Early prediction of battery remaining useful life using CNN-XGBoost model and Coati optimization algorithm

被引:12
作者
Safavi, Vahid [1 ]
Vaniar, Arash Mohammadi [2 ]
Bazmohammadi, Najmeh [1 ]
Vasquez, Juan C. [1 ]
Keysan, Ozan [2 ]
Guerrero, Josep M. [1 ,3 ,4 ]
机构
[1] Aalborg Univ, Ctr Res Microgrids CROM, AAU Energy, DK-9220 Aalborg, Denmark
[2] Middle East Tech Univ, Dept Elect & Elect Engn, TR-06800 Ankara, Turkiye
[3] Tech Univ Catalonia, Ctr Res Microgrids CROM, Dept Elect Engn, Barcelona 08034, Spain
[4] ICREA, Pg Lluis Co 23, Barcelona 08010, Spain
关键词
Lithium-ion batteries; Early remaining useful life prediction; Machine learning; XGBoost; CNN; Coati Optimization; CAPACITY FADE; ION;
D O I
10.1016/j.est.2024.113176
中图分类号
TE [石油、天然气工业]; TK [能源与动力工程];
学科分类号
0807 ; 0820 ;
摘要
Lithium-ion (Li-ion) batteries are essential for modern power systems but suffer from performance degradation over time. Accurate prediction of the remaining useful life (RUL) of these batteries is critical for ensuring the reliability and efficient operation of the power grid. On this basis, this paper presents a novel Coati-integrated Convolutional Neural Network (CNN)-XGBoost approach for the early RUL prediction of Li-ion batteries. This method incorporates CNN architecture to automatically extract features from the discharge capacity data of the battery via image processing techniques. The extracted features from the CNN model are concatenated with another set of features extracted from the first 100 cycles of measured battery data based on the charging policy information of the battery. This combined set of features is then fed into an XGBoost model to make the early RUL prediction. Additionally, the Coati Optimization Method (COM) is utilized for CNN hyperparameter tuning, to improve the performance of the proposed RUL prediction method. Numerical results reveal the effectiveness of the proposed approach in predicting the RUL of Li-ion batteries, where values of 106 cycles and 7.5% have been obtained for the RMSE and MAPE, respectively.
引用
收藏
页数:12
相关论文
共 50 条
[21]   Remaining useful life prediction of Lithium-ion batteries based on data preprocessing and CNN-LSSVR algorithm [J].
Dong, Ti ;
Sun, Yiming ;
Liu, Jia ;
Gao, Qiang ;
Zhao, Chunrong ;
Cao, Wenjiong .
INTERNATIONAL JOURNAL OF ELECTRICAL POWER & ENERGY SYSTEMS, 2025, 167
[22]   Indoor Occupancy Detection Based on Environmental Data Using CNN-XGboost Model: Experimental Validation in a Residential Building [J].
Mohammadabadi, Abolfazl ;
Rahnama, Samira ;
Afshari, Alireza .
SUSTAINABILITY, 2022, 14 (21)
[23]   Battery Remaining Useful Life Prediction Supported by Long Short-Term Memory Neural Network [J].
Marri, Iacopo ;
Petkovski, Emil ;
Cristaldi, Loredana ;
Faifer, Marco .
2023 IEEE INTERNATIONAL INSTRUMENTATION AND MEASUREMENT TECHNOLOGY CONFERENCE, I2MTC, 2023,
[24]   A Lithium-Ion Battery Remaining Useful Life Prediction Method with A New Algorithm Based on Incremental Capacity Analysis [J].
Cervellieri, Alice .
JOURNAL OF ELECTRICAL SYSTEMS, 2024, 20 (04) :2090-2099
[25]   Gravitational Search Algorithm Based LSTM Deep Neural Network for Battery Capacity and Remaining Useful Life Prediction With Uncertainty [J].
Reza, M. S. ;
Hannan, M. A. ;
Mansor, Muhammad Bin ;
Ker, Pin Jern ;
Tiong, Sieh Kiong ;
Hossain, M. J. .
IEEE TRANSACTIONS ON INDUSTRY APPLICATIONS, 2024, 60 (06) :9171-9183
[26]   Prediction of State-of-Health and Remaining-Useful-Life of Battery Based on Hybrid Neural Network Model [J].
Thi Minh Lien, Le ;
Quoc Anh, Vu ;
Duc Tuyen, Nguyen ;
Fujita, Goro .
IEEE ACCESS, 2024, 12 :129022-129039
[27]   A power model considering initial battery state for remaining useful life prediction of lithium-ion batteries [J].
Meng, Fanbing ;
Yang, Fangfang ;
Yang, Jun ;
Xie, Min .
RELIABILITY ENGINEERING & SYSTEM SAFETY, 2023, 237
[28]   Remaining Useful Life Prediction of LiFePO4 Battery Based on Particle Filter [J].
Geng, Fei ;
Kang, Yong-zhe ;
Li, Ze-yuan ;
Zhang, Cheng-hui ;
Duan, Bin .
2017 CHINESE AUTOMATION CONGRESS (CAC), 2017, :1149-1153
[29]   A Physics-Constrained Bayesian neural network for battery remaining useful life prediction [J].
Najera-Flores, David A. ;
Hu, Zhen ;
Chadha, Mayank ;
Todd, Michael D. .
APPLIED MATHEMATICAL MODELLING, 2023, 122 :42-59
[30]   Hybrid firefly algorithm-neural network for battery remaining useful life estimation [J].
Mustaffa, Zuriani ;
Sulaiman, Mohd Herwan .
CLEAN ENERGY, 2024, 8 (05) :157-166