Modelling competing risks and opportunistic maintenance with expert judgement

We look the use of expert judgement to parameterize a model for degradation, maintenance and repair by providing detailed information which is then calibrated at a higher level through course plant data. Equipment degradation provides signals by which inferences are made about the system state. These may be used informally through the use of red/yellow/green judgements, or may be based oil clear criteria from monitoring. Information from these signals informs the choices made about when opportunities for inspection or repair are taken up. We propose a stochastic decision model that can be used for two purposes: a) to gain an understanding of the data censoring processes, and b) to provide a tool that Could be used to assess whether maintenance opportunities should be taken or whether they should be put off to a following opportunity or scheduled maintenance. The paper discusses the competing risk and opportunistic maintenance modeling with expert judgement and the broad features of the model. Numerical examples are given to illustrate how the process works. This work is part of a larger study of power plant coal mills reliability.