A FULL HISTORY PROPORTIONAL HAZARDS MODEL FOR PREVENTIVE MAINTENANCE SCHEDULING

This paper is concerned with the development of a realistic preventive maintenance (PM) scheduling model. A heuristic approach for implement ing the semi-parametric proportional-hazards model (PHM) to schedule t he next preventive maintenance interval on the basis of the equipment' s full condition history is introduced. This heuristic can be used wit h repairable systems and does not require the unrealistic assumption o f renewal during repair, or even during PM. Two PHMs are fitted, for t he life of equipment following corrective work and the life of equipme nt following PM, using appropriate explanatory variables. These models are then used within a simulation framework to schedule the next prev entive maintenance interval. Optimal PM schedules are estimated using two different criteria, namely maximizing availability over a single P M interval and over a fixed horizon. History data from a set of four p umps operating in a continuous process industry is also used to demons trate the proposed approach. The results indicate a higher availabilit y for the recommended schedule than the availability resulting from ap plying the optimal PM intervals as suggested by using the conventional stationary models. (C) 1997 John Wiley & Sons, Ltd.