Compensation control method for robot flexible joints based on lstm hysteresis model

A flexible joint, compensation control technology, applied in the direction of program control manipulators, manipulators, manufacturing tools, etc., can solve problems such as the reduction of joint conversion accuracy, and achieve the effects of improving stability, compensating conversion errors, and improving conversion accuracy.

Active Publication Date: 2021-09-17
GUILIN UNIV OF ELECTRONIC TECH
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] What the present invention aims to solve is the problem that the complex hysteresis characteristics of the joints in the existing industrial robots are not accurately compensated, resulting in a decrease in the joint conversion accuracy, and provides a compensation control method for the robot's flexible joints based on the LSTM hysteresis model

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Compensation control method for robot flexible joints based on lstm hysteresis model
  • Compensation control method for robot flexible joints based on lstm hysteresis model
  • Compensation control method for robot flexible joints based on lstm hysteresis model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0021] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with specific examples.

[0022] Considering the memory characteristics of the output of the flexible joints of the industrial robot and the historical input, the present invention adopts the long-short-term memory neural network (Long Short-Term Memory Model, LSTM) that can save and transmit information for a long time and has memory characteristics. The complex nonlinear hysteresis characteristics exhibited by flexible joints of robots are modeled. In order to further improve the modeling accuracy, the present invention proposes the hysteresis modeling of the flexible joints of industrial robots based on the improved LSTM, and designs a compensation control method for the conversion error of the flexible joints of industrial robots based on the model, so as to realize high-precision angular posit...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a robot flexible joint compensation control method based on the LSTM hysteresis model, which uses the improved LSTM-based industrial robot flexible joint hysteresis characteristic model to online predict the robot joint output angle, and calculates the output torque angle by comparing with the ideal joint output. Corresponding to the angle compensation amount of the input end of the joint, the set input angle of the input end of the joint is compensated. From the motor drive end of the joint, the complex hysteresis characteristic of the joint is offset, and the joint conversion accuracy of the industrial robot is effectively improved. The hysteresis model has online learning ability, which not only compensates the transmission nonlinear error caused by the structure of the industrial robot joint itself, but also compensates the conversion error caused by the slow drift characteristic of the industrial robot joint under long-term operation, which improves the long-term operation of the joint. Stability under precision.

Description

technical field [0001] The invention relates to the technical field of industrial robots, in particular to a compensation control method for flexible joints of a robot based on an LSTM hysteresis model. Background technique [0002] Industrial robots have the advantages of high repeatability, automation, safety and strong applicability. In the context of intelligent manufacturing, the functions of industrial robots are becoming more and more powerful, and at the same time, higher requirements are placed on the execution accuracy of industrial robots. In recent years, robots such as lightweight robots and collaborative robots that have emerged use harmonic drives to drive their joint motions. The complex nonlinear hysteresis characteristics of the flexible joints of industrial robots composed of motors and harmonic reducers often affect the conversion accuracy of joints and directly affect the positioning accuracy of industrial robots. Modeling the nonlinear hysteresis char...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Patents(China)
IPC IPC(8): B25J9/16
CPCB25J9/16B25J9/1628
Inventor 党选举黄佳刘帆李晓伍锡如张向文原翰玫黄品高潘登
Owner GUILIN UNIV OF ELECTRONIC TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products