储能科学与技术 ›› 2024, Vol. 13 ›› Issue (9): 2972-2982.doi: 10.19799/j.cnki.2095-4239.2024.0289

• AI辅助先进电池设计与应用专刊 • 上一篇    下一篇

基于多特征量分析和LSTM-XGBoost模型的锂离子电池SOH估计方法

陆继忠1(), 彭思敏2(), 李晓宇3   

  1. 1.江苏省盐城技师学院电气工程学院，江苏 盐城 224000
    2.盐城工学院电气工程学院，江苏 盐城 224051
    3.深圳大学物理与光电工程学院，广东 深圳 518060
  • 收稿日期:2024-04-01 修回日期:2024-04-11 出版日期:2024-09-28 发布日期:2024-09-20
  • 通讯作者: 彭思敏 E-mail:120322268@qq.com;psmsteven@163.com
  • 作者简介:陆继忠（1974—），男，硕士，高级讲师，研究方向为电气自动化控制技术的应用研究，E-mail：120322268@qq.com；
  • 基金资助:
    国家自然科学基金(52177219);江苏高校“青蓝工程”(2021-11);盐城工学院校级科研(xjr2021052)

State-of-health estimation of lithium-ion batteries based on multifeature analysis and LSTM-XGBoost model

Jizhong LU1(), Simin PENG2(), Xiaoyu LI3   

  1. 1.School of Electrical Engineering, Jiangsu Yancheng Technician College, Yancheng 224000, Jangsu, China
    2.School of Electrical Engineering, Yancheng Institute of Technology, Yancheng 224051, Jangsu, China
    3.School of Physics and Optoelectronic Engineering, Shenzhen University, Shenzhen 518060, Guangdong, China
  • Received:2024-04-01 Revised:2024-04-11 Online:2024-09-28 Published:2024-09-20
  • Contact: Simin PENG E-mail:120322268@qq.com;psmsteven@163.com

RichHTML

13

PDF

73

摘要：

准确评估锂离子电池健康状态(state of health, SOH)对保证电动汽车的安全稳定运行至关重要。然而，传统SOH估计方法在有效提取健康特征(health features, HFs)和依赖大量特征测试数据上面临一些挑战。为此，本文提出一种基于多特征量分析和长短期记忆(long short-term memory, LSTM)-极端梯度提升(eXtreme gradient boosting, XGBoost)模型的锂离子电池SOH估计方法。首先，为准确描述电池的老化机理，从电池充电数据中提取关于时间、能量、IC三大类共6个HFs。考虑到同类型HFs之间存在大量冗余信息，采用一种基于双相关性的特征处理方法，筛选出可准确表征电池退化趋势的组合HFs。其次，针对传统SOH估计模型需要大量HFs测试数据的问题，提出一种基于LSTM-XGBoost的SOH估计模型。在该模型中，采用LSTM算法来预测电池剩余循环次数的HFs数据。同时，为解决LSTM模型进行HFs预测时计算效率不高的问题，采用LSTM-XGBoost模型进行电池SOH估计。利用NASA电池数据集进行验证，结果表明，所提出方法在不同测试数据量下能准确估计锂电池的SOH，且均方根误差保持在1%以内，具有较高的估计精度和鲁棒性。

关键词: 锂离子电池, 健康状态, 特征分析, 长短期记忆神经网络, 极端梯度提升

Abstract:

An accurate assessment of the state-of-health (SOH) of lithium-ion batteries is critical to ensure the safe and stable operation of electric vehicles. However, traditional SOH estimation methods face challenges in effectively extracting health features (HFs) and relying on large amounts of HF test data. This paper proposes an SOH estimation method for lithium-ion batteries based on multifeature analysis and the long short-term memory (LSTM)-eXtreme gradient boosting (XGBoost) model. First, to accurately describe the aging mechanism of a battery, six HFs were extracted from the battery charging data in three categories: time, energy, and IC. Considering a lot of redundant information exists among the same types of HFs, a feature-processing method based on double correlation was presented to screen out the combined HFs that can accurately characterize the trend of battery degradation. Second, to solve the problem that the traditional SOH estimation model requires a large amount of HF test data, an SOH estimation model based on the LSTM-XGBoost was proposed. In this model, the LSTM algorithm was used to predict the HF data of the number of battery remaining cycles. At the same time, to solve the problem of low computational efficiency in HF prediction using the LSTM model, the LSTM-XGBoost model was developed to estimate the SOH of batteries. The results show that the proposed method can accurately estimate the SOH of lithium batteries under different test data amounts, and the root-mean-square error is kept within 1%, which has high estimation accuracy and robustness.

Key words: lithium-ion battery, state of health, characteristic analysis, long short-term memory neural network, extreme gradient boosting

中图分类号: