Abstract
System reliability of an offshore power plant with several gas turbine engines is analyzed in this study to understand the failure intensity of a selected gas turbine engines under varying maintenance activities. A set of event data of a selected gas turbine engine is considered to identify system failure intensity levels, where unknown maintenance actions were implemented (i.e. various repairs disturb the failure rate). A non-homogeneous Poisson process (NHPP) is used to model the age dependent failure intensity of the same gas turbine engine and the maximum likelihood estimation (MLE) approach for calculating the respective model parameters is proposed. Several failure intensity rates (i.e. varying failure trends) in these models (i.e. during the system age of the gas turbine engine) are observed. Furthermore, these varying failure trend models are evaluated with actual failure events of the same gas turbine engine by considering two goodness-of-fit tests: Cramer-von Mises and Chi-square tests. Finally, system reliability of the gas turbine engine under the failure transition, failure intensity, mission reliability and mean time between failures (MTBF) is also discussed in this study.