Recurrent neural networks for aerodynamic parameter estimation with Lyapunov stability analysis

Aircraft parameter estimation is crucial for designing accurate and reliable flight dynamic models, essential for integration into flight simulators and developing effective control laws. These parameters, encompassing aerodynamic characteristics, play a pivotal role in enhancing aircraft performanc...

Full description

Saved in:
Bibliographic Details
Published in:Systems science & control engineering 2024-12, Vol.12 (1)
Main Authors: Mohan George, Sara, Selvi, S. S., Raol, J. R.
Format: Article
Language:English
Subjects:
Aerodynamic characteristics
Aerodynamic stability
Aircraft
Aircraft control
aircraft parameter estimation
Aircraft performance
Algorithms
Asymptotic methods
Asymptotic properties
Bias
Computation
Control stability
Dynamic models
Flight simulators
Flight tests
Kalman filters
Lyapunov energy function
Neural networks
Nonlinearity
Parameter estimation
Parameter robustness
Performance measurement
Recurrent neural networks
Stability analysis
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Aircraft parameter estimation is crucial for designing accurate and reliable flight dynamic models, essential for integration into flight simulators and developing effective control laws. These parameters, encompassing aerodynamic characteristics, play a pivotal role in enhancing aircraft performance, safety and overall operational efficiency. This paper explores aircraft parameter estimation using two Recurrent Neural Network (RNN) approaches: (i) the weight-bias method (RNN-WB) and (ii) the gradient-based method (RNN-Gradient). RNN-WB is based on the Hopfield neural network and relies on pre-computation of weight and bias information, applying non-linearity to the states of the network. RNN-Gradient computes direct gradients and applies non-linearity to the error. Simulated flight data is employed in MATLAB implementations to assess estimation results, considering both performance metrics and computation time. The estimated parameters were also compared with estimates obtained from Unscented Kalman Filter (UKF). A novel methodology is introduced to establish the asymptotic stability of RNN-WB and RNN-Gradient methods, utilizing the normalized Lyapunov energy functional. The asymptotic stability ensures the reliability and robustness of these techniques for parameter estimation. The RNN-Gradient shows a 20% performance improvement over RNN-WB. Satisfactory simulation results from both algorithms provide a promising foundation for their potential applications to real flight test data.
ISSN:2164-2583
2164-2583
DOI:10.1080/21642583.2024.2363387