史永胜等:基于CEEMDAN-LSTM组合的锂离子电池寿命预测方法 993· 和鲁棒性 useful life prediction with multi-channel charging profiles.IEEE (2)通过与EMD-LSTM和LSTM及其他机 4 ccess,.2020,8:20786 器学习算法的对比,所提出的组合模型预测精 [10]Zhang Y Z,Xiong R,He H W,et al.Long short-term memory 度相对EMD-LSTM、LSTM模型均有一定的提 recurrent neural network for remaining useful life prediction 升,CEEMDAN-LSTM组合算法的最大MAPE不 of lithium-ion batteries.IEEE Trans Veh Technol,2018,67(7): 超过1.5%,平均相对误差在3%以内 5695 (3)因为引入CEEMDAN分解算法,影响了 [11]Wei H Y,An J J,Chen J,et al.RUL prediction of lithium-ion LSTM模型的训练时间,所以CEEMDAN-LSTM battery based on improved particle filtering algorithm.Automor 组合预测模型的训练时间与LSTM模型相比较 Eg,2019,41(12:1377 长.后续的工作将在此基础上改进,在提高预测精 (韦海燕,安品品,陈静,等.基于改进粒子滤波算法实现锂离子 度的同时也可以节省模型训练时间 电池RUL预测.汽车工程,2019,41(12):1377) [12]Yu J B.State of health prediction of lithium-ion batteries: 参考文献 Multiscale logic regression and Gaussian process regression [Li L B,Ji L,Zhu Y Z,et al.Investigation of RUL prediction of ensemble.Reliab Eng Syst Saf,2018,174:82 lithium-ion battery equivalent cycle battery pack.ChinJ Eng, [13]Zhou Y P,Huang M H.Lithium-ion batteries remaining useful life 2020,42(6):796 prediction on a mixture of empirical mode decomposition and (李练兵,季亮,祝亚尊,等.等效循环电池组利余使用寿命预测 ARIMA model.Microelectron Reliab,2016,65:265 工程科学学报,2020,42(6):796) [14]Li X Y,Zhang L,Wang Z P,et al.Remaining useful life prediction [2]Liu D T,Zhou J B,Liao H T,et al.A health indicator extraction for lithium-ion batteries based on a hybrid model combining the and optimization framework for lithium-ion battery degradation long short-term memory and Elman neural networks.J Energy modeling and prognostics.IEEE Trans Syst Man Cybern:Syst. Storage,2019,21:510 2015,45(6):915 [15]Sayah M,Guebli D,Al Masry Z,et al.Robustness testing [3]Pan H P,Lv Z Q,Fu B,et al.Online estimation of lithium-ion framework for RUL prediction Deep LSTM networks./S4 Trans, battery's state of health using extreme learning machine.Automot https://doi.org/10.1016/j.isatra.2020.07.003 Eng,2017,39(12):1375 [16]Wang C S.Lu N Y,Wang S L,et al.Dynamic long short-term (潘海鸿,吕治强,付兵,等.采用极限学习机实现锂离子电池健 memory neural-network-based indirect remaining-useful-life 康状态在线估算.汽车工程,2017,39(12):1375) prognosis for satellite lithium-ion battery.App/Sci,2018,8(11): [4]Xiong R.Battery Management Algorithm for Electric Vehicles. 2078 Beijing:China Machine Press,2020 [17]Bruneo D,De Vita F.On the use of LSTM networks for predictive [5]Zhu J,Tan T X,Wu L F,et al.RUL prediction of lithium-ion maintenance in smart industries /2019 IEEE International battery based on improved DGWO-ELM method in a random Conference on Smart Computing (SMARTCOMP).Washington, discharge rates environment./EEE Access,2019,7:125176 2019:241 [6]Chen L,Chen J,Wang H M,et al.Prediction of battery remaining [18]Yan H R,Qin Y,Xiang S,et al.Long-term gear life prediction useful life based on wavelet packet energy entropy.Trans China based on ordered neurons LSTM neural networks.Measurement, Electrotech Soc,2020,35(8):1827 2020.165:108205 (陈琳,陈静,王惠民,等.基于小波包能量嫡的电池剩余寿命预 [19]Hu T Z,Yu J B.Life prediction of lithium-ion batteries based on 测.电工技术学报,2020,35(8):1827) multiscale decomposition and deep leamning.J Zhejiang Univ Eng [7]Zhang Y Z.Xiong R.He H W.et al.Lithium-ion battery Sci,2019,53(10):1852 remaining useful life prediction with Box-Cox transformation and (胡天中,余建波.基于多尺度分解和深度学习的锂电池寿命预 Monte Carlo simulation.IEEE Trans Ind Electron,2019,66(2): 测.浙江大学学报:工学版,2019,53(10):1852) 1585 [20]Zhang CL He YG.Yuan L F.Prediction approach for remaining [8]Yun Z H,Qin W H.Remaining useful life estimation of lithium- useful life of lithium-ion battery based on EEMD and MKRVM ion batteries based on optimal time series health indicator.IEEE Proc CSU-EPS4,2018,30(7):38 Acce8,2020,8:55447 (张朝龙,何怡刚,袁莉芬.基于EEMD和MKRVM的锂电池剩余 [9]Park K,Choi Y,Choi W J,et al.LSTM-based battery remaining 寿命预测方法.电力系统及其自动化学报,2018.30(7):38)和鲁棒性. ( 2)通过与 EMD –LSTM 和 LSTM 及其他机 器学习算法的对比,所提出的组合模型预测精 度相对 EMD–LSTM、 LSTM 模型均有一定的提 升 ,CEEMDAN−LSTM 组合算法的最大 MAPE 不 超过 1.5%,平均相对误差在 3% 以内. ( 3)因为引入 CEEMDAN 分解算法 ,影响了 LSTM 模型的训练时间 ,所以 CEEMDAN−LSTM 组合预测模型的训练时间与 LSTM 模型相比较 长. 后续的工作将在此基础上改进,在提高预测精 度的同时也可以节省模型训练时间. 参 考 文 献 Li L B, Ji L, Zhu Y Z, et al. Investigation of RUL prediction of lithium-ion battery equivalent cycle battery pack. Chin J Eng, 2020, 42(6): 796 (李练兵, 季亮, 祝亚尊, 等. 等效循环电池组剩余使用寿命预测. 工程科学学报, 2020, 42(6):796) [1] Liu D T, Zhou J B, Liao H T, et al. A health indicator extraction and optimization framework for lithium-ion battery degradation modeling and prognostics. IEEE Trans Syst Man Cybern: Syst, 2015, 45(6): 915 [2] Pan H P, Lv Z Q, Fu B, et al. Online estimation of lithium-ion battery’s state of health using extreme learning machine. Automot Eng, 2017, 39(12): 1375 (潘海鸿, 吕治强, 付兵, 等. 采用极限学习机实现锂离子电池健 康状态在线估算. 汽车工程, 2017, 39(12):1375) [3] Xiong R. Battery Management Algorithm for Electric Vehicles. Beijing: China Machine Press, 2020 [4] Zhu J, Tan T X, Wu L F, et al. RUL prediction of lithium-ion battery based on improved DGWO–ELM method in a random discharge rates environment. IEEE Access, 2019, 7: 125176 [5] Chen L, Chen J, Wang H M, et al. Prediction of battery remaining useful life based on wavelet packet energy entropy. Trans China Electrotech Soc, 2020, 35(8): 1827 (陈琳, 陈静, 王惠民, 等. 基于小波包能量熵的电池剩余寿命预 测. 电工技术学报, 2020, 35(8):1827) [6] Zhang Y Z, Xiong R, He H W, et al. Lithium-ion battery remaining useful life prediction with Box-Cox transformation and Monte Carlo simulation. IEEE Trans Ind Electron, 2019, 66(2): 1585 [7] Yun Z H, Qin W H. Remaining useful life estimation of lithiumion batteries based on optimal time series health indicator. IEEE Access, 2020, 8: 55447 [8] [9] Park K, Choi Y, Choi W J, et al. LSTM-based battery remaining useful life prediction with multi-channel charging profiles. IEEE Access, 2020, 8: 20786 Zhang Y Z, Xiong R, He H W, et al. Long short-term memory recurrent neural network for remaining useful life prediction of lithium-ion batteries. IEEE Trans Veh Technol, 2018, 67(7): 5695 [10] Wei H Y, An J J, Chen J, et al. RUL prediction of lithium-ion battery based on improved particle filtering algorithm. Automot Eng, 2019, 41(12): 1377 (韦海燕, 安晶晶, 陈静, 等. 基于改进粒子滤波算法实现锂离子 电池RUL预测. 汽车工程, 2019, 41(12):1377) [11] Yu J B. State of health prediction of lithium-ion batteries: Multiscale logic regression and Gaussian process regression ensemble. Reliab Eng Syst Saf, 2018, 174: 82 [12] Zhou Y P, Huang M H. Lithium-ion batteries remaining useful life prediction on a mixture of empirical mode decomposition and ARIMA model. Microelectron Reliab, 2016, 65: 265 [13] Li X Y, Zhang L, Wang Z P, et al. Remaining useful life prediction for lithium-ion batteries based on a hybrid model combining the long short-term memory and Elman neural networks. J Energy Storage, 2019, 21: 510 [14] Sayah M, Guebli D, Al Masry Z, et al. Robustness testing framework for RUL prediction Deep LSTM networks. ISA Trans, https://doi.org/10.1016/j.isatra.2020.07.003 [15] Wang C S, Lu N Y, Wang S L, et al. Dynamic long short-term memory neural-network-based indirect remaining-useful-life prognosis for satellite lithium-ion battery. Appl Sci, 2018, 8(11): 2078 [16] Bruneo D, De Vita F. On the use of LSTM networks for predictive maintenance in smart industries // 2019 IEEE International Conference on Smart Computing (SMARTCOMP). Washington, 2019: 241 [17] Yan H R, Qin Y, Xiang S, et al. Long-term gear life prediction based on ordered neurons LSTM neural networks. Measurement, 2020, 165: 108205 [18] Hu T Z, Yu J B. Life prediction of lithium-ion batteries based on multiscale decomposition and deep learning. J Zhejiang Univ Eng Sci, 2019, 53(10): 1852 (胡天中, 余建波. 基于多尺度分解和深度学习的锂电池寿命预 测. 浙江大学学报: 工学版, 2019, 53(10):1852) [19] Zhang C L, He Y G, Yuan L F. Prediction approach for remaining useful life of lithium-ion battery based on EEMD and MKRVM. Proc CSU–EPSA, 2018, 30(7): 38 (张朝龙, 何怡刚, 袁莉芬. 基于EEMD和MKRVM的锂电池剩余 寿命预测方法. 电力系统及其自动化学报, 2018, 30(7):38) [20] 史永胜等: 基于 CEEMDAN–LSTM 组合的锂离子电池寿命预测方法 · 993 ·