Anti-aerodynamic disturbance multi-unmanned aerial vehicle fixed time neural adaptive formation control method

By employing a hierarchical control architecture and improved sliding mode control, the deterministic convergence and safety issues of multi-UAV formations under complex aerodynamic disturbances were resolved, achieving fast and stable formation control and improving the robustness of the system and the effectiveness of the neural network.

CN122086102AActive Publication Date: 2026-05-26HARBIN INST OF TECH
5 Cites 1 Cited by

Patent Information

Application Number
CN202610535657.0
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-04-22
Publication Date
2026-05-26
Estimated Expiration
2046-04-22

AI Technical Summary

Technical Problem

Existing multi-UAV formation control technologies struggle to achieve deterministic convergence when faced with complex coupled aerodynamic uncertainties and strict time window constraints. Furthermore, neural networks are prone to failure under large disturbances, making it impossible to guarantee the safety and effectiveness of formation flight.

Method used

A hierarchical control architecture is adopted, which combines distributed reference generation and robust tracking controller design. Radial basis function neural network is used to compensate for aerodynamic disturbances, and an improved non-singular fixed-time sliding mode control protocol is used to ensure that formation errors converge rapidly within a predefined safe area. An obstacle safety mechanism is integrated to prevent neural network approach failure.

Benefits of technology

It achieves deterministic convergence of formation error under complex aerodynamic disturbances, improves convergence speed and robustness, ensures flight safety and the effectiveness of neural networks, avoids system instability, and provides smooth and singular control inputs.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention relates to the technical field of multi-unmanned aerial vehicle cooperative control, and discloses an anti-aerodynamic disturbance multi-unmanned aerial vehicle fixed time neural adaptive formation control method, which comprises the following steps: constructing a hierarchical controller architecture, the inner ring is a fixed time terminal sliding mode controller with a three-time nonsingular smooth switching mechanism; a fixed time sliding mode surface with a cubic nonsingular smooth switching mechanism is configured to realize deterministic convergence, an adaptive RBF neural network is adopted to actively compensate aerodynamic disturbance, a security mechanism based on a barrier function is combined to constrain the state of an unmanned aerial vehicle in a security set, and the fixed time stability of the system is verified through Lyapunov analysis. Simulation results of formation of six unmanned aerial vehicles show that the convergence speed of the method is increased by 29.6%, the robustness is better, and safe, accurate and rapid formation control of multiple unmanned aerial vehicles under complex aerodynamic disturbance can be realized.
Need to check novelty before this filing date? Find Prior Art