Kalman based neural network analysis with resampling methods for longitudinal aerodynamic coefficient estimation

Date

2020-01-01

Author

Millidere, Murat
Kurt, Huseyin Burak
Balli, Hakan
Uğur, Ömür

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

234
views

0
downloads

© 2020, American Institute of Aeronautics and Astronautics Inc, AIAA. All rights reserved.Accurateness of the approximated aerodynamic characteristics of an unstable aircraft is considerably significant in flight control system design or high-fidelity flight simulator development. Classical system identification technique consist of the equation and output error methods which are strongly influenced by data quality. Accordingly, unsatisfactory results may be arisen due to measurement or process noise. Consequently, most of the engineers rely on feed forward neural network in order to cope with those undesired drawbacks. But, noisy data dramatically degrades the performance of neural network as well; thus, the Kalman filter based backpropagation algorithm is proposed. Neural network approach has many parameters, including the hyperparameters, which have to be searched for an optimal result. To determine these optimal parameters, the genetic algorithm is used. In this paper, it is aimed to estimate longitudinal aerodynamic characteristics of highly maneuverable unstable aircraft with the engaged control system for flight simulation data. For this purpose, F-16 aircraft is modelled using the aerodynamic database derived from a low-speed wind tunnel test. Successful results show the effectiveness of the proposed method. To assess neural network approach performance, the most common resampling methods are used and compared in order to choose the best for each longitudinal aerodynamic coefficient.

URI

https://hdl.handle.net/11511/69748

DOI

https://doi.org/10.2514/6.2020-3197

Collections

Graduate School of Applied Mathematics, Conference / Seminar

Suggestions

OpenMETU
Core

An adaptive flight controller design for a tilt-prop fixed wing uav for all flight modes Yayla, Metehan; Kutay, Ali Türker (2020-01-01) © 2020, American Institute of Aeronautics and Astronautics Inc, AIAA. All rights reserved.In this study, we propose an autonomous flight control strategy (which is valid for all flight modes including vertical flight, hover, and level flight) for a vertical takeoff and landing capable, tilt-prop, fixed wing, tricopter unmanned aerial vehicle. In the inner loop of proposed hierarchical architecture, desired control forces and moments are generated using adaptive control theory, and these forces and moments a...
Computational modelling and analysis of porous bleed holes at supersonic speeds Akar, Gökhan; Eyi, Sinan (2020-01-01) © 2020, American Institute of Aeronautics and Astronautics Inc, AIAA. All rights reserved.Shock Wave / Boundary Layer Interaction is an important issue that should be taken into account when studying inlet design. Bleed holes have traditionally been used to remove the lower momentum part of the boundary layer to avoid separation from adverse Shock Wave / Boundary Layer Interaction. In this study, modeling of porous bleed holes investigated in computational fluid dynamics on a flat plate with and without an ...
Computational fluid dynamics and proper orthogonal decomposition based control of flow over supersonic cavities Gelisli, Kubra Asena; Aradag, Selin; Tascioglu, Yigit; Özer, Mehmet Bülent (2019-01-01) © 2019, American Institute of Aeronautics and Astronautics Inc, AIAA. All rights reserved.A Computational Fluid Dynamics (CFD) study is conducted to investigate the unsteady, turbulent supersonic cavity flow characteristics and to control the severe effects of the flow field. Simulations of Mach 1.5 supersonic cavity flow with a length to depth ratio of 5.07 are performed using commercial ANSYS Fluent solver. Unsteady density-based Reynolds Averaged Navier-Stokes equations are modeled with standard k-ω turb...
Parametric design and investigation of grid fin aerodynamics in supersonic flow using computational fluid dynamics Dinçer, Erdem; Sezer Uzol, Nilay (2022-01-01) © 2022, American Institute of Aeronautics and Astronautics Inc, AIAA. All rights reserved.Recently, with the advances in modern missile industry, faster and more maneuverable missiles became fashionable. Designing fast and agile missiles requires efficient and strong control surfaces and grid fin is a candidate to fulfill this need. Grid fins are unconventional control surfaces, which has an outer frame supporting interior web structure. In this paper, “MICOM Grid Fin” wind tunnel experiments are used as th...
A modeling and simulation tool for safe store separation envelope generation using monte carlo simulations Unal, Kenan; Baran, Özgür Uğraş (2018-01-01) © 2018, American Institute of Aeronautics and Astronautics Inc, AIAA. All rights reserved.When an air released store is developed or undergoes substantial updates, integration to aircraft is realized through a certification process. One of the most important steps of the certification process is to determine safe separation envelope. For this process there are several approaches: full scale flight tests, computational fluid dynamics (CFD) simulation techniques and wind tunnel captive trajectory tests. Separ...

Citation Formats

M. Millidere, H. B. Kurt, H. Balli, and Ö. Uğur, “Kalman based neural network analysis with resampling methods for longitudinal aerodynamic coefficient estimation,” 2020, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/69748.