Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A Machine Learning Based Joint Friction Identification Method for Serial Robots

A technology of robot joints and machine learning, applied in manipulators, program-controlled manipulators, manufacturing tools, etc., can solve the problems of inaccurate friction modeling and identification methods, achieve good practical significance, solve the inaccurate model, and achieve significant economic benefits Effect

Active Publication Date: 2022-05-17
SOUTH CHINA UNIV OF TECH +1
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a method for identifying joint friction of industrial robots, aiming to solve the problem of inaccuracy in existing friction modeling and identification methods

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
  • A Machine Learning Based Joint Friction Identification Method for Serial Robots
  • A Machine Learning Based Joint Friction Identification Method for Serial Robots
  • A Machine Learning Based Joint Friction Identification Method for Serial Robots

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0042] like figure 2 As shown, a machine learning-based joint friction identification method for series robots, the method is based on a robot joint friction identification platform including a six-axis industrial robot and a host computer, including the following steps:

[0043] S1. According to the periodic variation of the joint torque exhibited during the working process of the six-axis industrial robot, a model of the joint friction force of the six-axis industrial robot on the joint rotation angle and joint angular velocity is established;

[0044] S2, in a such as figure 1 The single-joint identification experiment is carried out on a six-axis industrial robot, which includes the first joint 1, the second joint 2, the third joint 3, the fourth joint 4, the fifth joint 5, and the sixth joint 6 in series; The sampling period is to collect the data during the experiment, and the state information to be collected includes the indication of the joint motor encoder and the ...

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 method for identifying the joint friction force of a serial robot based on machine learning, comprising steps: S1. According to the characteristics of the joint torque displayed during the working process of the serial robot, establishing the joint friction force of the serial robot with respect to the joint rotation angle and the joint angular velocity Joint friction model; S2, conduct identification experiments on the serial robot, collect state information at each moment in the movement, the collected state information includes the indication of the joint motor encoder and the current coefficient of the joint motor; S3, use step S2 The collected state information is used to solve the unknown parameters in the joint friction model of the industrial robot established in step S1, to obtain a joint friction model considering joint angle and angular velocity, and to obtain a prediction curve consistent with the actual friction force. The invention does not need to use other equipment, has the characteristics of small difficulty in realization and low cost, and solves the problem of inaccurate models in the existing friction force theory.

Description

technical field [0001] The invention relates to the field of joint friction identification of robots, in particular to a machine learning-based identification method for joint friction of serial robots. Background technique [0002] The modeling and identification of robot joint friction is the basis of robot motion control and control methods based on dynamic models. However, the current friction modeling and identification methods are still not accurate enough. In order to perform parameter identification, the model is usually simplified to a certain extent, and only the magnitude of friction is considered to be related to the relative motion speed of the contact surface. However, in the actual robot movement process, especially in the low-speed movement process, the friction force has obvious nonlinearity and is related to the joint rotation angle. [0003] Establish the relationship between robot joint friction force and joint angle and angular velocity, and use machine...

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
CPCB25J9/1605
Inventor 张铁李秋奋邹焱飚
Owner SOUTH CHINA UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com