Inter-engine variation analysis for health monitoring of aerospace gas turbine engines

This study investigates the development of a new inter-enginevariation analysis method for the purpose of Equipment healthmonitoring, in which the similarity - in both system behaviourand external disturbances - across multiple (sister) engines isleveraged. The sister engine provides a baseline descriptionof the engine under observation, such that the challenge becomesthe differentiation between normal inter-engine variationand the anomalous behaviour, bypassing the need todescribe highly complex engine dynamics. The inter-engineresiduals are modelled directly with input data from both engines,using previous healthy data for training. The trainedmodel is used to compensate known differences between realengines. Anomalous data is detected by comparison of thesimulated output with the true residuals. The method is demonstratedon a real data set containing both nominal, healthy enginedata, and engine data containing anomalies.