Battery SOC estimation from EIS data based on machine learning and equivalent circuit model

• Published in: Energy (Oxford) Vol. 283; p. 128461
• Main Authors: Buchicchio, Emanuele, De Angelis, Alessio, Santoni, Francesco, Carbone, Paolo, Bianconi, Francesco, Smeraldi, Fabrizio
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 15.11.2023
• Subjects: batteries; Battery; data collection; dielectric spectroscopy; domain; EIS; Electrochemical impedance spectroscopy; electronics; energy; SOC; State of charge; 68T99; State of charge; SOC; EIS; Battery; Electrochemical impedance spectroscopy
• ISSN: 0360-5442; 1873-6785
• DOI: 10.1016/j.energy.2023.128461

Estimating the state of charge (SOC) of batteries is fundamental for the proper management and safe operation of numerous systems, including electric vehicles, smart energy grids, and portable electronics. While there is no practical method for direct measurement of SOC, several estimation approaches have been developed, including a growing number of machine-learning-based techniques. Machine learning methods are intrinsically data-driven but can also benefit from a-priori knowledge embedded in a model. In this work, we first demonstrate, through exploratory data analysis, that it is possible to discriminate between different SOC from electrochemical impedance spectroscopy (EIS) measurements. Then we propose a SOC estimation approach based on EIS and an equivalent circuit model to provide a compact way to describe the frequency domain and time-domain behavior of the impedance of a battery. We experimentally validated this approach by applying it to a dataset consisting of EIS measurements performed on four lithium-ion cylindrical cells at different SOC values. The proposed approach allows for very efficient model training and produces a low-dimensional SOC classification model that achieves above 93% accuracy. The resulting low-dimensional classification model is suitable for embedding into battery-powered systems and for online SOC estimation. •Correct SOC estimation is crucial in any battery-powered device.•Lightweight yet accurate SOC estimation method based on EIS and an equivalent circuit model.•Validated on a real-world public available SOC/EIS dataset, the approach achieved accuracy 93%.•Experimental results demonstrate the feasibility of SOC estimation based on sparse sampling of the EIS spectra.•Equivalent circuit parameter fitting allows dimensionality reduction and improves accuracy.