RBF neural network adaptive control method for multiple single mechanical arms

Abstract

The invention discloses an RBF neural network adaptive control method for multiple single mechanical arms. The method comprises the steps of: approximating an unknown nonlinear function in a mechanical arm system by a neural network; introducing a dynamic surface technique to design a first-order filter to solve the computational explosion caused by repeated derivation on a control in a backstepping method; and processing the unknown parameters and output limitation by a Nussbaum function and an obstacle Lyapunov function. The method does not require an accurate mechanical kinetic model, can completely eliminate the output error caused by unknown kinetic parameters and random interference, solves the problem that a model-based multi-single mechanical arm control scheme depends on a precise kinetic model, and improves the dynamic performance of the mechanical arm and the trajectory tracking accuracy of a joint space. Finally, the feasibility and effectiveness of the control method are verified by simulation examples.

Description

technical field [0001] The invention relates to the technical field of artificial intelligence and control, in particular to an RBF neural network adaptive control method for multi-single-arm manipulators with limited output, unknown parameters and random interference. Background technique [0002] With the continuous development of science and technology, multi-single-arm manipulators appear as a powerful tool in modern assembly line production work. The single-arm manipulator has the limitations of poor flexibility and low efficiency. In the relatively large handling, installation, maintenance and welding work, the single-arm manipulator has shown certain limitations in some aspects such as information collection, control and processing, and Because the multi-single-arm manipulator has strong coordination operation flexibility and large load capacity, it can complete tedious and diverse task requirements. Therefore, it is of great significance to study the multi-single-arm...

AI Technical Summary

Problems solved by technology

The single-arm manipulator has the limitations of poor flexibility and low efficiency. In the relatively large handling, installation, maintenance and welding work, the single-arm manipulator has shown certain limitations in some aspects such as information collection, control and processing, and Because multi-single-arm manipulators have strong coordination operation flexibility and large load capacity, they can complete tedious and diverse task requirements. Therefore, it is of great significance to study multi-single-arm manipulator cooperation systems, especially in multi-agent systems. The design of a consistent output controller for a single-arm manipulator is of great significance, however, its relatively cumbersome control problem is a difficult problem

[0004] For systems with uncertain nonlinear terms, the adaptive neural network can approximate the unknown nonlinear function, and obtain the expression form of the final control input through backstepping control, but backstepping control has the problem of computational complexity explosion

Images