一种基于自适应反馈的飞行器自主学习控制系统及方法
By combining adaptive feedback and the TD3 algorithm, autonomous learning control of the aircraft was achieved, solving the problem of autonomous tuning of multiple gain parameters and improving the overall performance and intelligence level of the flight control system.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- BEIJING AEROSPACE AUTOMATIC CONTROL RES INST
- Filing Date
- 2024-11-28
- Publication Date
- 2026-07-17
AI Technical Summary
In existing flight control systems, autonomous tuning of multiple gain parameters is quite difficult. Traditional methods rely on model accuracy and the rationality of control gain, and the design process is cumbersome and highly dependent on experience.
An autonomous learning control method for aircraft based on adaptive feedback is adopted. By establishing a longitudinal model, designing state feedback gain, and using the TD3 algorithm to train the agent, the agent autonomously obtains the nonlinear mapping relationship between the current flight state combination and the gain parameters, thereby realizing altitude/speed tracking and attitude stabilization control.
It improves the overall performance of the flight control system, including tracking accuracy, state variable magnitude, and actuator swing amplitude, reduces reliance on design experience, and enhances the efficiency and intelligence level of autonomous learning control.
Smart Images
Figure CN120762435B_ABST
Abstract
Citation Information
Patent Citations
Hypersonic aircraft composite control method utilizing state feedback and neural network
CN106896722A
Supersonic cruise height control method based on backstepping method
CN117519257A