A method, device and equipment for laser welding defect recognition based on deep learning
A technology for laser welding and defect identification, which is applied in measuring devices, scientific instruments, and material analysis through optical means, can solve the problems of low accuracy of laser welding defect identification and the inability to accurately mark laser welding defects, and improve welding quality , avoid excessive cleaning, identify the effect of high accuracy
Active Publication Date: 2022-02-15
GUANGDONG UNIV OF TECH
View PDF3 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0006] The purpose of the present invention is to provide a laser welding defect recognition method, device and computer-readable storage medium based on deep learning to solve the problem that the prior art cannot accurately mark laser welding defects and the accuracy of laser welding defect recognition is low
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
[0047] The core of the present invention is to provide a laser welding defect identification method, device, equipment and computer-readable storage medium based on deep learning, which can accurately determine the laser welding defect of the data sample, and can more accurately determine the specific frame number of the laser welding defect; Moreover, the identification of laser welding defects is highly accurate, and it is suitable for various laser welding process parameters.
[0048] In order to enable those skilled in the art to better understand the solution of the present invention, the present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. Apparently, the described embodiments are only some of the embodiments of the present invention, but not all of them. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making cre...
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 laser welding defect recognition method, device, equipment and computer-readable storage medium based on deep learning, including: according to the photoelectric signal collected during the laser welding process and the dynamic video of the welding pool taken from the front and side, Determine the target frame number range where the welding defect is located; convert the photoelectric signal within the target frame number range, the dynamic video of the front and side welding pools into a photoelectric image set, a front welding image set, and a side welding image set; use the marked photoelectric The image set, front welding image set and side welding image set train the laser welding defect recognition network model; use the laser welding defect type recognition model after training to perform online welding defect recognition during the laser welding process. The method, device, equipment and computer-readable storage medium provided by the present invention can accurately judge defects and specific frame numbers of defects, and improve the accuracy rate of welding defect recognition.
Description
technical field [0001] The present invention relates to the technical field of laser welding, in particular to a deep learning-based laser welding defect identification method, device, equipment and computer-readable storage medium. Background technique [0002] Laser welding is a special processing method for precision welding with high-energy-density laser beams. Laser welding has the advantages of high precision, fast welding speed, and small thermal deformation. In addition to being used in aerospace, automobiles and ships, it is also used in precision welding of small and small parts, which is suitable for automation. Under the focusing of the high-energy laser beam, the metal material at the focal point evaporates and melts rapidly, and the evaporation in the molten pool increases, thereby promoting the flow of the small area of unsolidified liquid metal on the front and rear walls of the keyhole to form a dynamic balance. As the laser beam advances, the molten meta...
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): G01N21/956G06T7/00
CPCG01N21/956G06T7/0004G06T2207/30152G06T2207/20081
Inventor 潘雅灵游德勇
Owner GUANGDONG UNIV OF TECH