State of health estimation of lithium-ion batteries based on feature optimization and data-driven models

被引:2
作者
Mu, Guixiang [1 ]
Wei, Qingguo [1 ]
Xu, Yonghong [2 ]
Li, Jian [3 ]
Zhang, Hongguang [4 ]
Yang, Fubin [4 ]
Zhang, Jian [5 ]
Li, Qi [1 ]
机构
[1] North Univ China, Sch Energy & Power Engn, Taiyuan 030051, Peoples R China
[2] Beijing Informat Sci & Technol Univ, Mech Elect Engn Sch, Beijing 100192, Peoples R China
[3] Beijing Inst Technol, Sch Mech Engn, Beijing 100081, Peoples R China
[4] Beijing Univ Technol, Key Lab Enhanced Heat Transfer & Energy Conservat, Beijing Key Lab Heat Transfer & Energy Convers, MOE,Fac Environm & Life, Beijing 100124, Peoples R China
[5] Univ Wisconsin Green Bay, Richard J Resch Sch Engn, Mech Engn, Green Bay, WI 54311 USA
基金
北京市自然科学基金;
关键词
Lithium-ion battery; State of health estimation; Feature optimization; Data-driven models; Principal component analysis; Gaussian process regression;
D O I
10.1016/j.energy.2025.134578
中图分类号
O414.1 [热力学];
学科分类号
摘要
With the widespread application of lithium-ion batteries in electric vehicles, accurately estimating their state of health (SOH) has become a key focus of research. This paper explores various feature optimization methods and data-driven models with different structures, and constructs various SOH estimation models suitable for lithiumion batteries. Based on battery testing data, multiple features are extracted from voltage and temperature to characterize the battery aging process. To reduce information redundancy among features, filtering methods, Principal Component Analysis (PCA), and Multi-dimensional Scaling (MDS) are applied for optimization, aiming to maximize feature information utilization. This paper compares four common and structurally different datadriven models: linear regression (LR), Gaussian process regression (GPR), support vector regression (SVR), and long short-term memory (LSTM) networks. The effectiveness of each model is validated using multi-feature inputs, and a multi-dimensional assessment of feature selection and data-driven model performance in SOH estimation is conducted, the average absolute error of all models under 60 % training set conditions is 0.8 %. The average absolute error of estimating the four batteries using the fused PCA features as input and the GPR model is less than 1.2 %. At the same time, using the optimized features as input reduces the average training time by 46.63 % compared to using multiple features as input. In summary, the combination of PCA features and GPR models has good performance in both estimation accuracy and computational efficiency for different batteries.
引用
收藏
页数:12
相关论文
共 50 条
[21]   State of Health Estimation of Lithium-ion Battery Based on Feature Optimization and Random Forest Algorithm [J].
Wu, Ji ;
Fang, Leichao ;
Liu, Xingtao ;
Chen, Jiajia ;
Liu, Xiaojian ;
Lü, Bang .
Jixie Gongcheng Xuebao/Journal of Mechanical Engineering, 2024, 60 (12) :335-343
[22]   State-of-health estimation and knee point identification of lithium-ion battery based on data-driven and mechanism model [J].
Ni, Yulong ;
Song, Kai ;
Pei, Lei ;
Li, Xiaoyu ;
Wang, Tiansi ;
Zhang, He ;
Zhu, Chunbo ;
Xu, Jianing .
APPLIED ENERGY, 2025, 385
[23]   Feature parameter extraction and intelligent estimation of the State-of-Health of lithium-ion batteries [J].
Deng, Yuanwang ;
Ying, Hejie ;
Jiaqiang, E. ;
Zhu, Hao ;
Wei, Kexiang ;
Chen, Jingwei ;
Zhang, Feng ;
Liao, Gaoliang .
ENERGY, 2019, 176 :91-102
[24]   A Comprehensive Review on Data-Driven Methods of Lithium-Ion Batteries State-of-Health Forecasting [J].
Pham, Thien ;
Bui, Hung ;
Nguyen, Mao ;
Pham, Quang ;
Vu, Vinh ;
Le, Triet ;
Quan, Tho .
WILEY INTERDISCIPLINARY REVIEWS-DATA MINING AND KNOWLEDGE DISCOVERY, 2025, 15 (02)
[25]   Data-Driven Prediction Methods for Lithium-Ion Battery State of Health Based on Elbow Rule [J].
Zhang, Liu ;
Xing, Bo ;
Gao, Yanbing ;
Yao, Lei ;
Zhao, Dengfeng ;
Ding, Jinquan ;
Li, Yanyan .
IEEE ACCESS, 2024, 12 :183581-183595
[26]   Developing an online data-driven approach for prognostics and health management of lithium-ion batteries [J].
Khaleghi, Sahar ;
Hosen, Md Sazzad ;
Karimi, Danial ;
Behi, Hamidreza ;
Beheshti, S. Hamidreza ;
Van Mierlo, Joeri ;
Berecibar, Maitane .
APPLIED ENERGY, 2022, 308
[27]   State of Health Estimation for Lithium-Ion Batteries [J].
Kong, XiangRong ;
Bonakdarpour, Arman ;
Wetton, Brian T. ;
Wilkinson, David P. ;
Gopaluni, Bhushan .
IFAC PAPERSONLINE, 2018, 51 (18) :667-671
[28]   Comparative Study-Based Data-Driven Models for Lithium-Ion Battery State-of-Charge Estimation [J].
Hussein, Hossam M. ;
Esoofally, Mustafa ;
Donekal, Abhishek ;
Rafin, S. M. Sajjad Hossain ;
Mohammed, Osama .
BATTERIES-BASEL, 2024, 10 (03)
[29]   A hybrid statistical data-driven method for on-line joint state estimation of lithium-ion batteries [J].
Song, Yuchen ;
Liu, Datong ;
Liao, Haitao ;
Peng, Yu .
APPLIED ENERGY, 2020, 261 (261)
[30]   A review of feature extraction toward health state estimation of lithium-ion batteries [J].
Li, Qingwei ;
Xue, Wenli .
JOURNAL OF ENERGY STORAGE, 2025, 112