CN113850802B - MATLAB-based automatic extraction method for spectral data of welding arc characteristic spectral line image - Google Patents
MATLAB-based automatic extraction method for spectral data of welding arc characteristic spectral line image Download PDFInfo
- Publication number
- CN113850802B CN113850802B CN202111215791.6A CN202111215791A CN113850802B CN 113850802 B CN113850802 B CN 113850802B CN 202111215791 A CN202111215791 A CN 202111215791A CN 113850802 B CN113850802 B CN 113850802B
- Authority
- CN
- China
- Prior art keywords
- image
- data
- spectral line
- characteristic spectral
- target image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 230000003595 spectral effect Effects 0.000 title claims abstract description 77
- 238000003466 welding Methods 0.000 title claims abstract description 45
- 238000000605 extraction Methods 0.000 title claims abstract description 22
- 238000001228 spectrum Methods 0.000 claims abstract description 26
- 230000009467 reduction Effects 0.000 claims abstract description 10
- 238000007781 pre-processing Methods 0.000 claims abstract description 6
- 238000000034 method Methods 0.000 claims description 30
- 238000003708 edge detection Methods 0.000 claims description 17
- 238000000354 decomposition reaction Methods 0.000 claims description 6
- 150000003839 salts Chemical class 0.000 claims description 4
- 238000012935 Averaging Methods 0.000 claims description 3
- 238000013139 quantization Methods 0.000 claims description 3
- 238000003672 processing method Methods 0.000 claims 1
- 238000003745 diagnosis Methods 0.000 abstract description 9
- 238000013075 data extraction Methods 0.000 abstract description 5
- 230000008569 process Effects 0.000 description 4
- 230000008859 change Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000010891 electric arc Methods 0.000 description 2
- 238000010183 spectrum analysis Methods 0.000 description 2
- 235000002566 Capsicum Nutrition 0.000 description 1
- 239000006002 Pepper Substances 0.000 description 1
- 235000016761 Piper aduncum Nutrition 0.000 description 1
- 235000017804 Piper guineense Nutrition 0.000 description 1
- 244000203593 Piper nigrum Species 0.000 description 1
- 235000008184 Piper nigrum Nutrition 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000020169 heat generation Effects 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000877 morphologic effect Effects 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001629 suppression Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/10—Image enhancement or restoration using non-spatial domain filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20048—Transform domain processing
- G06T2207/20064—Wavelet transform [DWT]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30152—Solder
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Quality & Reliability (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a MATLAB-based automatic extraction method for spectral image spectral data of welding arc characteristic spectral lines, which relates to the technical field of welding arc spectral diagnosis and comprises the following steps: s1: acquiring an arc characteristic spectral line image and preprocessing the arc characteristic spectral line image, wherein S2: removing noise data S3: removing invalid data; s4: and (5) carrying out symmetry processing and wavelet noise reduction processing to obtain target spectrum data. The automatic extraction method of the welding arc characteristic spectral line image spectrum data based on MATLAB provided by the invention not only can remove arc reflection noise, welding spatter and dark current noise of a CMOS photosensitive element, effectively improve the accuracy of characteristic spectral line data extraction, but also effectively improve the extraction precision and diagnosis efficiency of arc spectrum data by means of interpolation processing, effective data extraction of characteristic spectral line images, data symmetry and the like, and lay a reliable foundation for subsequent arc spectrum diagnosis.
Description
Technical Field
The invention relates to the technical field of welding arc spectrum diagnosis, in particular to an automatic extraction method of welding arc characteristic spectral line image spectrum data based on MATLAB.
Background
The arc spectrum diagnosis is a non-contact detection means and has the advantages of high sensitivity, good selectivity, no intervention, high space-time resolution and the like. The method utilizes the spectrum information of the welding arc to quantitatively characterize the temperature distribution and the electron density in the arc, is favorable for understanding the arc heat generation mechanism, discovers welding defects, and provides theoretical basis for improving the welding process and the weld quality. The spectrum data can be interfered by arc reflection, welding spatter, dark current of a CMOS photosensitive element of a high-speed camera and other multiple noise signals in the process of collecting. Therefore, the characteristic spectral lines need to be preprocessed before arc spectrum diagnosis to remove noise signals. In order to further improve the pretreatment quality, the invention provides an automatic extraction method of welding arc characteristic spectral line image spectral data based on MATLAB, which is used for improving the accuracy and the automation level of spectral diagnosis.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides a welding arc characteristic spectral line image spectrum data automatic extraction method based on MATLAB, which comprises the following steps:
S1: acquiring an arc characteristic spectral line image and preprocessing the arc characteristic spectral line image to obtain a first target image;
S2: removing noise data in the first target image to obtain a second target image; the noise data comprises first noise data, second noise data and third noise data, wherein the first noise data is noise data generated by arc reflection on the surfaces of welding gun nozzles and welding workpieces, the second noise data is noise data generated by welding spatter and dark current of a CMOS photosensitive element of a high-speed camera on the periphery of the arc, and the third noise data is spiced salt noise data in the arc;
S3: removing invalid data in the second target image to obtain a third target image;
s4: and carrying out symmetry processing and wavelet noise reduction processing on the third target image to obtain target spectrum data.
Preferably, in step S1, the method for obtaining the first target image by acquiring and preprocessing the arc characteristic spectral line image comprises the following steps
S21, calling imread functions to obtain arc characteristic spectral line images according to a specified path;
S22, determining a rotation angle according to an included angle between the actual symmetry axis position of the arc characteristic spectral line image and the vertical line of the effective data of the first row of the nozzle;
S23, carrying out rotation processing on the arc characteristic spectral line image based on the rotation angle to obtain a preprocessed image;
S24, calling an ind2gray function to format the preprocessed image, and obtaining a first target image.
Preferably, in step S24, the method of formatting the first preprocessed image includes converting the first preprocessed image into an image of a gray mode, and forcibly converting data in the converted image into a double type.
Preferably, in step S2, the method for removing noise data in the preprocessed image to obtain the first target image includes the following steps:
S41, calling ginput functions to obtain upper and lower boundary pixel point coordinates of a preprocessed image, and removing first noise data based on the upper and lower boundary pixel point coordinates to obtain a first denoising image;
s42, acquiring an image edge detection result, and removing second noise data based on the edge detection result and the first denoising image to obtain a second denoising image;
And S43, calling medfilt2 function pairs to reject the third noise data, and obtaining a second target image.
Preferably, in step S42, the method for obtaining the edge detection result is:
s51: invoking graythresh a function to obtain an edge threshold of the second target image;
s52: invoking an im2bw function to perform binarization processing on the second target image to obtain a binarized image;
s53: and calling an edge function canny operator, and carrying out edge detection on the binarized image based on the edge threshold value to obtain an edge detection result.
Preferably, in step S3, the method for removing invalid data in the second target image to obtain the third target image includes: calling an inter 1 function, adopting a spline cubic spline interpolation method to improve the spectrum data processing resolution, and adopting a cell array form to store the data in the third target image after invalid data are removed.
Preferably, in step S4, the method of symmetry processing is as follows: and determining the symmetrical position of the third target image according to the parity number of the radial data in the third target image, and averaging the data with equal distances at the two sides of the symmetrical position.
Preferably, in step S4, the method of wavelet noise reduction processing is as follows: and invoking wden a function to perform wavelet decomposition, selecting a maximum and minimum threshold value according to noise conditions, and performing soft threshold quantization processing on the decomposed high-frequency coefficient, wherein the soft threshold value is confirmed according to the result of the first-layer wavelet decomposition.
The beneficial effects of the invention are as follows:
(1) According to the invention, according to the characteristic of welding arc spectrum collection, noise signals generated by arc reflection, welding splashing and dark current of a CMOS photosensitive element of a high-speed camera are removed, and the harmful influence of the noise signals on spectrum data is avoided.
(2) According to the invention, through characteristic spectral line data interpolation, wavelet noise reduction and symmetric processing, the extraction precision and the extraction efficiency of spectral data are effectively improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below. Like elements or portions are generally identified by like reference numerals throughout the several figures. In the drawings, elements or portions thereof are not necessarily drawn to scale.
FIG. 1 is a flow chart of an automatic extraction method of spectral data of a welding arc characteristic spectral line image based on MATLAB;
FIG. 2 is an arc characteristic spectral line image acquired by a high speed camera;
FIG. 3 is an arc characteristic spectral line image after eliminating arc reflection noise;
FIG. 4 is an arc characteristic line edge position;
FIG. 5 is an arc characteristic spectral line image after weld spatter and dark current noise rejection;
FIG. 6 is a spectral line intensity distribution of an arc characteristic spectral line image before third line symmetrization;
FIG. 7 is a line intensity distribution of a third line of the arc characteristic line image after symmetry;
Fig. 8 is a spectral line intensity distribution after the third line wavelet noise reduction processing of the arc characteristic spectral line image.
Detailed Description
Embodiments of the technical scheme of the present invention will be described in detail below with reference to the accompanying drawings. The following examples are only for more clearly illustrating the technical aspects of the present invention, and thus are merely examples, and are not intended to limit the scope of the present invention.
It is noted that unless otherwise indicated, technical or scientific terms used herein should be given the ordinary meaning as understood by one of ordinary skill in the art to which this application belongs.
As shown in fig. 1, an automatic extraction method for spectral data of welding arc characteristic spectral line images based on MATLAB comprises the following steps:
S1: acquiring an arc characteristic spectral line image and preprocessing the arc characteristic spectral line image to obtain a first target image;
S2: removing noise data in the first target image to obtain a second target image; the noise data comprises first noise data, second noise data and third noise data, wherein the first noise data is noise data generated by arc reflection on the surfaces of welding gun nozzles and welding workpieces, the second noise data is noise data generated by welding spatter and dark current of a CMOS photosensitive element of a high-speed camera on the periphery of the arc, and the third noise data is spiced salt noise data in the arc;
S3: removing invalid data in the second target image to obtain a third target image;
s4: and carrying out symmetry processing and wavelet noise reduction processing on the third target image to obtain target spectrum data.
The automatic extraction method of the welding arc image spectrum data based on MATLAB provided by the invention not only can remove arc reflection noise, welding spatter and dark current noise of a CMOS photosensitive element, and effectively improve the accuracy of characteristic spectral line data extraction, but also can effectively improve the extraction precision and diagnosis efficiency of the arc spectrum data by means of interpolation processing, effective data extraction of characteristic spectral line images, data symmetry and the like, and lays a reliable foundation for subsequent arc spectrum diagnosis.
In a preferred embodiment, in step S1, an arc characteristic spectral line image is acquired and preprocessed to obtain a first target image, the method comprising the steps of
S21, calling imread functions to obtain arc characteristic spectral line images according to a specified path;
S22, determining a rotation angle according to an included angle between the actual symmetry axis position of the arc characteristic spectral line image and the vertical line of the effective data of the first row of the nozzle;
S23, carrying out rotation processing on the arc characteristic spectral line image based on the rotation angle to obtain a preprocessed image;
S24, calling an ind2gray function to format the preprocessed image, and obtaining a first target image.
Specifically, the arc characteristic spectral line image is collected through a high-speed camera and stored in a designated path, as shown in fig. 2, a imread function is called to read a welding arc characteristic spectral line image in a program path, a imrotate function nearest linear interpolation algorithm is used for carrying out rotation processing on the image, the size of an output image after rotation is consistent with that of an input image, redundant parts are cut, the rotation angle is determined according to the included angle between the actual symmetry axis position of the image and the vertical line of effective data in the first row below a nozzle, the positive and negative directions of atand correspond to the reverse and the forward directions of the rotation direction, an ind2gray function is called according to image characteristic adjustment, an index mode image derived by the high-speed camera is converted into a gray mode, data are forcedly converted into a double type, and the subsequent spectrum data are convenient to preprocess.
As a preferred embodiment, in step S2, the method for removing noise data in the preprocessed image to obtain the second target image includes the following steps:
S41, invoking ginput functions to obtain upper and lower boundary pixel point coordinates of the preprocessed image, and removing first noise data based on the upper and lower boundary pixel point coordinates to obtain a first denoising image;
s42, acquiring an image edge detection result, and removing second noise data based on the edge detection result and the first denoising image to obtain a second denoising image;
And S43, calling medfilt2 function pairs to reject the third noise data, and obtaining a second target image.
Specifically, in step S42, the method for obtaining the edge detection result includes:
s51: invoking graythresh a function to obtain an edge threshold of the second target image;
s52: invoking an im2bw function to perform binarization processing on the second target image to obtain a binarized image;
S53: calling an edge function, and carrying out edge detection on the binarized image based on the edge threshold value to obtain an edge detection result;
Because of abrupt change of light intensity in arc light reflection areas on the surface of a welding gun nozzle and a welding workpiece, irregular distribution is presented; in the arc region, the light intensity distribution from the left edge to the right edge of the arc shows a change rule that the light intensity distribution is increased and then reduced, so that imagesc functions are called to zoom data in a first target image and display the image, the coordinates of upper and lower boundary pixels of the arc are obtained by adopting ginput functions, the data extraction region is adjusted, noise signals generated by arc reflection on the surfaces of a welding gun nozzle and a welding workpiece are removed, signal interference is reduced, and a first denoising image is obtained, as shown in fig. 3.
And calling graythresh a function to realize a maximum inter-class variance method, acquiring an edge threshold value of the arc characteristic spectral line image, and converting the gray level image into a binary image by adopting an im2bw function. And calling an edge function, and selecting a canny operator based on edge gradient direction non-maximum suppression to perform edge detection, so that an edge position is obtained, as shown in fig. 4.
And calling a morphological opening operation imopen function and a corrosion operation imerode function, performing product operation on the pixel point data from which arc reflection noise is removed and the arc edge detection result, removing second noise data, and realizing shielding of welding spatter outside the arc edge and noise signals generated by dark current of the CMOS photosensitive element to obtain a second denoising image.
For salt and pepper noise generated by dark current in the arc, a medfilt function is called to realize median filtering to restrain, so that a second target image is obtained, as shown in fig. 5.
In a preferred embodiment, in step S3, the method for removing invalid data in the second target image to obtain the third target image includes: calling an inter 1 function, adopting a spline cubic spline interpolation method to improve the spectrum data processing resolution, and adopting a cell array form to store the data in the third target image after invalid data are removed.
Specifically, an interpolation method is adopted to interpolate the radial direction and the axial direction of the arc by calling an interpolation 1 function by adopting a spline cubic spline interpolation method, so that the spectral data processing resolution is improved. The interpolation number can be changed according to the analysis requirement precision, and a cyclic statement is applied in the interpolation process to calibrate the pixel points which are very close to zero and generated by interpolation as invalid data so as to return the pixel points to zero.
For images acquired by high speed cameras, only a small fraction of the pixels are used to store arc characteristic spectral line intensities, while the remaining pixels store invalid information. In order to improve the efficiency of the subsequent spectrum analysis as much as possible and reduce the calculation amount, invalid information should be deleted in the process of extracting the spectrum data. In addition, because the arc characteristic spectral line image is in a bell shape as a whole, effective pixels close to the position of the welding gun nozzle for storing the arc characteristic spectral line intensity are fewer, and effective pixels close to the position of the welding workpiece are more. Therefore, the characteristic spectral line intensity of the electric arc is stored in a cell array mode, and the requirements of different effective pixel points of different heights of the electric arc are met.
In a preferred embodiment, in step S4, the method of symmetry processing is as follows: and determining the symmetrical position of the third target image according to the parity number of the radial data in the third target image, and averaging the data with equal distances at the two sides of the symmetrical position.
Specifically, if the number of data is even, carrying out average value processing on the data at two sides of the symmetrical center line; if the number of the data is odd, the data of the symmetry center is not processed, and the data on two sides of the symmetry center line is subjected to average value processing. In addition, in order to further improve the efficiency of the subsequent spectral analysis, only the data from the center to half of the edge of the arc is extracted, and the data of the third line of the arc characteristic spectral line image after the symmetrization processing is as shown in FIG. 7
As a preferred embodiment, in step S4, the method of wavelet noise reduction processing is as follows: and invoking wden a function to perform wavelet decomposition, selecting a maximum and minimum threshold value according to noise conditions, and performing soft threshold quantization processing on the decomposed high-frequency coefficient, wherein the soft threshold value is confirmed according to the result of the first-layer wavelet decomposition, and the data of the third line of the arc characteristic spectral line image after the wavelet noise reduction processing is shown in fig. 8.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some or all of the technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit of the invention, and are intended to be included within the scope of the appended claims and description.
Claims (8)
1. The automatic extraction method of the welding arc characteristic spectral line image spectral data based on MATLAB is characterized by comprising the following steps of:
S1: acquiring an arc characteristic spectral line image and preprocessing the arc characteristic spectral line image to obtain a first target image;
S2: removing noise data in the first target image to obtain a second target image; the noise data comprises first noise data, second noise data and third noise data, wherein the first noise data is noise data generated by arc reflection on the surfaces of welding gun nozzles and welding workpieces, the second noise data is noise data generated by welding spatter and dark current of a CMOS photosensitive element of a high-speed camera on the periphery of the arc, and the third noise data is spiced salt noise data in the arc;
S3: removing invalid data in the second target image to obtain a third target image;
s4: and carrying out symmetry processing and wavelet noise reduction processing on the third target image to obtain target spectrum data.
2. The automatic extraction method of welding arc characteristic spectral line image spectral data based on MATLAB according to claim 1, wherein in step S1, the method of obtaining an arc characteristic spectral line image and preprocessing the arc characteristic spectral line image to obtain a first target image comprises the following steps:
s21, calling imread functions to obtain arc characteristic spectral line images according to a specified path;
S22, determining a rotation angle according to an included angle between the actual symmetry axis position of the arc characteristic spectral line image and the vertical line of the effective data of the first row of the nozzle;
S23, carrying out rotation processing on the arc characteristic spectral line image based on the rotation angle to obtain a preprocessed image;
S24, calling an ind2gray function to format the preprocessed image, and obtaining a first target image.
3. The automatic extraction method of welding arc characteristic spectral line image spectral data based on MATLAB according to claim 2, wherein in step S24, the method of calling the ind2gray function to format the preprocessed image comprises:
and converting the preprocessed image into an image in a gray mode, and forcedly converting data in the converted image into a double type.
4. The automatic extraction method of welding arc characteristic spectral line image spectral data based on MATLAB according to claim 1, wherein in step S2, the method of removing noise data in the first target image to obtain a second target image comprises the following steps:
S41, calling ginput functions to obtain upper and lower boundary pixel point coordinates of a first target image, and removing first noise data based on the upper and lower boundary pixel point coordinates to obtain a first denoising image;
s42, acquiring an image edge detection result, and removing second noise data based on the edge detection result and the first denoising image to obtain a second denoising image;
and S43, calling medfilt a function to reject the third noise data, and obtaining a second target image.
5. The automatic extraction method of welding arc characteristic spectral line image spectrum data based on MATLAB as set forth in claim 4, wherein in step S42, the method for obtaining the edge detection result is as follows:
S51: calling graythresh a function to acquire an edge threshold value of the second target image;
s52: invoking an im2bw function to perform binarization processing on the second target image to obtain a binarized image;
s53: and calling an edge function canny operator, and carrying out edge detection on the binarized image based on the edge threshold value to obtain an edge detection result.
6. The automatic extraction method of welding arc characteristic spectral line image spectral data based on MATLAB according to claim 1, wherein in step S3, the method for removing invalid data in the second target image to obtain a third target image is as follows: calling an inter 1 function, adopting a spline cubic spline interpolation method to improve the spectrum data processing resolution, and adopting a cell array form to store the data in the third target image after invalid data are removed.
7. The automatic extraction method of welding arc characteristic spectral line image spectral data based on MATLAB according to claim 1, wherein in step S4, the method of symmetry processing is as follows: and determining the symmetrical position of the third target image according to the parity number of the radial data in the third target image, and averaging the data with equal distances at the two sides of the symmetrical position.
8. The automatic extraction method of welding arc characteristic spectral line image spectrum data based on MATLAB according to claim 1, wherein in step S4, the wavelet noise reduction processing method is as follows: and calling wden a function to perform wavelet decomposition, selecting a maximum and minimum threshold according to noise conditions, and performing soft threshold quantization processing on the decomposed high-frequency coefficient, wherein the soft threshold is confirmed according to the result of the first-layer wavelet decomposition.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111215791.6A CN113850802B (en) | 2021-10-19 | 2021-10-19 | MATLAB-based automatic extraction method for spectral data of welding arc characteristic spectral line image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111215791.6A CN113850802B (en) | 2021-10-19 | 2021-10-19 | MATLAB-based automatic extraction method for spectral data of welding arc characteristic spectral line image |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113850802A CN113850802A (en) | 2021-12-28 |
| CN113850802B true CN113850802B (en) | 2024-06-14 |
Family
ID=78978880
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111215791.6A Active CN113850802B (en) | 2021-10-19 | 2021-10-19 | MATLAB-based automatic extraction method for spectral data of welding arc characteristic spectral line image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113850802B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116921817B (en) * | 2023-09-15 | 2023-12-15 | 中建安装集团有限公司 | Automatic TIG welding arc concentration on-line monitoring and intelligent early warning method |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106504214A (en) * | 2016-10-31 | 2017-03-15 | 西京学院 | Wavelet transformation and the high spectrum image Banded improvement removing method of local interpolation fusion |
| CN111069748A (en) * | 2019-12-20 | 2020-04-28 | 南京理工大学 | Method and device for detecting and controlling arc rotation of hollow stud welding in real time |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR100615047B1 (en) * | 2005-03-11 | 2006-08-22 | 목포해양대학교 산학협력단 | Method for auto-detecting defect of welding position |
| CN104551347B (en) * | 2014-12-30 | 2016-05-25 | 江苏科技大学 | Infrared visual sensing detection method and the device of narrow gap weld seam deviation |
| CN113000988A (en) * | 2019-12-22 | 2021-06-22 | 深圳市新盛机器人有限公司 | Processing method of visual welding tracking sensing system |
-
2021
- 2021-10-19 CN CN202111215791.6A patent/CN113850802B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106504214A (en) * | 2016-10-31 | 2017-03-15 | 西京学院 | Wavelet transformation and the high spectrum image Banded improvement removing method of local interpolation fusion |
| CN111069748A (en) * | 2019-12-20 | 2020-04-28 | 南京理工大学 | Method and device for detecting and controlling arc rotation of hollow stud welding in real time |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113850802A (en) | 2021-12-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102479383B (en) | Method and device for removing salt and pepper noise | |
| CN109489566B (en) | Lithium battery diaphragm material slitting width detection method, detection system and device | |
| CN113850802B (en) | MATLAB-based automatic extraction method for spectral data of welding arc characteristic spectral line image | |
| CN116433666B (en) | Board card line defect online identification method, system, electronic equipment and storage medium | |
| CN110196252B (en) | Groove defect detection algorithm and device | |
| WO2022027877A1 (en) | Method and apparatus for measuring movement speed of contact of vacuum switch | |
| CN115661110B (en) | Transparent workpiece identification and positioning method | |
| CN111144318A (en) | Point cloud data noise reduction method for underwater sonar system | |
| CN110956624A (en) | Image definition evaluation method for three-dimensional object | |
| EP2902964B1 (en) | Image processing method and image processing apparatus | |
| CN109410137B (en) | Method for detecting dim and weak target | |
| CN116109695A (en) | Centroid positioning method and related equipment | |
| CN108492320B (en) | Infrared dim target detection method based on parallel processing | |
| Liu et al. | Image processing of welding seam based on single-stripe laser vision system | |
| CN111353952B (en) | Method for eliminating black boundary after image distortion correction | |
| CN114143451B (en) | Focusing method for stroke-free recording focusing motor | |
| Malathy et al. | Removal of impulse noise using decision tree based denoising method | |
| CN111915581B (en) | Method for detecting defects of smooth metal cambered surface | |
| CN117115174B (en) | Automatic detection method and system for appearance of pliers | |
| CN117036387A (en) | Glass contour detection method, device, equipment and medium | |
| Marković et al. | Improving sub-pixel estimation of laser stripe reflection center by autoconvolution on FPGA | |
| CN117291966A (en) | Method and system for extracting width of metal directional energy deposition molten pool | |
| CN117351072A (en) | Non-axisymmetric plasma arc temperature field calculation processing system and method | |
| Fang | Application of Improved Adaptive Median Filtering in Wheel Image Processing | |
| CN117078663A (en) | Weak and small target detection method based on background perception |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |