Weld quality parameter detection method based on structured light and visual imaging
A detection method and quality parameter technology, applied in image data processing, optical testing flaws/defects, image enhancement, etc., can solve problems such as poor anti-interference ability, low detection accuracy, and failure to meet detection needs, so as to improve automation level, The effect of reducing inspection costs
Active Publication Date: 2021-01-15
GUANGDONG INSPECTION & RES INST OF SPECIAL EQUIP ZHUHAI INSPECTION INST
View PDF14 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
This method has poor anti-interference ability and low detection accuracy, which cannot meet the detection needs
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0022] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the embodiments and accompanying drawings.
[0023] Such as figure 1 As shown, the detection method process of key quality parameters of welds based on structured light and visual imaging includes the following steps:
[0024] Step 10 Turn off the laser, take image A of the weld seam, turn on the laser, take image B;
[0025] Step 20: Perform grayscale processing on image A to obtain image G, and select two specific convolution operators S x , S y Perform convolution calculation with the image G to obtain the first-order partial derivative matrix I in the X-axis direction and the Y-axis direction at each pixel position in the image x , I y , and then calculate the gradient magnitude matrix M at each pixel position in the image, perform non-maximum suppression on the gradient magnitude mat...
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
Login to View More Abstract
The invention discloses a quality parameter detection method based on structured light and visual imaging for a welding seam. The method comprises the following steps of: shooting an image A and an image B of the welding seam; processing the image A to obtain an image G, selecting convolution operators S<x> and S<y>, performing convolution calculation with the image G to obtain partial matrixes I<x> and I<y> in a X axis direction and a Y axis direction, then calculating an image gradient magnitude matrix M, selecting welding seam width feature points P<1> and P<2>, and calculating the pitch ofP<1> and P<2> to obtain a welding seam width value w; setting a threshold value of a RGB channel in B to obtain a binary image L, processing L, extracting a center line L<c>, a maximum value point P<3> and minimum values P<4> and P<5> of L<c>, calculating the distance between P<3> and P<4>, and the distance between P<3> and P<5> to obtain the surplus height h of the welding seam, calculating thedistance between P<1> and P<4>, and the distance between P<2> and P<5> to obtain the left and right undercut depths d<1> and d<r> of the welding seam; and selecting a connecting line of boundary points of a laser line of the image B as a chord length, selecting two points P<6> and P<7> symmetrically about P<3>, calculating the distances D<1> and D<2> from the points P<6> and P<7> to an arc, and the distances D<3> and D<4> from the points to the chord length, and obtaining an edge angle e and an alignment tolerance value delta of the welding seam according to D<1>, D<2>, D<3>, and D<4>.
Description
technical field [0001] The invention relates to the field of welding quality detection in special equipment and manufacturing, in particular to a method for detecting key quality parameters of welds based on structured light and visual imaging. Background technique [0002] Welding is a common processing method in manufacturing. The quality of welding is the key factor that determines the quality of products. Affected by the welding working environment, when the welding work is completed, various defects will inevitably occur on the surface of the welded parts, such as undercuts and surface pits. The welding defect is the stress concentration point of the product, which leads to the failure of the welded product to reach the specified service life, at least the product is scrapped, and at the worst it causes casualties. Therefore, the regular inspection of weld appearance parameters of weldments is particularly important. [0003] The inspection of welded parts in the trad...
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
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G01N21/88G06T7/00G06T7/11G06T7/136G06T7/155
CPCG01N21/8851G01N2021/8874G01N2021/8887G06T7/0004G06T2207/30152G06T7/11G06T7/136G06T7/155
Inventor 陈英红杜明坤丛成龙杨宁祥
Owner GUANGDONG INSPECTION & RES INST OF SPECIAL EQUIP ZHUHAI INSPECTION INST