储能科学与技术 ›› 2025, Vol. 14 ›› Issue (9): 3538-3540.doi: 10.19799/j.cnki.2095-4239.2025.0536

• 储能测试与评价 • 上一篇    

锂离子电池储能电站的运行状态监测与评估

张磊()   

  1. 西安财经大学信息学院,陕西 西安 710100
  • 收稿日期:2025-06-05 修回日期:2025-06-20 出版日期:2025-09-28 发布日期:2025-09-05
  • 作者简介:张磊(1984—),男,博士,高级工程师,研究方向:数据科学、人工智能算法。E-mail:27214627@qq.com

Operating status monitoring and evaluation of lithium-ion battery energy storage power stations

Lei ZHANG()   

  1. (School of Information, Xi'an University of Finance and Economics, Xi'an 710100, Shaanxi, China )
  • Received:2025-06-05 Revised:2025-06-20 Online:2025-09-28 Published:2025-09-05

摘要:

针对锂离子电池储能电站中多源数据融合困难、传统方法无法有效捕捉非线性退化特征的问题,本文提出了一种融合机器学习、深度学习的储能电站运行状态监测与评估框架。系统性地设计了多层级特征提取与融合机制,解决了电压-电流-温度-气体等多模态数据时空错位、隐性退化特征提取不足等问题,为锂离子储能电站运行状态监测与评估提供了新的解决方案。

关键词: 锂离子电池, 储能系统, 储能电站, 状态监测

Abstract:

This paper proposes a collaborative monitoring and evaluation framework for the operation status of lithium-ion battery energy storage power plants, which integrates machine learning and deep learning, to address the difficulties in multi-source data fusion and the inability of traditional methods to effectively capture nonlinear degradation features. A multi-level feature extraction and fusion mechanism has been systematically designed to solve the problems of temporal and spatial misalignment of multimodal data such as voltage current temperature, and insufficient extraction of implicit degradation features, providing a new solution for the monitoring and evaluation of the operation status of lithium-ion energy storage power plants.

Key words: lithium-ion battery, energy storage system, energy storage power station, status monitoring

中图分类号: