Intelligent learning control method of fractional order nonlinear system under communication limitation

Through the intelligent learning control method, combined with the neural network observer and the Backstepping method, an adaptive neural network event-triggered fault-tolerant controller is constructed, which solves the tracking performance problems of the fractional-order nonlinear system under external perturbation and actuator failures of communications, and avoids the occurrence of the Zeno phenomenon, realizing the boundary of the system signal and saving communication resources.

CN119739037AActive Publication Date: 2025-04-01SICHUAN UNIV
7 Cites 0 Cited by

Patent Information

Application Number
CN202411882551.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-12-19
Publication Date
2025-04-01
Estimated Expiration
2044-12-19

AI Technical Summary

Technical Problem

In a fractional nonlinear system with limited communication, how to ensure the tracking performance of the system in the case of external disturbances and actuator failures and avoid the occurrence of Zeno phenomenon.

Method used

The intelligent learning control method is adopted, including building a state observer based on a radial basis function neural network, combining the Backstepping method and fractional-order Lyapunov stability theory, constructing an adaptive neural network event trigger fault-tolerant controller, and introducing a relative threshold event triggering strategy.

Benefits of technology

Ensure the tracking performance of fractional closed-loop system, make the tracking error converge to the neighborhood near the origin, and ensure the semi-global consistency of all signals in the system and ultimately bounded, while reducing the transmission frequency of the control signal and saving communication resources.

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

Abstract

The invention relates to the field of system control, and discloses an intelligent learning control method for a fractional-order nonlinear system under communication limitation, which comprises the following steps: constructing a networked fractional-order nonlinear system with external disturbance and uncertainty; identifying an unknown uncertain nonlinear function in the system by adopting a radial basis function neural network; constructing a compensation signal of the system, and designing a virtual controller, an actual neural network controller and a parameter adaptive law of the system in combination with a backstepping method and an instruction filter scheme; the stability of a closed-loop system is proved, it is ensured that tracking errors can be converged to a neighborhood near an original point, and it is ensured that all signals in the closed-loop system are semi-globally consistent and finally bounded. The innovative method has a wide application prospect in the field of automatic control systems, and is particularly suitable for processing systems with complex nonlinearity and uncertainty.
Need to check novelty before this filing date? Find Prior Art