Accurate battery parameter estimation with improved continuous time system identification methods
Résumé
The modeling of Lithium-ion batteries usually utilizes discrete-time system
identification methods to estimate parameters of discrete models. However,
in real applications, there is a fundamental limitation of the discrete-time
methods in dealing with sensitivity when the system is stiff and the storage
resolutions are limited. To overcome this problem, this paper adopts direct
continuous-time system identification methods to estimate the parameters of
equivalent circuit models for Lithium-ion batteries. Compared with discrete-
time system identification methods, the continuous-time system
identification methods provide more accurate estimates to both fast and slow
dynamics in battery systems and are less sensitive to disturbances. A case
of a second order equivalent circuit model is studied which shows that the
continuous-time estimates are more robust to high sampling rates,
measurement noises and rounding errors. In addition, the estimation by the
conventional continuous-time least squares method is further improved in the
case of noisy output measurement by introducing the instrumental variable
method. Simulation and experiment results validate the analysis and
demonstrate the advantages of the continuous-time system identification
methods in battery applications.