A delay-time model for repairable machinery: maximum likelihood estimation of optimum inspection intervals

A delay-time model is presented for a complex repairable systemin which defects arise according to a nonhomogeneous Poissonprocess. The focus of this paper is not on the resulting probabilisticmodel itself, but on the estimation of the model parametersand their errors from records of failure times and number ofdefects found at inspections of a machine which has been operatedfor some time under some (usually suboptimal) inspection regime.The likelihood function of the observed failure and inspectiondata is derived, and a general approach for estimating the optimuminspection interval is discussed. An example relating to themaintenance of medical equipment is used to illustrate the techniquesdescribed in the paper.