RBF adaptive neural network repetitive controller suitable for repetitive servo system

Abstract

The invention discloses an RBF adaptive neural network repetitive controller suitable for a repetitive servo system. According to the controller, the self-adaptive weight adjustment of an RBF neural network is utilized to approximate a servo motor input and output differential equation with unknown parameters; according to a repetitive control method, a control quantity at the current moment is corrected by utilizing the operation information of a previous period, so that periodic interference is overcome, and the tracking of a given periodic reference signal by an output quantity is realized.According to the RBF adaptive neural network repetitive controller suitable for the repetitive servo system, on the basis of the periodic operation characteristics of the repetitive servo system, onone hand, the RBF neural network is utilized to approximate the system model of unknown parameters, and on the other hand, the repetitive control method is introduced to eliminate common periodic interference in an repetitive operation process.

Description

technical field [0001] The invention relates to repetitive control technology, and is especially suitable for servo systems with unknown motor parameters under periodic reference signals, and also suitable for other periodic operation processes in industrial occasions. Background technique [0002] In industrial production sites, there are many repetitive operations. For example, when industrial robots perform tasks such as welding, handling, palletizing, milling and painting, they need to automatically and repeatedly perform work according to preset instructions. When the automatic arc welding robot performs the welding operation, it uses the welding seam track tracking technology to run along the welding seam while the length and quality of the welding rod gradually decrease. After completing an operation, it returns to the starting point and repeats the operation. The palletizing robot has the functions of repeated handling and palletizing, and requires high repeat posit...

AI Technical Summary

Problems solved by technology

[0004] In order to solve the controller design problem under the condition of periodic disturbance and unknown model in the repetitive servo system in complex working conditions, the present invention provides an RBF adaptive neural network repetitive controller suitable for the repetitive servo system. The invention aims at the periodic operation characteristics of the repetitive servo system. On the one hand, the RBF neural network is used to approximate the system model of unknown parameters, and on the other hand, the repetitive control method is introduced to eliminate the common periodic disturbance in the repetitive operation process.

Images