汽车工程 ›› 2024, Vol. 46 ›› Issue (10): 1897-1903.doi: 10.19562/j.chinasae.qcgc.2024.10.016

• • 上一篇    下一篇

基于多维度多尺度特征的锂离子电池RUL估计方法

张秋艳1,程泽2(),刘旭2   

  1. 1.榆林学院能源工程学院,榆林 719000
    2.天津大学电气自动化与信息工程学院,天津 300000
  • 收稿日期:2024-03-10 修回日期:2024-06-10 出版日期:2024-10-25 发布日期:2024-10-21
  • 通讯作者: 程泽 E-mail:chengze@tju.edu.cn
  • 基金资助:
    国家自然科学基金(61873180);陕西省教育厅专项科研计划项目(23JK0750)

RUL Estimation Method for Lithium-ion Batteries Based on Multi-dimensional and Multi-scale Features

Qiuyan Zhang1,Ze Cheng2(),Xu Liu2   

  1. 1.School of Energy Engineering, Yulin University, Yulin 719000
    2.School of Electrical Automation and Information Engineering, Tianjin University, Tianjin 300000
  • Received:2024-03-10 Revised:2024-06-10 Online:2024-10-25 Published:2024-10-21
  • Contact: Ze Cheng E-mail:chengze@tju.edu.cn

摘要:

准确预测锂离子电池的剩余使用寿命(RUL)对储能系统的高效安全运行具有重要意义。针对已有数据驱动方法估计RUL中提取老化特征不够全面以及需要先预测健康状态变化再估计RUL的不足,本文提出一种利用多维度多尺度特征的RUL估计方法,采用恒流充电电压片段数据直接估计电池的RUL。该模型对数据进行维度变换后利用不同尺度卷积操作提取电压片段的老化特征来映射RUL。基于牛津大学、NASA、马里兰大学公开数据集进行模型验证,验证结果表明该模型能够利用电压片段数据直接估算电池的RUL,无需电池自身SOH变化作为训练数据,对比于基于单一维度的固定尺度的特征具有更高的准确性和通用性。

关键词: 锂离子电池, 剩余使用寿命, 多维度多尺度特征, 深度学习

Abstract:

Accurately predicting the remaining useful life (RUL) of lithium-ion batteries is important for the efficient and safe operation of energy storage systems. For the deficiencies of existing data-driven methods for RUL estimation, which extract aging features non-comprehensively enough and need to predict health state changes before estimating RUL, a RUL estimation method using multi-dimensional and multi-scale features is proposed in this paper to directly estimate the RUL of a battery using constant-current charging voltage segment data. The model maps RUL by extracting aging features of voltage segments using different scale convolution operation after dimensionally transforming the data. The model is validated using publicly available datasets from the University of Oxford, NASA, and the University of Maryland. The validation results show that the model can directly estimate the RUL of the batteries using the voltage segment data without the need of the current historical SOH of the batteries as the training data, which has higher accuracy and universality compared to fixed scale features based on a single dimension.

Key words: lithium-ion battery, remaining useful life, multi-dimensional and multi-scale features, deep learning