Remaining Useful Life Prediction of an Aircraft Turbofan Engine Using Deep Layer Recurrent Neural Networks

The turbofan engine is a pivotal component of the aircraft. Engine components are susceptible to degradation over life their operation, which affects reliability and performance an engine. In order direct necessary maintenance behavior, remaining useful prediction key. This research uses machine learning provide framework for aircraft’s (RUL) based on entire cycle data deterioration parameter (ML). For engine’s lifetime assessment, Deep Layer Recurrent Neural Network (DL-RNN) model presented. suggested method compared Multilayer Perceptron (MLP), Nonlinear Auto Regressive with Exogenous Inputs (NARX), Cascade Forward (CFNN), as well Prognostics Health Management (PHM) conference Challenge dataset NASA’s C-MAPSS dataset. Mean Absolute Error (MAE) Root Square (RMSE) calculated both datasets, values in range 0.15% 0.203% DL-RNN, whereas other three topologies, they 0.2% 4.8%. Comparative results show better predictive accuracy respect ML algorithms.