Transfer Learning for Input Estimation of Vehicle Systems

TL;DR

This paper introduces a domain-adaptive, learning-based method using autoencoders for estimating vehicle suspension inputs from contaminated signals, achieving high accuracy and robustness across diverse vehicle types.

Contribution

The study presents a novel autoencoder-based approach that effectively separates tire-level inputs from suspension signals, accommodating vehicle diversity and nonlinearity in a crowdsensing context.

Findings

Achieved 98% vehicle classification accuracy.

Demonstrated robustness to vehicle dynamic variations.

Outperformed existing vehicle suspension deconvolution methods.

Abstract

This study proposes a learning-based method with domain adaptability for input estimation of vehicle suspension systems. In a crowdsensing setting for bridge health monitoring, vehicles carry sensors to collect samples of the bridge's dynamic response. The primary challenge is in preprocessing; signals are highly contaminated from road profile roughness and vehicle suspension dynamics. Additionally, signals are collected from a diverse set of vehicles vitiating model-based approaches. In our data-driven approach, two autoencoders for the cabin signal and the tire-level signal are constrained to force the separation of the tire-level input from the suspension system in the latent state representation. From the extracted features, we estimate the tire-level signal and determine the vehicle class with high accuracy (98% classification accuracy). Compared to existing solutions for the vehicle suspension deconvolution problem, we show that the proposed methodology is robust to vehicle dynamic variations and suspension system nonlinearity.