CN110751628A - Ultrasonic image-based automatic weld defect identification method - Google Patents
Ultrasonic image-based automatic weld defect identification method Download PDFInfo
- Publication number
- CN110751628A CN110751628A CN201910904310.9A CN201910904310A CN110751628A CN 110751628 A CN110751628 A CN 110751628A CN 201910904310 A CN201910904310 A CN 201910904310A CN 110751628 A CN110751628 A CN 110751628A
- Authority
- CN
- China
- Prior art keywords
- value
- activation region
- weldment
- image
- root
- 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.)
- Granted
Links
- 230000007547 defect Effects 0.000 title claims abstract description 21
- 238000000034 method Methods 0.000 title claims abstract description 17
- 230000004913 activation Effects 0.000 claims abstract description 34
- 238000003466 welding Methods 0.000 claims abstract description 17
- 239000011159 matrix material Substances 0.000 claims abstract description 12
- 238000010586 diagram Methods 0.000 claims abstract description 10
- 238000003708 edge detection Methods 0.000 claims abstract description 10
- 238000001514 detection method Methods 0.000 claims abstract description 8
- 230000011218 segmentation Effects 0.000 claims abstract description 8
- 238000000354 decomposition reaction Methods 0.000 claims abstract description 6
- 230000009466 transformation Effects 0.000 claims abstract description 6
- 239000002893 slag Substances 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 4
- 230000007797 corrosion Effects 0.000 claims description 4
- 238000005260 corrosion Methods 0.000 claims description 4
- 230000002950 deficient Effects 0.000 claims description 3
- 238000005259 measurement Methods 0.000 abstract description 2
- 238000004519 manufacturing process Methods 0.000 description 3
- 238000005034 decoration Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000035515 penetration Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 239000000523 sample Substances 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 229910000831 Steel Inorganic materials 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000010339 dilation Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000005530 etching Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000013441 quality evaluation Methods 0.000 description 1
- 239000010959 steel Substances 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
- 238000002604 ultrasonography Methods 0.000 description 1
Images
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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration using local operators
- G06T5/30—Erosion or dilatation, e.g. thinning
-
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10132—Ultrasound image
-
- 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
- G06T2207/20061—Hough transform
-
- 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)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Quality & Reliability (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Investigating Or Analyzing Materials By The Use Of Ultrasonic Waves (AREA)
Abstract
The invention discloses an automatic weld defect identification method based on ultrasonic images. Based on a weldment pairing diagram output by the welding seam ultrasonic detection device, the position of a groove line is automatically detected by utilizing vertical edge detection and Hough transformation, and then the position of the root of the weldment is automatically detected based on groove line distance measurement. And for a weld scanning image output by the ultrasonic equipment, obtaining the activation regions with different amplitudes by using two-stage threshold segmentation. Then, the number of the two stages of activation regions is counted, the axis of the activation region is obtained by using a method of performing eigenvalue decomposition on a covariance matrix of pixel point coordinates, the position relation between the activation region and a groove and the position relation between the activation region and the root are analyzed, and finally the defect type of the welding line is automatically identified.
Description
Technical Field
The invention belongs to the field of image processing, and relates to an automatic weld defect identification method based on an ultrasonic image.
Background
In recent years, welding techniques have been widely used in manufacturing various structures in the industry, and steel pipes and other welded parts are put into production in large quantities. In any industry, the welding quality has strict standards, and the defects of the welding seam can cause hidden dangers to life or production safety. When the quality evaluation of the welding seam is detected, an ultrasonic mode can be adopted. The moving probe of the ultrasonic wave is used for scanning the weldment along a certain direction, the amplitude of the echo is recorded and processed to generate an image, and then the ultrasonic welding seam images are manually identified and judged to have error defects. With the penetration of artificial intelligence in various industries, the processing and the discrimination of various signals are in transition to automation and intellectualization, but the automatic discrimination of the welding seam ultrasonic image has not made breakthrough progress.
Disclosure of Invention
In order to solve the problems, the invention provides an automatic weld defect identification method based on ultrasonic images.
The invention mainly adopts the technical scheme that:
an automatic weld defect identification method based on ultrasonic images comprises the following specific steps:
step S1: reading a weldment pairing diagram output by ultrasonic equipment, and automatically judging the positions of a groove and a root from the weldment pairing diagram;
step S2: reading an amplitude gray image I output by ultrasonic scanning of a welding seam, wherein the size of the amplitude gray image is recorded as h multiplied by w, h represents the height, and w represents the width; using a threshold value tau1Performing primary threshold segmentation to obtain a binary image I1，τ1The value range of (a) is 0.75-0.95;
step S3: will correspond to I in I1The gray value of the pixel point with the middle value of 1 is set to be 0, and the utilization threshold value of I is tau2Performing two-stage threshold segmentation to obtain a binary image I2，τ2The value range of (A) is 0.5-0.7;
step S4: to I1And I2Performing corrosion expansion treatment, statistics I1And I2The number n of connected regions (called active regions) having a pixel point value of 11,n2；
Step S5: if n is1If yes, go to step S6; if n is1If not, turning to step S7;
step S6: if n is2If the value is 0, judging that the film is not defective; if n is2If the air quantity is more than 0, judging the air bubble;
step S7: if n is1If it is 1, go to step S8; if n is1If the value is more than 1, turning to the step S11;
step S8: if n is2If yes, go to step S9; if n is2If the slag content is more than 0, judging the slag is 'strip slag';
step S9: calculation of I1The axis of the middle activation region is checked to determine whether the axis is matched with the groove position obtained in the step 1, if so, the defect type of the welding seam is judged to be 'groove unfused', and if not, the step S10 is switched to;
step S10: judging whether the area is consistent with the root position, if so, judging the type of the weld defect as 'root incomplete welding', if not, classifying as 'difficult sample', and waiting for manual treatment;
step 11: the specimen was judged to be "cracked".
The automatic determination of the position of the slope line and the root in the step S1 uses technologies such as edge detection and hough transform, and specifically includes the following steps:
step S1.1: binarizing the weldment group diagram by using a threshold value of 0.5, wherein the threshold value range is 0.4-0.6;
step S1.2: and (3) carrying out vertical edge detection on the binary image, wherein the used filter template is as follows:
step S1.3: carrying out Hough transformation on the image of the edge detection result, and searching a peak value in a parameter space after the Hough transformation;
step S1.4: converting the peak value in the parameter space into an original image space to obtain the position of a welded part slope line;
step S1.5: and transversely scanning a result image of the detection of the slope lines, calculating the distance between the slope lines, and marking the position with the shortest distance as the root position of the weldment.
In the step S9, it is determined whether the activation region is matched with the groove, and techniques such as covariance matrix construction and eigenvalue decomposition are used, and the specific steps are as follows:
step S9.1: constructing a matrix X, wherein the dimension of the matrix is Nx 2, N is the number of pixel points of the activation region, and each row of X stores the transverse coordinate value and the longitudinal coordinate value of a corresponding pixel point respectively;
step S9.2: calculating the average value of the transverse coordinates and the longitudinal coordinates of all coordinate points in the activation region, taking the average value as the coordinate value of the centroid of the activation region, and then subtracting the average value from each row of elements in the X;
step S9.3: solving covariance matrix
Step S9.4: carrying out eigenvalue decomposition on the sigma, and recording the eigenvector corresponding to the maximum eigenvalue as v;
step S9.5: taking the ratio of the second element to the first element in v as a slope, and solving a straight line passing through the centroid to obtain the axis of the activation region;
step S9.5: calculating included angles between the axis and all groove lines and distances from the center of mass to the groove lines, if the included angles are less than 10 degrees and the distances are less than
The axis is considered to coincide with the bevel line, otherwise it is not.
In the step S10, it is determined whether the activation region is matched with the root, and the specific steps are as follows:
step S10.1: calculating the mean value of the transverse coordinates and the longitudinal coordinates of all coordinate points in the activation region as the centroid of the activation region;
step S10.2: if the distance between the area centroid and the root line of the weldment is less than 0.1h, the activated area is judged to be matched with the root of the weldment, otherwise, the activated area is not matched.
The invention has the beneficial effects that:
based on a weldment pairing diagram output by the welding seam ultrasonic detection device, the position of a groove line is automatically detected by utilizing vertical edge detection and Hough transformation, and then the position of the root of the weldment is automatically detected based on groove line distance measurement. And for a weld scanning image output by the ultrasonic equipment, obtaining the activation regions with different amplitudes by using two-stage threshold segmentation. Then, the number of the two stages of activation regions is counted, the axis of the activation region is obtained by using a method of performing eigenvalue decomposition on a covariance matrix of pixel point coordinates, the position relation between the activation region and a groove and the position relation between the activation region and the root are analyzed, and finally the defect type of the welding line is automatically identified. The system can distinguish normal welding seams and five kinds of defective welding seams: and (3) classifying the samples which cannot be identified by the system into difficult samples to wait for manual treatment due to bubbles, strip slag, cracks, incomplete fusion of grooves and incomplete root penetration.
Drawings
FIG. 1 is a flow chart of the method of the present invention;
FIG. 2 illustrates a weldment set pairing in the embodiment;
FIG. 3 vertical edge detection results of a weldment set pair map;
fig. 4 extreme points in the hough transform parameter space;
FIG. 5 shows a detection result of a weld groove line position;
FIG. 6 shows the result of the detection of the root line position of the weldment;
the ultrasound scan amplitude map in the example of fig. 7;
FIG. 8 is a first level thresholding image;
FIG. 9 shows the results of the etching treatment;
FIG. 10 results of the dilation process;
FIG. 11 axis detection results of the activation region.
Detailed Description
In order to make those skilled in the art better understand the technical solutions in the present application, the technical solutions in the embodiments of the present application are clearly and completely described below, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
The technical solution of the present invention is further described in detail with reference to the accompanying drawings, which take an ultrasonic scan image of a certain weldment as an example.
Example (b):
an automatic weld defect identification method based on ultrasonic images is shown in fig. 1, and comprises the following specific steps:
step S1: reading a weldment group diagram output by ultrasonic equipment, as shown in FIG. 2, and automatically judging the positions of a groove and a root from the weldment group diagram;
step S2: reading an amplitude gray image I of a weldment output from an ultrasonic scan, the image having a size of 256 x 400, as shown in FIG. 7, using a threshold τ1Performing primary threshold segmentation to obtain a binary image I (0.8)1As shown in fig. 8;
step S3: will correspond to I in I1The gray value of the pixel point with the middle value of 1 is set to be 0, and the utilization threshold value of I is tau2Performing two-stage threshold segmentation to obtain binary image I (0.6)2In this case, none of the pixels of the obtained image is 1, which is a full black image;
step S4: to I1And I2Performing corrosion expansion treatment, statistics I1And I2The number n of connected regions (called active regions) having a pixel point value of 11,n2In this case I2Within which no activation region is detected, I1The corrosion and expansion results are shown in fig. 9 and 10, respectively;
step S5: if n is1If yes, go to step S6; if n is1> 0, go to step S7, since n is in this example1> 0, subsequently performing step S7;
step S7: if n is1If it is 1, go to step S8; if n is1If > 1, go to step S11, since n is the case1Step S8 is subsequently performed when it is 1;
step S8: if n is2If yes, go to step S9; if n is2If the value is more than 0, the value is judged to be 'bar slag', since n is in the example2When it is 0, step S9 is subsequently performed;
step S9: calculation of I1The axis of the activation region is detected, whether the position of the groove is consistent with the position of the groove obtained in the step 1 is checked,if the result of the calculation is agreement, the weld defect is identified as "groove unfused".
The specific steps of step S1 are as follows:
step S1.1: binarizing the weldment group by using a threshold value of 0.5;
step S1.2: and (3) carrying out vertical edge detection on the binary image, wherein the used filter template is as follows:
the detection results are shown in FIG. 3;
step S1.3: carrying out Hough transform on the image of the edge detection result, and searching a peak value in a parameter space after Hough transform, wherein the result is shown in FIG. 4;
step S1.4: converting the peak value in the parameter space to the original image space to obtain the position of the weld piece notch line, and the result is shown as a thick line in fig. 5;
step S1.5: the image is scanned transversely, the distance between the groove lines is calculated, and the position with the shortest distance is marked as the root position of the weldment, and the result is shown by the thick line in fig. 6.
The specific steps of step S9 are as follows:
step S9.1: constructing a matrix X, wherein the dimension of the matrix is Nx 2, N is the number of pixel points of the activation region, and each row of X stores the transverse coordinate value and the longitudinal coordinate value of a corresponding pixel point respectively;
step S9.2: calculating the average value of the transverse coordinates and the longitudinal coordinates of all coordinate points in the activation region, taking the average value as the coordinate value of the centroid of the region, and then subtracting the average value from each row of elements in the X;
step S9.3: solving a covariance matrix;
step S9.4: carrying out eigenvalue decomposition on the sigma, and recording the eigenvector corresponding to the maximum eigenvalue as v;
step S9.5: taking the ratio of the second element to the first element in v as a slope, finding a straight line passing through the centroid to obtain an axis of the activation region, wherein the axis is shown in fig. 11;
step S9.5: calculating the included angles between the axis and all the groove lines and the distances from the center of mass to the groove lines, wherein the included angle between the axis and the right groove line is 5 degrees less than 10 degrees, and the distance from the center of mass to the groove line is about 20 degrees and is also less thanThe axis is considered to coincide with the bevel line.
The foregoing is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, various modifications and decorations can be made without departing from the principle of the present invention, and these modifications and decorations should also be regarded as the protection scope of the present invention.
Claims (4)
1. An automatic weld defect identification method based on ultrasonic images is characterized by comprising the following specific steps:
step S1: reading a weldment pairing diagram output by ultrasonic equipment, and automatically judging the positions of a groove and a root from the weldment pairing diagram;
step S2: reading an amplitude gray image I output by ultrasonic scanning of a welding seam, wherein the size of the amplitude gray image I is recorded as h multiplied by w, h represents the height, and w represents the width; using a threshold value tau1Performing primary threshold segmentation to obtain a binary image I1，τ1The value range of (a) is 0.75-0.95;
step S3: will correspond to I in I1The gray value of the pixel point with the middle value of 1 is set to be 0, and the utilization threshold value of I is tau2Performing two-stage threshold segmentation to obtain a binary image I2，τ2The value range of (A) is 0.5-0.7;
step S4: to I1And I2Performing corrosion expansion treatment, statistics I1And I2The number n of connected regions with the pixel point value of 11,n2；
Step S5: if n is1If yes, go to step S6; if n is1If not, turning to step S7;
step S6: if n is2If the value is 0, judging that the film is not defective; if n is2If the gas is more than 0, judging the gas is a bubble;
step S7: if n is1If it is 1, go to step S8; if n is1If the value is more than 1, turning to the step S11;
step S8: if n is2If yes, go to step S9; if n is2If the slag content is more than 0, judging the slag is 'strip slag';
step S9: calculation of I1The axis of the middle activation region is checked whether the position of the groove is consistent with the position of the groove obtained in the step S1, if so, the defect type of the welding seam is judged to be that the groove is not fused, and if not, the step S10 is executed;
step S10: judging whether the area is matched with the root position, if so, judging that the type of the weld defect is that the root is not completely welded, if not, classifying the weld defect as a difficult sample, and waiting for manual treatment;
step 11: and judging the crack.
2. The method for automatically identifying the weld defect based on the ultrasonic image according to claim 1, wherein the step S1 includes the following steps:
step S1.1: binarizing the weldment group diagram by using a threshold value, wherein the range of the threshold value is 0.4-0.6;
step S1.2: and (3) carrying out vertical edge detection on the binary image, wherein the used filter template is as follows:
step S1.3: carrying out Hough transformation on the image of the edge detection result, and searching a peak value in a parameter space after the Hough transformation;
step S1.4: converting the peak value in the parameter space into an original image space to obtain the position of a welded part slope line;
step S1.5: and transversely scanning a result image of the detection of the slope lines, calculating the distance between the slope lines, and marking the position with the shortest distance as the root position of the weldment.
3. The method for automatically identifying the weld defect based on the ultrasonic image according to claim 1, wherein the step S9 includes the following steps:
step S9.1: constructing a matrix X, wherein the dimension of the matrix is Nx 2, N is the number of pixel points of the activation region, and each row of X stores the transverse coordinate value and the longitudinal coordinate value of a corresponding pixel point respectively;
step S9.2: calculating the average value of the transverse coordinates and the longitudinal coordinates of all coordinate points in the activation region, taking the average value as the coordinate value of the centroid of the activation region, and then subtracting the average value from each row of elements in the X;
step S9.3: solving covariance matrix
Step S9.4: carrying out eigenvalue decomposition on the sigma, and recording the eigenvector corresponding to the maximum eigenvalue as v;
step S9.5: taking the ratio of the second element to the first element in v as a slope, and solving a straight line passing through the centroid to obtain the axis of the activation region;
step S9.5: calculating included angles between the axis and all groove lines and distances from the center of mass to the groove lines, if the included angles are less than 10 degrees and the distances are less than
The axis is considered to coincide with the bevel line, otherwise it is not.
4. The ultrasonic image-based weld defect automatic identification method according to claim 1, characterized in that: the specific steps of step S10 are as follows:
step S10.1: calculating the mean value of the transverse coordinates and the longitudinal coordinates of all coordinate points in the activation region as the centroid of the activation region;
step S10.2: and if the distance between the centroid of the activation region and the root line of the weldment is less than 0.1h, judging that the activation region is matched with the root of the weldment, otherwise, not matching.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910904310.9A CN110751628B (en) | 2019-09-24 | 2019-09-24 | Ultrasonic image-based automatic weld defect identification method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910904310.9A CN110751628B (en) | 2019-09-24 | 2019-09-24 | Ultrasonic image-based automatic weld defect identification method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110751628A true CN110751628A (en) | 2020-02-04 |
| CN110751628B CN110751628B (en) | 2022-09-16 |
Family
ID=69276953
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910904310.9A Active CN110751628B (en) | 2019-09-24 | 2019-09-24 | Ultrasonic image-based automatic weld defect identification method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110751628B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112733884A (en) * | 2020-12-23 | 2021-04-30 | 树根互联技术有限公司 | Welding defect recognition model training method and device and computer terminal |
| CN113256566A (en) * | 2021-04-29 | 2021-08-13 | 广州杰赛科技股份有限公司 | Pipeline weld defect identification method |
| CN113469388A (en) * | 2021-09-06 | 2021-10-01 | 江苏中车数字科技有限公司 | Maintenance system and method for rail transit vehicle |
| CN113658132A (en) * | 2021-08-16 | 2021-11-16 | 沭阳九鼎钢铁有限公司 | Computer vision-based structural part weld joint detection method |
| CN115861307A (en) * | 2023-02-21 | 2023-03-28 | 深圳市百昌科技有限公司 | Fascia gun power supply drive plate welding fault detection method based on artificial intelligence |
| CN116228703A (en) * | 2023-02-21 | 2023-06-06 | 北京远舢智能科技有限公司 | Defect sample image generation method and device, electronic equipment and medium |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101393391B1 (en) * | 2012-12-28 | 2014-05-12 | 한밭대학교 산학협력단 | Vehicle license plate recognition method based on embedded system |
| CN107358221A (en) * | 2017-08-08 | 2017-11-17 | 大连万和海拓文化体育产业有限公司 | The chessboard localization method of spectrum is remembered in a kind of go based on video identification technology automatically |
-
2019
- 2019-09-24 CN CN201910904310.9A patent/CN110751628B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101393391B1 (en) * | 2012-12-28 | 2014-05-12 | 한밭대학교 산학협력단 | Vehicle license plate recognition method based on embedded system |
| CN107358221A (en) * | 2017-08-08 | 2017-11-17 | 大连万和海拓文化体育产业有限公司 | The chessboard localization method of spectrum is remembered in a kind of go based on video identification technology automatically |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112733884A (en) * | 2020-12-23 | 2021-04-30 | 树根互联技术有限公司 | Welding defect recognition model training method and device and computer terminal |
| CN113256566A (en) * | 2021-04-29 | 2021-08-13 | 广州杰赛科技股份有限公司 | Pipeline weld defect identification method |
| CN113658132A (en) * | 2021-08-16 | 2021-11-16 | 沭阳九鼎钢铁有限公司 | Computer vision-based structural part weld joint detection method |
| CN113658132B (en) * | 2021-08-16 | 2022-08-19 | 沭阳九鼎钢铁有限公司 | Computer vision-based structural part weld joint detection method |
| CN113469388A (en) * | 2021-09-06 | 2021-10-01 | 江苏中车数字科技有限公司 | Maintenance system and method for rail transit vehicle |
| CN115861307A (en) * | 2023-02-21 | 2023-03-28 | 深圳市百昌科技有限公司 | Fascia gun power supply drive plate welding fault detection method based on artificial intelligence |
| CN115861307B (en) * | 2023-02-21 | 2023-04-28 | 深圳市百昌科技有限公司 | Fascia gun power supply driving plate welding fault detection method based on artificial intelligence |
| CN116228703A (en) * | 2023-02-21 | 2023-06-06 | 北京远舢智能科技有限公司 | Defect sample image generation method and device, electronic equipment and medium |
| CN116228703B (en) * | 2023-02-21 | 2024-01-12 | 北京远舢智能科技有限公司 | Defect sample image generation method and device, electronic equipment and medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110751628B (en) | 2022-09-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110751628B (en) | Ultrasonic image-based automatic weld defect identification method | |
| CN113362326B (en) | Method and device for detecting defects of welding spots of battery | |
| WO2021213223A1 (en) | Weld quality inspection method, apparatus and system, and electronic device | |
| CN107808378B (en) | Method for detecting potential defects of complex-structure casting based on vertical longitudinal and transverse line profile features | |
| CN109859177B (en) | Deep learning-based industrial ray image evaluation method and device | |
| CN115184380B (en) | Method for detecting abnormity of welding spots of printed circuit board based on machine vision | |
| CN113344931A (en) | Plug-in visual detection and identification method, readable storage medium and device | |
| CN112053376B (en) | Workpiece weld joint identification method based on depth information | |
| CN112037203A (en) | Side surface defect detection method and system based on complex workpiece outer contour registration | |
| CN114240944B (en) | Welding defect detection method based on point cloud information | |
| US9996766B2 (en) | Imaging-based methods for detecting and measuring defects in extruded cellular ceramic articles | |
| CN114693610A (en) | Welding seam surface defect detection method, equipment and medium based on machine vision | |
| CN108876771B (en) | Undercut welding defect detection method | |
| CN113706537A (en) | Irregular workpiece detection method based on machine vision | |
| CN111390439B (en) | Welding seam detection method and device, welding robot and storage medium | |
| CN112950633A (en) | Aluminum alloy weld surface defect detection method based on line structured light | |
| Hu et al. | Rail surface spalling detection based on visual saliency | |
| CN111932490A (en) | Method for extracting grabbing information of visual system of industrial robot | |
| CN115619845A (en) | Self-adaptive scanning document image inclination angle detection method | |
| CN114677348A (en) | IC chip defect detection method and system based on vision and storage medium | |
| CN112101137B (en) | Welding seam identification and path extraction method for wall-climbing robot navigation | |
| CN116385433B (en) | Plastic pipeline welding quality assessment method | |
| CN108645865A (en) | A kind of measurement method of the submerged-arc welding steel pipe weld seam amount of the being partially welded parameter based on CCD | |
| CN114581385A (en) | Welding seam defect area mapping algorithm based on circle positioning | |
| CN110390649B (en) | Method for reducing noise of oil and gas pipeline weld image |
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 |