Open AccessA data-driven approach for capacity estimation of batteries based on voltage dependent health indicators
Author(s) -
Jinyu Kong,
Jie Liu,
Yikai Chen,
Dong Wang
Publication year - 2021
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 - 10.1088/1742-6596/1983/1/012115
Subject(s) - estimation , battery capacity , voltage , computer science , regression analysis , work (physics) , kriging , process (computing) , statistics , econometrics , battery (electricity) , mathematics , engineering , power (physics) , electrical engineering , mechanical engineering , physics , systems engineering , quantum mechanics , operating system
Battery capacity estimation plays an important role in the normal operation of electric vehicles. In this work, we presented a data-driven approach for capacity estimation of batteries based on voltage dependent health indicators. A difference-based model of discharge voltage and capacity was built. Next, two health indicators are constructed from partial voltage curves, and correlations between capacity and health indicators are investigated. Afterward, the capacity estimation approach based on Gaussian process regression model is expounded. To validate the accuracy of the proposed method, a case study is carried out. Results demonstrate that RMSE and RMSPE of capacity estimation are lower than 1% compared with actual capacity.