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
RAPID LIFT AND DRAG PREDICTION TOOL WITH MULTI-LAYER PERCEPTRON MODEL FOR SUPERCRITICAL AIRFOILS
Download
Thesis_CanerATLI_jüri_sonrası_v2_CA.pdf
Date
2023-1-20
Author
Atlı, Caner
Metadata
Show full item record
This work is licensed under a
Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License
.
Item Usage Stats
233
views
303
downloads
Cite This
In the early stages of aircraft design, selecting the shape of parts such as wings and tails can be time-consuming. Typically, tools that can provide rapid predictions of aerodynamic coefficients are used in these stages to reduce the duration of the preliminary design phase. However, available tools and research cannot provide accurate and reliable solutions in transonic and fully turbulent flows. A new tool is developed to provide aerodynamic properties such as drag, lift, maximum lift, and drag divergence Mach number by utilizing machine learning methodologies. The tool consist of a reliable shape descriptor for airfoil shape based on Class Shape Function Transformation. Then a Multilayer Perceptron machine learning method is developed using high-accuracy CFD solution database and airfoil shape descriptions. Then, new airfoil shapes and aerodynamic data is produced consistently and accurately in the transonic and turbulent flow regime. In the end, we have achieved a solution accuracy with an R2 score of 0.9935 for validation set lift coefficient using the new tool. Predicted aerodynamic coefficients are drag coefficient, lift coefficient and drag divergence Mach number. The tool provides solutions for 27000 cases within seconds or angle of attack range of -2° to 8°.
Subject Keywords
Deep Learning
,
Rapid Predictions
,
Drag Divergence
,
Preliminary Design
URI
https://hdl.handle.net/11511/102113
Collections
Graduate School of Natural and Applied Sciences, Thesis
Suggestions
OpenMETU
Core
Generic trim analysis and simulation algorithm creation for design and optimization of the fixed wing aircraft
Özdemir, Mustafa; Kurtuluş, Dilek Funda (2021-09-10)
In order to design a fixed wing aircraft, certain phases are needed to perform. From these phases, trim analysis and simulation are very crucial for design process. Trim and simulation analysis enable to calculate performance and stability characteristics of the aircraft. After aerodynamic, weight and engine database creation, the next step is trim analysis and simulations. However, database creation phase requires a huge amount of computing time, and for the preliminary design phase it is needed to perform...
Steady-State CFD Analysis of 3D Bio-inspired Flapping Wing Models
Bektaş, Mürvet; Kurtuluş, Dilek Funda; Güler, Mehmet Ali (2018-07-11)
The aerodynamics of insects flying at low Reynolds numbers is considered for Micro Air Vehicles (MAV) designs. The aim of this study is to analyze different flapping wing models and to predict generated forces and vortices around the wings. The analyses are significant for understanding properties of flying animals like birds, insects and for improving MAVs more. For three insect species (namely, bumblebee, hawkmoth, and hummingbird), three dimensional (3D) wing models are numerically analyzed at different ...
FAST AERODYNAMIC ANALYSIS AND DESIGN OF A JET AIRCRAFT BY USING PANEL METHOD
Kumser, Fatma Zülal; Öztürk, Ümran; Kıldiş, Pamir; Adam, Ali Ata; Sezer Uzol, Nilay; Ertem, Sercan; Ayan, Erdem (2021-09-10)
Fast and parametrical aerodynamic analyses for design of high speed jet aircraft is important especially during the initial design phases. In this study, different wing/body configurations defined with specific geometrical parameters for a jet aircraft are analyzed by using the panel method solver PANAIR. The analysis and design process is automated for the geometry and panel mesh generation and by using the Design of Experiment (DoE) methodology. The aerodynamic analysis and design study is p...
Optimal Design of a Miniature Quad Tilt Rotor UAV
Kahvecioglu, Ahmet Caner; Alemdaroglu, Nafiz (2015-06-12)
This paper describes the design procedure of a convertible miniature (mini and micro) quad tilt rotor unmanned air vehicle (UAV), which has about 2 meters of wing span, one hour of mission time and 5 kilograms of total weight. The aircraft is driven by four brushless direct current motors, and the structure of it completely made of composite materials. When the wing and tail of the aircraft are dismounted, it operates as a quad- rotor with tilting rotors. The aircraft is planned to carry a gimbal camera wei...
Design and analysis of a hybrid trailing edge control surface of a fully morphing unmanned aerial vehicle wing
Tunçöz, İlhan Ozan; Yaman, Yavuz; Department of Aerospace Engineering (2015)
In this thesis, the design and analysis of a hybrid trailing edge control surface of a fully morphing unmanned aerial vehicle wing having the ability to perform both camber and decamber morphings were conducted. The design of the control surface was done by CATIA V5-6R2012 package program. Two distinct designs, so-called open cell and closed cell designs were initially analyzed via Finite Element Method by using the commercial software ANSYS Workbench v14.0 in in-vacuo condition. Several trade-off studies i...
Citation Formats
IEEE
ACM
APA
CHICAGO
MLA
BibTeX
C. Atlı, “RAPID LIFT AND DRAG PREDICTION TOOL WITH MULTI-LAYER PERCEPTRON MODEL FOR SUPERCRITICAL AIRFOILS,” M.S. - Master of Science, Middle East Technical University, 2023.