[1]乔玉龙,王玉斐,李娜.基于隐马尔可夫模型的锂电池退化状态识别[J].应用科技,2018,45(02):29-33.[doi:10.11991/yykj.201612012]
 QIAO Yulong,WANG Yufei,LI Na.Recognition on regression state of lithium-ion battery by using hidden Markov model[J].Applied science and technology,2018,45(02):29-33.[doi:10.11991/yykj.201612012]
点击复制

基于隐马尔可夫模型的锂电池退化状态识别(/HTML)
分享到:

《应用科技》[ISSN:1009-671X/CN:23-1191/U]

卷:
第45卷
期数:
2018年02期
页码:
29-33
栏目:
现代电子技术
出版日期:
2018-03-15

文章信息/Info

Title:
Recognition on regression state of lithium-ion battery by using hidden Markov model
作者:
乔玉龙 王玉斐 李娜
哈尔滨工程大学 信息与通信工程学院, 黑龙江 哈尔滨 150001
Author(s):
QIAO Yulong WANG Yufei LI Na
College of Information and Communication Engineering, Harbin Engineering University, Harbin 150001, China
关键词:
锂电池视情维修电池管理系统隐马尔可夫模型k均值聚类状态监测神经网络混合高斯模型
Keywords:
lithium-ion cellcondition based maintenance (CBM)battery management system (BMS)hidden Markov modelk-means clusteringstate monitoringneural networkGMM
分类号:
TP206.3
DOI:
10.11991/yykj.201612012
文献标志码:
A
摘要:
针对电池容量在实际应用中难以测量的问题,从在线传感器直接观测的电压、电流、时间等参数中提取状态特征向量代替容量来表征电池的健康状况。使用隐马尔可夫模型(HMM)作为状态监测器,分别对不同的退化时期建立HMM,通过前向-后向算法对当前观测序列计算相似概率来判断当前电池的健康状况。使用马里兰大学先进寿命周期工程研究中心(CALCE)公开的数据集与BP神经网络进行了对比实验,实验结果表明HMMs对锂电池退化状态有很高的识别率。
Abstract:
The state monitoring and system management of lithium battery is one of the key constraints for battery storage systems. Aiming at the problem that the battery capacity is difficult to measure in the practical application, the paper used the state feature vectors extracted from such parameters as voltage, current and time directly observed from online sensors to replace capacity for indicating the health state of battery. The paper took hidden Markov model (HMM) as the state monitor, established HMMs for different health state periods, and calculated the similarity probability of the present observation sequence by forward-backward algorithm for judging the present health state of battery. The data set made public by CALCE were adopted to carry out a contrast experiment with BP neural network, the test results show that HMMs have a high recognition rate for the regression state of lithium battery.

参考文献/References:

[1] 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]. 中国科技论文, 2014, 9(1):28-36.
[2] 刘大同, 周建宝, 郭力萌, 等. 锂离子电池健康评估和寿命预测综述[J]. 仪器仪表学报, 2015, 36(1):1-16.
[3] 周建宝. 基于RVM的锂离子电池剩余寿命预测方法研究[D]. 哈尔滨:哈尔滨工业大学, 2013:6-17.
[4] 王红. 卫星锂离子电池剩余寿命预测方法及应用研究[D]. 哈尔滨:哈尔滨工业大学, 2013:2-9.
[5] SAHA B, GOEBEL K, CHRISTOPHERSEN J. Comparison of prognostic algorithms for estimating remaining useful life of batteries[J]. Transactions of the institute of measurement and control, 2009, 31(3/4):293-308.
[6] HE Wei, WILLIARD N, OSTERMAN M, et al. Prognostics of lithium-ion batteries using extended Kalman filtering[C]//IMAPS Advanced Technology Workshop on High Reliability Microelectronics for Military Applications. Linthicum Heights:IMAPS, 2011:17-19.
[7] LU Chen, TAO Laifa, FAN Huanzhen. Li-ion battery capacity estimation:A geometrical approach[J]. Journal of power sources, 2014, 261:141-147.
[8] LIU Zhijuan, LI Qing, LIU Xianhui, et al. A hybrid LSSVR/HMM-based prognostic approach[J]. Sensors, 2013, 13(5):5542-5560.
[9] CAMCI F, CHINNAM R B. Health-state estimation and prognostics in machining processes[J]. IEEE transactions on automation science and engineering, 2010, 7(3):581-597.
[10] RABINER L R. A tutorial on hidden Markov models and selected applications in speech recognition[J]. Proceedings of the IEEE, 1989, 77(2):257-286.
[11] PIAO Changhao, LI Zunchen, LU Sheng, et al. Analysis of real-time estimation method based on hidden Markov models for battery system states of health[J]. Journal of power electronics, 2016, 16(1):217-226.
[12] 翁立祥. 基于隐马尔可夫模型的动态纹理分类[D]. 哈尔滨:哈尔滨工程大学, 2015:34-36.
[13] HE Wei, WILLIARD N, OSTERMAN M, et al. Prognostics of lithium-ion batteries based on Dempster-Shafer theory and the Bayesian Monte Carlo method[J]. Journal of power sources, 2011, 196(23):10314-10321.
[14] 盛鲁英. 基于隐马尔科夫模型的电动汽车电池寿命的研究[D]. 哈尔滨:哈尔滨工业大学, 2012:20-23.

备注/Memo

备注/Memo:
收稿日期:2016-12-12。
基金项目:国家自然科学基金项目(81913080)
作者简介:乔玉龙(1978-),男,教授,博士;王玉斐(1991-),男,硕士研究生
通讯作者:王玉斐,E-mail:wangyufei@hrbeu.edu.cn
更新日期/Last Update: 2018-04-09