Development of a numerical tool based in machine learning for the prediction of fatigue cracks in the rails of railway lines
Metadatos
Mostrar el registro completo del ítemcomunitat-uji-handle:10234/158176
comunitat-uji-handle2:10234/71324
comunitat-uji-handle3:10234/114762
comunitat-uji-handle4:
TFG-TFMEste recurso está restringido
Metadatos
Título
Development of a numerical tool based in machine learning for the prediction of fatigue cracks in the rails of railway linesAutoría
Tutor/Supervisor; Universidad.Departamento
Moliner Cabedo, Emmanuela; Universitat Jaume I. Departament d'Enginyeria Mecànica i ConstruccióFecha de publicación
2018-01-28Editor
Universitat Jaume IResumen
This end-of-degree project (TFG) arises from the work carried out during an internship of 6
months (from 06/18/2018 to 12/17/2018) in the French railway company Société nationale des
chemins de fer français (SNCF) ... [+]
This end-of-degree project (TFG) arises from the work carried out during an internship of 6
months (from 06/18/2018 to 12/17/2018) in the French railway company Société nationale des
chemins de fer français (SNCF) in Paris, France.
Rail contact fatigue plays an important role in the maintenance of rails. It is caused by the
repetitive passage of the wheels of the trains on the rails and it manifest itself by the
appearance of defects that can cause the rail to break over the time.
Historical data collected by SNCF over the years about fatigue defects can be used for the
prediction of fatigue defects in order to optimize maintenance procedures and reduce the
cost.
Therefore, in this end-of-degree project, a first proposal of this statistical prediction model will
be made. The main objective of the work being the development of a predictive statistical
model for the appearance of fatigue cracks in rails based in machine learning which should
estimate the probability of appearance of cracks throughout the years in a specific zone of a
railway line. [-]
Palabras clave / Materias
Descripción
Treball final de Grau en Enginyeria en Tecnologies Industrials. Codi: ET1040. Curs acadèmic: 2018/2019
Tipo de documento
info:eu-repo/semantics/bachelorThesisDerechos de acceso
http://rightsstatements.org/vocab/CNE/1.0/
info:eu-repo/semantics/restrictedAccess
info:eu-repo/semantics/restrictedAccess