SciELO - Scientific Electronic Library Online

vol.28 issue3Factors of Leadership in the Gold Rush in the South Region of the EcuadorComparison of Numerical Solutions for a Mathematical Model of Theoretical Combustion and Conductivity Variation of Shell Palm in an Fixed Bed Reactor author indexsubject indexarticles search
Home Pagealphabetic serial listing  

Services on Demand




Related links

  • On index processCited by Google
  • Have no similar articlesSimilars in SciELO
  • On index processSimilars in Google


Información tecnológica

On-line version ISSN 0718-0764


GARCES, Diego A  and  CASTRILLON, Omar D. Design of Intelligent Technology to Identify and Reduce Downtime in a Production System. Inf. tecnol. [online]. 2017, vol.28, n.3, pp.157-170. ISSN 0718-0764.

This paper proposed a methodology based on an intelligent technique to analyze the failures in the different machines of a production line, in order to establish and identify the main variables that generate the greatest fraction of idle times in the system and to propose possible solutions. The development of the methodology was carried out in five steps. The first corresponds to the collection of information in a database; the second is the standardization of the description of the faults; the third is the application of data mining from the information collected; the fourth is the determination of the mathematical model to be applied; the fifth is to conclude from the results obtained. The tool used was WEKA (Waikato Environment for Knowledge Analysis) with the classification tree J48. The result of the proposed methodology in comparison with the current methodology, is positive, because it is achieved increase of 3.58 percentage points is achieved in the overall efficiency indicator. It is concluded that the tool is useful to identify and reduce idle times of a line of production.

Keywords : data mining; death time; maintenance; productions; WEKA; decision tree.

        · abstract in Spanish     · text in Spanish     · Spanish ( pdf )


Creative Commons License All the contents of this journal, except where otherwise noted, is licensed under a Creative Commons Attribution License