A Practical SoH Estimation using Adaptive ANN algorithm for the embedded EIS diagnosis in Industrial Applications

A practical estimation method of equivalent circuit parameters for rechargeable batteries that follows adaptive Artificial Neural Network (ANN) logic is proposed in this paper. The parameters must be obtained from the complex internal impedances, which are measured in a wide frequency range. The improved method uses the proposed optimal frequency region (OFR), for the three different Li-Ion chemistry batteries. The accuracy of the proposed method is confirmed by a comparison with the measured results obtained using a conventional frequency domain method. For obtaining the real-time diagnostics of the battery, an improved ANN system, which employs unequal sampling, is proposed to obtain the circuit parameters using a dual computational system for off-line training and online estimation. The deterioration of a battery can be detected from the estimated parameters, which can help in further investigations that aim to develop diagnostic models for the embedded circuit in industrial applications.