SciELO - Scientific Electronic Library Online

 
vol.28 número6Solución Metaheurística para el Problema de Enrutamiento (RWA) en Redes de Ópticas de Multiplexación por División de Longitud de Onda (WDM)Sistema Bayesiano para la Predicción de la Diabetes índice de autoresíndice de assuntospesquisa de artigos
Home Pagelista alfabética de periódicos  

Serviços Personalizados

Journal

Artigo

Indicadores

Links relacionados

  • Em processo de indexaçãoCitado por Google
  • Não possue artigos similaresSimilares em SciELO
  • Em processo de indexaçãoSimilares em Google

Compartilhar


Información tecnológica

versão On-line ISSN 0718-0764

Resumo

RAMIREZ, Jhon A; SARMIENTO, Henry O  e  LOPEZ-LEZAMA, Jesús M. Design of a Fuzzy Classifier for Establishing the Functional States of a Medical Air Production System. Inf. tecnol. [online]. 2017, vol.28, n.6, pp.147-160. ISSN 0718-0764.  http://dx.doi.org/10.4067/S0718-07642017000600016.

This article presents the design of a fuzzy classifier to establish the functional states of a medical air production system. The implementation of fuzzy logic in the classifier allows an object to belong to multiple classes, previously defined, in the tuning of the classifier. For the design of the classifier, the process historical data was used and a pre-processing of the information was done by eliminating redundant information. The classes obtained were subjected to a multivariable graphical analysis. The classification obtained in the training allowed identifying all functional states useful for the monitoring of the process. All test data were accurately classified. The establishment of functional states based on the fuzzy classification is presented as an alternative of the use of artificial intelligence for the scheduling of actions in the maintenance engineering, from the diagnosis of the processes.

Palavras-chave : fuzzy classifier; functional states; medical air production.

        · resumo em Espanhol     · texto em Espanhol     · Espanhol ( pdf )

 

Creative Commons License Todo o conteúdo deste periódico, exceto onde está identificado, está licenciado sob uma Licença Creative Commons