Please use this identifier to cite or link to this item: http://hdl.handle.net/10609/99187
Title: Detección y prognosis de anomalías aplicada a máquinas industriales
Author: Castilla Parrilla, Fernando de
Director: Casas-Roma, Jordi  
Tutor: Parada Medina, Raúl  
Abstract: The use of data mining and machine learning techniques in the industrial framework, applied to the machinery that forms the processes, represents a significant saving in maintenance costs, as well as a high impact on production thanks to the early detection of problems that cause unavailability of these equipment. Through the identification of anomalous events that have occurred on these devices throughout their historical operation data, the objective of predicting them in the future with sufficient anticipation and confidence, to plan the repair or replacement of the equipment prior to the failure, with a prior lower economic cost. In addition, obtaining a health index that measures the performance of the machines is essential to plan repair actions on them. The project has been raised on a data set of more than 2 million records with information on the operation of 1900 machines during several years of operation.
Keywords: industrial machines
anomaly detection
failure prediction
Document type: info:eu-repo/semantics/masterThesis
Issue Date: 9-Jun-2019
Publication license: http://creativecommons.org/licenses/by-nc-nd/3.0/es/  
Appears in Collections:Bachelor thesis, research projects, etc.

Files in This Item:
File Description SizeFormat 
fernandodecastillaTFM0619memoria.pdfMemoria del TFM703,09 kBAdobe PDFThumbnail
View/Open

fernandodecastillaTFM0619presentación.mp4

Presentación del TFM179,02 MBMP4View/Open
Share:
Export:
View statistics

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