Please use this identifier to cite or link to this item:

http://hdl.handle.net/10609/99386
Title: Modelos de clasificación para incidencias en entornos industriales con datos no balanceados
Author: Martínez Raya, José Manuel
Director: Casas Roma, Jordi
Tutor: Parada Medina, Raúl
Keywords: data mining
machine learning
anomaly detection
automation
Issue Date: 12-Jun-2019
Publisher: Universitat Oberta de Catalunya (UOC)
Abstract: At the moment, in the industrial and technological sector it is spoken of the fourth industrial revolution. A new paradigm where the factories of the future will be automated, digital, intelligent, flexible, sustainable and more human. An important point will be to predict possible errors and faults that can be found throughout the entire production process, from the reception of raw materials to the finished product. The tendency is that the process can be fully automated, where neither the human component has a supervisory role. They will be the same devices, automata, controlled by an IA capable of predicting errors and maintaining production at levels of excellence. But first, to reach this point, one must understand and identify the reason for some errors in the manufacturing process, in order to avoid them and improve the quality of the final product. Creating a classification model will help us optimize the performance of the machines and will be the first step for predictive maintenance to avoid future failures.
Language: Spanish
URI: http://hdl.handle.net/10609/99386
Appears in Collections:Bachelor thesis, research projects, etc.

Share:
Export:
Files in This Item:
File Description SizeFormat 
jmartinezrayTFM0619memoria.pdfMemoria del TFM3.06 MBAdobe PDFView/Open

This item is licensed under a Creative Commons License Creative Commons