Basic probabilistic and statistical concepts for maintenance of parts and systems

Mathematical models are presented which are useful for determiningwhen replacement or maintenance is needed. In addition, techniquesfor assessing the efficacy of maintenance and/or overhaul arediscussed. Since the underlying concepts and techniques fornonrepairable items are relatively well known, attention isfocused on repairable items. Moreover, great emphasis is placedon the major differences between the concepts, probabilisticmodels, and statistical analysis techniques appropriate fornonrepairable and repairable items respectively. Such emphasisis still required because the superficial similarities betweennonrepairable and repairable items have contributed to the widespreaduse of poor terminology and notation which, in turn, make thesimilarities appear to be substantive, rather than just superficial.This vicious circle—-which is still evident in most currentreliability texts and standards—-must be broken, and thispaper is intended to contribute to this campaign. It is alsostressed that, even to the very limited extent that repairablesystems concepts and techniques are discussed in the literature,excessive emphasis is placed on reliability growth or improvement.This has resulted in even less understanding of basic notionsof repairable-systems deterioration, i.e. of basic conceptsassociated with systems maintenance. This paper focuses on conceptsconnected with systems maintenance to help rectify this imbalance.Nonetheless, it is also stressed that the same models (withdifferent parameters) can often be used for both situations.     

Modelling preventive maintenance for deteriorating repairable systems

This paper is concerned with practical methods for the analysisand modelling of data for repairable systems which are subjectto preventive maintenance (PM) and still have an increasingrate of occurrence of failures. Aspects of testing for trendand fitting a nonhomogeneous Poission process to data are discussedModels for scheduling preventive maintenance to minimize costor maximize availability are proposed. They show that the optimalPM cycle interval for these systems decreases with increasingequipment age. One-cycle and two-cycle finite-time-zone replacementmodels are also developed to decide the optimal time for replacingthe equipment in current use.     

Using proportional-intensities models to schedule preventive-maintenance intervals

This paper is concerned with developing realistic models todetermine preventive-maintenance (PM) schedules for complexsystems when data have been collected on failure times and PMinterventions along with down times and man-hours expended oneach. The aim is to develop procedures for analysing such datain order to identify relevant cost-availability models for optimallyscheduling PM, while allowing for system deterioration or improvement.We propose the use of a proportional-intensities model and considerthe addition of Bayesian methods to incorporate prior knowledgeabout regression coefficients. The paper discusses further aspectsof this approach, which include extending the model to covertime-dependent explanatory variables, and presents an applicationof the proportional-intensities model to actual reliabilitydata from major industrial plants.