[1]王 正1,2.基于机器学习的新能源汽车电池剩余寿命预测[J].机械与电子,2019,(12):9-11.
 WANG Zheng,Remaining UsefulLife Prediction of New Energy Vehicle Battery Based on Machine Learning[J].Machinery & Electronics,2019,(12):9-11.
点击复制

基于机器学习的新能源汽车电池剩余寿命预测()
分享到:

机械与电子[ISSN:1001-2257/CN:52-1052/TH]

卷:
期数:
2019年12期
页码:
9-11
栏目:
设计与研究
出版日期:
2019-12-24

文章信息/Info

Title:
R emaining Useful Life Prediction of New Energy Vehicle Battery Based on M achine Learning
文章编号:
1001- 2257(2019)12- 0009- 03
作者:
王 正
1.宁夏大学新华学院,宁夏 银川 750021;
2.宁夏大学土木与水利工程学院,宁夏 银川 750021
Author(s):
WANG Zheng1 2
1.XinhuaCollegeofNingxiaUniversity,Yinchuan750021,China;
2.SchoolofCivilEngineeringandHydraulicEngineering,NingxiaUniversity,Yinchuan750021,China
关键词:
锂电池剩余寿命预测RVR NDM健康因子
Keywords:
lithium ionbatteryremainingusefullifepredictionRVR NDMhealthindicator
分类号:
TP206.3;TM912
文献标志码:
A
摘要:
利用一种改进的RVM模型(RVR-NDM)进行锂电池的剩余寿命预测,通过重构模型参数,提高了模型的预测性能,并将该方法应用于预测锂离子电池的剩余寿命。以充放电循环次数200、400和600为预测时间,分别进行了LR、RVR和RVR-NDM等3种不同方法对CALCE的数据集的验证。实验结果表明,当充放电循环次数为400或600时,RVR-NDM和RVR模型都展现出了良好的预测性能,且RVR-NDM的预测精度要高于RVR。
Abstract:
An improved RVM model (RVR-NDM) was used to predict the remaining useful life of lithium-ion batteries. By reconstructing model parameters, the prediction performance of the model was improved, and the method was applied to predict remaining useful life of lithium-ion batteries. The data sets of CALCE were validated by LR, RVR and RVR-NDM with charge-discharge cycles of 200, 400 and 600 as prediction time. The experimental results show that when charge-discharge cycles being 400 or 600, RVR-NDM and RVR-NDM models show good prediction performance, and the prediction accuracy of RVR-NDM is higher than RVR.

参考文献/References:

[1] 徐平,陈钦,张西华,等.废锂离子电池中锂提取技术研究进展[J].过程工程学报,2019,19(4):1- 7.

[2] 兰凤崇,李诗成,陈吉清,等.基于专利分析的锂离子动力电池产业发展趋势[J].科技管理研究,2019,39(12):144- 150.
[3] 李奇,刘嘉蔚,陈维荣.质子交换膜燃料电池剩余使用寿命预 测 方 法 综 述 及 展 望 [J].中 国 电 机 工 程 学 报,
2019,39(8):2365- 2375.
[4] WhiteRE,SanthabagopalanS.Quantifyingcell to cellvariationsinlithiumionbatteries[J].International JournalofElectrochemistry,2012,7(11):20- 25.
[5] VirkarA V.A modelfordegradationofelectrochemicaldevicesbasedonlinearnon equilibriumthermody
namicsanditsapplicationtolithiumionbatteries[J].JournalofPowerSources,2011,196(14):5970- 5984.
[6] XingYJ,Eden W M ,TsuiK L,etal.Anensemble modelforpredictingtheremainingusefulperformance oflithium ionbatteries[J].MicroelectronicsReliability,2013,53(6):811- 820.
[7] 房红征,史慧,韩立明,等.基于粒子群优化神经网络的卫星故障预测方法[J].计 算 机 测 量 与 控 制,2013,21
(7):1730- 1733,1745.
[8] LiuD T,PangJY,ZhouJB,etal.Prognosticsfor stateofhealthestimationoflithium ion batteries basedoncombination Gaussianprocessfunctionalregression[J].MicroelectronicsReliability,2013,53(6):
832- 839.
[9] PattipatiB,PattipatiK,ChristophersonJP,etal.Automotivebatterymanagementsystems[C]//IEEEAU-
TOTESTCON.NewYork:IEEE,2008:581- 586.
[10] NuhicA,TerzimehicT,Soczka GuthT,etal.Health diagnosisandremainingusefullifeprognosticsoflithium ionbatteriesusingdata driven methods[J].JournalofPowerSources,2013,239:680- 688.
[11] LongB,Xian W M,JiangL,etal.Animprovedautoregressivemodelbyparticleswarmoptimizationfor prognosticsoflithium ionbatteries[J].MicroelectronicsReliability,2013,53(6):821- 831.
[12] LiuJ,Saxena A,GoebelK.Anadaptiverecurrent neuralnetworkforremainingusefullifepredictionof
lithium ionbatteries[C]//ProceedingsoftheAnnual ConferenceofthePrognosticsand Health ManagementSociety,2010:1- 9.
[13] 彭宇,王建民,彭喜元.储备池计算概述[J].电子学 报,2011,39(10):2387- 2396.
[14] 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.
[15] ShiJM,LiYX,WangG,etal.Healthindexsynthetizationandremainingusefullifeestimationforturbofanenginesbasedonrun to failuredatasets[J].MaintenanceandReliability,2016,18(4):621- 631.

相似文献/References:

[1]刘东林,秦玉焘,麻浩军,等.基于马尔科夫链的车桥齿轮剩余寿命预测研究[J].机械与电子,2023,41(03):76.
 LIU Donglin,QIN Yutao,MA Haojun,et al.Research on Residual Life Prediction of Axle Gear Based on Markov Chain[J].Machinery & Electronics,2023,41(12):76.
[2]王丽玲,孙晓波,宋树平,等.基于 QPSO-LSTM 模型的锂电池剩余容量预测[J].机械与电子,2024,42(09):52.
 WANG Liling,SUN Xiaobo,SONG Shuping,et al.Prediction of Remaining Capacity of Lithium Battery Based on QPSO-LSTM Model[J].Machinery & Electronics,2024,42(12):52.
[3]王 正1,2.基于DAE-HTPF的新能源汽车电池剩余寿命预测[J].机械与电子,2020,(03):3.
 WANG Zheng,RemainingLife Prediction of New Energy Vehicle Battery Based on DAE-HTPF[J].Machinery & Electronics,2020,(12):3.

备注/Memo

备注/Memo:
收稿日期:2019- 08- 28
基金项目:宁夏大学新华学院科学研究基金资助项目(18XHKY01);宁夏2019年度高等学校“双师型教师实践锻炼计划”项目
作者简介:王 正 (1988-),男,宁夏银川人,讲师,研究方向为智能控制算法和数值模拟。
更新日期/Last Update: 2019-12-23