DBPnet: Damper Characteristics-Based Bayesian Physics-Informed Neural Network for Wheel Load Estimation

2026-05-24

AI Summary

Wheel load estimation remains highly challenging due to complex suspension geometry, nonlinear dynamics, and sensor noise, which significantly limit the performance of advanced driver-assistance systems. To address this, this work proposes DBPnet—a deep architecture that integrates suspension linkage-level modeling (SLLM) with Bayesian physics-informed neural networks (PINNs). DBPnet innovatively incorporates a physics-aware embedding module inspired by damper characteristics, enabling dynamic guidance from physical principles without relying on a fixed analytical model, while effectively quantifying system uncertainty. Experimental results demonstrate that DBPnet substantially outperforms existing methods in both high-fidelity simulation and real-vehicle tests, achieving notably lower root-mean-square error (RMSE) and peak error, thereby validating its high accuracy and strong robustness in wheel load estimation.

Abstract

Advanced driver assistance systems (ADAS) play an important role in modern automotive intelligence, significantly enhancing vehicle safety and stability. The performance of ADAS critically relies on accurate and reliable vehicle state estimation, particularly from vehicle dynamic sensors. Among these signals, wheel load is a key variable for chassis control and safety-critical functions, yet it remains difficult to estimate robustly due to complex suspension geometry, nonlinear dynamics, and measurement noise. To address this issue, we propose DBPnet, a Bayesian physics-informed neural network (PINN) with a physics-aware embedding module inspired by damper characteristics. First, this paper presents a suspension linkage-level modeling (SLLM) approach that constructs a nonlinear instantaneous dynamic model by explicitly considering the complex geometric structure of the suspension. Building upon SLLM, Bayesian inference is integrated into the PINN to effectively cope with noise and uncertainty in the vehicle chassis system, thereby improving the model's robustness. Then, a physics-informed loss function is employed to ensure consistency with fundamental physical principles, while the damper characteristics-inspired embedding module extracts temporal variation features of input signals and incorporates them into each layer of the PINN, ensuring that physical observations guide the neural network without being constrained by fixed physical models. Extensive evaluations on high-fidelity simulations and real-world experiments demonstrate that our DBPnet consistently achieves lower RMSE and MaxError than baseline methods. These results highlight the potential of our DBPnet to advance wheel load estimation and contribute to the development of more reliable ADAS actuator functions.

Problem

• wheel load estimation
• vehicle dynamics
• suspension geometry
• measurement noise
• nonlinear dynamics

Innovation

• Bayesian physics-informed neural network
• suspension linkage-level modeling
• damper characteristics embedding
• wheel load estimation
• uncertainty quantification