Machine vision-based automatic navigation method for magnetic grinding of elbow

A technology of automatic navigation and machine vision, applied in the fields of B-spline curve fitting, robot control, image processing, and computer vision, which can solve the problem that the axis curve of the elbow cannot be determined.

Inactive Publication Date: 2014-06-18
SHENYANG INST OF AUTOMATION - CHINESE ACAD OF SCI
View PDF4 Cites 17 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Another situation is that the axis curve of the bent pipe cannot be determined at all, and the processing of the whole bent pipe can only be completed by relying entirely on automatic navigation.

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
  • Machine vision-based automatic navigation method for magnetic grinding of elbow
  • Machine vision-based automatic navigation method for magnetic grinding of elbow
  • Machine vision-based automatic navigation method for magnetic grinding of elbow

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0034] The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments.

[0035] The technical solution of the invention is to use computer vision to track the free curved pipe in real time, so as to achieve magnetic grinding of the inner wall of the curved pipe.

[0036] Firstly, strict calibration and hand-eye calibration of the visual camera itself are required to determine the robot hand-eye relationship matrix;

[0037] The line structured light of the light source is irradiated on the outer surface of the cross-section of the elbow to form a semicircular light strip. The CCD camera captures the image and reconstructs it in 3D to obtain a set of three-dimensional points on the outer surface of the half cross-section of the elbow. The three-dimensional points The set is relative to the local coordinate system of the camera;

[0038] Carry out radius-constrained least-squares fitting and optimization on the thre...

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 relates to a machine vision-based automatic navigation method for magnetic grinding of an elbow. The machine vision-based automatic navigation method includes that: calibrating parameters of a CCD camera to obtain a hand-eye relationship matrix of a robot; allowing the CCD camera to capture a three-dimensional image of a light bar at the outer surface of the elbow to obtain a data point set of a semi-circle of a light plane space of the camera; carrying out least square fitting with radius constraint on the data point set, calculating to obtain a circle center coordinate of a coordinate system of the light plane of the camera and converting into a circle center coordinate of a reference coordinate system; carrying out B-splint curve fitting on a series of circle center points to obtain an axle center orbit of the elbow; regulating the posture of a magnetic polishing device of the robot according to the axle center orbit to finish the magnetic polishing processing for the elbow. The machine vision-based automatic navigation method for the magnetic grinding of the elbow is good in realtime performance and high in precision, is capable of processing complex elbows, and enables the processing period to be greatly shortened and the efficiency and the processing precision to be improved.

Description

technical field [0001] The invention relates to technologies such as computer vision, image processing, B-spline curve fitting, robot control, etc., and specifically uses a computer vision method to automatically navigate the magnetic grinding of the inner wall of a free curved pipe. Background technique [0002] In recent years, the high-precision pipe fittings that have appeared in the fields of mechanical transportation, aerospace and other fields have high requirements for the roughness of the inner surface of the pipe fittings because they transport high-purity gases or liquids. The high smoothness of the inner wall of the tube, on the one hand, can ensure smooth transportation, avoid turbulent flow and make the fluid pressure in the tube uniform; on the other hand, it can avoid pollution and corrosion due to surface defects, and improve the service life. Due to the limitation of the use environment, many pipe fittings are slender elbows with complex shapes and variable...

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 Applications(China)
IPC IPC(8): B24B1/00
CPCB24B1/005
Inventor 赵吉宾杨林李家智付生鹏王国强乔红超
Owner SHENYANG INST OF AUTOMATION - CHINESE ACAD OF SCI
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