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
Recommended Citation
Demir, Yusuf Kagan and Salihu, Flamur Melo de, "Challenges Encountered in OBD2 Data for Driving Cycle" (2023). UBT International Conference. 30.
https://knowledgecenter.ubt-uni.net/conference/IC/civil/30
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.