Open AccessState estimation of lithium-ion battery based on Gaussian process regression
Author(s) -
Jiabo Li,
Shengjie Jiao,
Yong Min,
Meng Wei
Publication year - 2020
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1633/1/012090
Subject(s) - kriging , state of charge , battery (electricity) , computer science , process (computing) , lithium ion battery , voltage , gaussian , state (computer science) , current (fluid) , gaussian process , estimation , control theory (sociology) , algorithm , engineering , artificial intelligence , machine learning , electrical engineering , power (physics) , control (management) , chemistry , physics , computational chemistry , quantum mechanics , operating system , systems engineering
The state of charge (SOC) of lithium-ion battery is one of the important parameters of battery management system (BMS). Accurate estimation of SOC can improve the safety of battery. Therefore, in order to improve the accuracy of SOC estimation, a new method based on Gaussian process regression (GPR) is proposed. The SOC estimated value at the previous time is used as the feedback vector, together with the current and voltage measured at the current time are used as the input vectors of the model to estimate the SOC at the current time. The experimental results show that the error of the proposed method is controlled within 2%, which verifies the effectiveness of the proposed method.