Industrial robot space grid precision compensation method based on neural network

An industrial robot and neural network technology, applied in the field of industrial robot calibration, can solve the problems of large measurement workload, large calculation amount, and unsatisfactory effect, so as to reduce the measurement workload, improve the absolute positioning accuracy, and the calculation process is simple and fast. Effect

Active Publication Date: 2012-07-25
江苏航鼎智能装备有限公司
View PDF4 Cites 27 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] 1) In order to enable the trained network to achieve a certain accuracy and adapt to all points within the envelope of the robot, training the neural network requires a large number of learning samples, so the measurement workload is heavy;
[0006] 2) This method needs to convert Cartesian coordinates

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
  • Industrial robot space grid precision compensation method based on neural network
  • Industrial robot space grid precision compensation method based on neural network
  • Industrial robot space grid precision compensation method based on neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0028] The steps of the industrial robot space grid precision compensation method based on particle swarm optimization neural network in the present invention are as follows:

[0029] Step 1: within the envelope of the industrial robot, the area to be processed in the envelope space of the robot is divided into a series of cubic grids according to a certain step size;

[0030] Step 2: Measure and establish the base coordinate system of the robot through the laser tracker, use the theoretical coordinates of the eight vertices of each cube grid divided in step 1 to control the robot for positioning at several different temperature levels, and track with the laser The instrument measures and records the actual positioning coordinates;

[0031] The steps to establish the association between the laser tracker and the robot base coordinate system are:

[0032] 1) The spherical fixed reflector SMR is fixed on the TCP of the end effector, and the position (angle) of the A2 to A6 axes...

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 an industrial robot space grid precision compensation method based on a neural network, and belongs to the technical field of calibration of industrial robots. By using the characteristic of high repeated positioning precision of industrial robots, training the back propagation (BP) neural network of particle swarm optimization to simulate the inherent law of the robots positioned under the same load and at different environment temperatures and combining the robot space grid precision compensation method, a random target positioning point in a robot enveloping space range is subjected to precision compensation, and the absolute positioning precision of the random target positioning point is improved. The measurement workload can be effectively reduced by determining the maximum step length of the divided grids for the industrial robots of different types, and the industrial robots are quickly put into application. Positive solution and inverse solution of robot kinematics are not required, the calculation process is simple and quick, and online compensation can be realized. The absolute positioning precision of the robots is improved, and the calibrated industrial robots can adapt to wide application occasions.

Description

technical field [0001] The invention relates to a robot positioning accuracy compensation method, in particular to a spatial three-dimensional grid accuracy compensation method for industrial robots based on a particle swarm optimization neural network, and belongs to the technical field of industrial robot calibration. Background technique [0002] The accuracy of the robot is an important index reflecting the performance of the robot, which includes absolute positioning accuracy and repeat positioning accuracy. The absolute positioning accuracy error is the deviation between the actual movement of the robot and the expected movement, which is generated by the deterministic original error (such as the error of the connecting rod parameter, the clearance of the kinematic pair, etc.); the repeat positioning accuracy error is when the robot repeatedly performs the same expected movement. The degree of mutual discreteness between the actual motions is generated by random origin...

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
IPC IPC(8): G01C21/00G06N3/02
Inventor 田威廖文和周炜沈建新周卫雪贺美华
Owner 江苏航鼎智能装备有限公司
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap