一种钠离子电池的健康状态估计方法  

An estimation method for state of health of sodium-ion batteries

作　　者：孙文杰 杨之乐 郭媛君[1,3] 姚文娇 许欢 周博文 SUN Wenjie;YANG Zhile;GUO Yuanjun;YAO Wenjiao;XU Huan;ZHOU Bowen(Institute of Integration Technical Research,Shenzhen Institute of Advanced Technology,Chinese Academy of Sciences,Shenzhen 518055,China;Institute of Carbon Neutrality,Shenzhen Institute of Advanced Technology,Chinese Academy of Sciences,Shenzhen 518055,China;Guangdong Institute of Carbon Neutrality(Shaoguan),Shaoguan 511100,China;College of Information Science and Engineering,Northeastern University,Shenyang 110819,China;Key Laboratory of Integrated Energy Optimizationand Secure Operation of Liaoning Province,Northeastern University,Shenyang 110819,China)

机构地区：[1]中国科学院深圳先进技术研究院集成技术研究所,广东深圳518055 [2]中国科学院深圳先进技术研究院碳中和技术研究所,广东深圳518055 [3]广东省碳中和研究院(韶关),广东韶关511100 [4]东北大学信息科学与工程学院,沈阳110819 [5]辽宁省综合能源优化与安全运行重点实验室,沈阳110819

出　　处：《综合智慧能源》2024年第7期74-80,共7页Integrated Intelligent Energy

基　　金：国家自然科学基金项目(52077213,62003332);深圳市优秀创新人才基金项目(RCYX20221008093036022);南岭团队项目(220212207220502)。

摘　　要：钠离子电池因其经济性和材料来源丰富而成为有巨大潜力的储能设备。准确评估电池健康状态对于确保其高效、安全运行至关重要。结合循环神经网络和扩展卡尔曼滤波技术,提出一种新颖的健康状态估计框架。利用循环神经网络对时间序列数据的处理能力为健康状态估计提供强大的支持,而扩展卡尔曼滤波则用于确保状态估计的鲁棒性。通过对3个钠离子电池的试验验证,该方法显示了出色的估计效果,其中估计值与实际值的平均绝对误差约为1.79%,均方根误差约为1.38%,模型拟合度高达96.28%。此研究不仅提供了一种钠离子电池健康状态的高效估计方法,还为实际应用中的电池管理和维护提供了宝贵的参考。Sodium ion batteries are promising energy storage devices due to their economy and abundant material sources.An accurate assessment on a battery's state of health(SOH)is essential to ensure its efficient and safe operation.Integrating the techniques of Recurrent Neural Networks(RNN)and Extended Kalman Filtering(EKF),a novel framework for SOH estimation is proposed.The RNN,with its capability to process time series data,offers a sound support for the SOH estimation,while the EKF ensures the robustness of state estimation.Through experimental validation on three sodium-ion batteries,the proposed method demonstrates outstanding estimating performances,with an average absolute error of less than 1.79%,a root mean square error of less than 1.38%,and a model fitting up to 96.28%.This research not only provides an efficient approach for the SOH estimation of sodium-ion batteries,but also offers valuable insights for battery management and maintenance in practical applications.

关 键 词：钠离子电池 健康状态估计 循环神经网络 扩展卡尔曼滤波 电池管理系统 

分 类 号：TK01[动力工程及工程热物理] TM912.1[电气工程—电力电子与电力传动]