New methodology combining neural network and extended great deluge algorithms for the ATR-42 wing aerodynamics analysis

The fast determination of aerodynamic parameters such as pressure distributions, lift, drag and moment coefficients from the known airflow conditions (angles of attack, Mach and Reynolds numbers) in real time is still not easily achievable by numerical analysis methods in aerodynamics and aeroelasti...

Full description

Saved in:
Bibliographic Details
Published in:Aeronautical journal 2016-07, Vol.120 (1229), p.1049-1080
Main Authors: Ben Mosbah, A., Botez, R.M., Dao, T.-M.
Format: Article
Language:English
Subjects:
Aerodynamics
Aeroelasticity
Aeronautics
Aerospace engineering
Air flow
Aircraft
Algorithms
Angle of attack
Back propagation
Control systems
Controllers
Drag
Fuzzy logic
Heuristic
Industrial engineering
International conferences
Laboratories
Neural networks
Neurons
Numerical analysis
Numerical methods
Pressure distribution
Preventive maintenance
Propagation
Reynolds number
Sensors
Stress concentration
Tubes
Wind tunnel testing
Wind tunnels
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The fast determination of aerodynamic parameters such as pressure distributions, lift, drag and moment coefficients from the known airflow conditions (angles of attack, Mach and Reynolds numbers) in real time is still not easily achievable by numerical analysis methods in aerodynamics and aeroelasticity. A flight parameters control system is proposed to solve this problem. This control system is based on new optimisation methodologies using Neural Networks (NNs) and Extended Great Deluge (EGD) algorithms. Validation of these new methodologies is realised by experimental tests using a wing model installed in a wind tunnel and three different transducer systems (a FlowKinetics transducer, an AEROLAB PTA transducer and multitube manometer tubes) to determine the pressure distribution. For lift, drag and moment coefficients, the results of our approach are compared to the XFoil aerodynamics software and the experimental results for different angles of attack and Mach numbers. The main purpose of this new proposed control system is to improve, in this paper, wing aerodynamic performance, and in future to apply it to improve aircraft aerodynamic performance.
ISSN:0001-9240
2059-6464
DOI:10.1017/aer.2016.46