Machine and Deep Learning Models for the Prediction of Performance and Speed Regulation Parameters of a Turbojet Engine Using Electric Power Transfer

In this paper, we focus our attention on “Machine Learning and Deep Learning Models for Prediction of Performance and Speed Regulation Parameters of a Turbojet Engine Using Electric Power Transfer Concept”. The principal objective of the study is to implement and compare deep learning and machine learning models for the Prediction of Performance and Speed regulation Parameters of a Turbojet Engine Using the Electric Power Transfer Concept. The novelty of this work is the direct calculation of SFC and Net thrust without any sub-model with a good precision. The data for this study are from the CFM 56–3 turbojet engine equipped with a special EPT architecture. The work showed that the different models (Multi-Linear Regression, Random Forest, and Artificial Neural Networks) give reliable and precise results. Globally neural network model produces the most precise results (Except for LPTCN), and the Linear Regression model is the least precise. The ANN gives an Root Mean Square Error (RMSE) value between 0.19% and 7% of the range of the concerned variable, which is better than those observed in the literature. The results of this work could serve as the first tools for more optimal design and control of next-generation turbojets.