工程科学学报.第43卷，第7期：985-994.2021年7月 Chinese Journal of Engineering,Vol.43,No.7:985-994,July 2021 https://doi.org/10.13374/j.issn2095-9389.2020.06.30.007;http://cje.ustb.edu.cn 基于CEEMDAN-LSTM组合的锂离子电池寿命预测方法 史永胜”，施梦琢)区，丁恩松)，洪元涛，欧阳 1)陕西科技大学电气与控制工程学院.西安7100212)江苏润寅石墨烯科技有限公司.扬州225600 ☒通信作者，E-mail:84770540@gqq.com 摘要针对目前锂离子电池寿命预测结果不准确的问题，提出了一种多模态分解的锂离子电池组合预测模型，从而学习锂 离子电池退化过程的微小变化.该方法在单一长短期记忆(LSTM)预测模型的基础上，采用了自适应噪声完全集成的经验模 态分解(CEEMDAN)算法将锂电池容量分为主退化趋势和若干局部退化趋势，然后使用长短期记忆神经网络(LSTMNN)算 法分别对所分解的若干退化数据进行寿命预测，最后将若干预测结果进行有效集成.结果表明，所提出的CEEMDAN- LSTM锂离子电池组合预测模型最大平均绝对百分比误差不超过1.5%.平均相对误差在3%以内，且优于其他预测模型 关键词电池健康管理：锂离子电池：剩余使用寿命：长短期记忆神经网络：自适应噪声完全集成经验模态分解 分类号TM912 Combined prediction method of lithium-ion battery life based on CEEMDAN-LSTM SHI Yong-sheng,SHI Meng-zhuo,DING En-song?,HONG Yuan-tao,OU Yang 1)College of Electrical and Control Engineering,Shaanxi University of Science and Technology,Xi'an 710021,China 2)Jiangsu Runyin Graphene Technology Co.,Yangzhou 225600,China Corresponding author,E-mail:84770540@qq.com ABSTRACT As a new generation of new energy battery,lithium-ion battery is widely used in various fields,including electronic products,electric vehicles,and power supply,due to its advantages of high energy density,light weight,long cycle life,small self- discharge,no memory effect,and no pollution.With the wide application of lithium-ion battery,numerous research on its performance has been done,including its health assessment as one of the hot spots.Repeated charging and discharging of a lithium-ion battery that was run under full charge state results to internal irreversible chemical changes leading to a fall in the maximum available capacity. Specifically,a decline to 70%80%of the rated capacity results in lithium-ion battery failure.Battery failure may lead to electrical equipment damage,resulting in safety accidents.Therefore,it is of great significance to predict the remaining usable life of lithium-ion battery for improving system reliability.In this paper,a combination prediction model for lithium-ion batteries with multimode decomposition was presented based on the long and short-term memory (LSTM)prediction model to learn about small changes in its degradation process.A complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN)algorithm was used to divide the capacity into main degradation trend and some local degradation trend.Long Short-Term Memory Neural Network (LSTMNN)algorithm was then introduced to perform the capacity prediction of decomposed degradation data.Finally,some prediction results were integrated effectively.The maximum mean absolute percentage error(MAPE)of the proposed CEEMDAN-LSTM lithium- ion battery combination prediction model does not exceed 1.5%.The average relative error is less than 3%,which is better than the other prediction model. KEY WORDS battery health management;lithium-ion batteries;remaining useful life;long-and short-term memory neural network; complete ensemble empirical mode decomposition with adaptive noise(CEEMDAN) 收稿日期：2020-06-30 基金项目：国家自然科学基金资助项目(61871259)基于 CEEMDAN–LSTM 组合的锂离子电池寿命预测方法 史永胜1)，施梦琢1) 苣，丁恩松2)，洪元涛1)，欧    阳1) 1) 陕西科技大学电气与控制工程学院，西安 710021    2) 江苏润寅石墨烯科技有限公司，扬州 225600 苣通信作者，E-mail：84770540@qq.com 摘    要    针对目前锂离子电池寿命预测结果不准确的问题，提出了一种多模态分解的锂离子电池组合预测模型，从而学习锂 离子电池退化过程的微小变化. 该方法在单一长短期记忆（LSTM）预测模型的基础上，采用了自适应噪声完全集成的经验模 态分解 (CEEMDAN) 算法将锂电池容量分为主退化趋势和若干局部退化趋势，然后使用长短期记忆神经网络（LSTMNN）算 法分别对所分解的若干退化数据进行寿命预测，最后将若干预测结果进行有效集成. 结果表明，所提出的 CEEMDAN− LSTM 锂离子电池组合预测模型最大平均绝对百分比误差不超过 1.5%，平均相对误差在 3% 以内，且优于其他预测模型. 关键词    电池健康管理；锂离子电池；剩余使用寿命；长短期记忆神经网络；自适应噪声完全集成经验模态分解 分类号    TM912 Combined prediction method of lithium-ion battery life based on CEEMDAN–LSTM SHI Yong-sheng1) ，SHI Meng-zhuo1) 苣 ，DING En-song2) ，HONG Yuan-tao1) ，OU Yang1) 1) College of Electrical and Control Engineering, Shaanxi University of Science and Technology, Xi’an 710021, China 2) Jiangsu Runyin Graphene Technology Co., Yangzhou 225600, China 苣 Corresponding author, E-mail: 84770540@qq.com ABSTRACT    As  a  new  generation  of  new  energy  battery,  lithium-ion  battery  is  widely  used  in  various  fields,  including  electronic products,  electric  vehicles,  and  power  supply,  due  to  its  advantages  of  high  energy  density,  light  weight,  long  cycle  life,  small  self￾discharge, no memory effect, and no pollution. With the wide application of lithium-ion battery, numerous research on its performance has been done, including its health assessment as one of the hot spots. Repeated charging and discharging of a lithium-ion battery that was run under full charge state results to internal irreversible chemical changes leading to a fall in the maximum available capacity. Specifically,  a  decline  to  70%–80% of  the  rated  capacity  results  in  lithium-ion  battery  failure.  Battery  failure  may  lead  to  electrical equipment damage, resulting in safety accidents. Therefore, it is of great significance to predict the remaining usable life of lithium-ion battery  for  improving  system  reliability.  In  this  paper,  a  combination  prediction  model  for  lithium-ion  batteries  with  multimode decomposition was presented based on the long and short-term memory (LSTM) prediction model to learn about small changes in its degradation  process.  A  complete  ensemble  empirical  mode  decomposition  with  adaptive  noise  (CEEMDAN)  algorithm  was  used  to divide  the  capacity  into  main  degradation  trend  and  some  local  degradation  trend.  Long  Short-Term  Memory  Neural  Network (LSTMNN) algorithm was then introduced to perform the capacity prediction of decomposed degradation data. Finally, some prediction results were integrated effectively. The maximum mean absolute percentage error (MAPE) of the proposed CEEMDAN–LSTM lithium￾ion battery combination prediction model does not exceed 1.5%. The average relative error is less than 3%, which is better than the other prediction model. KEY WORDS    battery health management；lithium-ion batteries；remaining useful life；long- and short-term memory neural network； complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) 收稿日期: 2020−06−30 基金项目: 国家自然科学基金资助项目（61871259） 工程科学学报，第 43 卷，第 7 期：985−994，2021 年 7 月 Chinese Journal of Engineering, Vol. 43, No. 7: 985−994, July 2021 https://doi.org/10.13374/j.issn2095-9389.2020.06.30.007; http://cje.ustb.edu.cn