A Deep Learning Micro-Scale Model to Estimate the CO₂ Emissions from Light-Duty Diesel Trucks Based on Real-World Driving

Abstract

On-road carbon dioxide (CO2) emissions from light-duty diesel trucks (LDDTs) are greatly affected by driving conditions, which may be better predicted with the sequence deep learning model as compared to traditional models. In this study, two typical LDDTs were selected to investigate the on-road CO2 emission characteristics with a portable emission measurement system (PEMS) and a global position system (GPS). A deep learning-based LDDT CO2 emission model (DL-DTCEM) was developed based on the long short-term memory network (LSTM) and trained by the measured data with the PEMS. Results show that the vehicle speed, acceleration, VSP, and road slope had obvious impacts on the transient CO2 emission rates. There was a rough positive correlation between the vehicle speed, road slope, and CO2 emission rates. The CO2 emission rate increased significantly when the speed was >5 m/s, especially at high acceleration. The correlation coefficient (R2) and the root mean square error (RMSE) between the monitored CO2 emissions with PEMS and the predicted values with the DL-DTCEM were 0.986–0.990 and 0.165–0.167, respectively. The results proved that the model proposed in this study can predict very well the on-road CO2 emissions from LDDTs.

Keywords

• vehicle emission model
• deep learning
• light-duty diesel truck (LDDT)
• CO₂ emissions
• portable emission measurement system (PEMS)
• long short-term memory network (LSTM)