A Nonlinear TSNN Based Model of a Lead Acid Battery

El Mehdi Laadissi, Anas El Filali, Malika Zazi


The paper studies a nonlinear model based on time series neural network system (TSNN) to improve the highly nonlinear dynamic model of an automotive lead acid cell battery. Artificial neural network (ANN) take into consideration the dynamic behavior of both input-output variables of the battery charge-discharge processes. The ANN works as a benchmark, its inputs include delays and charging/discharging current values. To train our neural network, we performed a pulse discharge on a lead acid battery to collect experimental data. Results are presented and compared with a nonlinear Hammerstein-Wiener model. The ANN and nonlinear autoregressive exogenous model (NARX) models achieved satisfying results.


ANN, Hammerstein-wiener, Lead acid battery, NARX, TSNN

Full Text:


DOI: https://doi.org/10.11591/eei.v7i2.675


  • There are currently no refbacks.

Bulletin of EEI Stats