Journal of Jilin University(Engineering and Technology Edition) ›› 2026, Vol. 56 ›› Issue (2): 355-367.doi: 10.13229/j.cnki.jdxbgxb.20240871

Previous Articles    

Real-time estimation of Li-ion battery state of health based on segment charging data and DUKF

Xian-hua SONG(),Wen-lu SUN,Wei XIE   

  1. School of Science，Harbin University of Science and Technology，Harbin 150080，China
  • Received:2024-08-04 Online:2026-02-01 Published:2026-03-17

RICH HTML

 0   

PDF (PC)

11

Abstract:

Accurate and real-time evaluation of the battery's state of health is the core of the battery management system in electric vehicles. This paper proposes a novel model for estimating the full charging time of lithium batteries. Firstly， utilizing the high estimation accuracy of the Unscented Kalman Filter for nonlinear problems， a dual Unscented Kalman Filter prediction correction framework with further improved accuracy is designed， which can accurately estimate the current full charge time of lithium batteries. Under this framework， the measurement equation of the Unscented Kalman Filter is linearly weighted using Gaussian Process Regression and Support Vector Regression prediction results. The experimental results show that the framework proposes in this paper has high accuracy and real-time performance， with an average relative error of 0.001 6 for estimating 180 full charge times. Compared with the EKF and DEKF based algorithms， the average relative error has reduced by 98.87% and 98.15%， respectively.

Key words: state of health, segment data, dual unscented kalman filter, gaussian process regression, support vector regression

CLC Number: 

  • TM911

Fig.1

Flowchart of DUKF-GPR-SVR"

Fig.2

Constant current charging mode"

Fig.3

Constant current discharging mode"

Fig.4

Estimated whole charging time and true whole charging time"

Fig.5

Absolute error of estimated full charge time"

Fig.6

Relative error of estimated full charge time"

Fig.7

Absolute value of relative error of estimated full charge time"

Fig.8

Absolute error of six methods"

Fig.9

Absolute error of six methods"

Fig.10

Absolute error of six methods"

Table 1

Average relative error of six methods"

指标DUKF-GPRDUKF-SVR

UKF-

GPR

UKF-

SVR

UKF-GPR-SVRDUKF-GPR-SVR
Average0.001 90.003 10.002 70.003 30.002 60.001 4

Fig.11

Comparison results of the three estimation methods"

Table 2

Average relative error of three methods"

指标EKF-GPRDEKF-WNN-WLSTMDUKF-GPR-SVR
Average0.01760.01010.0014

Fig.12

Absolute error of three methods"

Fig.13

Relative error of the three methods"

Fig.14

Absolute value of relative error of the three methods"

Fig.15

Estimated SoH of the three methods"

Table 3

Average relative error of three methods"

指标EKF-GPRDEKF-WNN-WLSTMDUKF-GPR-SVR
Average0.14180.08640.0016

Table 4

Short term running time comparison"

指标EKF-GPRDEKF-WNN-WLSTMDUKF-GPR-SVR
时间/s10>>3 60028

Table 5

Long term running time comparison"

指标EKF-GPRDEKF-WNN-WLSTMDUKF-GPR-SVR
时间/s14>>3 60047

Fig.16

Estimated SoH of the three methods"

[1] Wen G, Yuan S, Dong Z, et al. Recycling of spent lithium iron phosphate battery cathode materials: a review[J]. Journal of Cleaner Production, 2024, 474: 143625.
[2] Hopkins B J, Bashian N H. Modernizing rechargeable military batteries[J]. Joule, 2024, 8(8): 2178-2182.
[3] Nyamathulla S, Dhanamjayulu C. A review of battery energy storage systems and advanced battery management system for different applications: challenges and recommendations[J]. Journal of Energy Storage, 2024, 86: 111179.
[4] Dai H, Zhao G, Lin M, et al. A novel estimation method for the state of health of lithium-ion battery using prior knowledge-based neural network and Markov chain[J]. IEEE Transactions on Industrial Electronics, 2018, 66(10): 7706-7716.
[5] Yang B, Qian Y, Li Q, et al. Critical summary and perspectives on state-of-health of lithium-ion battery[J]. Renewable and Sustainable Energy Reviews, 2024, 190: 114077.
[6] Love C T, Virji M B V, Rocheleau R E, et al. State-of-health monitoring of 18650 4S packs with a single-point impedance diagnostic[J]. Journal of Power Sources, 2014, 266: 512-519.
[7] Hu W, Peng Y, Wei Y, et al. Application of electrochemical impedance spectroscopy to degradation and aging research of lithium-ion batteries[J]. The Journal of Physical Chemistry C, 2023, 127(9): 4465-4495.
[8] Koseoglou M, Tsioumas E, Ferentinou D, et al. Lithium plating detection using dynamic electrochemical impedance spectroscopy in lithium-ion batteries[J]. Journal of Power Sources, 2021, 512: 230508.
[9] Çarkıt T, Alçı M. Investigation of VoC and SoH on Li-ion batteries with an electrical equivalent circuit model using optimization algorithms[J]. Electrical Engineering, 2022: 1-12.
[10] Gao Y, Liu K, Zhu C, et al. Co-estimation of state-of-charge and state-of-health for lithium-ion batteries using an enhanced electrochemical model[J]. IEEE Transactions on Industrial Electronics, 2021, 69(3): 2684-2696.
[11] Liu F, Shao C, Su W, et al. Online joint estimator of key states for battery based on a new equivalent circuit model[J]. Journal of Energy Storage, 2022, 52: 104780.
[12] 高仁璟, 吕治强, 赵帅, 等. 基于电化学模型的锂离子电池健康状态估算[J]. 北京理工大学学报: 自然科学版, 2022, 42(8): 791-797.
Gao Ren-jing, Lv Zhi-qiang, Zhao Shuai, et al. Health state estimation of lithium-ion batteries based on electrochemical models[J]. Journal of Beijing Institute of Technology (Natural Science Edition), 2022, 42 (8): 791-797.
[13] Yao L, Fang Z, Xiao Y, et al. An intelligent fault diagnosis method for lithium battery systems based on grid search support vector machine[J]. Energy, 2021, 214: No.118866.
[14] Zhou D, Fu P, Yin H, et al. A study of online state-of-health estimation method for in-use electric vehicles based on charge data[J]. IEICE Transactions on Information and Systems, 2019, 102(7): 1302-1309.
[15] Jia J, Liang J, Shi Y, et al. SOH and RUL prediction of lithium-ion batteries based on gaussian process regression with indirect health indicators[J]. Energies, 2020, 13(2): 375.
[16] 王萍, 弓清瑞, 张吉昂, 等. 一种基于数据驱动与经验模型组合的锂电池在线健康状态预测方法[J]. 电工技术学报, 2021, 36(24): 5201-5212.
Wang Ping, Gong Qing-rui, Zhang Ji-ang, et al. An online state of health prediction method for lithium batteries based on combination of data-driven and empirical model[J]. Transactions of China Electrotechnical Society, 2021, 36(24): 5201-5212.
[17] Qu J, Liu F, Ma Y, et al. A neural-network-based method for RUL prediction and SOH monitoring of lithium-ion battery[J]. IEEE Access, 2019, 7: 87178-87191.
[18] Guo Y, Yang D, Zhang Y, et al. Online estimation of SOH for lithium-ion battery based on SSA-Elman neural network[J]. Protection and Control of Modern Power Systems, 2022, 7(3): 1-17.
[19] Chen Z, Sun M, Shu X, et al. Online state of health estimation for lithium-ion batteries based on support vector machine[J]. Applied Sciences, 2018, 8(6): No.925.
[20] Wang J, Deng Z, Yu T, et al. State of health estimation based on modified Gaussian process regression for lithium-ion batteries[J]. Journal of Energy Storage, 2022, 51: 104512.
[21] 周頔, 宋显华, 卢文斌, 等. 基于日常片段充电数据的锂电池健康状态实时评估方法研究[J]. 中国电机工程学报, 2019, 39(1): 105-111.
Zhou Di, Song Xian-hua, Lu Wen-bin, et al. Real-time SOH estimation algorithm for lithium-ion batteries based on daily segment charging data[J]. Proceedings of the CSEE, 2019, 39(1): 105-111.
[22] 宋显华, 姚全正. 基于片段充电数据和 DEKF-WNN-WLSTM 的锂电池健康状态实时估计[J]. 电工技术学报, 2024, 39(5): 1565-1576.
Song Xian-hua, Yao Quan-zheng. Real time estimation of lithium battery state of health based on segment charging data and DEKF-WNN-WLSTM[J]. Transactions of China Electrotechnical Society, 2024, 39(5): 1565-1576.
[23] Yang D, Zhang X, Pan R, et al. A novel gaussian process regression model for state-of-health estimation of lithium-ion battery using charging curve[J]. Journal of Power Sources, 2018, 384: 387-395.
[24] 黄小平. 卡尔曼滤波原理及应用: MATLAB仿真[M]. 北京: 电子工业出版社, 2022.
[25] Cortes C, Vapnik V. Support-vector networks[J]. Machine Learning, 1995, 20: 273-297.
[1] Jing-hua ZHAO,Da LIU,Yu-qi ZHOU,Long WEN,Qian-yu LIU,Jie LIU,Fang-xi XIE. Air⁃fuel ratio control of engines based on Gaussian process regression intake prediction [J]. Journal of Jilin University(Engineering and Technology Edition), 2025, 55(6): 1854-1861.
[2] Yi-yan LIU,Jie DAI. Deformation detection algorithm for main materials of power tower based on carrier phase difference [J]. Journal of Jilin University(Engineering and Technology Edition), 2024, 54(12): 3693-3698.
[3] Jing QIN,De ZHENG,Yi-qiang PEI,Yong LYU,Qing-peng SU,Ying-bo WANG. Prediction method of engine performance and emission based on PSO-GPR [J]. Journal of Jilin University(Engineering and Technology Edition), 2022, 52(7): 1489-1498.
[4] Xing-tao LIU,Xiao-jian LIU,Ji WU,Yao HE,Xin-tian LIU. State of health estimation method for lithium⁃ion battery based on curve compression and extreme gradient boosting [J]. Journal of Jilin University(Engineering and Technology Edition), 2022, 52(6): 1273-1280.
[5] Chun-you ZHANG,Liang WANG,Hong LI,Tong-yan WU,Yan LI. Wind speed prediction based on machine learning and new energy pumping unit wind power control [J]. Journal of Jilin University(Engineering and Technology Edition), 2021, 51(6): 1997-2006.
[6] Bin ZHANG,Guo-zan CHENG,Hao-cen HONG,Chun-xiao ZHAO,Da-peng BAI,Hua-yong YANG. Structure optimization of triangular groove of valve plate in axial piston pump based on SVR [J]. Journal of Jilin University(Engineering and Technology Edition), 2021, 51(4): 1213-1221.
[7] ZONG Fang, WANG Zhan-zhong, JIA Hong-fei, JIAO Yu-ling, WU Yang. Prediction of commuter's daily activity-travel duration time with support vector regression [J]. 吉林大学学报(工学版), 2016, 46(2): 406-411.
[8] YANG Zhao-jun, YANG Chuan-gui, CHEN Fei, HAO Qing-bo, ZHENG Zhi-tong, WANG Song. Parameter estimation of reliability model of machining center based on particle swarm optimization and support vector regression [J]. 吉林大学学报(工学版), 2015, 45(3): 829-836.
[9] WU Jian, ZHAO Yang, HE Rui. Fault detection and diagnosis of EMB sensor system based on SVR [J]. 吉林大学学报(工学版), 2013, 43(05): 1178-1183.
[10] WANG Su-jing, ZHOU Chun-guang, ZHANG Na, LI Jian-peng, ZHANG Li-biao. Age estimation by extracting facial features of shape and texture [J]. 吉林大学学报(工学版), 2011, 41(05): 1383-1387.
[11] ZHANG Yong-Ming, CHEN Lie, QI Wei-Gui. Probabilistic prediction approach of heat load based on support vector interval regression [J]. 吉林大学学报(工学版), 2010, 40(06): 1693-1697.
[12] Yu Zhong-dang,, Wang Long-shan, Chen Xiang-wei. Mechanical part linear edge subpixel image detection based on support vector regression [J]. 吉林大学学报(工学版), 2006, 36(03): 371-0375.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
Copyright © Journal of Jilin University(Engineering and Technology Edition), All Rights Reserved.
Tel: +86-431-85095297　Fax: +86-431-85094074　E-mail: xbgxb@jlu.edu.cn
Powered by Beijing Magtech Co. Ltd