Prediction of remaining Useful lifetime (RUL) of turbofan engine using machine learning

Abstract

One of the most important factors in the field of flying is the maintenance of the aircraft engine, that is because of the accidents that happened more than once. This requires a knowledge not only in the system of the aircraft engines, but also how they work and how their performance degrades over time. This drives us to the prediction field where machine learning plays an important role in analyzing and the data measurements from the equipment and attempt to predict any failure that could happen. In this thesis a study of prediction of the remaining useful life (RUL) of aircraft’s turbo fan engine has been investigated by bringing a dataset from turbo fan engine from the Prognostics Data Repository of NASA and using Principal Component Analysis (PCA) and Independent Component Analysis (ICA) techniques for data analytics and preprocessing, then selecting two machine learning algorithms Random Forest and Gradient Boosted Machine (GBM) so that a model can be trained. The idea is to develop a model to estimate the remaining useful life of the functionality of the turbofan engine and predict failure before it actually happens.