Optimization of replacement stocks using a maintenance programme derived from reliability studies of production systems

Abstract

This paper is the outcome of a study carried out in a nine‐cell flexible manufacturing unit which produces components for Diesel engine injection pumps. The study involved the monitoring and recording of the various types of failure which led to interruptions in production. The objective of the study was to design a maintenance system for the optimal management of replacement stocks, both from the technical and economic point of view. The design of this programme was based on matching a given statistical distribution (Weibull’s distribution, exponential, normal, log‐normal, or gamma) to the time between failures. By means of this fit, the basic system parameters were determined: average lifetime, failure rate, mean time between failures, mean time between inspections. Knowledge of these variables permits us to determine the frequency of inspections in relation to the level of reliability we require of the system. This information also enables us to establish a programme to determine which elements require inspection, the frequency of these inspections and the operations that need to be carried out.