Energetic and exergetic efficiency modeling of a cargo aircraft by a topology improving neuro-evolution algorithm

Tolga Baklacioglu, Hakan Aydin and Onder Turan

Energy, 2016, vol. 103, issue C, 630-645

Abstract: An aircraft is a complex system that requires methodologies for an efficient thermodynamic design process. So, it is important to gain a deeper understanding of energy and exergy use throughout an aircraft. The aim of this study is to propose a topology improving NE (neuro-evolution) algorithm modeling for assessing energy and exergy efficiency of a cargo aircraft for the phases of a flight. In this regard, energy and exergy data of the aircraft achieved from several engine runs at different power settings have been utilized to derive the ANN (artificial neural network) models optimized by a GA (genetic algorithm). NE of feed-forward networks trained by a BP (backpropagation) algorithm with momentum has assured the accomplishment of optimum initial network weights as well as the improvement of the network topology. The linear correlation coefficients very close to unity obtained for the derived ANN models have proved the tight fitting of the real data and the estimated values of the efficiencies provided by the models. Finally, compared to the trial-and-error case, evolving the networks by GAs has enhanced the accuracy of the modeling simply further as the reduction in the MSE (mean squared errors) for the energy and exergy efficiencies indicates.

Keywords: Exergy; Energy; Cargo aircraft; Neuro-evolution algorithm; Artificial neural networks; Genetic algorithms (search for similar items in EconPapers)
Date: 2016
References: Add references at CitEc
Citations: View citations in EconPapers (6)

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0360544216302626
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:energy:v:103:y:2016:i:c:p:630-645

DOI: 10.1016/j.energy.2016.03.018

Access Statistics for this article

Energy is currently edited by Henrik Lund and Mark J. Kaiser

More articles in Energy from Elsevier
Bibliographic data for series maintained by Catherine Liu ().