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

Deformed curved surface grinding method, device and system based on computer vision

A computer vision and grinding technology, applied in the field of computer vision, can solve problems such as overgrinding, undergrinding, and the inability to automatically identify the polished area, so as to improve the quality of the grinding surface, avoid overgrinding and undergrinding, and improve production efficiency and effect

Active Publication Date: 2022-06-03
SHANGHAI JIAO TONG UNIV +1
View PDF10 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] Since the thickness of the attachment on the deformed workpiece is inconsistent, it is necessary to monitor the surface of the workpiece at all times to prevent over-grinding. However, the research on the above-mentioned related technologies is all about the overall grinding of the workpiece, and it is impossible to automatically identify the polished area, so there is a high probability Over-grinding or under-grinding

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
  • Deformed curved surface grinding method, device and system based on computer vision
  • Deformed curved surface grinding method, device and system based on computer vision
  • Deformed curved surface grinding method, device and system based on computer vision

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0065] It should be understood that the specific embodiments described herein are only used to explain the present invention, but not to limit the present invention.

[0066] refer to figure 1 , figure 1 This is a schematic flowchart of the first embodiment of the method for establishing a virtual reality system for a shipborne satellite antenna according to the present invention.

[0067] In the first embodiment, the method for establishing the virtual reality system of the shipboard satellite antenna includes the following steps:

[0068] Step S10, set initial grinding parameters and perform fine grinding along the initial grinding track, the initial grinding track is taught by the standard part, and the initial grinding parameters include the running speed of the abrasive belt, the grinding force and the feed speed.

[0069] In step S20, for each grinding step, a grinding surface image of the workpiece is acquired, and the grinding surface image is evenly divided into n s...

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 the technical field of computers, and discloses a deformed curved surface grinding method, device and system based on computer vision, and the method comprises the steps that initial grinding parameters are set, and accurate grinding is conducted along an initial grinding track; obtaining a grinding surface image of the workpiece every time the workpiece is ground, and uniformly dividing the grinding surface image into n sub-images; inputting the n sub-images into a classification model to obtain corresponding n classification results; if the n classification results all show that polishing is completed, it is determined that polishing of the workpiece is completed; if the n classification results are all continuous grinding, continuous grinding is carried out according to the initial grinding parameters and the initial grinding track; and if the n classification results are that polishing is completed and polishing is continued, the initial grinding track and the initial grinding parameters are optimized according to the center point coordinates of all the to-be-polished areas, and the to-be-polished areas are ground according to the optimized grinding track and the optimized grinding parameters. Over-grinding and under-grinding can be avoided, and the grinding precision is improved.

Description

technical field [0001] The invention relates to the technical field of computer vision, in particular to a method, device and system for grinding deformed surfaces based on computer vision. Background technique [0002] In industry, grinding is often the last step of machining, which plays a crucial role in the final molding quality of the product, and ultimately determines the grade of the product. Manual grinding, special machine grinding and CNC machine grinding are the three most important modes of traditional grinding. Workpieces working in high temperature environments, such as aerospace parts, will be deformed to a certain extent due to the influence of temperature and force, but because such workpieces are relatively expensive and the cost of reproducing new parts is high, they often need to be ground and polished , and reuse it after removing the surface attachments. Due to the different degree of deformation of each workpiece, it is difficult to establish a unifi...

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): B24B21/00B24B49/12B24B49/16B24B51/00G06T1/00G06T7/11G06T7/80G06K9/62G06V10/764
CPCB24B21/006B24B49/12B24B49/16B24B51/00G06T1/0014G06T7/11G06T7/80G06T2207/20021G06F18/24Y02P90/30
Inventor 王宇翔郭文兴黄小康陈华斌陈小奇李振任伟培
Owner SHANGHAI JIAO TONG UNIV
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