Published in Transportation Research Part D (under review), 2025
This study develops a scalable, data-driven framework that leverages OBD remote transmission data to identify urea depletion and consumption patterns in HDDVs, enabling the detection of potential tampering and providing policymakers with a cost-effective tool for targeted emission control.
Published in Journal of Hazard Materials, 2025
This article presents a data-driven method for imputing missing OBD data, aiming to reconstruct the real-world emission profiles of HDDVs.
Recommended citation: Cao, Z. et al. Reconstructing missing NOx emissions in heavy-duty diesel vehicle OBD data: A machine learning approach. Journal of Hazardous Materials 494, 138619, doi:https://doi.org/10.1016/j.jhazmat.2025.138619 (2025).
Download Paper
Published in NPJ Sustainable Mobility and Transport, 2025
This study proposes a cross-regional vehicle energy consumption assessment framework. Real-world driving data are first used, in combination with Markov chains, to construct a regional driving cycle database. This database is then coupled with machine learning models to estimate energy consumption across different regions.
Published in Environmental Pollution, 2025
The study utilizes OBD data from OBM big data platform and develops a comprehensive data analysis framework that integrates data preprocessing, high-emission vehicle identification, and factor analysis using both binning and machine learning approaches.
Recommended citation: Cao Z, Shi K, Qin H, et al. A Comprehensive OBD Data Analysis Framework: Identification and Factor Analysis of High-Emission Heavy-Duty Vehicles[J]. Environmental Pollution, 2025: 125751.
Download Paper