Impact of Physics-Informed Features on Neural Network Complexity for Li-ion Battery Voltage Prediction in Electric Vertical Takeoff and Landing Aircrafts

TL;DR

This paper explores how incorporating physics-based features into neural networks can reduce model complexity while maintaining accuracy in predicting Li-ion battery voltage for eVTOL aircraft, enabling more efficient onboard systems.

Contribution

It demonstrates that physics-informed features enable simpler neural networks with fewer parameters without sacrificing predictive accuracy.

Findings

Physics-informed models use up to 75% fewer parameters.

Comparable accuracy achieved with simpler models.

Significant reduction in computational overhead.

Abstract

The electrification of vertical takeoff and landing aircraft demands high-fidelity battery management systems capable of predicting voltage response under aggressive power dynamics. While data-driven models offer high accuracy, they often require complex architectures and extensive training data. Conversely, equivalent circuit models (ECMs), such as the second-order model, offer physical interpretability but struggle with high C-rate non-linearities. This paper investigates the impact of integrating physics-based information into data-driven surrogate models. Specifically, we evaluate whether physics-informed features allow for the simplification of neural network architectures without compromising accuracy. Using the open-source electric vertical takeoff and landing (eVTOL) battery dataset, we compare pure data-driven models against physics-informed data models. Results demonstrate that physics-informed models achieve comparable accuracy to complex pure data-driven models while using up to 75% fewer trainable parameters, significantly reducing computational overhead for potential on-board deployment.