Integration of Second-generation On-board Diagnostics Data via Deep Learning to Develop Eco-driving Analysis System Applicable to Large and Small Cars
Reducing greenhouse gas emissions is an imperative of climate policy worldwide. The transport sector accounts for a large proportion of CO2 emissions; therefore, the development of eco-driving has become a critical topic in the study of fuel efficiency and environmental protection. Although consider...
Saved in:
Published in | Sensors and materials Vol. 34; no. 6; p. 2467 |
---|---|
Main Authors | , , , , |
Format | Journal Article |
Language | English |
Published |
Tokyo
MYU Scientific Publishing Division
30.06.2022
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | Reducing greenhouse gas emissions is an imperative of climate policy worldwide. The transport sector accounts for a large proportion of CO2 emissions; therefore, the development of eco-driving has become a critical topic in the study of fuel efficiency and environmental protection. Although considerable research has been carried out on cars, there has been little research involving large vehicles. In this study, second-generation on-board diagnostics (OBD-II) was used to sense and collect the driving data of cars and light-duty buses. These data were then used for predicting real-time fuel consumption by using deep learning methods and a fuel efficiency driving analysis system for both large and small cars. The prediction results demonstrated a correlation coefficient of approximately 90% with actual data and confirmed the applicability of the system to different vehicle types. This system can be integrated with professional driver training centers to improve training quality and promote the development of eco-driving. |
---|---|
ISSN: | 0914-4935 2435-0869 |
DOI: | 10.18494/SAM3796 |