A Hybrid Neural Network‐Based Finite‐Time Sliding Mode Control for Robust Trajectory Tracking of UAVs With Dynamic Payloads.
Saved in:
| Title: | A Hybrid Neural Network‐Based Finite‐Time Sliding Mode Control for Robust Trajectory Tracking of UAVs With Dynamic Payloads. |
|---|---|
| Authors: | Elkhider, Siddig M.1 (AUTHOR) selnaiem@kfu.edu.sa, Habib, Mohammad Rezwan1 (AUTHOR) mohabib@wiley.com |
| Source: | International Journal of Aerospace Engineering. 9/2/2026, Vol. 2026, p1-16. 16p. |
| Subjects: | Drone aircraft, Dynamic loads, Radial basis functions, Lyapunov stability, Artificial neural networks, Sliding mode control, Damping (Mechanics) |
| Abstract: | This paper presents a novel hybrid control strategy, integrating a neural network (NN) with a finite‐time sliding mode control (FTSMC) scheme, to enhance the robust trajectory tracking performance of unmanned aerial vehicles (UAVs) operating under dynamic payload variations and external disturbances. Traditional sliding mode control (SMC) offers high robustness against uncertainties but often suffers from the undesirable chattering phenomenon, which can degrade system performance and lead to actuator wear. The proposed Hybrid NN‐FTSMC utilizes the universal approximation properties of radial basis function neural networks (RBFNNs) to estimate and compensate for unknown system dynamics and external disturbances in real‐time. This adaptive compensation allows the discontinuous switching gain of the robust term to be reduced so that it only needs to control the small NN approximation error rather than the full lumped uncertainty, thereby effectively minimizing chattering while maintaining the inherent robustness and finite‐time reaching properties of the FTSMC. A rigorous Lyapunov stability analysis is conducted to theoretically prove the uniform ultimate boundedness of the closed‐loop tracking errors and the NN weight estimation errors. The proposed controller is compared against three baselines, a classical proportional‐integral‐derivative (PID) controller, a classical SMC, and a conventional FTSMC, on a quadrotor model subjected to time‐varying mass and inertia and external disturbances. The evaluation includes the sliding‐surface evolution, the Lyapunov function and its derivative, the boundedness of the adaptive weights, and tests from multiple initial conditions. The results illustrate that the proposed Hybrid NN‐FTSMC achieves superior tracking accuracy, an approximately 98% reduction in control chattering relative to the FTSMC, and lower control effort, while preserving stability under time‐varying payloads. [ABSTRACT FROM AUTHOR] |
| Copyright of International Journal of Aerospace Engineering is the property of Wiley-Blackwell and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
|
Full text is not displayed to guests.
Login for full access.
|
|
| Abstract: | This paper presents a novel hybrid control strategy, integrating a neural network (NN) with a finite‐time sliding mode control (FTSMC) scheme, to enhance the robust trajectory tracking performance of unmanned aerial vehicles (UAVs) operating under dynamic payload variations and external disturbances. Traditional sliding mode control (SMC) offers high robustness against uncertainties but often suffers from the undesirable chattering phenomenon, which can degrade system performance and lead to actuator wear. The proposed Hybrid NN‐FTSMC utilizes the universal approximation properties of radial basis function neural networks (RBFNNs) to estimate and compensate for unknown system dynamics and external disturbances in real‐time. This adaptive compensation allows the discontinuous switching gain of the robust term to be reduced so that it only needs to control the small NN approximation error rather than the full lumped uncertainty, thereby effectively minimizing chattering while maintaining the inherent robustness and finite‐time reaching properties of the FTSMC. A rigorous Lyapunov stability analysis is conducted to theoretically prove the uniform ultimate boundedness of the closed‐loop tracking errors and the NN weight estimation errors. The proposed controller is compared against three baselines, a classical proportional‐integral‐derivative (PID) controller, a classical SMC, and a conventional FTSMC, on a quadrotor model subjected to time‐varying mass and inertia and external disturbances. The evaluation includes the sliding‐surface evolution, the Lyapunov function and its derivative, the boundedness of the adaptive weights, and tests from multiple initial conditions. The results illustrate that the proposed Hybrid NN‐FTSMC achieves superior tracking accuracy, an approximately 98% reduction in control chattering relative to the FTSMC, and lower control effort, while preserving stability under time‐varying payloads. [ABSTRACT FROM AUTHOR] |
|---|---|
| ISSN: | 16875966 |
| DOI: | 10.1155/ijae/4259776 |
