CN111438460A - Vision-based thick plate T-shaped joint welding seam forming characteristic online measurement method - Google Patents
Vision-based thick plate T-shaped joint welding seam forming characteristic online measurement method Download PDFInfo
- Publication number
- CN111438460A CN111438460A CN202010308187.7A CN202010308187A CN111438460A CN 111438460 A CN111438460 A CN 111438460A CN 202010308187 A CN202010308187 A CN 202010308187A CN 111438460 A CN111438460 A CN 111438460A
- Authority
- CN
- China
- Prior art keywords
- welding
- weld
- welding seam
- slope
- points
- 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
- 238000003466 welding Methods 0.000 title claims abstract description 89
- 238000000691 measurement method Methods 0.000 title claims abstract description 10
- 238000000034 method Methods 0.000 claims abstract description 51
- 238000001514 detection method Methods 0.000 claims abstract description 20
- 238000009499 grossing Methods 0.000 claims abstract description 18
- 238000003745 diagnosis Methods 0.000 claims abstract description 14
- 230000004927 fusion Effects 0.000 claims abstract description 12
- 230000035772 mutation Effects 0.000 claims abstract description 11
- 238000005259 measurement Methods 0.000 claims abstract description 8
- 238000005070 sampling Methods 0.000 claims description 22
- 238000004364 calculation method Methods 0.000 claims description 10
- 230000000007 visual effect Effects 0.000 claims description 9
- 238000000605 extraction Methods 0.000 claims description 5
- 230000001629 suppression Effects 0.000 claims description 4
- 238000001914 filtration Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 3
- 238000013519 translation Methods 0.000 claims description 2
- 230000015572 biosynthetic process Effects 0.000 abstract description 5
- 230000035515 penetration Effects 0.000 abstract description 5
- 238000012544 monitoring process Methods 0.000 abstract description 3
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 3
- 238000002474 experimental method Methods 0.000 description 2
- 230000002401 inhibitory effect Effects 0.000 description 2
- 238000000611 regression analysis Methods 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000005672 electromagnetic field Effects 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B23—MACHINE TOOLS; METAL-WORKING NOT OTHERWISE PROVIDED FOR
- B23K—SOLDERING OR UNSOLDERING; WELDING; CLADDING OR PLATING BY SOLDERING OR WELDING; CUTTING BY APPLYING HEAT LOCALLY, e.g. FLAME CUTTING; WORKING BY LASER BEAM
- B23K31/00—Processes relevant to this subclass, specially adapted for particular articles or purposes, but not covered by only one of the preceding main groups
- B23K31/12—Processes relevant to this subclass, specially adapted for particular articles or purposes, but not covered by only one of the preceding main groups relating to investigating the properties, e.g. the weldability, of materials
- B23K31/125—Weld quality monitoring
Abstract
The invention provides an online measurement method for welding seam forming characteristics of a T-shaped joint of a thick plate based on vision, which can be used for online measurement of penetration, fusion width and sectional area of seam forming. Firstly, designing a weld contour feature point recognition algorithm based on a slope mutation and supervision method according to an extracted weld contour, and realizing detection of feature points; secondly, aiming at the influence of various random interferences in welding on the detection of the welding seam contour characteristic points, a method based on cubic exponential smoothing is provided for fault diagnosis, and effective characteristic points are further obtained; and finally, calculating weld penetration, weld width and cross section on line by using the weld contour and the characteristic points extracted before welding and in welding and by adopting a high-order nonlinear fitting method. The invention is beneficial to controlling the formation of the welding seam through effectively measuring the forming characteristics of the welding seam, thereby realizing the online monitoring of the welding quality. The method has the advantages of time consumption reduction, high measurement precision, strong robustness and the like.
Description
Technical Field
The invention relates to a thick plate T-shaped joint welding seam forming characteristic on-line measuring method based on vision, and belongs to the technical field of multilayer multi-channel welding seam forming detection.
Background
One of the keys to weld quality is to control the weld formation to achieve the desired fill level. Weld formation is related to multiple heterogeneous influencing factors, and under a specific welding situation, welding process parameters are key factors influencing weld formation. The automatic and intelligent robot welding process needs to adjust welding process parameters according to the welding seam forming characteristics, and the on-line monitoring of the welding quality is realized. Thus, efficient measurement of weld formation characteristics helps to advance automation and intelligence of the welding process.
Currently, on-line measurement of weld forming characteristics mostly adopts a method based on visual sensing. The method is characterized in that a set of effective algorithm flow is designed to accurately obtain the characteristic points of the weld contour. The multi-layer and multi-pass welding seam contour feature points, the welding seam forming appearance and the filling area of the thick plate T-shaped joint have changeable characteristics, and the welding seam forming feature is detected based on a visual method and is easily interfered by an electromagnetic field, strong arc light and welding gun vibration, so that the challenge is provided for accurately obtaining the welding seam forming feature by the current method. Therefore, the working condition particularity of thick plate welding is comprehensively considered, and an algorithm which can provide basis for the online decision of the welding process parameters of the robot based on visual sensing and can accurately obtain the penetration, the fusion width and the sectional area of the multi-pass welding seam forming of the T-shaped joint of the thick plate is necessary in engineering design.
Disclosure of Invention
Aiming at the defects of the multilayer multi-pass welding seam outline characteristic point of the thick plate T-shaped joint and the welding seam forming characteristic parameter acquisition method, the invention provides the visual-based online measurement method for the welding seam forming characteristic of the thick plate T-shaped joint, and aims to conveniently realize the online detection of the typical characteristic parameters of the welding seam forming in a visual mode, and provide decision basis for controlling the welding seam forming to achieve the required filling amount and further realizing the online monitoring of the welding quality. In order to achieve the purpose, the technical scheme adopted by the invention is as follows:
the thick plate T-shaped joint welding seam forming characteristic on-line measuring method based on vision comprises the following steps:
the method comprises the steps of firstly, calculating the slope value of each data point of the extracted linear weld contour by utilizing an average sliding idea, then, inhibiting the influence generated by slope local disturbance by adopting an average high-order nonlinear fitting method, effectively approaching the overall change characteristic of the slope, carrying out mutation detection on the fitted data, and finally obtaining weld contour characteristic points according to a supervision method.
And step two, aiming at the invalid welding seam profile feature recognition condition, according to the sampling data before the current sampling moment, adopting a cubic exponential smoothing algorithm, providing a welding seam profile feature point extraction fault detection method, and realizing fault diagnosis of feature point recognition.
And thirdly, according to the situation that the welding seam profile can shift in the image under different space-time conditions, a method for measuring fusion width, fusion depth and sectional area in welding seam forming is provided based on a high-order nonlinear fitting method, and online measurement of the welding seam forming characteristics changed in multilayer multi-pass welding is effectively achieved.
Further, the specific steps of the first step are as follows:
the first step is as follows: the slope calculation and the fluctuation suppression are specifically described as firstly calculating slope values of all points by using an average sliding idea:
where x (), y () denote the coordinates of the linear weld profile data points, n denotes the number of data points used for each calculation, i denotes the data point footer, j denotes the footer of the data point adjacent to i, kjThe average of the n slopes is shown.
The second step is that: and performing smooth filtering on the slope by adopting a one-dimensional smoothing filter.
The third step: the slope data is averagely divided into two sections, and polynomial fitting for 50 times is respectively adopted for each section of data to carry out least square method fitting, and the polynomial fitting expression is as follows:
f(x)＝a1x50+a2x49+…a50
wherein the coefficient a1,a2,…a50Determined by the coordinates of the fitted data points.
The fourth step: the slope mutation detection is specifically described as that the slope fitting result replaces original slope data to carry out mutation detection, a slope monotonous interval is obtained, the length of each interval is marked according to the slope change rate of each monotonous interval, and the monotonous interval is defined by the formula:
the fifth step: sorting the length values of the monotonous intervals from large to small, and appointing the number of characteristic points of the weld contour according to a supervision method, thereby determining the number of the sorted monotonous intervals, and marking the middle position of each monotonous interval as the position of the characteristic point.
Furthermore, the fault diagnosis of the feature point identification adopts a cubic exponential smoothing algorithm, and accurately predicts the current feature point according to the sampling data before the current sampling moment, and specifically comprises the following steps:
the first step is as follows: the welding gun is positioned at the initial welding position before welding, and the welding seam outline characteristic points at the initial welding position are determined according to the method in the step one;
the second step is that: calculating Euclidean distances between the feature points obtained at the current sampling moment and the reference point by taking the effective feature points at the previous sampling moment as reference, and starting fault diagnosis if all the Euclidean distances are greater than a pixel threshold value;
the third step: the fault diagnosis adopts a cubic exponential smoothing algorithm, and the calculation formula is as follows:
wherein α is a smoothing coefficient, xtThe horizontal and vertical coordinates of the tracked characteristic point t in the image are shown. Based on the detection values at the previous T moments, the predicted value at the T + T moment is:
xt+T＝at+btT+ctT2
wherein: t is the image sampling and processing period, and has:
further, the third step comprises the following specific steps:
the first step is as follows: the visual sensor respectively acquires the welding seam contour F before welding and in welding1(x,y)、F2(x, y), simultaneously obtaining feature points of each contour: f. of1i(x,y)(i＝1,2…m)、f2j(x,y)(j＝1,2…p)。
Wherein m and p are the number of characteristic points of the weld contour before and after welding, and x and y are the coordinates of the characteristic points in the image.
The second step is that: merging the characteristic points at the leftmost side of the weld seam outlines in the two images, and simultaneously merging the weld seam outlines before and after welding in a translation manner:
F(x,y)＝F1(x,y)∧F2(x,y)
wherein the symbol Λ represents a logical and operation.
The third step: determining a weld forming area by respectively using the characteristic points of the relevant parts of the two weld outlines, and accordingly establishing an upper boundary line segment and a lower boundary line segment l of the weld forming area1、l2. Finally to l1And l2Fitting by high-order polynomial least square method to obtain l1And l2Expression l of1:
l2：
The fourth step: the three parameters of weld forming characteristics, fusion width B, fusion depth H and sectional area S, are calculated as:
B＝||f22(x,y)-f23(x,y)||
H＝max||g(x)-h(x)||
the invention has the beneficial effects that: the invention provides an online measurement method for welding seam forming characteristics of a T-shaped joint of a thick plate based on vision, which is an economic and reliable universal method.
Drawings
FIG. 1 is a flow chart of an on-line measurement method for a multi-pass weld forming characteristic of a thick plate T-shaped joint provided by the invention;
FIG. 2 is a flowchart of the weld contour feature point extraction in step one of the present invention;
FIG. 3 is a flowchart illustrating the process of extracting the weld contour feature points in step three of the present invention;
FIG. 4 is an exemplary graph of the overall variation characteristic of the fitted approximation slope according to step one of the present invention;
FIG. 5 is an exemplary diagram of fault diagnosis based on cubic exponential smoothing feature point extraction in step two of the present invention;
FIG. 6 is a diagram illustrating an example of a process for determining a weld forming region in an image according to step three of the present invention;
FIG. 7 is an exemplary diagram of an actual weld forming area according to step three of the present invention.
Detailed Description
The present invention will be further described with reference to the following specific examples, but the present invention is not limited to these examples.
Example 1: the on-line measurement method for the forming characteristics of the welding seam of the thick plate T-shaped joint based on vision, as shown in figure 1, comprises the following steps:
the method comprises the steps of firstly, calculating the slope value of each extracted data point of the linear weld contour by utilizing an average sliding idea, then, inhibiting the influence generated by slope local disturbance by adopting an average high-order nonlinear least square fitting method, effectively approaching the overall change characteristic of the slope, carrying out mutation detection on the fitted data, and finally obtaining weld contour characteristic points according to a supervision method.
And step two, aiming at the invalid welding seam profile feature recognition condition, according to the sampling data before the current sampling moment, adopting a cubic exponential smoothing algorithm, providing a welding seam profile feature point extraction fault detection method, and realizing fault diagnosis of feature point recognition.
And thirdly, according to the situation that the welding seam profile can shift in the image before welding and during welding, a method for measuring fusion width, fusion depth and sectional area in welding seam forming is provided based on a high-order nonlinear least square fitting method, and online measurement of the welding seam forming characteristics changed in multilayer multi-pass welding is effectively realized.
In the first step of this example, the method for identifying and acquiring the weld contour feature points adopts the idea of piecewise high-order nonlinear fitting, as shown in fig. 2, and adopts MAT L AB software to perform programmed calculation, and visualizes data for verification, and the specific steps are as follows:
the first step is as follows: the slope calculation and the fluctuation suppression are specifically described as firstly calculating slope values of all points by using an average sliding idea:
wherein x (), y () denote coordinates of the linear weld profile data points, n denotes the number of data points involved in each calculation, and where n is 5, i denotes the data point subscript, j denotes the subscript of the data point adjacent to i, k denotes the subscript of the data point adjacent to ijThe average of the n slopes is shown.
And secondly, a one-dimensional smoothing filter is adopted to further suppress irregular disturbance of the slope, the disturbance influence can be effectively reduced when the window of the filter is within the range of 1 × 3-1 × 30, the final result of identifying the weld contour feature point is not influenced, the suppression effect is more obvious when the window is larger, and preferably, the slope is subjected to smoothing filtering by adopting the filter 1 × 9 of the one-dimensional window.
The third step: experiments prove that the slope data is subjected to nonlinear least square method segmentation (average) fitting by adopting a polynomial of 50 times, the slope change trend can be effectively approximated by the segmentation fitting, and the influence of slope local disturbance on subsequent mutation detection is reduced (figure 4). The polynomial fit is expressed as:
f(x)＝a1x50+a2x49+…a50
wherein the coefficient a1,a2,…a50Determined by the coordinates of the fitted data points.
The fourth step: the slope mutation detection is specifically described as that the fitting result replaces original slope data to carry out mutation detection, a slope monotonous interval is obtained, the length of each interval is marked according to the slope change rate of each monotonous interval, and the monotonous interval is defined by the following formula:
the fifth step: and sequencing the lengths of the monotonous intervals from large to small, determining the monotonous intervals with corresponding number according to the number of the characteristic points specified by the supervision method and the sequence of the lengths of the intervals from large to small, and marking the central position of the monotonous interval as the position of the characteristic point.
And the fault diagnosis of the characteristic point identification adopts a cubic exponential smoothing algorithm, and the position of the current characteristic point is accurately predicted according to the sampling data before the current sampling moment. The method specifically comprises the following steps:
the first step is as follows: the welding gun is positioned at the initial welding position before welding, and the welding seam outline characteristic points at the initial welding position are determined according to the method in the step one;
the second step is that: taking the effective characteristic point at the previous sampling moment as a reference, calculating Euclidean distances between the characteristic point obtained at the current sampling moment and the reference point, and if all the Euclidean distances are greater than a pixel threshold value, wherein the pixel threshold value is 5 pixels in the embodiment, starting fault diagnosis;
the third step: the fault diagnosis adopts a cubic exponential smoothing algorithm, and the calculation formula is as follows:
wherein α is a smoothing coefficient, α is 0.36 and x is selected by experimentstAre the abscissa and ordinate (independent prediction) of the tracked feature point t in the image. Based onThe predicted values at T + T time of the detection values at the first T times are as follows:
xt+T＝at+btT+ctT2
wherein: t is the image sampling and processing period, and has:
where T is 1, and an initial time
Stipulate when the number of samples is less than 3
Initializing the coordinates of the designated characteristic points; when the number of samples is equal to or greater than 3,
predict value xt+1As the coordinates of the feature point corresponding to the time t + 1. In the example application as shown in fig. 5, the number of image samples is 700, and the second feature point is taken as the tracking point (fig. 5 b). In the abscissa and ordinate directions, the maximum deviations of the predictions are 0.47 pixels and 1.6 pixels, respectively, and when the sampling time T is 311 (at the circle in fig. 5c and d), the second feature point detected is unsatisfactory (5 pixels or more away from the tracking point at the previous time), and the predicted position is used as the tracking point at this time (at the circle in fig. 5 e).
The weld contour characteristic parameter measurement process comprises the following steps of measuring real weld forming characteristic parameters in an off-line mode, and establishing a relation between weld forming visual characteristic parameters and real values by utilizing regression analysis, wherein the specific process comprises the following steps:
the first step is as follows: ensuring that the vision sensor acquires the weld profile F before and during welding in the same attitude1(x,y)、F2(x, y), simultaneously obtaining feature points of each contour: f. of1i(x,y)(i＝1,2…m)、f2j(x,y)(j＝1,2…p)。
Wherein m and p are the number of characteristic points of the weld contour before and after welding, and x and y are the coordinates of the characteristic points in the image.
The second step is that: and (3) aligning and combining the weld seam outlines before and after welding by taking the leftmost characteristic point of the weld seam outlines in the two images as a reference:
F(x,y)＝F1(x,y)∧F2(x,y)
wherein the symbol Λ represents a logical and operation.
The third step: determining a weld forming area by respectively using the characteristic points of the relevant parts of the two weld outlines, and accordingly establishing an upper boundary line segment and a lower boundary line segment l of the weld forming area1、l2. Finally to l1And l2Fitting by high-order polynomial least square method to obtain l1And l2Expression l of1:
l2：
Finally, the three parameters of the weld width (B), the weld depth (H) and the sectional area (S) which can effectively describe the weld forming characteristics are obtained as follows:
B＝||f22(x,y)-f23(x,y)||
H＝max||g(x)-h(x)||
the penetration in fig. 6 was measured to be 59.8 pixels, the penetration width was 121 pixels, and the cross-sectional area was 4988.5 pixels. The real weld forming characteristic parameters can be measured off-line (figure 7), and the relation between the weld forming visual characteristic parameters and the real values is established by utilizing regression analysis, so that the on-line feedback of the welding state is effectively realized.
The foregoing merely represents preferred embodiments of the invention, which are described in some detail and detail, and therefore should not be construed as limiting the scope of the invention. It should be noted that, for those skilled in the art, various changes, modifications and substitutions can be made without departing from the spirit of the present invention, and these are all within the scope of the present invention. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (4)
1. The thick plate T-shaped joint welding seam forming characteristic on-line measuring method based on vision is characterized in that: the method comprises the following steps:
calculating the slope value of each data point of the extracted linear weld contour by utilizing an average sliding idea, then adopting an average high-order nonlinear fitting method to inhibit the influence generated by local disturbance of the slope, effectively approaching the overall change characteristic of the slope, carrying out mutation detection on the fitted data, and finally obtaining weld contour characteristic points according to a supervision method;
step two, aiming at the invalid welding seam profile feature recognition condition, according to the sampling data before the current sampling moment, a three-time exponential smoothing algorithm is adopted, a welding seam profile feature point extraction fault detection method is provided, and fault diagnosis of feature point recognition is realized;
and thirdly, according to the situation that the welding seam profile can shift in the image under different space-time conditions, a method for measuring fusion width, fusion depth and sectional area in welding seam forming is provided based on a high-order nonlinear fitting method, and online measurement of the welding seam forming characteristics changed in multilayer multi-pass welding is effectively achieved.
2. The vision-based on-line measurement method for the forming characteristics of the T-shaped joint welding seam of thick plate according to claim 1, characterized in that: the specific steps of the first step are as follows:
the first step is as follows: the slope calculation and the fluctuation suppression are specifically described as calculating slope values of all points by using an average sliding idea:
wherein x (), y () denote coordinates of the linear weld profile data points, n denotes the number of data points used for each calculation, i denotes the data point subscript, j denotes the data point subscriptSubscript, k, representing data points adjacent to ijRepresents the average of n slopes;
the second step is that: performing smooth filtering on the slope by adopting a one-dimensional smoothing filter;
the third step: the slope data is averagely divided into two sections, and a polynomial of 50 times is adopted for each section to carry out least square fitting, wherein the polynomial fitting is expressed as:
f(x)＝a1x50+a2x49+…a50
wherein the coefficient a1,a2,…a50Determining coordinates of the fitted data points;
the fourth step: the slope mutation detection is specifically described as that the fitting result replaces original slope data to carry out mutation detection, a slope monotonous interval is obtained, the length of each interval is marked according to the slope change rate of each monotonous interval, and the monotonous interval is defined by the following formula:
the fifth step: sorting the length values of the monotonous intervals from large to small, and appointing the number of characteristic points of the weld contour according to a supervision method, thereby determining the number of the sorted monotonous intervals, and marking the middle position of each monotonous interval as the position of the characteristic point.
3. The vision-based on-line measurement method for the forming characteristics of the T-shaped joint welding seam of thick plate according to claim 1, characterized in that: the method for fault diagnosis of feature point identification adopts a cubic exponential smoothing algorithm, accurately predicts the current feature point according to the sampling data before the current sampling moment, and specifically comprises the following steps:
the first step is as follows: the welding gun is positioned at the initial welding position before welding, and the welding seam outline characteristic points at the initial welding position are determined according to the method in the step one;
the second step is that: calculating Euclidean distances between the feature points obtained at the current sampling moment and the reference point by taking the effective feature points at the previous sampling moment as reference, and starting fault diagnosis if all the Euclidean distances are greater than a pixel threshold value;
the third step: the fault diagnosis adopts a cubic exponential smoothing algorithm, and the calculation formula is as follows:
wherein α is a smoothing coefficient, xtThe horizontal and vertical coordinates of the tracked characteristic point t moment in the image are obtained; based on the detection values at the previous T moments, the predicted value at the T + T moment is:
xt+T＝at+btT+ctT2
wherein: t is the image sampling and processing period, and has:
4. the vision-based on-line measurement method for the forming characteristics of the T-shaped joint welding seam of thick plate according to claim 1, characterized in that: the third step comprises the following specific steps:
the first step is as follows: the visual sensor respectively acquires the welding seam contour F before welding and in welding1(x,y)、F2(x, y), simultaneously obtaining feature points of each contour: f. of1i(x,y)(i＝1,2…m)、f2j(x,y)(j＝1,2…p)；
Wherein m and p are the number of characteristic points of the weld contour before and after welding, and x and y are coordinates of the characteristic points in the image;
the second step is that: merging the characteristic points at the leftmost side of the weld seam outlines in the two images, and simultaneously merging the weld seam outlines before and after welding in a translation manner:
F(x,y)＝F1(x,y)∧F2(x,y)
wherein the symbol Λ represents a logical and operation;
the third step: determining the weld forming area by using the characteristic points of the relevant parts of the two weld profiles respectively, and establishing the weld forming areaUpper and lower boundary line segment l1、l2Finally, to l1And l2Fitting by high-order polynomial least square method to obtain l1And l2Expression (2)
The fourth step: the three parameters of weld forming characteristics, fusion width B, fusion depth H and sectional area S, are calculated as:
B＝||f22(x,y)-f23(x,y)||
H＝max||g(x)-h(x)||
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010308187.7A CN111438460B (en) | 2020-04-18 | 2020-04-18 | Vision-based thick plate T-shaped joint welding seam forming characteristic online measurement method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010308187.7A CN111438460B (en) | 2020-04-18 | 2020-04-18 | Vision-based thick plate T-shaped joint welding seam forming characteristic online measurement method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111438460A true CN111438460A (en) | 2020-07-24 |
| CN111438460B CN111438460B (en) | 2021-05-07 |
Family
ID=71656010
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010308187.7A Active CN111438460B (en) | 2020-04-18 | 2020-04-18 | Vision-based thick plate T-shaped joint welding seam forming characteristic online measurement method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111438460B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115338556A (en) * | 2022-08-03 | 2022-11-15 | 湖南科技大学 | Weld joint quality detection method for thick-wall welding workpiece and computer equipment |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103955927A (en) * | 2014-04-26 | 2014-07-30 | 江南大学 | Fillet weld automatic tracking method based on laser vision |
| CN104985289A (en) * | 2015-07-31 | 2015-10-21 | 华南理工大学 | Laser sensor-based welding seam automatic tracking test device and test method thereof |
| CN105844622A (en) * | 2016-03-16 | 2016-08-10 | 南京工业大学 | V-shaped groove welding seam detection method based on laser visual sense |
| CN106312397A (en) * | 2016-10-12 | 2017-01-11 | 华南理工大学 | Laser vision guided automatic welding track tracking system and method |
| CN107424176A (en) * | 2017-07-24 | 2017-12-01 | 福州智联敏睿科技有限公司 | A kind of real-time tracking extracting method of weld bead feature points |
| JP2018010391A (en) * | 2016-07-12 | 2018-01-18 | 株式会社Ihi | Image processing method and image processor |
| CN107798330A (en) * | 2017-11-10 | 2018-03-13 | 上海电力学院 | A kind of weld image characteristics information extraction method |
| CN108765419A (en) * | 2018-06-20 | 2018-11-06 | 天津大学 | Structure light vision weld image information self-adapting extracting method |
-
2020
- 2020-04-18 CN CN202010308187.7A patent/CN111438460B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103955927A (en) * | 2014-04-26 | 2014-07-30 | 江南大学 | Fillet weld automatic tracking method based on laser vision |
| CN104985289A (en) * | 2015-07-31 | 2015-10-21 | 华南理工大学 | Laser sensor-based welding seam automatic tracking test device and test method thereof |
| CN105844622A (en) * | 2016-03-16 | 2016-08-10 | 南京工业大学 | V-shaped groove welding seam detection method based on laser visual sense |
| JP2018010391A (en) * | 2016-07-12 | 2018-01-18 | 株式会社Ihi | Image processing method and image processor |
| CN106312397A (en) * | 2016-10-12 | 2017-01-11 | 华南理工大学 | Laser vision guided automatic welding track tracking system and method |
| CN107424176A (en) * | 2017-07-24 | 2017-12-01 | 福州智联敏睿科技有限公司 | A kind of real-time tracking extracting method of weld bead feature points |
| CN107798330A (en) * | 2017-11-10 | 2018-03-13 | 上海电力学院 | A kind of weld image characteristics information extraction method |
| CN108765419A (en) * | 2018-06-20 | 2018-11-06 | 天津大学 | Structure light vision weld image information self-adapting extracting method |
Non-Patent Citations (1)
| Title |
|---|
| 余亮 等: ""基于斜率单调区间跨度分割的焊缝轮廓特征点的提取"", 《焊接》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115338556A (en) * | 2022-08-03 | 2022-11-15 | 湖南科技大学 | Weld joint quality detection method for thick-wall welding workpiece and computer equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111438460B (en) | 2021-05-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Xu et al. | Computer vision technology for seam tracking in robotic GTAW and GMAW | |
| CN112053376B (en) | Workpiece weld joint identification method based on depth information | |
| EP3812105A1 (en) | Artificial intelligence architecture for industrial welding | |
| Ye et al. | A robust algorithm for weld seam extraction based on prior knowledge of weld seam | |
| CN110544261B (en) | Method for detecting coal injection state of blast furnace tuyere based on image processing | |
| WO2023082418A1 (en) | Power utility tunnel settlement crack identification method based on artificial intelligence technology | |
| CN111815555A (en) | Metal additive manufacturing image detection method and device combining anti-neural network with local binary | |
| CN109509181B (en) | Cladding pool shape visual detection method based on serial contour search | |
| CN111438460B (en) | Vision-based thick plate T-shaped joint welding seam forming characteristic online measurement method | |
| CN114897908B (en) | Machine vision-based method and system for analyzing defects of selective laser powder spreading sintering surface | |
| CN112734750B (en) | Tank cover visual detection and positioning method and system, medium and device | |
| CN106875430A (en) | Single movement target method for tracing and device based on solid form under dynamic background | |
| CN115592324A (en) | Automatic welding robot control system based on artificial intelligence | |
| CN108399614B (en) | Fabric defect detection method based on non-sampling wavelet and Gumbel distribution | |
| CN110910363A (en) | Insufficient solder joint detection method, system and medium based on machine vision and deep learning | |
| CN111915649A (en) | Strip steel moving target tracking method under shielding condition | |
| Wang et al. | Online detection of weld surface defects based on improved incremental learning approach | |
| CN111968072B (en) | Automatic decision-making method for welding position of thick plate T-shaped joint based on Bayesian network | |
| CN116740044B (en) | Copper pipe milling surface processing method and system based on visual detection and control | |
| CN110290118A (en) | A kind of repetition process concealment attack detection method based on hidden Markov model | |
| CN109558877A (en) | Naval target track algorithm based on KCF | |
| CN112967267B (en) | Laser directional energy deposition sputtering counting method of full convolution neural network | |
| CN116664508A (en) | Weld surface quality detection method and computer readable storage medium | |
| CN114932292A (en) | Narrow-gap passive visual weld joint tracking method and system | |
| CN114820383A (en) | Pollution grade evaluation method based on insulator visible light 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 | ||
| EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20200724 Assignee: Nanchang Chuangda new building materials Co.,Ltd. Assignor: Nanchang University Contract record no.: X2023980052156 Denomination of invention: Visual based online measurement method for welding seam forming characteristics of thick plate T-joints Granted publication date: 20210507 License type: Common License Record date: 20231213 |
|
| EE01 | Entry into force of recordation of patent licensing contract | ||
| OL01 | Intention to license declared | ||
| OL01 | Intention to license declared |