Computational Technology Resources - CCP

P. Martínez¹, R. Insa¹, P. Salvador¹ and A. Rovira²

¹Department of Transport Engineering and Infrastructure, Polytechnic University of Valencia, Spain
²Department of Mechanical Engineering and Materials, Polytechnic University of Valencia, Spain

doi:10.4203/ccp.104.245

purchase the full-text of this paper

, "Estimation of Train Energy Consumption in Different Operational Scenarios by means of a Neural Network", in J. Pombo, (Editor), "Proceedings of the Second International Conference on Railway Technology: Research, Development and Maintenance", Civil-Comp Press, Stirlingshire, UK, Paper 245, 2014. doi:10.4203/ccp.104.245

Keywords: diesel consumption, energetic efficiency, neural networks, railways, flow meter, train velocity.

Summary

This paper presents the development, training and validation of a neural network capable of modelling the fuel consumption of a diesel train. Real consumption data was measured in the Valencia-Alcoy and Valencia-Cuenca lines (Spain) and used to train the network. Several input variables were tested, including train speed and acceleration, engine traction, engine revolutions, track slope, etc. It was found that the combination of train speed and engine revolutions provides the best solution, yielding a correlation over 0.95 and a ratio between the network Mean Square Error and the data variance under 10%. The network, thus trained, provided a rather good fit with the actual consumption data as it modelled the evolution of the consumption along the whole journey. Overall modelled consumption was also very similar to the measured one. These results prove that neural networks have a great potential as tools to calculate, assess and improve the energetic efficiency of railways.

purchase the full-text of this paper (price £20)

go to the previous paper
go to the next paper
return to the table of contents
return to the book description
purchase this book (price £65 +P&P)

	Computational & Technology Resources an online resource for computational, engineering & technology publications
	not logged in - login
Front Page Browse CCP CSETS CTR IJRT Other Authors Search Purchase Guide FAQ Contact us	Civil-Comp Proceedings ISSN 1759-3433 CCP: 104 PROCEEDINGS OF THE SECOND INTERNATIONAL CONFERENCE ON RAILWAY TECHNOLOGY: RESEARCH, DEVELOPMENT AND MAINTENANCE Edited by: J. Pombo Paper 245 Estimation of Train Energy Consumption in Different Operational Scenarios by means of a Neural Network P. Martínez¹, R. Insa¹, P. Salvador¹ and A. Rovira² ¹Department of Transport Engineering and Infrastructure, Polytechnic University of Valencia, Spain ²Department of Mechanical Engineering and Materials, Polytechnic University of Valencia, Spain doi:10.4203/ccp.104.245 purchase the full-text of this paper Full Bibliographic Reference for this paper , "Estimation of Train Energy Consumption in Different Operational Scenarios by means of a Neural Network", in J. Pombo, (Editor), "Proceedings of the Second International Conference on Railway Technology: Research, Development and Maintenance", Civil-Comp Press, Stirlingshire, UK, Paper 245, 2014. doi:10.4203/ccp.104.245 Keywords: diesel consumption, energetic efficiency, neural networks, railways, flow meter, train velocity. Summary This paper presents the development, training and validation of a neural network capable of modelling the fuel consumption of a diesel train. Real consumption data was measured in the Valencia-Alcoy and Valencia-Cuenca lines (Spain) and used to train the network. Several input variables were tested, including train speed and acceleration, engine traction, engine revolutions, track slope, etc. It was found that the combination of train speed and engine revolutions provides the best solution, yielding a correlation over 0.95 and a ratio between the network Mean Square Error and the data variance under 10%. The network, thus trained, provided a rather good fit with the actual consumption data as it modelled the evolution of the consumption along the whole journey. Overall modelled consumption was also very similar to the measured one. These results prove that neural networks have a great potential as tools to calculate, assess and improve the energetic efficiency of railways. purchase the full-text of this paper (price £20) go to the previous paper go to the next paper return to the table of contents return to the book description purchase this book (price £65 +P&P)
Back to top	©Civil-Comp Limited 2023 - terms & conditions