汽车工程

汽车工程 ›› 2023, Vol. 45 ›› Issue (2): 175-182.doi: 10.19562/j.chinasae.qcgc.2023.02.002

所属专题： 新能源汽车技术-动力电池&燃料电池2023年

• • 上一篇    下一篇

实车数据驱动的锂电池剩余使用寿命预测方法研究

兰凤崇,陈继开,陈吉清(),蒋心平,李子涵,潘威   

  1. 1.华南理工大学机械与汽车工程学院，广州　510641
    2.华南理工大学，广东省汽车工程重点实验室，广州　510641
  • 收稿日期:2022-07-14 修回日期:2022-08-14 出版日期:2023-02-25 发布日期:2023-02-21
  • 通讯作者: 陈吉清 E-mail:chenjq@scut.edu.cn
  • 基金资助:
    国家重点研发计划(2018YFB0104100);广东省科技计划(2015B010137002);全国车辆事故深度调查体系（NAIS）和新能源汽车事故调查协作网资助

Research on Lithium Battery Remaining Useful Life Prediction Method Driven by Real Vehicle Data

Fengchong Lan,Jikai Chen,Jiqing Chen(),Xinping Jiang,Zihan Li,Wei Pan   

  1. 1.School of Mechanical and Automotive Engineering，South China University of Technology，Guangzhou　510641
    2.South China University of Technology，Guangdong Provincial Automobile Engineering Key Laboratory，Guangzhou　510641
  • Received:2022-07-14 Revised:2022-08-14 Online:2023-02-25 Published:2023-02-21
  • Contact: Jiqing Chen E-mail:chenjq@scut.edu.cn

RichHTML

32

PDF (PC)

395

赞

摘要：

锂离子动力电池剩余使用寿命（RUL）预测对于认识全生命周期电动汽车的安全和可靠性、改善电池管理系统的设计具有重要意义。通常基于深度学习的时序预测方法，本质上是一个递推的过程，每一次预测的误差会随预测次数增加而累积，难以保证预测精度和预测效率。基于深度学习序列预测和误差分析理论，建立一种ARIMA-EDLSTM融合模型的锂电池RUL预测方法，使用编码器-解码器（ED）框架改进长短时记忆神经网络模型（LSTM）构建从序列到序列预测的EDLSTM模型，并融合ARIMA模型预测误差趋势，进而修正最终预测结果。理论分析和实车采集数据验证表明，该方法在预测比例超过历史数据总量35%的情况下，仍然能较好地拟合实车SOH衰退曲线，有效提高锂电池剩余使用寿命的预测精度。

关键词: 锂离子动力电池, 剩余使用寿命预测, 数据驱动, 深度学习

Abstract:

The prediction of remaining useful life （RUL） of lithium-ion power battery is of great significance for understanding the safety and reliability of electric vehicles in the whole life cycle and improving the design of battery management system. Generally， the time series prediction method based on deep learning is a recursive process. The error of each prediction will accumulate with the increase of prediction times， which is difficult to ensure the prediction accuracy and efficiency. Based on the theory of deep learning sequence prediction and error analysis， an ARIMA-EDLSTM fusion model is established for lithium battery remaining useful life prediction. The encoder decoder （ED） framework is used to improve the long short-term memory neural network model （LSTM）， establish the EDLSTM model of sequence to sequence prediction， and fuse the ARIMA model to predict the error trend and modify the prediction results. Theoretical analysis and real vehicle data verification show that this method can still better fit the real vehicle SOH decline curve when the prediction proportion exceeds 35% of the total history data， and effectively improve the prediction accuracy of the remaining useful life of lithium battery.

Key words: lithium-ion power battery, remaining useful life prediction, data driven, deep learning