Multi‑Level Driving Behavior Modeling and Hydrogen Refueling Analysis in Fuel Cell Vehicles Using Big Data

This study shows a new data-driven framework for analyzing driver behavior using high-frequency data from fuel cell vehicles (FCEVs). The proposed pipeline involves data collection and processing, trip segmentation, segment-level preprocessing, segment-level features extraction and processing, and unsupervised clustering across both dynamic and stationary behavior. PCA–UMAP–KMeans pipeline has been used on the driving behavior research by classifying drivers into different driving styles. Stationary behaviors including the hydrogen refueling characteristics is researched by integrating dynamic signal and related location date. Finally, both driving and stationary behaviors are integrated and combined as individual driver profile for FCEVs for future vehicle product development.