Optimal Maintenance Decisions Over Unbounded Horizons on the Basis of ExpertJudgment

摘要

Due to a lack of data, many maintenace optimization models have to be initializedon the basis of expert judgement. Rather than eliciting the parameters of a continuous lifetime distribution, experts give more reliable answers when assessing a discrete lifetime distribution. If the prior uncertainty in the probabilities of failure per unit time is expressed in terms of a Dirichlet distribution, Bayes estimates can be obtained of three cost-based criteria to compare maintenenace decisions over unbounded time-horizons: (1) the expected average costs per unit time, (2) the expected discounted costs over an unbounded horizon, and (3) the expected equivalent average costs per unit time. The maintenance model presented here can be easily implemented and is illustrated by determining optimal age replacement and life cycle costing policies. (Copyright (c) 1995, Faculty of Technical Mathematics and Information, Delft).