Please use this identifier to cite or link to this item:
Title: Artificial neural networks applied to the measurement of lateral wheel-rail contact force: A comparison with a harmonic cancellation method
Authors: Urda, Pedro
Aceituno, Javier F.
Muñoz, Sergio
Es, José L.
Abstract: This paper presents a method for the experimental measurement of the lateral wheel-rail contact force based on Artificial Neural Networks (ANN). It is intended to demonstrate how an Artificial Intelligence (AI) method proves to be a valid alternative to other approaches based on sophisticated mathematical models when it is applied to the wheel-rail contact force measurement problem. This manuscript addresses the problem from a computational and experimental approach. The artificial intelligence algorithm has been experimentally tested in a real scenario using a 1:10 instrumented scaled railway vehicle equipped with a dynamometric wheelset running on a 5-inch-wide track. The obtained results show that the ANN approach is an easy and computationally efficient method to measure the applied lateral force on the instrumented wheel that requires the use of fewer sensors.
Keywords: Artificial neural network
Multibody system
Contact force measurement
Scaled railway vehicle
Dynamometric wheelset
Experimental validation
Issue Date: 2020
metadata.dc.description.sponsorship: Conserjería de Economía, Conocimiento, Empresas y Universidad de la Junta de Andalucía. Project reference US-1257665. Project: 2020/00000096.
Publisher: ELSEVIER
Appears in Collections:DIMM-Artículos

Files in This Item:
File Description SizeFormat 
UrdaEtAl_ANN_2020_AcceptedManuscript.pdfAccepted_manuscript27,3 MBAdobe PDFView/Open

This item is protected by original copyright

Items in RUJA are protected by copyright, with all rights reserved, unless otherwise indicated.