Forecasting overhaul or replacement intervals based on estimated system failure intensity

Abstract

System reliability can be expressed in terms of the pattern of failure events over time. Assuming a nonhomogeneous Poisson process, and Weibull intensity function for complex repairable system failures, the degree of system deterioration can be approximated. Maximum likelihood estimators (MLEs) for the system Rate of Occurrence of Failure (ROCOF) function are presented. Evaluating the integral of the ROCOF over annual usage intervals yields the expected number of annual system failures. By associating a cost of failure with the expected number of failures, budget and program policy decisions can be made based on expected future maintenance costs. Monte Carlo simulation is used to estimate the range and the distribution of the net present value and intemal rate of return of alternative cash flows based on the distributions of the cost inputs and confidence intervals of the MLEs. (AN)