An ANN Model for Estimating Internal Impedance of Lithium-Ion Battery Cell for Industrial Application

A parameter-estimating method for a battery equivalent circuit using an Artificial Neural Network (ANN) is proposed in this paper. Although degradation of Lithium-Ion (Li-Ion) battery cell is inevitable, accurate estimation of the actual state is needed to extend its life of usage. The battery condition can be detected by the internal impedance of the cell. The parameters of the equivalent circuit of the internal impedance have been known as an index of the condition. It is, however, difficult to calculate the parameters by conventional methods, because the parameters are nonlinearly involved in the mathematical notation of the impedance. The proposed ANN model enables to estimate the parameter from the measured battery impedance. It can help the further investigations in the development of diagnostic system for Li-Ion battery.