Challenges Encountered in OBD2 Data for Driving Cycle

Session

Civil Engineering, Infrastructure and Environment

Description

Integrated vehicle emission modelling has been a main problem by many authors recently as the complexity of transportation system in urban areas has increased significantly. However, current models such as MOVES require driving cycle for emission predictions. Driving cycle, in addition to reflecting the behavior of the driver, is a speed-time curve that also captures the physical state of the urban network and traffic conditions. Due to the volume of data, the calculation of this curve from second-based data collected from drivers becomes a big data problem. This study summarizes a series of challenges and solutions, including the collection, cleaning, and grouping of second-based OBD2 data. In a driving cycle study conducted for the city of Pristina, it was observed that a significant portion of the collected data could not be used due to missing location data caused by GPS signal loss. Additionally, it was observed that GPS signals deviate due to reflection effects, and data needs to be corrected using matching algorithms.

Keywords:

Driving cycle, real data measurements, OBD, speed-time profile, Pristina

Proceedings Editor

Edmond Hajrizi

ISBN

978-9951-550-95-6

Location

UBT Lipjan, Kosovo

Start Date

28-10-2023 8:00 AM

End Date

29-10-2023 6:00 PM

DOI

10.33107/ubt-ic.2023.366

This document is currently not available here.

Share

COinS
 
Oct 28th, 8:00 AM Oct 29th, 6:00 PM

Challenges Encountered in OBD2 Data for Driving Cycle

UBT Lipjan, Kosovo

Integrated vehicle emission modelling has been a main problem by many authors recently as the complexity of transportation system in urban areas has increased significantly. However, current models such as MOVES require driving cycle for emission predictions. Driving cycle, in addition to reflecting the behavior of the driver, is a speed-time curve that also captures the physical state of the urban network and traffic conditions. Due to the volume of data, the calculation of this curve from second-based data collected from drivers becomes a big data problem. This study summarizes a series of challenges and solutions, including the collection, cleaning, and grouping of second-based OBD2 data. In a driving cycle study conducted for the city of Pristina, it was observed that a significant portion of the collected data could not be used due to missing location data caused by GPS signal loss. Additionally, it was observed that GPS signals deviate due to reflection effects, and data needs to be corrected using matching algorithms.