A Hybrid Surrogate for Electric Vehicle Parameter Estimation and Power Consumption via Physics-Informed Neural Operators

2025-08-18

AI Summary

This study addresses the problem of estimating time-varying vehicle parameters—motor/regenerative braking efficiency, aerodynamic and rolling resistance, effective mass, and auxiliary power—and predicting battery power consumption for electric vehicles using only speed and acceleration measurements. We propose a physics-informed hybrid surrogate model. Methodologically, it integrates a Fourier neural operator to construct a spectral parameter operator for frequency-domain feature extraction and global modeling, and incorporates a differentiable physics-based forward module that enforces parameter evolution via explicit physical equations—ensuring physical consistency without residual loss terms. The modular architecture endows each parameter with clear physical interpretability and significantly enhances generalization across diverse driving cycles and sampling rates. Evaluated on real-world data from Tesla Model 3/S and Kia EV9, the model achieves mean absolute power prediction errors of 0.2 kW and 0.8 kW, respectively, demonstrating high accuracy and robustness.

Technology Category

• Planning, Routing, and Scheduling: Model-Based Reasoning
• Machine Learning: Mixture of Experts (MoE)
• Intelligent Robots: State Estimation

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

We present a hybrid surrogate model for electric vehicle parameter estimation and power consumption. We combine our novel architecture Spectral Parameter Operator built on a Fourier Neural Operator backbone for global context and a differentiable physics module in the forward pass. From speed and acceleration alone, it outputs time-varying motor and regenerative braking efficiencies, as well as aerodynamic drag, rolling resistance, effective mass, and auxiliary power. These parameters drive a physics-embedded estimate of battery power, eliminating any separate physics-residual loss. The modular design lets representations converge to physically meaningful parameters that reflect the current state and condition of the vehicle. We evaluate on real-world logs from a Tesla Model 3, Tesla Model S, and the Kia EV9. The surrogate achieves a mean absolute error of 0.2kW (about 1% of average traction power at highway speeds) for Tesla vehicles and about 0.8kW on the Kia EV9. The framework is interpretable, and it generalizes well to unseen conditions, and sampling rates, making it practical for path optimization, eco-routing, on-board diagnostics, and prognostics health management.

Problem

• Estimates electric vehicle parameters from speed and acceleration
• Predicts power consumption using physics-informed neural operators
• Generalizes to unseen conditions for practical vehicle applications

Innovation

• Hybrid surrogate model with neural operators
• Differentiable physics module for parameter estimation
• Interpretable framework for electric vehicle diagnostics