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
Keywords: industrial machines
anomaly detection
failure prediction
Issue Date: 9-Jun-2019
Publisher: Universitat Oberta de Catalunya (UOC)
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.
Language: Spanish
URI: http://hdl.handle.net/10609/99187
Appears in Collections:Bachelor thesis, research projects, etc.

Share:
Export:
Files in This Item:
File Description SizeFormat 
fernandodecastillaTFM0619memoria.pdfMemoria del TFM703.09 kBAdobe PDFView/Open
fernandodecastillaTFM0619presentación.mp4Presentación del TFM179.02 MBMP4View/Open

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