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

Visual detection method for mechanical component defect

A technology of mechanical parts and visual inspection, applied in the field of visual inspection, can solve the problems of human error, reduce measurement accuracy, increase production cycle, etc., achieve the effect of reducing the amount of data, simple processing, and small amount of processing and compression

Active Publication Date: 2019-04-05
DONGGUAN UNIV OF TECH
View PDF4 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] With the development of industrial technology, the processing method of mechanical parts presents a development trend of high precision, high speed and automation. The traditional contact detection method is slow, which is easy to cause damage to the parts and will reduce the measurement accuracy. The measurement technology based on computer vision has the advantages of With the advantages of high speed, good real-time performance, non-touch, low cost, etc., it is widely used in the precise detection of processing defects of various parts
[0003] Testing and inspection is one of the most basic activities in the manufacturing process. Through testing and inspection activities, the quality information of the product and its manufacturing process is provided, and the manufacturing process of the product is controlled according to this information—correction and compensation activities are carried out to make waste The rate of products and repaired products is reduced to a minimum, ensuring the stability of the product quality formation process and the consistency of the output products; the traditional inspection and inspection mainly rely on people, and are mainly completed by hand, which is time-consuming and expensive. The production cycle increases and the production cost increases; at the same time, the traditional inspection and testing activities are mainly carried out after the manufacturing process, once the defective products are detected, the loss has already occurred; in addition, the information based on manual inspection often contains human errors According to the influence of such information, the control of the manufacturing process according to such information is not only implemented after the process, but also introduces human errors; therefore, this information cannot be relied on to achieve real-time or on-machine process control; new inspections and inspections often It is based on a variety of advanced sensing technologies and is easy to combine with computer systems; with the support of appropriate software, this type of automatic detection or inspection system can automatically complete data collection, processing, feature extraction and identification, and multiple analysis and calculation

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
  • Visual detection method for mechanical component defect
  • Visual detection method for mechanical component defect

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0047] The present invention and its specific implementations will be described in further detail below in conjunction with the accompanying drawings.

[0048] A visual inspection method for defects in mechanical parts, the method comprising:

[0049] Use a 3D coordinate measuring instrument and a close-range camera to perform 3D scanning and close-range photography on the surface of mechanical parts and store the images;

[0050] The median filtering method is used to denoise the noise and reflective areas that affect the image features, and the image is binarized by threshold automatic segmentation through the ostu algorithm;

[0051] First use the Candy edge detection algorithm to obtain pixel-level edges, and then use the spatial matrix edge location method to use the two-dimensional space gray matrix to determine the edge sub-pixels of the edge position to refine the edge, and then refine the edge location accuracy from coarse to fine. into the interior of the pixel to e...

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 visual detection method for a mechanical component defect. Defect parts in the mechanical component and on the surface of the mechanical component can be continuously scanned, and an acquired image can be processed and analyzed to acquire the area of the surface and internal defects, the barycentric coordinates of the defects and the defect shapes, so that operating personnel can see the defect parts clearly; then a three-dimensional model about the surface texture, color feature and internal structure of the mechanical component is recovered via three-dimensional reconstruction reverse engineering design, and thus the surface and internal defect positions and the defect range of the mechanical component are displayed, and the three-dimensional reconstruction system of the defect is displayed as a three-dimensional PDF document.

Description

technical field [0001] The invention relates to a visual detection method, in particular to a visual detection method for defects of mechanical parts. Background technique [0002] With the development of industrial technology, the processing method of mechanical parts presents a development trend of high precision, high speed and automation. The traditional contact detection method is slow, which is easy to cause damage to the parts and will reduce the measurement accuracy. The measurement technology based on computer vision has the advantages of With the advantages of high speed, good real-time performance, non-touch, low cost, etc., it is widely used in the precise detection of processing defects of various parts. [0003] Testing and inspection is one of the most basic activities in the manufacturing process. Through testing and inspection activities, the quality information of the product and its manufacturing process is provided, and the manufacturing process of the pr...

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): G01N21/88G01N23/046G01B11/00G06T7/00G06T7/11G06T7/13G06T7/136G06T7/66G06T7/90
CPCG06T7/0004G06T7/11G06T7/13G06T7/136G06T7/66G06T7/90G01B11/005G01N21/8851G01N23/046G01N2223/1016G01N2223/401G01N2021/8887G06T2207/20084G06T2207/10081G06T2207/30164
Inventor 魏亚东龙建宇
Owner DONGGUAN 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