储能科学与技术 ›› 2025, Vol. 14 ›› Issue (9): 3564-3566.doi: 10.19799/j.cnki.2095-4239.2025.0719

• 储能测试与评价 • 上一篇    

基于大数据与深度学习的锂电池SOC与SOH联合评估方法

邵换峥()   

  1. 漯河食品工程职业大学，河南 漯河 462300
  • 收稿日期:2025-08-08 修回日期:2025-08-13 出版日期:2025-09-28 发布日期:2025-09-05
  • 作者简介:邵换峥（1981—），女，硕士，副教授，研究方向为计算机科学与技术、大数据应用技术、职业教育，E-mail：13939587215@163.com。

Joint evaluation method for SOC and SOH of lithium batteries based on big data and deep learning

Huanzheng SHAO()   

  1. Luohe Food Engineering Vocational University, Luohe 462300, Henan, China
  • Received:2025-08-08 Revised:2025-08-13 Online:2025-09-28 Published:2025-09-05

RichHTML

0

PDF

0

摘要：

锂电池荷电状态(SOC)与健康状态(SOH)的联合评估，是保证电池稳定高效运行的前提，对此本研究针对当前相关联合评估方法进行了综述。首先依次分析了锂电池SOC和SOH评估所面临的难点，包括初始值依赖、线性特征、物理场耦合问题等；然后详细分析了大数据和深度学习技术加持下，新兴的锂电池SOC与SOH联合评估方法。重点探讨了不同数据驱动模型下的评估侧重和运行逻辑，最后综述了近年来相关领域技术的发展进程，期望对储能产业发展和锂电池评估技术的研究提供一定借鉴。

关键词: 大数据, 深度学习, 锂电池, 评估

Abstract:

The joint evaluation of state of charge (SOC) and state of health (SOH) of lithium batteries is a prerequisite for ensuring stable and efficient operation of batteries. This study provides a review of current related joint evaluation methods. Firstly, the difficulties faced in evaluating the SOC and SOH of lithium batteries were analyzed in sequence, including initial value dependence, linear characteristics, and physical field coupling issues; Then, a detailed analysis was conducted on the emerging joint evaluation methods for SOC and SOH of lithium batteries, which are supported by big data and deep learning technologies. The focus was on exploring the evaluation emphasis and operational logic under different data-driven models. Finally, the development process of related technologies in recent years was summarized, hoping to provide some reference for the development of energy storage industry and research on lithium battery evaluation technology.

Key words: big data, deep learning, lithium battery, assessment

中图分类号: