Artificial Intelligence Applied to Evaluate Emissions and Energy Consumption in Commuter Railways: Comparison of Liquefied Natural Gas as an Alternative Fuel to Diesel (original) (raw)
Related papers
2016
The reduction of CO 2 emission which is in direct relationship with fuel consumption is of prime importance for the future sustainable use of passenger cars. For the given passenger car, the fuel consumption in urban areas is mostly affected by the conditions related to traffic and driving behavior. In this paper, an artificial neural network model for the prediction of passenger car fuel consumption in the City of Nis was developed based on experimentally measured data recorded through on-board diagnostics equipment. Fuel consumption was assumed to be a function of car speed, a city zone, an hour of day and a day of week. A comprehensive preliminary investigation revealed that single hidden layer artificial neural network model having ten neurons can be efficiently trained with Levenberg-Marquardt algorithm to provide satisfactory prediction accuracy. Finally, the analysis of effects of the selected independent variables on the fuel consumption was discussed based on twelve 3D surf...
Transport, 2016
The publication presents the results arising from the experimental and mathematical modelling studies, which mainly aimed to investigate the selection and optimization of the rational operation modes particular to diesel engines of freight locomotives in the possession of the JSC ‘Lithuanian Railways’ (AB ‘Lietuvos geležinkeliai’). The goal of the optimization is to increase the energy efficiency, reduce fuel consumption and emissions of harmful air pollutants to the environment from diesel engines of locomotives during freight transportation via the main lines of the Lithuanian railway network. A complex energy efficiency and environmental pollution assessment criterion KE–E adjusted for diesel engines of freight locomotives has been suggested. The use of KE–E on the basis of the conducted complex experimental mathematical computer modelling studies has determined that the reserves reducing fuel consumption, harmful emissions and greenhouse gas (CO2) emissions constitute 6÷15% on a...
Energies
Cities have been struggling for many years with many transport problems, including the impact of carbon monoxide emitted by vehicles on the environment, traffic jams, high energy consumption, numerous accidents or high infrastructure costs. There is also a dynamic growth of vehicles on the roads, which is why an increasing number of cities are introducing intelligent transportation systems (ITS), which is part of the concept of smart cities. This paper proposes a new matrix to assess the effects of the ITS implementation in the context of a concept Smart City, which consists of five criteria: (1) movement speed; (2) safety; (3) environmental; (4) economic; (5) satisfaction and amenities for society/passengers. In this new approach the benchmark values of the indicators assigned to the criteria are involved and, therefore, it is possible to determine the level of effectiveness of the ITS in public transport that uses low-carbon energy. This research used literature studies to establi...
APPLICATION OF DATA MINING METHODS FOR ANALYZING OF THE FUEL CONSUMPTION AND EMISSION LEVELS
This paper is aimed to investigate application potential of data mining in automotive industry. Most important usage and driving parameters, which effects fuel consumption and emission level of passenger cars identified and classified by using data mining methods. A dataset created by combining Euro 6 data of passenger cars has been analyzed using different tools of SPSS, such as; descriptive statistics, correlations, regression and etc. Results have been compared and effecting parameters have been derived by segmentation algorithms aiming better results by categorizing variables for upcoming analysis. The importance of each parameter has been evaluated to predict its contribution on fuel consumption by data mining technics. Therefore, it will be possible to build optimal control strategies for fuel efficiency for future cars, such as; electric, connected and automated vehicles. Adopted data mining technics in this study are classification algorithms, such as; neural networks, Bayesian networks and C5.0 algorithm as well as segmentation algorithms (e.g. K-means and Two-step) targeting foreseeability and simplicity. Application of those technics by Clementine 12.0 has shown that weight and engine capacity of passenger cars were the most important parameters in fuel consumption, respectively. Depending on the evaluation of the performance of those methods by Evaluation Node of Clementine, it has been found that C5.0 was the most efficient method in prediction of fuel consumption among others. However, the evaluation charts (Gain, Profit, ROI, etc.) have shown that neural network could have better results in prediction in some conditions.
WIT Transactions on the Built Environment 130, pp. 201-211 , 2013
This paper describes the first results of a research project where the main focus is to implement a Decision Support System (DSS) to optimise energy consumption of rail systems. In order to achieve this objective, we implement an optimisation module for the design of energy-efficient driving strategies, in terms of speed profiles, that requires a railway simulation model as a subroutine. Here we focus on the general framework of the optimisation module and on the calibration of the railway simulation model .All elaborations are implemented in a MatLab environment, aiming at defining possible energy-efficient speed profiles, in accordance with energy-saving strategies, through optimised speed profile parameters, in terms of acceleration, target speed, deceleration, coasting phase, and driving behaviour, represented by the jerk. The model is calibrated on real data recorded on a double track section of a railway line in the city of Naples (Italy). Initial results show that consumption is very variable with the speed profile and with driver behaviour, but the model is able to reproduce the average consumption of each driving strategy and should be able, within the DSS, to suggest the best driving strategies for each rail section. Keywords: energy-efficient driving, railway systems, optimisation models.
Applied Energy, 2015
Hybrid and electric powertrains and alternative fuels (e.g., compressed natural gas (CNG), biodiesel, or hydrogen) can often reduce energy consumption and emissions from transit bus operations relative to conventional diesel. However, the magnitude of these energy and emissions savings can vary significantly, due to local conditions and transit operating characteristics. This paper introduces the transit Fuel and Emissions Calculator (FEC), a mode-based life-cycle emissions modeling tool for transit bus and rail technologies that compares the performance of multiple alternative fuels and powertrains across a range of operational characteristics and conditions. The purpose of the FEC is to provide a practical, yet technically sophisticated tool for regulatory agencies and policy analysts in assessing transit fleet options. The FEC’s modal modeling approach estimates emissions as a function of engine load, which in turn is a function of transit service parameters, including duty cycle (idling and speed-acceleration profile), road grade, and passenger loading. This approach allows for customized assessments that account for local conditions. Direct emissions estimates are derived from the scaled tractive power (STP) operating mode bins and emissions factors employed in the U.S. EPA’s MOVES (MOtor Vehicle Emissions Simulator) model. Life-cycle emissions estimates are calculated using emissions factors from the GREET (Greenhouse Gases, Regulated Emissions, and Energy Use in Transportation) model. The case study presented in this paper applies the FEC to second-by-second GPS position data collected from buses operating in metropolitan Atlanta, GA. These operations, from two different transit agencies, feature distinctly different transit service types: local transit bus operations and longer-distance express bus operations. The results illustrate that the decision as to which bus technology-fuel combination produces the least greenhouse gas emissions is a function of location and route characteristics. For the express bus operations monitored, the case study shows that CNG vehicles offer greater emissions reductions than Biodiesel (B20). For local bus services, battery electric buses show the greatest emissions savings in the fuel cycle, as long as range limitations can be met for the specific routes. The amount of these emissions savings is, however, highly dependent on the power generation mix. Among CNG, B20, parallel hybrid, series hybrid, and fuel cell buses, the least emitting option varies by location, due to complex interactions of factors such as duty cycle, meteorology, and terrain.
Application of Artificial Neural Network to Predict Exhaust Emissions from Road Transport
International Journal of Scientific and Technological Research, 2018
Vehicle manufacturers have to meet the standards due to the emission standard limitations. For this reason, every new vehicle must satisfy the limits of emission regulations by passing the driving cycle test accepted by their markets. However, even the new cars satisfy emission limits, our environment is being polluted more than expectations due to the old vehicles used in transportations and unrepresentative driving cycle for real world conditions so that real time exhaust emissions were analyzed in this study. It is aimed to calculate the exhaust gas released by road transports by using IPCC second approach method in Istanbul. Then an artificial neural network model was developed to predict a correlation between real-time exhaust emissions and vehicle number, mean speed. With using different training functions, it is demanded to define the optimum percentage error between the target and the predicted values. It was observed that the ANN model can predict exhaust gases with correla...