Journal of Aeronautics & Aerospace Engineering
Open Access
ISSN: 2168-9792
ISSN: 2168-9792
Nima Hajimirza Amin, Armita Firoozi Fard, Reza Javadi, Ashkan Abdalisousan*
In the aviation industry, fuel efficiency and emissions reductions are critical, but safety and performance must also be maintained. Using predictive analytics, we can identify trends, patterns and inefficiencies in fuel consumption and optimize engine performance. Using machine learning algorithms, we develop an analytical model to predict fuel consumption on a Boeing 787-9 Dreamliner. To predict fuel consumption, we evaluate several machine learning algorithms, including General Linear Regression (GLR), random forest, gradient boosting and Artificial Neural Networks (ANN). A stepwise linear regression algorithm provided the best performance with a Root Mean Squared Error (RMSE) of 1.0532. Temperature, thrust, altitude and Mach number affect the Trent 1000 engine's fuel consumption. It is possible to identify inefficiencies and opportunities for improvement by predicting fuel consumption for different flight scenarios. We optimize engine performance and fuel efficiency to reduce fuel consumption and emissions while maintaining high safety and performance standards. In the aviation industry, predictive analytics can improve sustainability and inform greener strategies and policies. The aviation industry can benefit from machine learning algorithms for predicting fuel consumption and improving engine performance. Operators and policymakers in the aviation industry can use the predictive model developed in this research to predict other types of aircraft and engines. The results of this research can be used to develop strategies and policies aimed at reducing fuel consumption and emissions while maintaining safety and reliability.
Published Date: 2025-03-14; Received Date: 2024-03-04