ARIMA Based Research on Cell Inconsistency Prediction of Power Battery

Cell inconsistency affects battery life and driving safety. In order to solve the accuracy problem of cell inconsistency prediction of power battery, a health indicator(HI) was constructed to reflect the degradation trends of cell inconsistency in the time dimension based on massive historical data...

Full description

Saved in:
Bibliographic Details
Main Authors: SONG Chao, XIONG Gang, XIE Yongbo, WANG Wenming
Format: Article
Language:zho
Published: Editorial Office of Control and Information Technology 2019-01-01
Series:Kongzhi Yu Xinxi Jishu
Subjects:
Online Access:http://ctet.csrzic.com/thesisDetails#10.13889/j.issn.2096-5427.2019.05.018
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Cell inconsistency affects battery life and driving safety. In order to solve the accuracy problem of cell inconsistency prediction of power battery, a health indicator(HI) was constructed to reflect the degradation trends of cell inconsistency in the time dimension based on massive historical data of the vehicle network platform, and health indicator time series were extracted based on the segmentation interval of SOC. Considering the fluctuation of the health indicator after a long time, a ARIMA model was introduced for small sample prediction, only using the health indicator time series in recent several discharge conditions. The prediction results show that the method requires less training samples and less hardware resources, and the overall prediction accuracy is not less than 90%, which can meet the practical requirements.
ISSN:2096-5427