An integrated unscented kalman filter and relevance vector regression approach for lithium-ion battery remaining useful life and short-term capacity prediction
详细信息 查看全文
- 作者：Xiujuan Zheng zxj_hust@163.com" class="auth_mail" title="E-mail the corresponding author ; Huajing Fang ; hjfang@mail.hust.edu.cn" class="auth_mail" title="E-mail the corresponding author
- 关键词：Lithium-ion battery ; Capacity prediction ; Remaining useful life ; Relevance vector regression ; Unscented Kalman filter
- 刊名：Reliability Engineering & System Safety
- 出版年：2015
- 出版时间：December 2015
- 年：2015
- 卷：144
- 期：Complete
- 页码：74-82
- 全文大小：1279 K
文摘
- class="listitem" id="list_li0005">
- class="label">•
An integrated method is proposed for RUL prediction as well as short-term capacity prediction.
- class="label">•
Relevance vector regression model is employed as a nonlinear time-series prediction model.
- class="label">•
Unscented Kalman filter is used to recursively update the states for battery model parameters during the prediction.
- class="label">•
A time-varying weighting scheme is utilized to improve the accuracy of the RUL prediction.
- class="label">•
The proposed method demonstrates high reliability and prediction accuracy.