Lithium Battery State-of-Health Estimation Based on Sample Data Generation and Temporal Convolutional Neural Network

被引:5
作者
Guo, Fang [1 ]
Huang, Guangshan [1 ]
Zhang, Wencan [1 ]
Wen, An [2 ]
Li, Taotao [1 ]
He, Hancheng [1 ]
Huang, Haolin [1 ]
Zhu, Shanshan [1 ]
机构
[1] Foshan Univ, Sch Mechatron Engn & Automat, Foshan 528200, Peoples R China
[2] Univ Elect Sci & Technol China, Yangtze Delta Reg Inst, Huzhou 313098, Peoples R China
关键词
battery; state of health; limited data; sample generation; Variational Auto-Encoder; temporal convolutional neural network; ION; MODEL;
D O I
10.3390/en16248010
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
Accurate estimation of battery health is an effective means of improving the safety and reliability of electrical equipment. However, developing data-driven models to estimate battery state of health (SOH) is challenging when the amount of data is restricted. In this regard, this study proposes a method for estimating the SOH of lithium batteries based on sample data generation and a temporal convolutional neural network. First, we analyzed the charge/discharge curves of the batteries, from which we extracted features that were highly correlated with the SOH decay. Then, we used a Variational Auto-Encoder (VAE) to learn the features and distributions of the sample data to generate highly similar data and enrich the number of samples. Finally, a temporal convolutional neural network (TCN) was built to mine the nonlinear relationship between features and SOH by combining the source and extended domain data to realize SOH estimation. The experimental results show that the proposed method in this study has less than 2% error in SOH estimation, which improves the accuracy by 64.9% based on its baseline model. The feasibility of using data-driven models for battery health management in data-constrained application scenarios is demonstrated.
引用
收藏
页数:15
相关论文
共 39 条
[1]   Application domain extension of incremental capacity-based battery SoH indicators [J].
Agudelo, Brian Ospina ;
Zamboni, Walter ;
Monmasson, Eric .
ENERGY, 2021, 234
[2]  
Bai SJ, 2018, Arxiv, DOI [arXiv:1803.01271, 10.48550/arXiv.1803.01271]
[3]   Hybrid deep neural network with dimension attention for state-of-health estimation of Lithium-ion Batteries [J].
Bao, Xinyuan ;
Chen, Liping ;
Lopes, Antonio M. ;
Li, Xin ;
Xie, Siqiang ;
Li, Penghua ;
Chen, YangQuan .
ENERGY, 2023, 278
[4]   Lithium-ion battery state of health estimation using the incremental capacity and wavelet neural networks with genetic algorithm [J].
Chang, Chun ;
Wang, Qiyue ;
Jiang, Jiuchun ;
Wu, Tiezhou .
JOURNAL OF ENERGY STORAGE, 2021, 38
[5]   Battery state-of-health estimation based on a metabolic extreme learning machine combining degradation state model and error compensation [J].
Chen, Lin ;
Wang, Huimin ;
Liu, Bohao ;
Wang, Yijue ;
Ding, Yunhui ;
Pan, Haihong .
ENERGY, 2021, 215
[6]   Battery Life Prediction Based on a Hybrid Support Vector Regression Model [J].
Chen, Yuan ;
Duan, Wenxian ;
Ding, Zhenhuan ;
Li, Yingli .
FRONTIERS IN ENERGY RESEARCH, 2022, 10
[7]   Online state of charge estimation of Li-ion battery based on an improved unscented Kalman filter approach [J].
Chen, Zewang ;
Yang, Liwen ;
Zhao, Xiaobing ;
Wang, Youren ;
He, Zhijia .
APPLIED MATHEMATICAL MODELLING, 2019, 70 :532-544
[8]   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
[9]   Battery health estimation with degradation pattern recognition and transfer learning [J].
Deng, Zhongwei ;
Lin, Xianke ;
Cai, Jianwei ;
Hu, Xiaosong .
JOURNAL OF POWER SOURCES, 2022, 525
[10]   State of health estimation of large-cycle lithium-ion batteries based on error compensation of autoregressive model [J].
Feng, Hailin ;
Yan, Huimin .
JOURNAL OF ENERGY STORAGE, 2022, 52