Please use this identifier to cite or link to this item: http://hdl.handle.net/10609/132746
Title: Mantenimiento Prescriptivo a partir de la predicción de eventos anómalos
Author: González Martínez, Diego
Director: Casas-Roma, Jordi  
Tutor: Parada Medina, Raúl  
Abstract: Fourth Industrial Revolution, also called Industry 4.0, arises as an essential challenge to guarantee the continuity of production processes and foresee unexpected anomalous events, for this purpose it is essential to have prediction tools that allow minimizing the impact that these unexpected anomalies can lead into over supply chain, the cost, quality and safety at work. With the application of Data Mining and Machine Learning techniques we will build an nalytical model that allows the early detection of anomalous events in primary states that help us determine the most appropriate moment to maintenance on industrial equipment before they lead to a failure and consequently in unforeseen breakdowns. For that, we will establish the life cycle of the equipment by determining their health from the information obtained from the different sensors of each equipment. Design a real-time monitoring system to support decision-making and analysis of the main factors that can affect the useful life of each equipment and its operational performance.
Keywords: data mining
machine learning
predictive maintenance
industry 4.0
Document type: info:eu-repo/semantics/masterThesis
Issue Date: 16-Jun-2021
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 
gonmardTFM0621memoria.pdfMemoria del TFM3,56 MBAdobe PDFThumbnail
View/Open
gonmardTFM0621presentación.pdfPresentación del TFM2,55 MBAdobe PDFThumbnail
View/Open