There have been numerous studies on traffic accidents and their severity, particularly in relation to weather conditions and road geometry. In these studies, traditional statistical methods have been employed, such as linear regression, logistic regression, and negative binomial regression modeling, which are the most common linear and non-linear regression analysis methods. In this research, machine learning architecture was applied to this problem using the random forest, artificial neural network, and decision tree techniques to ascertain the strengths and weaknesses of these methods. Three data sets were used: road geometry data, precipitation data, and traffic accident data over nine years corresponding to the Naebu Expressway, which is located in Seoul, Korea. For the model evaluation, three measures were employed: the out-of-bag estimate of error rate (OOB), mean square error (MSE), and root mean square error (RMSE). The low mean OOB, MSE, and RMSE observed in the results obtained using the proposed random forest model demonstrate its accuracy.

Euro 6 standards impose stringent nitrogen oxide (NO_x) emission limits on diesel cars. NO_x emissions are significantly different between Euro 6 diesel cars and the previous standards in real-world driving. In this research, the NO_x concentrations of Euro 6 diesel engines during real-world driving were studied considering various factors. Real driving emission (RDE) tests were conducted using vehicles equipped with portable emissions measurement systems. Urban, rural, and motorway test routes were utilized. Road environment, atmospheric, and after-treatment performance factors were collected in each case. An artificial neural network was used for evaluation using RDE test data and various statistical parameters. It was found that the proposed method predicted the pollutant emissions effectively. Lastly, the relative importance of each predictor was derived, and the NO_x concentrations were analyzed. These approaches provide accurate emission information for an environmental effect evaluation that reflects more realistic road conditions.

This study analyzed the characteristics and distribution of emissions from diesel vehicles that are sold in Korea and satisfy the Euro-6 standards, according to after-treatment systems. To identify the emission distribution of diesel vehicles according to after-treatment systems, results of the certification tests conducted on 266 vehicle models were examined. Results of the certification tests on 86 vehicle models that were manufactured based on the standards for RDE after 2017 were examined according to the engine displacement and power. The emission characteristics of six vehicle models equipped with different types of after-treatment systems were verified through certification tests in the New European Driving Cycle and Worldwide Harmonized Light Vehicle Test Procedure modes and RDE tests, according to the after-treatment systems. Specifically, a chassis dynamometer and an emission analyzer were used in the certification test modes; a portable emissions measurement system was used in the RDE test. The results indicated that the amount of NO_x emissions from diesel vehicles has been constantly decreasing since 2017 due to the implementation of standards for RDE and advancements in after-treatment systems. Furthermore, it was found that selective catalyst reduction systems must be installed in vehicles to satisfy Euro-6 standards for permissible emissions on real-roads.

Passenger cars account for the largest share of GHG emissions in the road sector. However, given that the number of heavy-duty vehicles registered is lower but accounts for about a quarter of GHG emissions in the road sector, it is necessary to reduce carbon dioxide (CO₂) emissions by improving the fuel efficiency of heavy-duty vehicles. However, experiments using dynamometers during the vehicle development process consume a lot of time and cost. Conversely, simulations can quantitatively analyze the sensitivity of parameters and accelerate optimization. Therefore, in this study, we modeled a heavy-duty vehicle using an AVL Cruise simulation and analyzed the effects of payload, air drag coefficient, and rolling resistance on fuel economy, CO₂ emission, and the valid window ratio among the moving average window (MAW) for three driving routes. When the average vehicle speed was higher, the effect of the air drag coefficient on fuel economy was high. Additionally, when the average vehicle speed was lowered, the effect of the reduced rolling resistance on improving fuel efficiency was higher than that of the reducing air drag. Thus, the fuel efficiency improvement rate according to each 10% decrease in rolling resistance was higher by 2.2%, on average, in the low average speed route. Additionally, it was confirmed that the valid window ratio was high when driving in a section with a high vehicle speed first. Thus, the valid window ratio was almost 100% in the test of the route conditions starting from the highway section.

This study was primarily focused on the experimental comparison of the particle emission characteristics of diesel and liquefied-natural-gas (LNG) fuels for heavy-duty vehicles. Particulate matter from various heavy-duty engines and vehicles were analysed with a golden particle measurement system recommended by the Particle Measurement Program. This system consists of a constant-volume sampler, a particle number counter, and particle number diluters. To verify the particle number and size distribution characteristics of diesel-fuelled engines and buses, including LNG fuel, various dynamic operation modes, such as the European Transient Cycle (ETC) mode, the European Stabilized Cycle (ESC) mode, and the National Institute of Environmental Research mode, uniquely developed in Korea, were evaluated. The formation of the particles depended closely upon the vehicle speed and the load conditions of each mode. In particular, the particle number sharply increased for fast-transient-acceleration and high-load operation within a heavy-duty engine. The partial diesel particulate filter efficiency was evaluated under the ETC and ESC modes using both engine and vehicle dynamometers.