Evaluation of aircraft engine performance during takeoff phase with machine learning methods

Abstract

During the takeoff phase, aircraft engines reach maximum speed and temperature to achieve the required thrust. Due to these harsh operating conditions, the performance of aircraft engines may decrease. This decrease in performance increases both fuel consumption and environmental damage. Reducing or eliminating the damages caused by aircraft is among the objectives of ICAO. In order to achieve this goal, aircraft engines are compulsorily tested, evaluated by experts and certified. The data obtained during the test process is recorded and stored in the engine emission databank (EEDB). During the takeoff phase, there is no system that can evaluate aircraft engines without dismantling and without expert knowledge. In this study, EEDB 2019 and 2021 takeoff phase data sets were used. Fuel flow T/O parameter is an important parameter used both in the calculation of aircraft emissions and in the evaluation of engine performance. Gaussian process regression (GPR), support vector machine (SVM) and multilayer perceptron (MLP) models were used to estimate the fuel flow T/O parameter. The results obtained were compared according to error performance criteria and the best model was selected. In MATLAB® environment, confidence intervals were plotted with the estimated fuel flow T/O value at 99% confidence level. This study demonstrates that the performance evaluation of aircraft engines during the takeoff phase can be performed without the need for expert knowledge.