Modelling of Predictive Maintenance for a Periodically Inspected System

Predictive maintenance (PM) includes condition monitoring and prognosis of future system condition, where maintenance decision-making depends on the results of prediction. In this study, the modelling of PM is conducted. It is assumed that the system is periodically checked using imperfect measuring equipment. The decision rule for predictive check (PC) is formulated and expressions to calculate the probabilities of the right and wrong decisions are proposed. The effectiveness of PM is evaluated using the following indicators: average availability, average total downtime and downtime cost per unit time. The mathematical models are proposed to calculate the maintenance indicators for an arbitrary distribution of time to failure. The proposed approach is illustrated by determining the optimal number of PCs for a specific stochastic deterioration process. Numerical example illustrates the advantage of PM over corrective maintenance.