Multi-source quality monitoring method based on spectral visual collaborative perception
A technology of collaborative perception and quality monitoring, applied in image analysis, image enhancement, instruments, etc., can solve problems such as incomplete visual information, inability to solve the problem of high and low slag inclusion quality of shielding gas flow, and achieve simple and efficient calculation and high accuracy. , the effect of stable performance
Active Publication Date: 2022-07-05
NANJING UNIV OF SCI & TECH
View PDF2 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0003] In molten pool quality monitoring, visual images can be used to monitor welding speed stability, but it cannot solve quality problems such as shielding gas flow rate and slag inclusion. Therefore, a single visual information is not comprehensive, and other measurement data need to be introduced to complement molten pool information
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
[0050] The following is a detailed description with examples in conjunction with the accompanying drawings, but the provided examples are not intended to limit the scope of the present invention, and the description of the structure operation is not intended to limit the order of its execution. Any recombination of components The structure and the resulting device with equal efficacy are all within the scope of the present invention.
[0051] see figure 1 , figure 2 and image 3 As shown, the present invention proposes a multi-source quality monitoring method based on spectral visual synergistic perception.
[0052] Step 1. The spectral processing of LPP-KNN classification refers to using LPP dimensionality reduction to further mine the spectral information of the selected characteristic band range, and perform KNN classification on the final spectral features, which is mainly used for the monitoring of protective gas flow. The spectral data processing based on LPP-KNN cla...
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 multi-source quality monitoring method based on spectral visual synergistic perception, comprising the following steps: 1) collecting welding current parameters, collecting the spectral data of the molten pool at the peak moment of the current, and collecting the welding current at the base value moment of the current. The visual image of the pool; 2), based on the spectral data obtained in step 1), select the characteristic waveband, and carry out LPP-KNN classification according to the characteristic waveband to realize the quality monitoring of the protective gas flow; 3), based on the molten pool obtained in step 1) Welding speed stability monitoring of visual image CC-KNN; 4), base metal defect monitoring based on spectral processing of the spectral data a priori threshold obtained in step 1). Various algorithms in the multi-source quality monitoring method based on spectral visual collaborative perception of the present invention are simple and efficient in calculation and have strong real-time performance. Through the combination of visual classification and spectral classification, there are more categories of quality problems that can be located online, with higher accuracy and more stable performance. Furthermore, the present invention is not limited to a single welding process and a single material.
Description
technical field [0001] The invention belongs to the technical field of multi-source classification, and relates to a multi-source quality monitoring method based on spectral visual collaborative perception. Background technique [0002] On-line monitoring of molten pool quality has always been a technical hotspot in the field of welding and one of the main research contents of intelligent welding technology. Vision is one of the main functions of human perception of external information. In traditional manual quality supervision, welders' judgment on welding quality mainly relies on visual information and personal experience. The weld pool image contains rich weld pool information, which is closely related to the welding quality. [0003] In molten pool quality monitoring, visual images can be used to monitor welding speed stability, but it cannot solve quality problems such as shielding gas flow rate and slag inclusion, so a single visual information is not comprehensive, ...
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): G06T7/00G06V10/771G06V10/764G06K9/62
CPCG06T7/0004G06T2207/30152G06F18/211G06F18/24147
Inventor 柏连发韩静张毅王克鸿郭逸汀赵壮孙钡彭冲冲
Owner NANJING UNIV OF SCI & TECH