A delay-time modelling of preventive maintenance (PM) of plant given limited PM data and selective repair at PM

This paper presents a maintenance-modelling case study of a plant manufacturing brake linings. A delay-time model is developed and applied to model and optimize preventive maintenance (PM). A key subsystem in the plant is used to illustrate the modelling process and management reaction. Defects identified at PM may not all be removed. This incomplete response to PM is a feature which has not been modelled before. The parameter values of the delay-time process are estimated from objective data from maintenance records of failures, using the method of maximum likelihood. This is aided by a theorem extending results on the NHPP arrival rate of failures in a perfect-inspection case to the non-perfect-inspection case. Problems of parameter estimation given inadequate data collected at PMs are discussed, and the necessity to augment objective data with subjective assessments is highlighted. Based upon the estimated model parameters and delay-time distribution, an inspection model is constructed to describe the relationship between the total unit downtime and the PM interval. The response of management is discussed.