Have a personal or library account? Click to login
Advanced Modeling of Uav Dynamics Using Artificial Neural Networks and the Output Error Method Cover

Advanced Modeling of Uav Dynamics Using Artificial Neural Networks and the Output Error Method

Acta Mechanica et Automatica
Volume 19 (2025): Issue 4 (December 2025)
By: Pedro JIMENEZ-SOLER,  Piotr LICHOTA and  Piotr FELISIAK  
Open Access
|Dec 2025

Figures & Tables

Fig. 1.

Multiplex FunCub Airplane [23]
Multiplex FunCub Airplane [23]

Fig. 2.

Flight Test in an R/C Model Runway
Flight Test in an R/C Model Runway

Fig. 3.

Flight Envelope for Tests Performed
Flight Envelope for Tests Performed

Fig. 4.

Bode magnitude plot of the pitching moment for optimum frequency range determination
Bode magnitude plot of the pitching moment for optimum frequency range determination

Fig. 5.

Longitudinal response dataset
Longitudinal response dataset

Fig. 6.

Schematic of Output Error Method [8]
Schematic of Output Error Method [8]

Fig. 7.

Schematic of Neural Network Training for Aerodynamic Coefficient Prediction
Schematic of Neural Network Training for Aerodynamic Coefficient Prediction

Fig. 8.

Schematic of a single Neuron in ANNs
Schematic of a single Neuron in ANNs

Fig. 9.

Time histories of measured (blue line) and estimated parameters (red line), using OEM method
Time histories of measured (blue line) and estimated parameters (red line), using OEM method

Fig. 10.

Time History of Estimated parameters: ANNs Prediction Cycle
Time History of Estimated parameters: ANNs Prediction Cycle

Fig. 11.

Comparison of CL, CD and Cm between OEM and ANN
Comparison of CL, CD and Cm between OEM and ANN

Aerodynamic non-dimensional coefficients

IDPar.ValueIDPar.ValeIDPar.Value
1CD00.01775CLV-0.00259Cmα-1.6173
2CDv0.01366CLα4.230510Cmq-8.0193
3CDα0.12237Cm00.044611Cmδe-1.4830
4CL00.15188CmV-0.0092

Aerodynamic non-dimensional coefficients comparison

IDParameterEstimated value OEMRelative error OEMEstimated value ANNsRelative error ANNs
1CD00.01760.62%0.0180.56%
2CDV0.01314.04%0.0132.94%
3CDα0.12170.50%0.1230.25%
4CL00.15240.42%0.1530.46%
5CLV-0.003540.80%-0.00324.00%
6CLα4.25090.48%4.2330.05%
7Cm00.04430.61%0.0451.12%
8CmV-0.00952.83%-0.01010.87%
9Cmα-1.56813.04%-1.6190.09%
10Cmq-6.971413.07%-7.9231.20%
11Cmδe-1.41634.50%-1.4920.61%
DOI: https://doi.org/10.2478/ama-2025-0076 | Journal eISSN: 2300-5319 | Journal ISSN: 1898-4088
Journal RSS Feed
Language: English
Page range: 673 - 682
Submitted on: Mar 28, 2025
|
Accepted on: Nov 27, 2025
|
Published on: Dec 19, 2025
Published by: Bialystok University of Technology
In partnership with: Paradigm Publishing Services
Publication frequency: 4 issues per year
Keywords:
Unmanned Aerial Vehicles (UAVs),
Output Error Method (OEM),
Artificial Neural Networks (ANNs),
Maximum Likelihood Estimation (MLE),
Machine Learning,
System Identification,
Aerodynamics,
Flight Mechanics
Related subjects:
Engineering,
Electrical engineering,
Electronics,
Mechanical engineering,
Mechanics,
Bioengineering and biomedical engineering,
Biomechanics,
Civil engineering,
Environmental engineering

© 2025 Pedro JIMENEZ-SOLER, Piotr LICHOTA, Piotr FELISIAK, published by Bialystok University of Technology
This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License.

Previous articleVolume 19 (2025): Issue 4 (December 2025)Next article