EV-PINN: A Physics-Informed Neural Network for Predicting Electric Vehicle Dynamics

TL;DR

EV-PINN is a physics-informed neural network that accurately predicts electric vehicle battery power and energy consumption using real-world data, enabling better path planning without extra sensors.

Contribution

The paper introduces EV-PINN, a novel physics-informed neural network that models EV dynamics and estimates parameters directly from in-situ data, improving prediction accuracy and generalization.

Findings

High accuracy in battery power and energy consumption prediction.

Validated on Tesla Model 3 and Model S data with low validation loss.

Effective parameter estimation from minimal input data.

Abstract

An onboard prediction of dynamic parameters (e.g. Aerodynamic drag, rolling resistance) enables accurate path planning for EVs. This paper presents EV-PINN, a Physics-Informed Neural Network approach in predicting instantaneous battery power and cumulative energy consumption during cruising while generalizing to the nonlinear dynamics of an EV. Our method learns real-world parameters such as motor efficiency, regenerative braking efficiency, vehicle mass, coefficient of aerodynamic drag, and coefficient of rolling resistance using automatic differentiation based on dynamics and ensures consistency with ground truth vehicle data. EV-PINN was validated using 15 and 35 minutes of in-situ battery log data from the Tesla Model 3 Long Range and Tesla Model S, respectively. With only vehicle speed and time as inputs, our model achieves high accuracy and generalization to dynamics, with validation losses of 0.002195 and 0.002292, respectively. This demonstrates EV-PINN's effectiveness in estimating parameters and predicting battery usage under actual driving conditions without the need for additional sensors.