A Real-time Extraction Method of Welding Pool Image Contour
A welding pool and image contour technology, which is applied in image analysis, image enhancement, image data processing, etc., can solve the lack of effective means for image extraction of welding pool, unsatisfactory online quality control effect, and inability to obtain the real contour of molten pool, etc. problem, achieve the effect of overcoming the artificial setting of segmentation rules, and the detection method is simple and reliable
Active Publication Date: 2021-11-05
SHANGHAI JIAO TONG UNIV
View PDF4 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
This method has a certain ability to identify mutation points, but it is not targeted at the edge of the molten pool. Therefore, it is difficult to screen the edge of the molten pool in a complex background
In addition, for materials such as aluminum alloy, the contrast between the molten pool image and the workpiece background is small, and the edge extraction method based on the high-frequency component of the image has a low success rate
[0008] In summary, the defects of the existing technology are: there is no effective means for contour extraction of welding pool images, mainly referring to static image contour extraction algorithms, or relying on manual experience for simplification or correction, and it is impossible to obtain the real contour of the molten pool during the actual welding process. As a result, the online quality control effect of the welding process is not ideal, and it is difficult to meet the needs of production applications
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
[0049]The following describes several preferred embodiments of the present invention with reference to the accompanying drawings, so as to make the technical content clearer and easier to understand. The present invention can be embodied in many different forms of embodiments, and the protection scope of the present invention is not limited to the embodiments mentioned herein.
[0050] In the drawings, components with the same structure are denoted by the same numerals, and components with similar structures or functions are denoted by similar numerals. The size and thickness of each component shown in the drawings are shown arbitrarily, and the present invention does not limit the size and thickness of each component. In order to make the illustration clearer, the thickness of parts is appropriately exaggerated in some places in the drawings.
[0051] Such as figure 1 As shown, it is a flow chart of the real-time extraction method for the weld pool image contour of the pres...
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 method for real-time extraction of weld pool image contours, which relates to the field of welding. A high-speed camera is used to obtain continuous molten pool images in the welding process, and the number of image frames participating in the calculation is determined according to the shooting frame frequency and the flow characteristics of the molten pool, and the calculation is continuous. The coefficient of variation of the gray value of each pixel in the image is used to obtain the coefficient of variation image, and the gray histogram is drawn after the low-pass filtering of the coefficient of variation image. The threshold value is used to binarize the variation coefficient image, and the difference method is used to extract the outline of the molten pool. The invention can assist the high-speed camera system to accurately obtain the outline of the molten pool, has high measurement accuracy and good stability, and can effectively overcome the influence of imaging system differences and shooting environments, especially for materials that have no significant color difference between the molten pool and the rear semi-solidified area. applicability.
Description
technical field [0001] The invention relates to the field of welding, in particular to a method for real-time extraction of weld pool image contours. Background technique [0002] The molten pool is an important part of the welding process, and the characteristics of the molten pool play an important role in the formation of the weld and the inspection of the welding quality. Due to the large changes in the welding environment, the lack of stable lighting, and the interference of the complex reflection characteristics of the molten pool surface and the intense light intensity of the arc, it is difficult for traditional image segmentation algorithms to obtain stable and accurate molten pool segmentation results. [0003] The search found that the current representative achievements in this field include: [0004] The paper "A Method for Extracting Weld Pool Edge Using Mathematical Morphology and Active Contour Model" proposes a welding pool edge extraction method combining m...
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): G06T7/12G06T7/136
CPCG06T2207/10004G06T2207/30152G06T7/12G06T7/136
Inventor 蔡艳王伟成徐晓磊华学明李芳
Owner SHANGHAI JIAO TONG UNIV