Coupling Neural Networks and Physics Equations For Li-Ion Battery State-of-Charge Prediction
This work addresses battery management for improving system lifetime, representing an incremental advance by merging physics-based and data-driven approaches.
The authors tackled the problem of predicting a battery's State of Charge (SoC) by proposing a novel neural network architecture with cascaded branches and integrating physics equations into training, showing that their Physics-Informed Neural Networks outperform purely data-driven models and achieve superior accuracy with a smaller architecture compared to state-of-the-art methods.
Estimating the evolution of the battery's State of Charge (SoC) in response to its usage is critical for implementing effective power management policies and for ultimately improving the system's lifetime. Most existing estimation methods are either physics-based digital twins of the battery or data-driven models such as Neural Networks (NNs). In this work, we propose two new contributions in this domain. First, we introduce a novel NN architecture formed by two cascaded branches: one to predict the current SoC based on sensor readings, and one to estimate the SoC at a future time as a function of the load behavior. Second, we integrate battery dynamics equations into the training of our NN, merging the physics-based and data-driven approaches, to improve the models' generalization over variable prediction horizons. We validate our approach on two publicly accessible datasets, showing that our Physics-Informed Neural Networks (PINNs) outperform purely data-driven ones while also obtaining superior prediction accuracy with a smaller architecture with respect to the state-of-the-art.