基于改进HHO-SVR算法的锂电池健康状态评估

吴健; 金辉; 葛红娟; 宫綦; 常琦; 赵佳怡

doi:doi:10.19912/j.0254-0096.tynxb.2024-0638

English Version Reader LoginJournal Login

您当前的位置：

首页 >

文章列表页 >

基于改进HHO-SVR算法的锂电池健康状态评估

更新时间：2026-01-08

- 基于改进HHO-SVR算法的锂电池健康状态评估
- Vol. 46, Issue 12, Pages: 91-100(2025)
- 作者机构：
- 作者简介：
- 基金信息：
- DOI：doi:10.19912/j.0254-0096.tynxb.2024-0638
  CLC： TM912
- Published Online：07 January 2026，
  
  Published：2025
- 稿件说明：
移动端阅览
吴健, 金辉, 葛红娟, et al. 基于改进HHO-SVR算法的锂电池健康状态评估[J]. 2025, 46(12): 91-100.
DOI：

吴健, 金辉, 葛红娟, et al. 基于改进HHO-SVR算法的锂电池健康状态评估[J]. 2025, 46(12): 91-100. DOI： doi:10.19912/j.0254-0096.tynxb.2024-0638.

摘要

在分析锂电池健康特征的基础上

提出一种基于改进哈里斯鹰优化算法（IHHO）和支持向量机回归（SVR）的锂电池健康状态评估方法;IHHO引入池化机制和迁移搜索策略以及螺旋位置更新策略

解决现有哈里斯鹰优化算法（HHO）的早熟收敛问题。基于CEC2017测试套件比较研究IHHO、HHO等算法的寻优能力

结果表明IHHO算法的收敛速度和寻优精度更好

在部分测试函数上寻优精度提升3个数量级以上

能有效避免早熟收敛。进一步

面向NASA锂电池数据集

采用IHHO算法对SVR的惩罚系数C、不敏感损失因子ε和核参数γ进行寻优

开展基于IHHO-SVR的锂电池健康状态评估实验

结果表明IHHO-SVR能有效提高锂电池健康状态的预测精度

相较于HHO-SVR

均方根误差降低40%以上;此外

将该文所构建的IHHO-SVR模型与其他文献进行对比

结果表明IHHO-SVR模型性能优越

在部分预测结果上

IHHO-SVR的预测均方根误差降低15%以上。

Abstract

This study extracts health characteristics of lithium batteries from charge and discharge data with incremental capacity analysis to predict the capacity of lithium-ion batteries. Meanwhile

a method for estimating the state of health of lithium-ion batteries is proposed based on the improved Harris hawk optimization algorithm （IHHO） and support vector regression （SVR）. To address the problem that the Harris hawk optimization algorithm （HHO） tends to stagnate at local optima

the IHHO algorithm introduces a pooling mechanism and a migrating search strategy based on the HHO algorithm

while modifying the position update equation to prevent premature convergence. Based on comparisons using the CEC2017 test suite

the optimization capabilities of IHHO and HHO algorithms are evaluated. This shows that the IHHO algorithm has a higher convergence speed and optimization accuracy. For some test functions

the optimization accuracy of the IHHO algorithm is improved by more than three orders of magnitude

effectively avoiding premature convergence. In addition

the comparative experiments are conducted on the NASA lithium-ion battery dataset to optimize the standard SVR with IHHO and HHO algorithms. The results show that IHHO-SVR significantly improves the prediction accuracy of the state of health

reducing the root mean square error by more than 40% compared to the HHO-SVR. In addition

comparisons with other literature models indicate the superior performance of the IHHO-SVR model. For certain prediction results

the root mean square error of IHHO-SVR is reduced by at least 15%.

关键词

Keywords

references

杨斌, 樊立萍, 高迎慧, 等. 超高功率密度锂离子电池放电性能及容量预估研究[J]. 太阳能学报, 2023, 44(11): 419-425.

王超君, 陈翔, 彭思侃, 等. 锂离子电池发展现状及其在航空领域的应用分析[J]. 航空材料学报, 2021, 41(3): 83-95.

CHEN J G, HAN X B, SUN T, et al.Analysis and prediction of battery aging modes based on transfer learning[J]. Applied energy, 2024, 356: 122330.

杨智鹏, 宋政湘, 孟锦豪, 等. 基于单体到模组迁移的磷酸铁锂储能系统SOH评估方法[J]. 高电压技术, 2023, 49(10): 4142-4149.

金辉, 胡寅逍, 葛红娟, 等. 基于分段惩罚参数SVM算法的锂电池失效识别[J]. 西南交通大学学报, 2025, 60(3): 770-780.

谢松, 巩译泽, 李明浩. 锂离子电池在民用航空领域中应用的进展[J]. 电池, 2020, 50(4): 388-392.

吴青峰, 杨凯义, 于少娟, 等. 基于无通讯的微电网储能系统主动SOH协同控制方案[J]. 太阳能学报, 2023, 44(5): 40-47.

CHE Y H, HU X S, LIN X K, et al.Health prognostics for lithium-ion batteries: mechanisms, methods, and prospects[J]. Energy & environmental science, 2023, 16(2): 338-371.

KHODADADI SADABADI K, JIN X, RIZZONI G.Prediction of remaining useful life for a composite electrode lithium ion battery cell using an electrochemical model to estimate the state of health[J]. Journal of power sources, 2021, 481: 228861.

李炳金, 韩晓霞, 张文杰, 等. 锂离子电池剩余使用寿命预测方法综述[J]. 储能科学与技术, 2024, 13(4): 1266-1276.

ELMAHALLAWY M, ELFOULY T, ALOUANI A, et al.A comprehensive review of lithium-ion batteries modeling, and state of health and remaining useful lifetime prediction[J]. IEEE access, 2022, 10: 119040-119070.

何冰琛, 杨薛明, 王劲松, 等. 基于PCA-GPR的锂离子电池剩余使用寿命预测[J]. 太阳能学报, 2022, 43(5): 484-491.

魏孟, 王桥, 叶敏, 等. 基于NARX动态神经网络的锂离子电池剩余寿命间接预测[J]. 工程科学学报, 2022, 44(3): 380-388.

OUYANG M S, SHEN P C.Prediction of remaining useful life of lithium batteries based on WOA-VMD and LSTM[J]. Energies, 2022, 15(23): 8918.

张振全, 李醒飞, 杨少波. 基于AR-SVR模型的有效波高短期预测[J]. 太阳能学报, 2021, 42(7): 15-20.

HUANG W C, LIU H Y, ZHANG Y, et al.Railway dangerous goods transportation system risk identification: comparisons among SVM, PSO-SVM, GA-SVM and GS-SVM[J]. Applied soft computing, 2021, 109: 107541.

HEIDARI A A, MIRJALILI S, FARIS H, et al.Harris Hawks optimization: algorithm and applications[J]. Future generation computer systems, 2019, 97: 849-872.

陈永辉, 苏建徽, 解宝, 等. 基于HHO-FA的PEMFC电堆辨识建模[J]. 太阳能学报, 2024, 45(3): 282-289.

NGUYEN H, BUI X N, TOPAL E.Enhancing predictions of blast-induced ground vibration in open-pit mines: comparing swarm-based optimization algorithms to optimize self-organizing neural networks[J]. International journal of coal geology, 2023, 275: 104294.

KUMAR T S, JOTHILAKSHMI S, JAMES B C, et al.HHO-based vector quantization technique for biomedical image compression in cloud computing[J]. International journal of image and graphics, 2023, 23(3): 2240008.

闫晓斌, 方洋旺, 彭维仕. 基于自适应高斯变异的多目标哈里斯鹰优化算法[J]. 北京航空航天大学学报, 2024, 50(8): 2636-2645.

胡振辉, 袁鹏, 司先才, 等. 数据驱动的潮流能水轮机叶片翼型性能保真替代计算模型对比研究[J]. 太阳能学报, 2022, 43(12): 495-502.

YAN X A, HUA X, JIANG D, et al.A novel robust intelligent fault diagnosis method for rolling bearings based on SPAVMD and WOA-LSSVM under noisy conditions[J]. Measurement science and technology, 2024, 35(5): 056121.

HU R X, BAO L Y, DING H W, et al.Analysis of the influence of population distribution characteristics on swarm intelligence optimization algorithms[J]. Information sciences, 2023, 645: 119340.

WANG M, WANG J S, LI X D, et al.Harris hawk optimization algorithm based on Cauchy distribution inverse cumulative function and tangent flight operator[J]. Applied intelligence, 2022, 52(10): 10999-11026.

NADIMI-SHAHRAKI M H, ZAMANI H, MIRJALILI S. Enhanced whale optimization algorithm for medical feature selection: a COVID-19 case study[J]. Computers in biology and medicine, 2022, 148: 105858.

ZHOU K, WANG W Y, HU T, et al.Time series forecasting and classification models based on recurrent with attention mechanism and generative adversarial networks[J]. Sensors, 2020, 20(24): 7211.

吴伟丽, 卢双双. 基于PCA-CEEMDAN和改进SVR的锂电池RUL预测[J]. 电源学报, 2025, 23(6): 267-280.

李英顺, 阚宏达, 郭占男, 等. 基于数据预处理和VMD-LSTM-GPR的锂离子电池剩余寿命预测[J]. 电工技术学报, 2024, 39(10): 3244-3258.

金辉, 胡寅逍, 葛红娟, 等. 基于改进GWO-SVR算法的锂电池剩余寿命预测[J]. 工程科学学报, 2024, 46(3): 514-524.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

基于SUKF-EKF融合的锂电池状态估计方法

基于改进堆优化算法和TimesNet神经网络的锂电池剩余寿命预测方法

考虑多时间尺度特性的锂离子电池建模与参数辨识

Related Author

何玉财

盛强

王期文

张楚

王熠炜

张越

陈佳雷

彭甜

Related Institution

Datang North China Electric Power Test and Research Institute

Hebei Key Laboratory of Low Carbon and High Efficiency Power Generation Technology, Department of Power Engineering, North China Electric Power University

Institute of Applied Mathematics, Hebei Academy of Sciences

College of Electronic Information Engineering, Taiyuan University of Science and Technology

Rundian Energy Science Technology Co., Ltd.

AI问答

⁰