Evaluación de las solicitudes de mantenimiento correctivo usando técnicas de agrupamiento y reglas de asociación

Translated title of the contribution: Evaluation of corrective maintenance requests using clustering techniques and association rules.

Antonio Miguel Cruz, Cameron Barr, Norberto Castilla Casado

Research output: Contribution to journalArticlepeer-review

Abstract

In this research association discovering and clustering techniques for the resolution of the low efficiency problem in the sterilization service in a hospital under study were used. The aim was to find and to discriminate the main causes of the problem under study and then to apply corrective solutions. To conduct this research the information contained in corrective maintenance work orders and service requests in the period under study (2002-2004) was collected. First a segmentation of the information was carried out using the indicator: corrective service request versus number of medical devices. The levels of the information segmentation were: equipment types, services or cost centre, original equipment manufacturer and models. Then the association discovery technique was used. It revealed that the main causes of low efficiency in sterilization service were: users’ training (errors in operation procedures), intrinsic failures in medical devices, and bad scheduled maintenance policies. Clustering technique uncovered the main causes of failures: malfunctioning of the power supply system (steam and water, in 75% of all cases). With the evidence obtained corrective actions were taken. The service requests dropped dramatically from 6.4 to 0.4 during the period 2005-2006.
Translated title of the contributionEvaluation of corrective maintenance requests using clustering techniques and association rules.
Original languageSpanish (Colombia)
Pages (from-to)65-76
Number of pages12
JournalRevista Ingeniería Biomédica
Volume2
Issue number3
StatePublished - 2008

All Science Journal Classification (ASJC) codes

  • Biomedical Engineering

Fingerprint

Dive into the research topics of 'Evaluation of corrective maintenance requests using clustering techniques and association rules.'. Together they form a unique fingerprint.

Cite this