Selección de variables relacionadas con fallos de chumaceras aplicando reconocimiento lógico combinatorio de patrones

The text experts in industrial diagnostics can provide essential information, expressed in mixed variables (quantitative and qualitative), about journal bearing faults. However, researches on feature selection for fault diagnostic applications disobey the important knowhow expertise. This work is focused on the identification of the most important features for fault identification in a steam turbine journal bearings. The values sets that support this research come from stored diagnostics and maintenance reports from an active thermoelectric power plant. Mixed data processing was accomplished by means of logical combinatorial pattern recognition tools. Confusion of raw features set was obtained by employing different comparison criteria. Subsequently, the testor and typical testor were identified and the informational weight of features that conform typical testor was also computed. The high importance of the mixed features that came from the expert knowledge was revealed by the obtained achievements.