Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Eymen Ipek, Assoc. Mario Hirz

TL;DR

The paper tackles voltage prediction for Li-ion batteries in eVTOLs under dynamic power profiles, where purely data-driven models are accurate but computationally heavy and physics-based models lack real-time practicality. It proposes a physics-informed neural network (PINN) that learns only a residual on top of a $2RC$ equivalent-circuit physics prior, with $V_{ ext{phy}} = ext{OCV} - I R_0 - V_{RC1} - V_{RC2}$ and RC state updates $V_{RCj,i} = e^{- rac{ abla t_i}{ au_j}} V_{RCj,i-1} + R_j igl(1 - e^{- rac{ abla t_i}{ au_j}}igr) I_i$, producing $V_{ ext{pred}} = V_{ ext{phy}} + abla V_ heta(x)$. Using the open eVTOL battery dataset, the authors show that a shallow PINN can match or exceed the performance of deeper pure data-driven models while using up to $75\%$ fewer trainable parameters, significantly reducing onboard computation. This approach enhances interpretability through the physics prior and enables efficient edge AI deployment for onboard BMS and flight controllers. The work demonstrates concrete gains in RMSE, peak error, and parameter efficiency, highlighting a viable path toward lightweight, accurate battery voltage prediction in aggressive eVTOL mission profiles.

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.

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

TL;DR

The paper tackles voltage prediction for Li-ion batteries in eVTOLs under dynamic power profiles, where purely data-driven models are accurate but computationally heavy and physics-based models lack real-time practicality. It proposes a physics-informed neural network (PINN) that learns only a residual on top of a equivalent-circuit physics prior, with and RC state updates , producing . Using the open eVTOL battery dataset, the authors show that a shallow PINN can match or exceed the performance of deeper pure data-driven models while using up to fewer trainable parameters, significantly reducing onboard computation. This approach enhances interpretability through the physics prior and enables efficient edge AI deployment for onboard BMS and flight controllers. The work demonstrates concrete gains in RMSE, peak error, and parameter efficiency, highlighting a viable path toward lightweight, accurate battery voltage prediction in aggressive eVTOL mission profiles.

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.
Paper Structure (4 sections, 4 equations, 2 figures, 1 table)

This paper contains 4 sections, 4 equations, 2 figures, 1 table.

Table of Contents

  1. Introduction
  2. Methodology
  3. Results and Discussion
  4. CONCLUSION

Figures (2)

  • Figure 1: Performance comparison of PINN versus FNN architectures. The PINN architectures consistently achieve significantly lower RMSE and maximum error compared to their FNN counterparts, even when the PINN is much simpler than the most complex FNN tested.
  • Figure 2: Voltage prediction and error analysis under dynamic eVTOL profiles. (a) the actual voltage versus the FNN (2 hidden layers, 128 neurons each) predicted voltage, (b) the error voltage for the FNN, (c) the actual voltage versus the PINN (2 hidden layers, 128 neurons each) predicted voltage (d) the error voltage for the PINN.