储能科学与技术 ›› 2023, Vol. 12 ›› Issue (4): 1244-1256.doi: 10.19799/j.cnki.2095-4239.2022.0708

• 储能测试与评价 • 上一篇    下一篇

基于CEEMDANISOA-ELM的锂电池荷电状态预测

刘峰(), 陈海忠()   

  1. 江苏理工学院,江苏 常州 213000
  • 收稿日期:2022-11-29 修回日期:2022-12-26 出版日期:2023-04-05 发布日期:2023-05-08
  • 通讯作者: 陈海忠 E-mail:1036980618@qq.com;11715452@qq.com
  • 作者简介:刘峰(1998—),男,硕士研究生,主要研究方向为电池建模及预测,E-mail:1036980618@qq.com

Lithium-ion battery state prediction based on CEEMDAN and ISOA-ELM

Feng LIU(), Haizhong CHEN()   

  1. Jiangsu University of Technology, Changzhou 213000, Jiangsu, China
  • Received:2022-11-29 Revised:2022-12-26 Online:2023-04-05 Published:2023-05-08
  • Contact: Haizhong CHEN E-mail:1036980618@qq.com;11715452@qq.com

摘要:

锂电池具有能量密度高、输出电压高、无记忆效应等优点,但过充过放电易引发安全事故,精确预测锂电池荷电状态(SOC)让其工作在最佳状态,具有重要现实意义,本文提出了一种基于自适应噪声集成经验模态分解(CEEMDAN)和数据驱动模型组合预测锂离子电池荷电状态的方法,对锂电池原始电流数据进行模态分解,得到多个子序列模态分量,提出一种基于惯性权重与Levy飞行机制的改进海鸥算法(ISOA),对极限学习机预测模型(ELM)参数进行优化,构建ISOA-ELM锂电池预测模型;训练模型得到锂电池SOC预测结果。实验结果表明,该模型在实际工作中能够更贴合实际SOC,更有利于锂电池工作在最佳状态。

关键词: 锂离子电池, 荷电状态, 自适应噪声经验模态分解, 极限学习机, 海鸥优化算法

Abstract:

Lithium batteries have high energy density, high output voltage, and no memory effect, but their overcharge and over-discharge can cause accidents. In this regard, accurate prediction of the state of charge (SOC) of lithium batteries serves as the best condition. In this paper, a method based on an adaptive noise integrated Empirical Mode decomposition (CEEMDAN) and data-driven model is proposed to predict the state of charge of lithium-ion batteries. The original voltage data of lithium-ion batteries were modally decomposed to obtain the modal components of multiple sub-sequences. An improved Seagull algorithm (ISOA) based on the inertia weight and the Levy flight mechanism was proposed. The parameters of the extreme learning machine prediction model were optimized, and ISOA-ELM lithium battery prediction model was built. The SOC prediction results of the lithium batteries were obtained by training the model. The experimental results show that the model can better fit the actual SOC in practice and is more conducive to the lithium battery working in the best state.

Key words: lithium-ion batteries, state of charge, complete ensemble empirical mode decomposition with adaptive noise, extreme learning machine, seagull optimization algorithm

中图分类号: