Rough Set Based Gas Turbine Fault Isolation Study
Gas path fault isolation is one of the key techniques in Engine HealthManagement systems. In order to accomplish gas path fault isolationsuccessfully for a gas turbine engine, both an accurate off-design performancemodel and an effective fault isolation approach are necessary. In this thesis, twooriginal and useful contributions to knowledge are presented: a new gas turbineoff-design performance model adaptation approach and a new gas turbine faultisolation approach. This new adaptation approach uses optimal multiple scaling factors obtained byusing a Genetic Algorithm to scale inaccurate component characteristic maps ingas turbine performance models to improve their prediction accuracy in differentoff-design conditions. The major feature of this approach is that it provides non-linear map scaling and therefore is able to provide more effective adaptation. The new fault isolation approach can be used to discover knowledge hidden inengine fault samples, transfers that knowledge into rules, and then uses thoserules for fault isolation. In addition, it is also capable of selecting appropriatemeasurements for fault isolation, dealing with uncertainty caused bymeasurement noise. Enhanced fault signatures, which are represented by themeasurement deviations and their ranking pattern in terms of magnitude, aredeveloped to make gas turbine faults easier to distinguish and hence make thisfault isolation approach more effective. The new adaptation approach was applied to the off-design performance modeladaptation of a gas turbine, while the new fault isolation approach wasemployed for fault isolation in a gas turbine. The results show that the newadaptation approach is very effective in improving the prediction accuracy of off-design performance models and the new fault isolation approach is not onlyeffective in fault isolation but also in selecting measurements for isolation andgenerating fault isolation rules.