Comparison of ANN and SVR for State of Charge Regression Evaluating EIS Spectra

Abstract

The demand for energy storage is increasing massively due to the electrification of transport and the expansion of renewable energies. Current battery technologies cannot satisfy this growing demand because they are difficult to recycle, because the necessary raw materials are mined under precarious conditions, and because the energy density is insufficient. Metal-air batteries offer a high energy density because there is only one active mass inside the cell and the cathodic reaction uses the ambient air. Various metals can be used, but zinc is very promising because of its disposability, non-toxic behavior, and because operation as a secondary cell is possible. Typical characteristics of zinc-air batteries are flat charge and discharge curves. On the one hand, this is an advantage for the subsequent power electronics, which can be optimized for smaller and constant voltage ranges. On the other hand, the state determination of the system becomes more complex, since the voltage level is not sufficient to determine the state of the battery. In this context, electrochemical impedance spectroscopy is a promising candidate since the resulting impedance spectra depend on the state of charge, working point, state of aging, and temperature. Therefore, in this publication, electrochemical impedance spectroscopy is combined with multiple machine learning techniques to also determine successfully the state of charge during charging of the cell at non-fixed charging currents.

Funded by organization EFRE-0801585.