储能科学与技术

• XXXX •    

多约束动态融合与SSA-ELM误差补偿的锂离子电池功率状态高精度鲁棒估计

巫春玲1,4(), 马耀1, 常展豪1, 杨太平1, 孟锦豪2,3, 常亚婷3, 王莉4(), 何向明4   

  1. 1.长安大学能源与电气工程学院 陕西 西安 710064
    2.西安交通大学电气工程学院 陕西 西安 710049
    3.西安迅湃快速充电技术有限公司 陕西 西安 710076
    4.清华大学核能与新能源技术研究院 北京 100084
  • 收稿日期:2025-05-14 修回日期:2025-07-02
  • 通讯作者: 王莉 E-mail:wuchl@chd.edu.cn;wang-l@tsinghua.edu.cn
  • 作者简介:巫春玲（1978-），女，博士，副教授，主要研究方向为锂电池管理系统研究， E-mail： wuchl@chd.edu.cn；
  • 基金资助:
    国家重点研发计划项目(2021YFB2601304);陕西省重点研发计划(2022GY-193);陕西省教育厅服务地方专项科学研究计划项目(23JE021)

High precision estimation of SOP of lithium-ion batteries using multi constraint collaborative optimization and SSA-ELM dynamic compensation

Chunling WU1,4(), Yao MA1, Zhanhao CHANG1, Taiping YANG1, jinhao MENG2,3, Yating CHANG3, Li WANG4(), Xiangming HE4   

  1. 1.School of Energy and Electrical Engineering, Chang'an University, Xi 'an 710064
    2.School of Electrical Engineering, Xi'an Jiaotong University, Xi'an, 710049, China
    3.Xi'an Stropower Technologies Co. , Ltd, Xi'an, 710076, China
    4.Institute of Nuclear and New Energy Technology, Tsinghua University, Beijing, 100084, China
  • Received:2025-05-14 Revised:2025-07-02
  • Contact: Li WANG E-mail:wuchl@chd.edu.cn;wang-l@tsinghua.edu.cn

摘要：

动力电池峰值功率状态（State of Power, SOP）的准确估计是保障新能源汽车安全运行及提升续航能力的关键。针对现有SOP估计方法精度不足的问题，本研究提出一种融合多约束条件（Multi-Constraint Conditions, MCC）与麻雀搜索算法（Sparrow Search Algorithm, SSA）优化的极限学习机（Extreme Learning Machine, ELM）误差预测校正方法，构建了MCC-SSA-ELM联合估计模型。以单体锰酸锂电池为研究对象，首先建立二阶RC等效电路模型，采用基于遗忘因子的递推最小二乘法实现模型参数的在线辨识，并利用自适应扩展卡尔曼滤波（Adaptive Extended Kalman Filter, AEKF）算法对电池荷电状态（State of Charge, SOC）进行动态估计。进一步，根据放电持续时间划分30s、2min和5min三级工况，综合考虑SOC、电压及最大允许放电电流等多重约束条件，构建不同持续时间下的SOP初步估计模型。在此基础上，通过多约束条件下SOP估计值与实测值的绝对误差数据集，分别训练ELM和SSA-ELM误差预测模型，实现对初步估计值的动态补偿与校正。实验结果表明，经误差校正后，SOP估计精度显著提升，与MCC和MCC-ELM模型相比，所提出的MCC-SSA-ELM模型在30s、2min和5min持续工况下的平均相对误差分别降低0.382%、6.215%和6.858%，最终误差均控制在0.15%以内，验证了该方法的优越性与工程实用性。

关键词: 电池峰值功率状态, 麻雀优化算法, 极限学习机, 多约束条件

Abstract:

Accurate estimation of the peak power state (State of Power, SOP) for power batteries is crucial to ensuring the safe operation and enhancing the driving range of new energy vehicles. To address the insufficient accuracy of existing SOP estimation methods, this study proposes a joint estimation model, MCC-SSA-ELM, which integrates multi-constraint conditions (MCC) with a Sparrow Search Algorithm (SSA)-optimized Extreme Learning Machine (ELM) for error prediction and correction. Using a single lithium manganese oxide (LMO) battery as the research subject, a second-order RC equivalent circuit model is first established. Online parameter identification is achieved through a forgetting factor-based recursive least squares method, and the battery's State of Charge (SOC) is dynamically estimated using an adaptive extended Kalman filter (AEKF) algorithm. Furthermore, three-level operational conditions (30 seconds, 2 minutes, and 5 minutes) are defined based on discharge durations to simulate real-world scenarios. A preliminary SOP estimation model under varying durations is developed by comprehensively considering constraints including SOC, voltage and the maximum allowable discharge current. Subsequently, absolute error datasets between SOP estimated values and measured values under multi-constraint conditions are utilized to train both ELM and SSA-ELM error prediction models, enabling dynamic compensation and correction of preliminary estimates. Experimental results demonstrate that the proposed MCC-SSA-ELM model significantly improves SOP estimation accuracy. Compared to the MCC and MCC-ELM models, the average relative errors of the MCC-SSA-ELM model under 30-second, 2-minute, and 5-minute durations are reduced by 0.382%, 6.215%, and 6.858%, respectively, with final errors consistently controlled within 0.15%. These findings validate the superiority and engineering practicality of the proposed method.

Key words: SOP, Sparrow Search Algorithm, Extreme Learning Machine, Multi-constraint conditions

中图分类号: