controlled within 1.4%.Meanwhile,IWOA-SVR significantly outperforms the comparison algorithms in two key evaluation metrics,namely,mean absolute percentage error(MAPE)and root mean square error(RMSE),which fully proves its high accuracy and strong robustness in the online detection of SOH in lithium-ion batteries.
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在链接到云南高校图书馆文献保障联盟下载...
云南高校图书馆联盟文献共享服务平台 版权所有©
您的IP:216.73.216.179