Prediction of the Jet Engine Performance Deterioration
This paper deals with performance deterioration modelling of a single spool gas turbine engine based on time-series methods. Towards this end, two univariate and multivariate methods, namely the Autoregressive Integrated Moving Average (ARIMA) and the Vector Autoregressive (VAR) schemes are applied to predict the Turbine Entry Temperature (TET) evolution during the flight cycles for maintenance purposes. In the VAR scheme, two engine process parameters i.e. the Turbine Entry Temperature (TET) and the Compressor Temperature are employed to achieve this prediction goal. The results show that employing multivariate modelling methods lead to better prediction horizons. For each method two scenarios are considered to demonstrate the effectiveness of the models.