Show/Hide Menu
Hide/Show Apps
Logout
Türkçe
Türkçe
Search
Search
Login
Login
OpenMETU
OpenMETU
About
About
Open Science Policy
Open Science Policy
Open Access Guideline
Open Access Guideline
Postgraduate Thesis Guideline
Postgraduate Thesis Guideline
Communities & Collections
Communities & Collections
Help
Help
Frequently Asked Questions
Frequently Asked Questions
Guides
Guides
Thesis submission
Thesis submission
MS without thesis term project submission
MS without thesis term project submission
Publication submission with DOI
Publication submission with DOI
Publication submission
Publication submission
Supporting Information
Supporting Information
General Information
General Information
Copyright, Embargo and License
Copyright, Embargo and License
Contact us
Contact us
Identification of the abnormal fuel consumption in a commercial flight by an artificial neural network surrogate model
Download
10499030.pdf
Date
2022-9-02
Author
Demirhan, Oğulcan
Metadata
Show full item record
This work is licensed under a
Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License
.
Item Usage Stats
379
views
347
downloads
Cite This
Since the 1980s, numerous fuel consumption modeling studies have been conducted in the literature. Lately, fuel efficiency studies have become more of an issue due to carbon emission and its consequence; global warming. In this study, a feed-forward neural network is modeled, and trained with high-fidelity simulation data (operational flight plans). Later, the actual flight data from Quick Access Recorder (QAR) is used for tuning the hyperparameters of the model. The ten models which have the least loss have been selected and subjected to test with a portion of QAR data. The best model has been selected at the end of the statistical comparison between these ten models. Finally, an identification process has been explained for the flights whose fuel consumption estimation errors exceed the three-sigma boundary. Although this model is built only by five fundamental parameters (takeoff weight, air distance, mean cruise Mach number, altitude parameter, and fuel mileage deviation), the accuracy level of the model is promising when compared to the studies in the literature. Moreover, the study proposes an additional method for the identification of abnormal fuel consumption.
Subject Keywords
Aircraft Fuel Consumption Modeling
,
Neural Networks
,
Surrogate Models
,
Medium-Fidelity Modeling
URI
https://hdl.handle.net/11511/99592
Collections
Graduate School of Natural and Applied Sciences, Thesis
Suggestions
OpenMETU
Core
Determination of kinetic parameters of different origin coals using software
Ertunc, Goker; Kök, Mustafa Verşan (2015-02-01)
In this study, combustion characteristics and kinetics of three coal samples are examined. A series of thermogravimetry (TG-DTG) and differential scanning calorimetry (DSC) measurements were carried out in non-isothermal conditions at heating rates of 5, 10, and 15 K min(-1). Reaction regions, peak and burn-out temperatures, mass loss, and heat of reactions of the samples were determined for each heating rate from TG-DTG and DSC curves. A variety of computational methods, available in the software developed...
Computation of instantaneous fuel consumption for the determination of combustion efficiency with special reference to coal briquette size
Altun, Naci Emre; Bagci, AS (Informa UK Limited, 2006-04-01)
This study comprises of the computation of instantaneous fuel consumptions as a straight means for the interpretation of combustion-related characteristics of coal. The model relies on the determination of the extent of combustion by the calculated fuel combustion amounts at specific instants in order to examine the oxidation behavior and possible influences governed by any variable of interest. In this context, coal briquettes prepared by varying dimensions with and without a volume constraint were evaluat...
Characterization of the MgO/GaSe0.5S0.5 heterojunction designed for visible light communications
Qasrawi, A. F.; AlGarni, S. E.; Hasanlı, Nızamı (2015-11-01)
In this study an optoelectronic design is reported and characterized. The device is made of p-type MgO solved in sodium silicate binder and n-type GaSe0.5S0.5 heterojunction. It is described by means of X-ray diffraction, optical absorption and reflection in the incident light wavelength range of 190-1100 nm and by means of dark and 406 nm laser excited current (I)-voltage (V) characteristics. The optical reflectance was also measured as a function of angle of incidence of light in the range of 35-80. The s...
Characterization and Development of Drilling Fluid Type for an Oil Field
Kök, Mustafa Verşan (Informa UK Limited, 2010-01-01)
In this study, different types of drilling fluids are developed and analyzed for a mature oil field. The optimum conditions were developed for shallow and deep formations. The experimental procedure that was followed for viscosity, fluid loss, density, and pH calculations is based on the standards dictated by API RP 13B. At the end of the experiments, it was also observed that for shallow depths, 0.2-0.3 lb of caustic soda will be enough for one barrel of drilling fluid. On the other hand, lignosulphanate t...
Synthesis and Cytotoxicity Studies on Novel Piperazinylacetamides
Bobtaina, Eman; GÜRDAL HAKGÖR, ENİSE ECE; Durmaz, Irem; Atalay, Rengül; YARIM YÜKSEL, MİNE (2019-01-01)
Background: In this study, nine novel compounds, bearing N-[2-(4-substituted piperazine-1-yl)acetyl]-N'-[bis-(4-fluorophenyl)methyl]piperazine structures were synthesized.
Citation Formats
IEEE
ACM
APA
CHICAGO
MLA
BibTeX
O. Demirhan, “Identification of the abnormal fuel consumption in a commercial flight by an artificial neural network surrogate model,” M.S. - Master of Science, Middle East Technical University, 2022.