Development of Scalable Impedance Data Collection System for Li‐Ion Batteries and State Estimation Using Neural Networks

In recent years, the importance of accurate state estimation techniques for lithium‐ion batteries (LIBs) has been increasing. An approach that combines electrochemical impedance spectroscopy (EIS) with machine learning is highlighted as a promising method for high‐precision state estimation. However, traditional EIS measurements pose a significant barrier to implementation due to the cost of collecting data from many battery samples. Furthermore, many existing studies are limited to measurements under steady‐state conditions in laboratory environments, requiring dedicated high‐precision impedance measurement equipment. In practical applications, it is necessary to respond to dynamic changes in battery states, making the implementation of expensive measurement equipment unrealistic. To address these challenges, this study developed a low‐cost EIS measurement circuit. We demonstrated that impedance data obtained from the developed circuit can be used to construct a state estimation model for commercially available cylindrical LIBs. Using the system, we collected impedance data from brand new batteries and built a model that can accurately estimate temperature and state of charge. This work will accelerate the construction of large‐scale impedance datasets for LIBs and is expected to be an important step toward next‐generation battery management systems. © 2025 The Author(s). IEEJ Transactions on Electrical and Electronic Engineering published by Institute of Electrical Engineers of Japan and Wiley Periodicals LLC.