Accurate battery parameter estimation with improved continuous time system identification methods
Résumé
The modeling of Lithium-ion batteries usually utilizes discrete-time systemidentification methods to estimate parameters of discrete models. However,in real applications, there is a fundamental limitation of the discrete-timemethods in dealing with sensitivity when the system is stiff and the storageresolutions are limited. To overcome this problem, this paper adopts directcontinuous-time system identification methods to estimate the parameters ofequivalent circuit models for Lithium-ion batteries. Compared with discrete-time system identification methods, the continuous-time systemidentification methods provide more accurate estimates to both fast and slowdynamics in battery systems and are less sensitive to disturbances. A caseof a second order equivalent circuit model is studied which shows that thecontinuous-time estimates are more robust to high sampling rates,measurement noises and rounding errors. In addition, the estimation by theconventional continuous-time least squares method is further improved in thecase of noisy output measurement by introducing the instrumental variablemethod. Simulation and experiment results validate the analysis anddemonstrate the advantages of the continuous-time system identificationmethods in battery applications.
Domaines
Automatique / Robotique
Loading...