A competing risk model for dependent and imperfect condition–based preventive and corrective maintenances

Abstract

This article develops a model for dependent and imperfect condition-based preventive and corrective maintenance actions. The approach is based on the combination of the intensity proportional repair alert, a competing risks-based model and the generalized renewal process. Typically, intensity proportional repair alert can identify either how preventive actions may modify the distribution of the time between critical failures or how corrective events may change the frequency of preventive maintenances, but this method fails to analyze the effectiveness of the maintenance actions because they are treated as being perfect. On the other hand, generalized renewal process is able to capture the quality of maintenance, classifying it as perfect, minimal or imperfect depending on the value of a rejuvenation parameter. However, generalized renewal process cannot distinguish how different types of maintenance influence each other as intensity proportional repair alert does. Therefore, the intensity proportional repair alert-generalized renewal process hybrid approach is proposed here to fill this gap. This article also develops the maximum likelihood estimators for the proposed model as well as a Monte Carlo-based algorithm to estimate the expected number of preventive and corrective maintenances over time. The proposed model is validated through two example applications for which the intensity proportional repair alert-generalized renewal process model results show close agreement with the failure datasets.

A Mixed Kijima Model Using the Weibull-Based Generalized Renewal Processes

“…As, in the cases of deteriorating(improving) systems, the hazard function is directly(inversely) proportional to the age, the better the interventions the lesser(greater) the virtual age, always decreasing hazard characteristics underlying the system. Several examples in literature, such as [ 2 – 5 ], and [ 6 ] make use of this reasoning.…”

“…Authors like [ 2 , 3 ], and [ 7 ] have resorted to the Weibull-based GRP (WGRP). In these cases, the parameters set of the WGRP is thus ( α , β , q ), representing, in this order, the scale, shape, and virtual age parameters.…”

“…To date, real world dynamical systems frequently involve different classes of interventions, thus impacting on the recent (Kijima Type I), complete (Kijima Type II) or intermediate history of the system (proposed mixed model). From literature, [ 2 ] presents a model that capture the rejuvenation parameter for two classes of intervention—corrective and preventive maintenances. This coupling is performed here by appending the class label of each intervention i , say y i , and the respective coefficients, say θ y i and (1 − θ y i ), in a linear combination between the Kijima Types I and II models.…”

A rolling horizon approach for production planning and condition-based maintenance under uncertain demand

“…in which C Ã is the expected maintenance cost per unit time in each PM cycle and deduced from equation (5). Similar to the advancement procedure, the cost change of the PM postponement can be calculated as…”

“…Much research that concentrates on optimizing the control limits and/or inspection intervals of CBM have been done. [4][5][6][7][8] On the one hand, unlike TBM that determines maintenance activities based on a probabilistic model of system failure, CBM makes maintenance decision based on the real-time condition of the system, which is more accurate. On the other hand, due to the development of sensor technology, the degradation behavior of the system can be easily monitored to predict failure events.…”