por Jesús Ferrero Bermejo, Juan Francisco Gómez Fernández, Fernando A. Olivencia Polo, Pablo Martínez-Galán and Adolfo Crespo Márquez, University of Seville, Ingeman 12 de junio, 2018 XML
< Volver

The recent and remarkable use of Artificial Intelligence (AI) techniques, and particularly, of data mining, allows the improvement of industrial processes through pattern analysis. These tools become very useful when considering condition-based maintenance (CBM) processes, where it is necessary to detect the inflection point in normal operation conditions. In this paper, a novel methodology for CBM is proposed, consisting of 3 data mining techniques: Artificial Neural Networks (ANN), Support Vector Machines (SVM) and Random Forests (RF). Initial analysis of the experiment outcomes suggests that it is recommended to continue the researching efforts in this field because of the improvement obtained in predictive maintenance.

Introduction
European standard EN13306-2011 defines maintenance as the “combination of technical, administrative and management actions, throughout an asset lifecycle, intended to keep or restore to a required operational state”.
The goal of maintenance process is that the asset performs its required function without losses, which is a rather complicated mission.
Therefore, it is necessary to develop techniques that support assets life extension with optimum performance, mitigating failure rate, or, at least, reducing failure impact. Moreover, it is needed the deployment of techniques that are able to anticipate failure occurrence.

Noticias relacionadas

comments powered by Disqus

Utilizamos cookies propias y de terceros para analizar nuestros servicios y mostrarle publicidad relacionada con sus preferencias en base a un perfil elaborado a partir de sus hábitos de navegación (por ejemplo, páginas visitadas o videos vistos). Puedes obtener más información y configurar sus preferencias.

Configurar cookies

Por favor, activa las que quieras aceptar y desactiva de las siguientes las que quieras rechazar. Puedes activar/desactivar todas a la vez clicando en Aceptar/Rechazar todas las cookies.

Aceptar/rechazar todas
Cookies Analíticas

Cookies que guardan información no personal para registrar información estadística sobre las visitas realizadas a la web.

Cookies de Marketing

Cookies necesarias para determinadas acciones de marketing, incluyendo visualización de vídeos provenientes de plataformas como Youtube, Vimeo, etc. y publicidad de terceros.

Cookies de Redes Sociales

Cookies relacionadas con mostrar información provenientes de redes sociales o para compartir contenidos de la web en redes sociales.