基于最优充放电曲线的锂离子电池寿命预测方法  

Lithium-ion battery life prediction method based on optimal charge and discharge curve

作　　者：宁青菊[1] 施梦琢 史永胜[2] 丁恩松 洪元涛 欧阳 NING Qing-ju;SHI Meng-zhuo;SHI Yong-sheng;DING En-song;HONG Yuan-tao;OU Yang(School of Materials Science and Engineering, Shaanxi University of Science & Technology, Xi′an 710021, China;School of Electrical and Control Engineering, Shaanxi University of Science & Technology, Xi′an 710021, China;Jiangsu Runyin Graphene Technology Co., Ltd., Gaoyou 225600, China)

机构地区：[1]陕西科技大学材料科学与工程学院,陕西西安710021 [2]陕西科技大学电气与控制工程学院,陕西西安710021 [3]江苏润寅石墨烯科技有限公司,江苏高邮225600

出　　处：《陕西科技大学学报》2021年第2期153-160,共8页Journal of Shaanxi University of Science & Technology

基　　金：国家自然科学基金项目(61871259)。

摘　　要：准确预测锂离子电池剩余使用寿命在电池健康管理中起着越来越重要的作用.然而由于直接反映电池退化的内阻、容量等参数在实际应用中的复杂性和不易测量,从侧面评估锂离子电池寿命状态十分必要.本文通过对锂离子电池充放电数据分析,结合Pearson和Spearman两种相关性分析法,构造了反映锂离子电池退化的两种最优健康因子,然后在此基础上提出了一种灰狼优化算法(GWO)和长短期记忆神经网络(LSTMNN)相结合的锂离子电池寿命预测模型.仿真结果表明,该方法能有效对锂离子电池的退化状态跟踪,预测的最大MAPE不超过2%,与传统的LSTM算法相比,具有很高的可靠性.Accurately predicting the remaining useful life plays an increasingly important role in battery health management.However,due to the complexity and difficulty in measuring parameters such as internal resistance and capacity which directly reflect battery degradation in practical application,it is necessary to evaluate the remaining useful life from the side.Based on analysis of lithium ion battery charge and discharge data,this paper Pearson and Spearman correlation analysis were used to construct two optimal health factors reflecting the degradation of lithium ion batteries.Then,a lithium-ion battery life prediction model based on Grey Wolf Optimization Algorithm(GWO)and Long Short Term Memory Neural Network(LSTMNN)was proposed.Experimental results show that the proposed method can effectively predicting the degradation state of lithium-ion batteries,and the predicted largest MAPE is less than 2%.Compared with the traditional LSTM algorithm,the proposed method has high reliability.

关 键 词：锂离子电池 剩余使用寿命 灰狼优化算法 长短期记忆神经网络 

分 类 号：TM912[电气工程—电力电子与电力传动]