Resumen
In repairable systems, a fundamental aspect to be considered is predict the reliability of the systems being studied. However, the standard methods used to analyze reparable system data ignore the cumulative effect of stopping time to the repair and the heterogeneity of systems. Thus, this work explores a general class of frailty models in repairable systems that uses a term that allows to verify the effect of the accumulation of the occurrence of repairs and a term of frailty, characterized by the use of a random effect, that is, an unobservable random variable that represents information that could not or was not observed. The inferential method to estimate the parameters will be shown to models in repairable systems under minimal repair. For the proposed methodology, it will be considered simulation studies and applications to a sugarcane harvesters data set and a dump truck data set.