scholarly journals A Comparative Study on Fuel Consumption Prediction Methods of Heavy-Duty Diesel Trucks Considering 21 Influencing Factors

Energies ◽  
2021 ◽  
Vol 14 (23) ◽  
pp. 8106
Author(s):  
Jian Gong ◽  
Junzhu Shang ◽  
Lei Li ◽  
Changjian Zhang ◽  
Jie He ◽  
...  
Keyword(s):  
Neural Network ◽  
Random Forest ◽  
Decision Tree ◽  
Fuel Consumption ◽  
Back Propagation ◽  
Machine Learning Algorithms ◽  
Heavy Duty ◽  
Naturalistic Driving ◽  
Heavy Duty Diesel ◽  
Diesel Trucks

With increasingly prominent environmental problems, controlling automobile exhaust has become essential to the environment. The fuel consumption of transportation is the critical factor that determines exhaust gas. By analyzing the naturalistic driving data of heavy-duty diesel trucks (HDDTs), this paper explored the influence of engine technical state, road features, weather, and temperature conditions on fuel consumption during driving. The detailed process is as follows: Firstly, we collected 1153 naturalistic driving data from 34 HDDTs and made a specific analysis and summary description of the data; secondly, by establishing a binary Logistic regression model, we quantitatively explored the influence of significant factors on the fuel consumption; meanwhile, based on quantitative analysis of factor’s effectiveness, this research used several machine learning algorithms (back-propagation neural network, decision tree, and random forest) to build fuel consumption predictors, and compared the prediction performance of different algorithms. The results showed that the prediction accuracy of the decision tree, back-propagation (BP) neural network, and random forest is 81.38%, 83.98%, and 86.58%, respectively. The random forest showed the best performance in predicting. The conclusions can assist transportation companies in formulating driving training strategies and contribute to reducing energy consumption and emissions.

scholarly journals Modeling Impacts of Highway Circular Curve Elements on Heavy-Duty Diesel Trucks’ CO2 Emissions

2019 ◽  
Vol 16 (14) ◽  
pp. 2514 ◽  
Author(s):  
Xiaodong Zhang ◽  
Jinliang Xu ◽  
Menghui Li ◽  
Qunshan Li ◽  
Lan Yang
Keyword(s):  
Field Experiment ◽  
Fuel Consumption ◽  
Co2 Emissions ◽  
Co2 Emission ◽  
Shaanxi Province ◽  
Emission Model ◽  
Heavy Duty ◽  
Heavy Duty Diesel ◽  
Diesel Trucks ◽  
Circular Curve

Heavy-duty trucks contribute a significant component of all transportation in cargo terminals, such as Shaanxi Province, China. The emissions from these vehicles are the primary source of carbon emissions during highway operations. While several studies have attempted to address emission issues by improving traffic operations, a few focused on the relationship between emissions and highway geometric design, especially for heavy-duty trucks. The primary goal of this research was to understand the impact of circular curve on carbon dioxide (CO2) emissions produced by heavy-duty diesel trucks. Firstly, appropriate parameters were specified in MOVES (motor vehicle emission simulator) model according to the geometrical characteristics. Fuel consumption, speed and location data were collected by hiring five skilled drivers on the automotive proving ground located at Chang’an University, Shaanxi Province. The associated carbon emission data were derived from fuel consumption data by applying the IPCC (Intergovernmental Panel on Climate Change) method. After this, the applicability of MOVES model was verified by the field experiment. Moreover, a multiple regression model for CO2 emissions incorporated with roadway segment radius, circular curve length, and initial vehicle speed was established with data generated by the MOVES model. The proposed CO2 emission model was also verified by field experiment with relative error of 6.17%. It was found that CO2 emission had monotone decreasing property with radius increasing, and the minimum radius that influenced diesel CO2 emission was 550 m. The proposed quantitative CO2 emission model can provide a reference for low-carbon highway design, leading to environment-friendly transportation construction.

scholarly journals Characterization of Real-World Pollutant Emissions and Fuel Consumption of Heavy-Duty Diesel Trucks with Latest Emissions Control

Atmosphere ◽  
2019 ◽  
Vol 10 (9) ◽  
pp. 535 ◽  
Author(s):  
Christos Keramydas ◽  
Leonidas Ntziachristos ◽  
Christos Tziourtzioumis ◽  
Georgios Papadopoulos ◽  
Ting-Shek Lo ◽  
...  
Keyword(s):  
Fuel Consumption ◽  
Real World ◽  
Emission Factors ◽  
Pollutant Emissions ◽  
Particulate Filter ◽  
Emission Measurement ◽  
Heavy Duty ◽  
Heavy Duty Diesel ◽  
Diesel Trucks ◽  
The Impact

Heavy-duty diesel trucks (HDDTs) comprise a key source of road transport emissions and energy consumption worldwide mainly due to the growth of road freight traffic during the last two decades. Addressing their air pollutant and greenhouse gas emissions is therefore required, while accurate emission factors are needed to logistically optimize their operation. This study characterizes real-world emissions and fuel consumption (FC) of HDDTs and investigates the factors that affect their performance. Twenty-two diesel-fueled, Euro IV to Euro VI, HDDTs of six different manufacturers were measured in the road network of the Hong Kong metropolitan area, using portable emission measurement systems (PEMS). The testing routes included urban, highway and mixed urban/highway driving. The data collected corresponds to a wide range of driving, operating, and ambient conditions. Real-world distance- and energy-based emission levels are presented in a comparative manner to capture the effect of after-treatment technologies and the role of the evolution of Euro standards on emissions performance. The emission factors’ uncertainty is analyzed. The impact of speed, road grade and vehicle weight loading on FC and emissions is investigated. An analysis of diesel particulate filter (DPF) regenerations and ammonia (NH3) slip events are presented along with the study of Nitrous oxide (N2O) formation. The results reveal deviations of real-world HDDTs emissions from emission limits, as well as the significant impact of different operating and driving factors on their performance. The occasional high levels of N2O emissions from selective catalytic reduction equipped HDDTs is also revealed, an issue that has not been thoroughly considered so far.

scholarly journals Application of Data Mining Algorithms for Dementia in People with HIV/AIDS

2021 ◽  
Vol 2021 ◽  
pp. 1-8
Author(s):  
Luana Ibiapina Cordeiro Calíope Pinheiro ◽  
Maria Lúcia Duarte Pereira ◽  
Marcial Porto Fernandez ◽  
Francisco Mardônio Vieira Filho ◽  
Wilson Jorge Correia Pinto de Abreu ◽  
...  
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Data Mining ◽  
Logistic Regression ◽  
Random Forest ◽  
Decision Tree ◽  
Learning Algorithms ◽  
Principal Component ◽  
Machine Learning Algorithms ◽  
Hiv Aids

Dementia interferes with the individual’s motor, behavioural, and intellectual functions, causing him to be unable to perform instrumental activities of daily living. This study is aimed at identifying the best performing algorithm and the most relevant characteristics to categorise individuals with HIV/AIDS at high risk of dementia from the application of data mining. Principal component analysis (PCA) algorithm was used and tested comparatively between the following machine learning algorithms: logistic regression, decision tree, neural network, KNN, and random forest. The database used for this study was built from the data collection of 270 individuals infected with HIV/AIDS and followed up at the outpatient clinic of a reference hospital for infectious and parasitic diseases in the State of Ceará, Brazil, from January to April 2019. Also, the performance of the algorithms was analysed for the 104 characteristics available in the database; then, with the reduction of dimensionality, there was an improvement in the quality of the machine learning algorithms and identified that during the tests, even losing about 30% of the variation. Besides, when considering only 23 characteristics, the precision of the algorithms was 86% in random forest, 56% logistic regression, 68% decision tree, 60% KNN, and 59% neural network. The random forest algorithm proved to be more effective than the others, obtaining 84% precision and 86% accuracy.

scholarly journals Comparative analysis of machine learning algorithms in water extraction

2021 ◽  
Vol 2076 (1) ◽  
pp. 012045
Author(s):  
Aimin Li ◽  
Meng Fan ◽  
Guangduo Qin
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Logistic Regression ◽  
Comparative Analysis ◽  
Random Forest ◽  
Decision Tree ◽  
Water Body ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Support Vector

Abstract There are many traditional methods available for water body extraction based on remote sensing images, such as normalised difference water index (NDWI), modified NDWI (MNDWI), and the multi-band spectrum method, but the accuracy of these methods is limited. In recent years, machine learning algorithms have developed rapidly and been applied widely. Using Landsat-8 images, models such as decision tree, logistic regression, a random forest, neural network, support vector method (SVM), and Xgboost were adopted in the present research within machine learning algorithms. Based on this, through cross validation and a grid search method, parameters were determined for each model.Moreover, the merits and demerits of several models in water body extraction were discussed and a comparative analysis was performed with three methods for determining thresholds in the traditional NDWI. The results show that the neural network has excellent performances and is a stable model, followed by the SVM and the logistic regression algorithm. Furthermore, the ensemble algorithms including the random forest and Xgboost were affected by sample distribution and the model of the decision tree returned the poorest performance.

Sign in / Sign up

Export Citation Format

Share Document