Radial basis function network based iterative learning control method for robot arm

By adopting an iterative learning control method based on radial basis function networks, the problem of insufficient trajectory tracking accuracy of robotic arms under nonlinear systems and external disturbances is solved, achieving high-precision trajectory tracking and improving system stability, thus adapting to complex dynamic environments.

CN119795191BActive Publication Date: 2025-11-21NANJING TECH UNIV
1 Cites 0 Cited by

Patent Information

Application Number
CN202510201379.0
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2025-02-24
Publication Date
2025-11-21
Estimated Expiration
2045-02-24

AI Technical Summary

Technical Problem

Traditional iterative learning control methods suffer from insufficient trajectory tracking accuracy and robustness when dealing with nonlinear systems and external disturbances in robotic arms. They are particularly difficult to adapt effectively to unknown nonlinear characteristics and external disturbances in complex dynamic environments.

Method used

An iterative learning control method based on radial basis function networks is adopted. By constructing a dynamic model of the robotic arm system, designing the radial basis function network and dynamic learning gain, and combining feedback control and nonlinear compensation, the trajectory error is optimized. The stability and error convergence of the system are analyzed using Lyapunov stability theory.

Benefits of technology

It achieves high precision and rapid error convergence in robotic arm trajectory tracking, enhances the system's adaptability and robustness in complex dynamic environments, and improves trajectory tracking accuracy and control system stability.

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

Abstract

The application discloses a mechanical arm iterative learning control method based on a radial basis function network, which solves the limitations of traditional mechanical arm control methods in dealing with nonlinear characteristics and external disturbance problems in a complex dynamic environment. The method comprises the following steps: firstly, constructing a mechanical arm system dynamics model, and adopting a dynamic correction strategy to dynamically correct and optimize a reference trajectory; then, designing a radial basis function neural network to construct a nonlinear compensation term, and designing dynamic weight parameters and dynamic learning gains for optimizing the performance of a controller; finally, designing an iterative learning controller, and verifying the stability and error convergence of the control algorithm. Through the radial basis function network, the dynamic adjustment strategy and the iterative learning strategy, the control precision, adaptability and error convergence speed of the mechanical arm system are improved.
Need to check novelty before this filing date? Find Prior Art