Please wait a minute...
浙江大学学报(工学版)
浙江大学学报(工学版)  2019, Vol. 53 Issue (10): 1852-1864    DOI: 10.3785/j.issn.1008-973X.2019.10.002
机械与能源工程     
基于多尺度分解和深度学习的锂电池寿命预测
胡天中(),余建波*()
同济大学 机械与能源工程学院，上海 201804
Life prediction of lithium-ion batteries based on multiscale decomposition and deep learning
Tian-zhong HU(),Jian-bo YU*()
School of Mechanical Engineering, Tongji University, Shanghai 201804, China
 全文: PDF(3701 KB)   HTML
摘要：

针对目前的剩余寿命预测（RUL）方法存在模型适应性差及预测不准确等问题，提出多尺度深度神经网络的锂电池健康退化预测模型. 通过经验模态分解（EEMD）方法和相关性分析（CA），将采集到的锂电池能量数据分解为主趋势数据和波动数据；采用深度置信网络（DBN）和长短期记忆网络（LSTM），分别对主趋势与波动数据进行建模；将DBN与LSTM预测结果进行有效集成，得到锂电池的健康预测结果. 实验结果表明，利用该方法能够有效地对锂电池的健康趋势进行拟合，得到准确的RUL预测结果，性能优于其他典型的预测方法.
关键词： 锂电池;  剩余寿命预测 (RUL);  多尺度分析;  深度置信网络;  长短期记忆网络(LSTM)    
Abstract:

A health degradation prediction model of lithium batteries based on multi-scale deep neural network was proposed aiming at the problems of poor model adaptability and inaccurate prediction in current remaining useful life (RUL) prediction methods. The collected energy data of lithium-ion batteries were decomposed into main trend data and fluctuation data by ensemble empirical mode decomposition (EEMD) and correlation analysis (CA). Then deep belief network (DBN) and long short-term memory (LSTM) were used to model the main trend and fluctuation data respectively. The predicting outcomes of DBN and LSTM were effectively integrated to obtain the health predicted results of lithium-ion battery. The experimental results show that the method can effectively fit the health trend of lithium-ion batteries and obtain accurate RUL prediction results. The performance of the method is better than other typical prediction methods.
Key words: lithium-ion battery    remaining useful life (RUL)    multiscale analysis    deep belief network    long short-term memory (LSTM)
收稿日期: 2019-05-13 出版日期: 2019-09-30
CLC:  TH 165  
通讯作者: 余建波     E-mail: 305122638@qq.com;jbyu@tongji.edu.cn
作者简介: 胡天中（1995—），男，硕士生，从事深度学习与信号处理的研究. orcid.org/0000-0003-3705-7433. E-mail： 305122638@qq.com
服务　　
把本文推荐给朋友
加入引用管理器
E-mail Alert
作者相关文章　　
胡天中
余建波

引用本文:

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[J]. 浙江大学学报(工学版), 2019, 53(10): 1852-1864.

Tian-zhong HU,Jian-bo YU. Life prediction of lithium-ion batteries based on multiscale decomposition and deep learning. Journal of ZheJiang University (Engineering Science), 2019, 53(10): 1852-1864.

链接本文:

http://www.zjujournals.com/eng/CN/10.3785/j.issn.1008-973X.2019.10.002    或    http://www.zjujournals.com/eng/CN/Y2019/V53/I10/1852

图 1  基于多尺度分解和深度学习的锂电池寿命预测方法
图 2  深度置信网络的训练流程
图 3  长短期记忆网络结构
图 4  长短期记忆网络的训练流程
电池编号 AT/°C CC/A DC/A EOC/V EOLC/%
#5 24 1.5 2 2.7 30
#6 24 1.5 2 2.5 30
#7 24 1.5 2 2.2 30
#18 24 1.5 2 2.5 30
表 1  用于预测实验的锂电池参数
图 5  电池容量的变化曲线
IMFs 数值 IMFs 数值
b 0.042 e 0.152
c 0.107 f 0.691
d 0.150 g 0.878
表 2  本征模态函数的相关系数
图 6  基于集合经验模态分解的健康状态时间序列
图 7  相关性分析的筛选结果
输入数 输出数 迭代次数 学习率 网络结构
3 1 100 0.001 3-35-25-15-1
表 3  深度置信网络的参数设置
输入数 输出数 细胞数 学习率 迭代次数
8 1 20 0.01 3 000
表 4  长短期记忆网络的参数设置
图 8  各个模型的预测结果
图 9  集成预测结果
多尺度分解 DBN训练 DBN预测 LSTM训练 LSTM预测
3.19 10.41 0.28 1.66 1.08
表 5  预测算法的运行时间
电池编号 AT/°C CC/A DC/A EOC/V EOLC/%
#32 43 1.5 4 2.7 30
表 6  用于高温预测实验的锂电池参数
图 10  高温环境下的预测结果
图 11  各个集成模型的一步预测结果
图 12  各个集成模型的一步预测指标值
图 13  各个对比模型的一步预测指标值
图 14  各个集成模型的5步预测结果
图 15  各个集成模型的5步预测指标值
图 16  各个对比模型的5步预测指标值
图 17  剩余使用寿命的预测结果
电池编号 SPP EoL EoP PE
#5 80 129 145 16
#5 90 129 121 8
#5 100 129 128 1
#6 80 113 108 13
#6 90 113 106 10
#6 100 113 99 8
表 7  剩余使用寿命的预测结果
图 18  不确定性分析的实验结果
1 GOEBEL K, SAHA B, SAXENA A, et al Prognostics in battery health management[J]. IEEE Instrumentation and Measurement Magazine, 2008, 11 (4): 33- 40
doi: 10.1109/MIM.2008.4579269
2 OLIVARES B E, CERDA M, MATIAS A, et al Particle-filtering-based prognosis framework for energy storage devices with a statistical characterization of state-of-health regeneration phenomena[J]. IEEE Transactions on Instrumentation and Measurement, 2013, 62 (2): 364- 376
doi: 10.1109/TIM.2012.2215142
3 YU J Local and nonlocal preserving projection for bearing defect classification and performance assessment[J]. IEEE Transactions on Industrial Electronics, 2012, 59 (5): 2363- 2376
doi: 10.1109/TIE.2011.2167893
4 KIM I S A Technique for estimating the state of health of lithium batteries through a dual-sliding-mode observer[J]. IEEE Transactions on Power Electronics, 2010, 25 (4): 1013- 1022
doi: 10.1109/TPEL.2009.2034966
5 LIU D, XIE W, LIAO H, et al Integrated prognostic framework with probability ensemble for lithium-ion battery[J]. IEEE Transactions on Instrumentation and Measurement, 2015, 64 (3): 660- 670
doi: 10.1109/TIM.2014.2348613
6 张洋, 陈浩, 郭波, 等 锂离子电池剩余寿命在线预测[J]. 机械科学与技术, 2016, 35 (8): 1286- 1290
ZHANG Yang, CHEN Hao, GUO Bo, et al Online prediction of remaining useful lifetime for lithium-ion batteries[J]. Mechanical Science and Technology for Aerospace Engineering, 2016, 35 (8): 1286- 1290
7 王常虹, 董汉成, 凌明祥, 等 车用锂离子电池剩余使用寿命预测方法[J]. 汽车工程, 2015, 37 (4): 476- 479
WANG Chang-hong, DONG Han-cheng, LING Ming-xiang, et al Remaining useful life prediction of automotive lithium-ion battery[J]. Automotive Engineering, 2015, 37 (4): 476- 479
doi: 10.3969/j.issn.1000-680X.2015.04.019
8 ASHWIN T R, CHUNG Y M, WANG J Capacity fade modelling of lithium-ion battery under cyclic loading conditions[J]. Journal of Power Sources, 2016, 328: 586- 598
doi: 10.1016/j.jpowsour.2016.08.054
9 LYU C, LAI Q, GE T, et al A lead-acid battery’s remaining useful life prediction by using electrochemical model in the particle filtering framework[J]. Energy, 2017, 120: 975- 984
doi: 10.1016/j.energy.2016.12.004
10 LI D, WANG W, ISMAIL F A mutated particle filter technique for system state estimation and battery life prediction[J]. IEEE Transactions on Instrumentation and Measurement, 2014, 63 (8): 2034- 2043
doi: 10.1109/TIM.2014.2303534
11 LEE S, KIM J, LEE J, et al State-of-charge and capacity estimation of lithium-ion battery using a new open-circuit voltage versus state-of-charge[J]. Journal of Power Sources, 2008, 185 (2): 1367- 1373
doi: 10.1016/j.jpowsour.2008.08.103
12 李赛, 庞晓琼, 林慧龙, 等 基于相关向量机的锂离子电池剩余寿命预测[J]. 计算机工程与设计, 2018, 39 (8): 2682- 2686
LI Sai, PANG Xiao-qiong, LIN Hui-long, et al RUL prediction for lithium-ion batteries based on relevance vector machine[J]. Computer Engineering and Design, 2018, 39 (8): 2682- 2686
13 王春雷, 赵琦, 秦孝丽, 等 基于改进相关向量机的锂电池寿命预测方法[J]. 北京航空航天大学学报, 2018, 44 (9): 1998- 2003
WANG Chun-lei, ZHAO Qi, QIN Xiao-li, et al Research on improved relevance vector machine life prediction method of lithium battery[J]. Journal of Beijing University of Aeronautics and Astronautics, 2018, 44 (9): 1998- 2003
14 HU C, JAIN G, SCHMIDT C, et al Online estimation of lithium-ion battery capacity using sparse Bayesian learning[J]. Journal of Power Sources, 2015, 289: 105- 113
doi: 10.1016/j.jpowsour.2015.04.166
15 ZHANG Y, GUO B Online capacity estimation of lithium-ion batteries based on novel feature extraction and adaptive multi-kernel relevance vector machine[J]. Energies, 2015, 8 (11): 12439- 12457
doi: 10.3390/en81112320
16 WANG S, ZHAO L L, SU X H, et al Prognostics of lithium-ion batteries based on battery performance analysis and flexible support vector regression[J]. Energies, 2014, 7 (10): 6492- 6508
doi: 10.3390/en7106492
17 陈雄姿, 于劲松, 唐荻音, 等 基于贝叶斯LS-SVR的锂电池剩余寿命概率性预测[J]. 航空学报, 2013, 34 (9): 2219- 2229
CHEN Xiong-zi, YU Jin-song, TANG Di-yin, et al Probabilistic residual life prediction for lithium-ion batteries based on Bayesian LS-SVR[J]. Acta Aeronautica ET Astronautica Sinica, 2013, 34 (9): 2219- 2229
18 庞景月, 马云彤, 刘大同, 等 锂离子电池剩余寿命间接预测方法[J]. 中国科技论, 2014, 9 (1): 28- 36
PANG Jing-yue, MA Yun-tong, LIU Da-tong, et al Indirect remaining useful life prognostics for lithium-ion battery[J]. China Sciencepaper, 2014, 9 (1): 28- 36
doi: 10.3969/j.issn.2095-2783.2014.01.006
19 EDDAHECH A, BRIAT O, BERTRAND J, et al Behavior and state-of-health monitoring of lithium-ion batteries using impedance spectroscopy and recurring neural networks[J]. International Journal of Electrical Power and Energy, 2012, 42 (1): 487- 494
doi: 10.1016/j.ijepes.2012.04.050
20 XING Y, MA E W M, TSUI K L, et al An ensemble model for predicting the remaining useful performance of lithium-ion batteries[J]. Microelectronics Reliability, 2013, 53: 811- 820
doi: 10.1016/j.microrel.2012.12.003
21 LI H, PAN D, CHEN C L P Intelligent prognostics for battery health monitoring using the mean entropy and relevance vector machine[J]. IEEE Transactions on Systems Man and Cybernetics Systems, 2014, 44 (7): 851- 862
doi: 10.1109/TSMC.2013.2296276
22 SAHA B, GOEBEL K, POLL S, et al Prognostics methods for battery health monitoring using a Bayesian framework[J]. IEEE Transactions on Instrumentation and Measurement, 2009, 58 (2): 291- 296
doi: 10.1109/TIM.2008.2005965
23 DONG H, JIN X, LOU Y, et al Lithium-ion battery state of health monitoring and remaining useful life prediction based on support vector regression-particle filter[J]. Journal of Power Sources, 2014, 271: 114- 123
doi: 10.1016/j.jpowsour.2014.07.176
24 YU J B State of health prediction of lithium-ion batteries: multiscale logic regression and gaussian process regression ensemble[J]. Reliability Engineering and System Safety, 2018, 174: 82- 95
doi: 10.1016/j.ress.2018.02.022
25 沈延斌, 陈岭, 郭浩东, 等 基于深度学习的放置方式和位置无关运动识别[J]. 浙江大学学报: 工学版, 2016, 50 (6): 1141- 1148
SHEN Yan-bin, CHEN Ling, GUO Hao-dong, et al Deep learning based activity recognition independent of device orientation and placement[J]. Journal of Zhejiang University: Engineering Science, 2016, 50 (6): 1141- 1148
26 NAIR V, HINTON G E. 3-D object recognition with deep belief nets [C] // Advances in Neural Information Processing Systems 22: 23rd Annual Conference on Neural Information Processing Systems. Vancouver: Curran Associates Inc, 2012: 1527-1554.
27 BAKER J, DENG L, GLASS J Developments and directions in speech recognition and understanding[J]. IEEE Signal Processing Magazine, 2009, 26 (3): 75- 80
doi: 10.1109/MSP.2009.932166
28 TAMILSELVAN P, WANG P Failure diagnosis using deep belief learning based health state classification[J]. Reliability Engineering and System Safety, 2013, 115: 124- 135
doi: 10.1016/j.ress.2013.02.022
29 SHAO H, JIANG H, ZHANG X, et al Rolling bearing fault diagnosis using an optimization deep belief network[J]. Measurement Science and Technology, 2015, 26 (11): 1- 17
30 袁公萍, 汤一平, 韩旺明, 等 基于深度卷积神经网络的车型识别方法[J]. 浙江大学学报: 工学版, 2018, 52 (4): 694- 702
YUAN Gong-ping, TANG Yi-ping, HAN Wang-ming, et al Vehicle category recognition based on deep convolutional neural network[J]. Journal of Zhejiang University: Engineering Science, 2018, 52 (4): 694- 702
31 陶洁, 刘义伦, 付卓, 等 基于Teager能量算子和深度置信网络的滚动轴承故障诊断[J]. 中南大学学报: 自然科学版, 2017, 48 (1): 61- 68
TAO Jie, LIU Yi-lun, FU Zhuo, et al Fault damage degrees diagnosis for rolling bearing based on Teager energy operator and deep belief network[J]. Journal of Central South University: Science and Technology, 2017, 48 (1): 61- 68
32 MA X, TAO Z, WANG Y, et al Long short-term memory neural network for traffic speed prediction using remote microwave sensor data[J]. Transportation Research Part C: Emerging Technologies, 2015, 54: 187- 197
doi: 10.1016/j.trc.2015.03.014
33 KUREMOTO T, KIMURA S, KOBAYASHI K, et al Time series forecasting using a deep belief network with restricted Boltzmann machines[J]. Neurocomputing, 2014, 137 (15): 47- 56
34 WU Y, YUAN M, DONG S, et al Remaining useful life estimation of engineered systems using vanilla LSTM neural networks[J]. Neurocomputing, 2017, 275: 16- 179
35 ZHANG C, LIM P, QIN A K, et al Multi-objective deep belief networks ensemble for remaining useful life estimation in prognostics[J]. IEEE Transactions on Neural Networks and Learning Systems, 2017, 28 (10): 2306- 2318
doi: 10.1109/TNNLS.2016.2582798
36 HUANG N E, SHEN Z, LONG S R, et al The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis[J]. Proceedings A, 1998, 454 (1971): 903- 995
37 熊炘, 杨世锡, 周晓峰 旋转机械振动信号的固有模式函数降噪方法[J]. 浙江大学学报: 工学版, 2011, 45 (8): 1376- 1381
XIONG Xin, YANG Shi-xi, ZHOU Xiao-feng IMF-based denoising method for vibration signal in rotating machinery[J]. Journal of Zhejiang University: Engineering Science, 2011, 45 (8): 1376- 1381
38 WU Z, HUANG N E Ensemble empirical mode decomposition: a noise-assisted data analysis method[J]. Advances in Adaptive Data Analysis, 2009, 1 (1): 1- 41
doi: 10.1142/S1793536909000047
39 SAHA B, GOEBEL K. " Battery Data Set”, NASA Ames prognostics data repository [DB/OL]. [2016-05-12]. http://ti.arc.nasa.gov/project/prognostic-data-repository/.
40 姜媛媛, 刘柱, 罗慧, 等 锂电池剩余寿命的ELM间接预测方法[J]. 电子测量与仪器学报, 2016, 30 (2): 179- 185
JIANG Yuan-yuan, LIU Zhu, LUO Hui, et al ELM indirect prediction method for the remaining life of lithium-ion battery[J]. Journal of Electronic Measurement and Instrumentation, 2016, 30 (2): 179- 185
[1] 余文韬,谢旭,成程. 焊接构造对T型接头超低周疲劳性能的影响[J]. 浙江大学学报(工学版), 2021, 55(1): 31-37.
[2] 吴佳铭,陈自强. 可变低温环境锂电池组内部短路故障诊断[J]. 浙江大学学报(工学版), 2020, 54(7): 1433-1439.
[3] 杨冰,王小华,杨鑫,黄孝喜. 基于HOG金字塔人脸识别方法[J]. 浙江大学学报(工学版), 2014, 48(9): 1564-1569.
[4] 彭海,赵巨峰,冯华君,徐之海,李奇,陈跃庭. 基于区域显著性的双波段图像融合方法[J]. J4, 2012, 46(11): 2109-2115.
[5] 金津, 何乐年, 陈琛, 叶益迭. 多节串联锂电池的多功能管理芯片设计与实现[J]. J4, 2011, 45(2): 306-313.
[6] 胡清琮 陈琛 王菁 张鲁 陈东坡 梁斌 何乐年. 基于恒流/恒压方式的锂电池充电保护芯片设计[J]. J4, 2008, 42(4): 632-635.
[7] 郭健 孙炳楠. 基于小波变换的桥梁健康监测多尺度分析[J]. J4, 2005, 39(1): 114-118.