基于多尺度分解和深度学习的锂电池寿命预测

被引：82

作者：

胡天中

余建波

机构：

[1] 同济大学机械与能源工程学院

来源：

浙江大学学报(工学版) | 2019年 / 53卷 / 10期

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);

D O I：

暂无

中图分类号：

TM912 [蓄电池]; TP181 [自动推理、机器学习];

学科分类号：

080802 [电力系统及其自动化]; 140502 [人工智能];

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.

引用

页码：1852 / 1864

页数：13

共 25 条

[1]

State of health prediction of lithium-ion batteries: Multiscale logic regression and Gaussian process regression ensemble.[J].Jianbo Yu.Reliability Engineering and System Safety.2018,

[2]

Remaining useful life estimation of engineered systems using vanilla LSTM neural networks.[J].Yuting Wu;Mei Yuan;Shaopeng Dong;Li Lin;Yingqi Liu.Neurocomputing.2018,

[3]

A lead-acid battery's remaining useful life prediction by using electrochemical model in the Particle Filtering framework.[J].Chao Lyu;Qingzhi Lai;Tengfei Ge;Honghai Yu;Lixin Wang;Na Ma.Energy.2016,

[4]

Rolling bearing fault diagnosis using an optimization deep belief network [J].

Shao, Haidong ;

Jiang, Hongkai ;

Zhang, Xun ;

Niu, Maogui .

MEASUREMENT SCIENCE AND TECHNOLOGY, 2015, 26 (11)

[5]

Online estimation of lithium-ion battery capacity using sparse Bayesian learning.[J].Chao Hu;Gaurav Jain;Craig Schmidt;Carrie Strief;Melani Sullivan.Journal of Power Sources.2015,

[6]

Long short-term memory neural network for traffic speed prediction using remote microwave sensor data.[J].Xiaolei Ma;Zhimin Tao;Yinhai Wang;Haiyang Yu;Yunpeng Wang.Transportation Research Part C.2015,

[7]

Lithium-ion battery state of health monitoring and remaining useful life prediction based on support vector regression-particle filter.[J].Hancheng Dong;Xiaoning Jin;Yangbing Lou;Changhong Wang.Journal of Power Sources.2014,

[8]

Failure diagnosis using deep belief learning based health state classification.[J].Prasanna Tamilselvan;Pingfeng Wang.Reliability Engineering and System Safety.2013,

[9]

An ensemble model for predicting the remaining useful performance of lithium-ion batteries [J].

Xing, Yinjiao ;

Ma, Eden W. M. ;

Tsui, Kwok-Leung ;

Pecht, Michael .

MICROELECTRONICS RELIABILITY, 2013, 53 (06) :811-820

[10]

Time series forecasting using a deep belief network with restricted Boltzmann machines.[J].Takashi Kuremoto;Shinsuke Kimura;Kunikazu Kobayashi;Masanao Obayashi.Neurocomputing.2014,

← 1 2 3 →