Modeling the fuel flow-rate of transport aircraft during flight phases using genetic algorithm-optimized neural networks

Abstract Predicting the fuel consumption of transport aircraft is vital for minimizing the detrimental effects of fuel emissions on the environment, saving fuel energy sources, reducing flight costs, achieving more accurate aircraft trajectory prediction, and providing effective and seamless management of air traffic. In this study, a genetic algorithm-optimized neural network topology is designed to predict the fuel flow-rate of a transport aircraft using real flight data. This model incorporates the cruise flight phase and the fuel consumption dependency with respect to both the variation of true airspeed and altitude. Feed-forward backpropagation and Levenberg–Marquardt algorithms are applied, and a genetic algorithm is utilized to design the optimum network architecture regarding time and effort. The predicted fuel flow-rates closely match the real data for both neural network training algorithms. Backpropagation gives the best accuracy for the climb and cruise phases, whereas the Levenberg–Marquardt algorithm is optimal for the descent phase.

[1]  H. Troy Nagle,et al.  Performance of the Levenberg–Marquardt neural network training method in electronic nose applications , 2005 .

[2]  Gregg G. Fleming,et al.  Modeling of Terminal-Area Airplane Fuel Consumption , 2009 .

[3]  Andrzej Cichocki,et al.  Neural networks for optimization and signal processing , 1993 .

[4]  Goldberg,et al.  Genetic algorithms , 1993, Robust Control Systems with Genetic Algorithms.

[5]  Aydogan Savran,et al.  Intelligent adaptive nonlinear flight control for a high performance aircraft with neural networks. , 2006, ISA transactions.

[6]  Jonathan Love,et al.  Process Automation Handbook: A Guide to Theory and Practice , 2007 .

[7]  Marc A. Rosen,et al.  Relationship between fuel consumption and altitude for commercial aircraft during descent: Preliminary assessment with a genetic algorithm , 2012 .

[8]  Thomas Bräunl.  Embedded robotics - mobile robot design and applications with embedded systems (2. ed.) , 2003 .

[9]  C. Ochoa-Martínez,et al.  Prediction of mass transfer kinetics during osmotic dehydration of apples using neural networks , 2007 .

[10]  Trevor M. Young,et al.  Simplified Thrust and Fuel Consumption Models for Modern Two-Shaft Turbofan Engines , 2008 .

[11]  B. P. Collins,et al.  Estimation of aircraft fuel consumption , 1982 .

[12]  Vijander Singh,et al.  ANN-based estimator for distillation using Levenberg-Marquardt approach , 2007, Eng. Appl. Artif. Intell..

[13]  Antonio A. Trani,et al.  A Neural Network Model to Estimate Aircraft Fuel Consumption , 2004 .

[14]  A. Chipperfield,et al.  Introduction to genetic algorithms , 1997 .

[15]  David J. Montana,et al.  Neural Network Weight Selection Using Genetic Algorithms , 2002 .

[16]  Aydan Cavcar,et al.  Aero-Propulsive Modeling of Transport Aircraft for Air Traffic Management Applications , 2004 .

[17]  Mitsuo Gen,et al.  Genetic algorithms and engineering design , 1997 .