Digital Twins for Electric Vehicle SoX Battery Modeling: Status and Proposed Advancements

The State of X (SoX) variables, where X stands for Charge, Health, and Energy, are important in battery systems, as they serve as inputs for many algorithms responsible for monitoring, controlling, and protecting the battery pack. SoX monitoring and estimation is even more crucial in electric vehicles, whose batteries are crucial to ensure their operation and are, at the same time, subject to aging and performance deterioration over time. For this reason, many solutions have been proposed for SoX monitoring, falling under the umbrella of Battery Digital Twins. This work reviews the current status and challenges and proposes a structure of a battery digital twin designed to reflect battery SoX at the run time accurately. To ensure a high degree of correctness concerning non-linear phenomena, the digital twin relies on data-driven models trained on traces of battery evolution over time, retrained periodically to reflect the impact of aging. The proposed digital twin structure is exemplified on two public datasets to motivate its adoption and prove its effectiveness.