CN118023683B - Welding quality real-time control method and system based on visual detection - Google Patents
Welding quality real-time control method and system based on visual detection Download PDFInfo
- Publication number
- CN118023683B CN118023683B CN202410438671.XA CN202410438671A CN118023683B CN 118023683 B CN118023683 B CN 118023683B CN 202410438671 A CN202410438671 A CN 202410438671A CN 118023683 B CN118023683 B CN 118023683B
- Authority
- CN
- China
- Prior art keywords
- convex
- welding
- height
- dimensional structure
- tiny
- 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
- 238000003466 welding Methods 0.000 title claims abstract description 228
- 238000000034 method Methods 0.000 title claims abstract description 29
- 230000000007 visual effect Effects 0.000 title claims abstract description 25
- 238000001514 detection method Methods 0.000 title claims abstract description 18
- 238000000926 separation method Methods 0.000 claims abstract description 13
- 238000013499 data model Methods 0.000 claims description 17
- 239000012535 impurity Substances 0.000 claims description 8
- 238000005520 cutting process Methods 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 3
- 238000011179 visual inspection Methods 0.000 claims 3
- 238000004364 calculation method Methods 0.000 claims 1
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 238000004458 analytical method Methods 0.000 description 8
- 239000002184 metal Substances 0.000 description 3
- 230000001066 destructive effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
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
- B23K11/00—Resistance welding; Severing by resistance heating
- B23K11/10—Spot welding; Stitch welding
- B23K11/11—Spot welding
-
- 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
- B23K11/00—Resistance welding; Severing by resistance heating
- B23K11/36—Auxiliary equipment
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
The invention discloses a welding quality real-time control method and a system based on visual detection, which relate to the technical field of welding structure quality and comprise the following steps: step 1): acquiring a weld joint three-dimensional structure of an entity; step 2): reading the outline shape of the weld joint three-dimensional structure by using a visual micro scanning method; step 3): separating the convex welding spots and the fine openings by using a species separation method; step 4): extracting shape characteristics of convex welding spots and shape characteristics of fine openings; step 5): comparing the welding quality of the welding seam three-dimensional structure according to the shape characteristics of the convex welding spots and the shape characteristics of the tiny openings; the invention has the beneficial effects that: and comparing the welding quality of the welding seam three-dimensional structure according to the shape characteristics of the convex welding spots and the shape characteristics of the tiny holes and the forming quantity of the convex welding spots and the forming quantity of the tiny holes.
Description
Technical Field
The invention relates to the technical field of welding structure quality, in particular to a welding quality real-time control method and system based on visual detection.
Background
Electric spot welding is the most basic technology of welding, and the number of welded welding spots after electric spot welding can reach thousands of welding spots, and the welding spots are distributed on the surface of a welding seam. The mechanical properties of the weld joint are critical to the fatigue resistance and the overall strength of the vehicle body between welded parts and even for the welded part structure.
The essence of electric spot welding is that the resistance heat of the metal in the welding area and the plastic deformation under the action of pressure are utilized to make the metal atoms of the joint surface reach the lattice distance to form metal bonds, generate enough common grains and obtain welding spots, welding seams or butt joints under the action of external pressure.
In order to ensure the reliability of structural connection between welding parts, the structural welding spot performance detection method adopted at present is a destructive detection method, namely, two welded welding parts are thrown together to realize structural welding spot performance detection, but the destructive detection method can accurately judge the quality of welding spots on the welding spot performance, but is time-consuming and labor-consuming, and brings great inconvenience to the structural connection production between the welding parts.
Disclosure of Invention
The invention provides a welding quality real-time control method and a welding quality real-time control system based on visual detection, which are used for reading the outline shape of a welding seam three-dimensional structure by a visual micro-scanning method, further reading convex welding spots and tiny holes on the welding seam three-dimensional structure, separating the convex welding spots and the tiny holes by a species separation method, and comparing the welding quality of the welding seam three-dimensional structure according to the shape characteristics of the convex welding spots and the shape characteristics of the tiny holes and the forming quantity of the convex welding spots and the forming quantity of the tiny holes.
A welding quality real-time control method based on visual detection comprises the following steps:
Step 1): acquiring a weld joint three-dimensional structure of an entity;
Step 2): reading the outline shape of the weld joint three-dimensional structure by using a visual micro scanning method, wherein a convex welding point on the weld joint three-dimensional structure and a tiny opening on the weld joint are read;
step 3): separating the convex welding spots and the fine openings by using a species separation method;
Step 4): extracting shape characteristics of convex welding spots and shape characteristics of fine openings;
Step 5): and comparing the welding quality of the welding seam three-dimensional structure according to the shape characteristics of the convex welding spots and the shape characteristics of the small openings.
Optionally, in step 1), a weld three-dimensional structure is acquired, and the following steps are adopted:
step 11): scanning a field weld joint three-dimensional structure to obtain a weld joint three-dimensional structure of an electronic data model, and cutting the weld joint three-dimensional structure of the whole electronic data model into a plurality of pieces along the length direction of the weld joint three-dimensional structure, wherein impurities are removed from the outer contour of each cut piece-shaped weld joint three-dimensional structure, and the analysis of welding quality after welding can be conveniently carried out on the surface of the weld joint three-dimensional structure of the electronic data model in a state of removing the impurities;
Step 12): and recovering each welding seam three-dimensional structure cut into a sheet shape to an original welding seam three-dimensional structure, and obtaining the welding seam three-dimensional structure of the electronic data model with impurities removed.
Optionally, in step 2), the outer contour shape of the weld three-dimensional structure is read by using a visual micro-scanning method, and the following steps are adopted:
Step 21): scanning the outer contour of the weld joint three-dimensional structure of the whole electronic data model, and reading out all convex welding spots and tiny openings on the outer contour of the weld joint three-dimensional structure, wherein the convex welding spots are set to be convex points on the weld joint three-dimensional structure, and the tiny openings are set to be concave points on the weld joint three-dimensional structure;
Step 22): and detecting the read convex welding spots and the small openings again to determine the shapes of the convex welding spots and the small openings again.
Further, in step 21), the convex welding spot and the fine opening are read by the following formula (1):
(1)；
In the formula (1), the convex welding spots and the fine openings are set to be rectangular, B is the volume change amount in unit temperature, Is the change amount of unit volume,As a function of the amount of change per unit volume,AndThe length and the width of the rectangle are respectively,AndIs not changed in the vector direction of (a),Equal to，=Or (b)=，Rectangular vector height difference whenWhen the vector of (2) is positive, the rectangle is a tiny mouth; when (when)When the vector of (2) is positive, the rectangle is a convex welding spot; by calculating the volume change per unit temperature, the volume change of the convex welding spot or the fine opening in the unit temperature can be read.
In the reading process of the convex welding spot and the fine opening, the length and width of the convex welding spot and the length and width of the fine opening are read in one direction, and therefore,AndIs not changed in the vector direction of (a),Is the vector height of the convex spot weld,Is the vector height or vector depth of the tiny mouth,Is a complex vector, i.e=Or (b)=If (if)When the vector of (2) is positive, the rectangle is small, ifWhen the vector of (2) is positive, the rectangle is a convex welding point.
Optionally, in step 3), the method of calculating the species separation method is represented by formula (2):
(2)；
in the formula (2) of the present invention, For the height vector of the convex spot weld,For the height or depth vector of the ostium,Is a plane perpendicular to the convex spot weld height vector,Is a plane perpendicular to the minor orifice height or depth vector,AndThe two parts are overlapped together,Is the height vector of the convex welding point relative to the plane perpendicular to the height vector of the convex welding pointIs provided with a height of (1),Is the height or depth vector of the tiny mouth relative to the height or depth vector plane of the tiny mouthIs provided with a height of (1),Miden (.) is a function of comparing the difference between the height of the convex welding spot and the height or depth of the tiny opening, and the difference between the height of the convex welding spot and the height or depth of the tiny opening is compared to distinguish the convex welding spot and the tiny opening of the outer contour of the three-dimensional structure of the welding seam.
Optionally, in step 4), the steps of extracting the shape features of the convex welding spot and extracting the shape features of the fine mouth are adopted as follows:
step 41): setting a convex welding spot to be extracted as required according to the shape of the convex welding spot which tends to form a rectangle, wherein the shape of the convex welding spot which tends to form a rectangle is formed according to the change of temperature;
step 42): setting a desired extraction of the fine mouth according to a shape in which the fine mouth tends to form a rectangle, wherein the shape in which the fine mouth tends to form a rectangle is formed according to a change in temperature;
Step 43): comparing the number of shapes that the convex spot weld tends to form a rectangle with the number of shapes that the fine opening tends to form a rectangle;
Step 44): the weld stereo structural features of the whole electronic data model are analyzed and extracted according to the number of shapes that the convex welding spots tend to form a rectangle and the number of shapes that the tiny holes tend to form a rectangle.
Further, in step 41), the shape of the convex spot welds that tend to form a rectangle is formed in response to a change in temperature per degree celsius;
wherein, the convex welding spot changes in volume per cubic unit when the temperature changes per degree centigrade until the temperature does not change per degree centigrade any more, and the convex welding spot does not change in volume per cubic unit any more.
Further, in step 42), the shape of the fine orifice that tends to form a rectangle is formed according to the change in temperature per degree celsius;
wherein, when the temperature changes every degree centigrade, the volume of the tiny opening every cubic changes until the temperature no longer changes every degree centigrade, and the volume of the tiny opening every cubic no longer changes.
Optionally, in step 5), the weld three-dimensional structure is compared, and the following steps are adopted:
Step 51), comparing the number of the formed convex welding spots with the number of the formed tiny holes, and if the number of the formed convex welding spots is larger than the number of the formed tiny holes, forming the welding seams to be convex; if the number of the convex welding spots is smaller than the number of the small openings, the welding seams are concave; if the number of the convex welding spots is equal to the number of the small openings, the welding seams are in a flat surface shape;
Step 52), comparing the height of forming the convex welding spot with the height or depth of forming the tiny hole, and if the height of forming the convex welding spot is larger than the height or depth of forming the tiny hole, forming the welding seam to be convex; if the height of the convex welding spot is smaller than the height or depth of the small opening, the welding seam is concave; if the height of the convex welding spot is equal to the height or depth of the tiny hole, the welding seam is in a flat surface shape.
A vision detection-based welding quality real-time control system, comprising:
an acquisition module;
the scanning module is used for reading the outline shape of the welding line by a visual micro scanning method;
The analysis module is used for analyzing the convex welding spots and the tiny openings on the separation weld joint three-dimensional structure by a species separation method;
the comparison module is used for extracting the shape characteristics of the convex welding spots and the small openings and comparing the shape characteristics of the convex welding spots and the small openings;
the acquisition module, the scanning module, the analysis module and the comparison module are uniformly connected to a network data line.
The invention has the beneficial effects that:
1. The invention reads the outline shape of the weld joint three-dimensional structure by a visual micro scanning method, further reads the convex welding spots on the weld joint three-dimensional structure and the tiny holes on the weld joint, separates the convex welding spots and the tiny holes by a species separation method, and compares the welding quality of the weld joint three-dimensional structure according to the shape characteristics of the convex welding spots and the shape characteristics of the tiny holes and the forming quantity of the convex welding spots and the forming quantity of the tiny holes.
2. Comparing the number of the formed convex welding spots with the number of the formed tiny holes, and if the number of the formed convex welding spots is larger than the number of the formed tiny holes, forming a welding seam in a convex shape; if the number of the convex welding spots is smaller than the number of the small openings, the welding seams are concave; if the number of the convex welding spots is equal to the number of the small openings, the welding seams are in a flat surface shape;
Comparing the height of forming the convex welding spot with the height or depth of forming the tiny hole, and if the height of forming the convex welding spot is larger than the height or depth of forming the tiny hole, forming the welding seam to be convex; if the height of the convex welding spot is smaller than the height or depth of the small opening, the welding seam is concave; if the height of the convex welding spot is equal to the height or depth of the tiny hole, the welding seam is in a flat surface shape.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a system block diagram of the present invention;
Fig. 2 is a flow chart of the operation of the present invention.
Detailed Description
Embodiments of the present application will be described in detail below with reference to the accompanying drawings.
Example 1
As shown in fig. 1, the present embodiment provides a welding quality real-time control system based on visual detection, including: the device comprises an acquisition module, a scanning module, an analysis module and a comparison module, wherein the scanning module is used for reading the outline shape of a welding line by a visual micro-scanning method, the analysis module is used for analyzing convex welding points and tiny holes on a three-dimensional structure of the welding line separated by a species separation method, and the comparison module is used for extracting the shape characteristics of the convex welding points and the tiny holes and comparing the shape characteristics of the convex welding points and the tiny holes.
The acquisition module, the scanning module, the analysis module and the comparison module are uniformly connected to a network data line.
The network port is also connected with the network data line connected with the acquisition module, the scanning module, the analysis module and the comparison module, and the network port outputs data.
Example 2
Based on embodiment 1, as shown in fig. 2, the present embodiment provides a welding quality real-time control method based on visual detection, including the following steps:
Step 1): acquiring a weld joint three-dimensional structure of an entity;
Step 2): reading the outline shape of the weld joint three-dimensional structure by using a visual micro scanning method, wherein a convex welding point on the weld joint three-dimensional structure and a tiny opening on the weld joint are read;
step 3): separating the convex welding spots and the fine openings by using a species separation method;
Step 4): extracting shape characteristics of convex welding spots and shape characteristics of fine openings;
Step 5): and comparing the welding quality of the welding seam three-dimensional structure according to the shape characteristics of the convex welding spots and the shape characteristics of the small openings.
Optionally, in step 1), a weld three-dimensional structure is acquired, and the following steps are adopted:
step 11): scanning a field weld joint three-dimensional structure to obtain a weld joint three-dimensional structure of an electronic data model, and cutting the weld joint three-dimensional structure of the whole electronic data model into a plurality of pieces along the length direction of the weld joint three-dimensional structure, wherein impurities are removed from the outer contour of each cut piece-shaped weld joint three-dimensional structure, and the analysis of welding quality after welding can be conveniently carried out on the surface of the weld joint three-dimensional structure of the electronic data model in a state of removing the impurities;
Step 12): and recovering each welding seam three-dimensional structure cut into a sheet shape to an original welding seam three-dimensional structure, and obtaining the welding seam three-dimensional structure of the electronic data model with impurities removed.
Optionally, in step 2), the outer contour shape of the weld three-dimensional structure is read by using a visual micro-scanning method, and the following steps are adopted:
Step 21): scanning the outer contour of the weld joint three-dimensional structure of the whole electronic data model, and reading out all convex welding spots and tiny openings on the outer contour of the weld joint three-dimensional structure, wherein the convex welding spots are set to be convex points on the weld joint three-dimensional structure, and the tiny openings are set to be concave points on the weld joint three-dimensional structure;
Step 22): and detecting the read convex welding spots and the small openings again to determine the shapes of the convex welding spots and the small openings again.
Further, in step 21), the convex welding spot and the fine opening are read by the following formula (1):
(1)；
In the formula (1), the convex welding spots and the fine openings are set to be rectangular, B is the volume change amount in unit temperature, Is the change amount of unit volume,As a function of the amount of change per unit volume,AndThe length and the width of the rectangle are respectively,AndIs not changed in the vector direction of (a),Equal to，=Or (b)=，Rectangular vector height difference whenWhen the vector of (2) is positive, the rectangle is a tiny mouth; when (when)When the vector of (2) is positive, the rectangle is a convex welding spot; by calculating the volume change per unit temperature, the volume change of the convex welding spot or the fine opening in the unit temperature can be read.
In the reading process of the convex welding spot and the fine opening, the length and width of the convex welding spot and the length and width of the fine opening are read in one direction, and therefore,AndIs not changed in the vector direction of (a),Is the vector height of the convex spot weld,Is the vector height or vector depth of the tiny mouth,Is a complex vector, i.e=Or (b)=If (if)When the vector of (2) is positive, the rectangle is small, ifWhen the vector of (2) is positive, the rectangle is a convex welding point.
Optionally, in step 3), the method of calculating the species separation method is represented by formula (2):
(2)；
in the formula (2) of the present invention, For the height vector of the convex spot weld,For the height or depth vector of the ostium,Is a plane perpendicular to the convex spot weld height vector,Is a plane perpendicular to the minor orifice height or depth vector,AndThe two parts are overlapped together,Is the height vector of the convex welding point relative to the plane perpendicular to the height vector of the convex welding pointIs provided with a height of (1),Is the height or depth vector of the tiny mouth relative to the height or depth vector plane of the tiny mouthIs provided with a height of (1),Miden (.) is a function of comparing the difference between the height of the convex welding spot and the height or depth of the tiny opening, and the difference between the height of the convex welding spot and the height or depth of the tiny opening is compared to distinguish the convex welding spot and the tiny opening of the outer contour of the three-dimensional structure of the welding seam.
Optionally, in step 4), the steps of extracting the shape features of the convex welding spot and extracting the shape features of the fine mouth are adopted as follows:
step 41): setting a convex welding spot to be extracted as required according to the shape of the convex welding spot which tends to form a rectangle, wherein the shape of the convex welding spot which tends to form a rectangle is formed according to the change of temperature;
step 42): setting a desired extraction of the fine mouth according to a shape in which the fine mouth tends to form a rectangle, wherein the shape in which the fine mouth tends to form a rectangle is formed according to a change in temperature;
Step 43): comparing the number of shapes that the convex spot weld tends to form a rectangle with the number of shapes that the fine opening tends to form a rectangle;
Step 44): the weld stereo structural features of the whole electronic data model are analyzed and extracted according to the number of shapes that the convex welding spots tend to form a rectangle and the number of shapes that the tiny holes tend to form a rectangle.
Further, in step 41), the shape of the convex spot welds that tend to form a rectangle is formed in response to a change in temperature per degree celsius;
wherein, the convex welding spot changes in volume per cubic unit when the temperature changes per degree centigrade until the temperature does not change per degree centigrade any more, and the convex welding spot does not change in volume per cubic unit any more.
Further, in step 42), the shape of the fine orifice that tends to form a rectangle is formed according to the change in temperature per degree celsius;
wherein, when the temperature changes every degree centigrade, the volume of the tiny opening every cubic changes until the temperature no longer changes every degree centigrade, and the volume of the tiny opening every cubic no longer changes.
Optionally, in step 5), comparing the weld three-dimensional structure, the following steps are adopted:
Step 51), comparing the number of the convex welding spots with the number of the tiny holes, and if the number of the convex welding spots is larger than the number of the tiny holes, forming a welding seam in a convex shape; if the number of the convex welding spots is smaller than the number of the small openings, the welding seams are concave; if the number of the convex welding spots is equal to the number of the small openings, the welding seams are in a flat surface shape;
Step 52), comparing the height of forming the convex welding spot with the height or depth of forming the tiny hole, and if the height of forming the convex welding spot is larger than the height or depth of forming the tiny hole, forming the welding seam to be convex; if the height of the convex welding spot is smaller than the height or depth of the small opening, the welding seam is concave; if the height of the convex welding spot is equal to the height or depth of the tiny hole, the welding seam is in a flat surface shape.
Example 3
Based on the embodiment 1-2, the invention collects the on-site weld joint three-dimensional structure into a welding quality real-time control system based on visual detection, and the welding quality real-time control system based on visual detection analyzes the weld joint three-dimensional structure of the digital model.
The real-time monitoring of the welding quality is performed by observing a visual detection welding quality real-time control system, and the visual detection welding quality real-time control system is provided with a display (not shown in the figure), wherein the display can monitor or monitor the welding quality.
The invention reads the outline shape of the weld three-dimensional structure by a visual micro-scanning method, further reads the convex welding spots on the weld three-dimensional structure and the tiny openings on the weld, and separates the convex welding spots and the tiny openings by a species separation method.
The above description is merely an embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily think about changes or substitutions within the technical scope of the present invention, and it is intended to cover the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (6)
1. The welding quality real-time control method based on visual detection is characterized by comprising the following steps of:
Step 1): acquiring a weld joint three-dimensional structure of an entity;
Step 2): reading the outline shape of the weld joint three-dimensional structure by using a visual micro scanning method, wherein a convex welding point on the weld joint three-dimensional structure and a tiny opening on the weld joint are read;
step 3): separating the convex welding spots and the fine openings by using a species separation method;
Step 4): extracting shape characteristics of convex welding spots and shape characteristics of fine openings;
step 5): comparing the welding quality of the welding seam three-dimensional structure according to the shape characteristics of the convex welding spots and the shape characteristics of the tiny openings;
In the step 2), the outer contour shape of the weld three-dimensional structure is read by using the visual micro-scanning method, and the following steps are adopted:
Step 21): scanning the outer contour of the welding seam three-dimensional structure of the whole electronic data model, and reading out all the convex welding spots and the tiny openings on the outer contour of the welding seam three-dimensional structure, wherein the convex welding spots are set to be convex points on the welding seam three-dimensional structure, and the tiny openings are set to be concave points on the welding seam three-dimensional structure;
Step 22): detecting the read convex welding spots and the small openings again to determine the shapes of the convex welding spots and the small openings again;
In the step 21), the reading mode of the convex welding spot and the fine opening adopts the following formula (1):
(1)；
In the formula (1), the convex welding spots and the fine openings are set to be rectangular, B is the volume change amount in unit temperature, Is the change amount of unit volume,As a function of the amount of change per unit volume,AndThe length and the width of the rectangle are respectively,AndIs not changed in the vector direction of (a),Equal to，=Or (b)=，Rectangular vector height difference whenWhen the vector of (2) is positive, the rectangle is a tiny mouth; when (when)When the vector of (2) is positive, the rectangle is a convex welding spot; the volume change of the convex welding spots or the small openings in the unit temperature can be read out by calculating the volume change of the unit temperature;
wherein in the step 3), the calculation mode of the species separation method is formula (2):
(2)；
in the formula (2) of the present invention, For the height vector of the convex spot weld,For the height or depth vector of the ostium,Is a plane perpendicular to the convex spot weld height vector,Is perpendicular to the plane of the height or depth vector of the ostiumAnd saidThe two parts are overlapped together,Is the height vector of the convex welding point relative to the plane perpendicular to the height vector of the convex welding pointIs provided with a height of (1),Is the height or depth vector of the tiny mouth relative to the height or depth vector plane of the tiny mouthIs provided with a height of (1),Miden (.) is a function of comparing the difference between the height of the convex spot and the height or depth of the fine orifice.
2. The method for controlling welding quality in real time based on visual inspection according to claim 1, wherein in the step 1), the weld three-dimensional structure is collected, and the following steps are adopted:
Step 11): scanning a field weld joint three-dimensional structure to obtain a weld joint three-dimensional structure of an electronic data model, and cutting the weld joint three-dimensional structure of the whole electronic data model into a plurality of pieces along the length direction of the weld joint three-dimensional structure, wherein impurities are removed from the outer contour of each cut piece-shaped weld joint three-dimensional structure;
Step 12): and recovering each welding seam three-dimensional structure cut into a sheet shape to an original welding seam three-dimensional structure, and obtaining the welding seam three-dimensional structure of the electronic data model with impurities removed.
3. The method according to claim 1, wherein in the step 4), the shape features of the convex welding spot and the shape features of the fine mouth are extracted by:
step 41): setting a convex welding spot to be extracted as required according to the shape of the convex welding spot which tends to form a rectangle, wherein the shape of the convex welding spot which tends to form a rectangle is formed according to the change of temperature;
step 42): setting a desired extraction of the fine mouth according to a shape in which the fine mouth tends to form a rectangle, wherein the shape in which the fine mouth tends to form a rectangle is formed according to a change in temperature;
Step 43): comparing the number of shapes that the convex spot weld tends to form a rectangle with the number of shapes that the fine opening tends to form a rectangle;
Step 44): the weld stereo structural features of the whole electronic data model are analyzed and extracted according to the number of shapes that the convex welding spots tend to form a rectangle and the number of shapes that the tiny holes tend to form a rectangle.
4. A method of real time control of weld quality based on visual inspection according to claim 3, characterized in that in said step 41) the shape of the convex spot weld tending to form a rectangle is formed according to the variation of temperature per degree celsius;
wherein, the convex welding spot changes in volume per cubic unit when the temperature changes per degree centigrade until the temperature does not change per degree centigrade any more, and the convex welding spot does not change in volume per cubic unit any more.
5. A method of real time control of weld quality based on visual inspection according to claim 3, wherein in said step 42) the shape of the thin mouth that tends to form a rectangle is formed according to the change of temperature per degree celsius;
wherein, when the temperature changes every degree centigrade, the volume of the tiny opening every cubic changes until the temperature no longer changes every degree centigrade, and the volume of the tiny opening every cubic no longer changes.
6. The method according to claim 1, wherein in the step 5), the welding quality of the weld three-dimensional structure is compared by:
Step 51), comparing the number of the convex welding spots with the number of the tiny holes, and if the number of the convex welding spots is larger than the number of the tiny holes, forming a welding seam in a convex shape; if the number of the convex welding spots is smaller than the number of the small openings, the welding seams are concave; if the number of the convex welding spots is equal to the number of the small openings, the welding seams are in a flat surface shape;
Step 52), comparing the height of forming the convex welding spot with the height or depth of forming the tiny hole, and if the height of forming the convex welding spot is larger than the height or depth of forming the tiny hole, forming the welding seam to be convex; if the height of the convex welding spot is smaller than the height or depth of the small opening, the welding seam is concave; if the height of the convex welding spot is equal to the height or depth of the tiny hole, the welding seam is in a flat surface shape.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410438671.XA CN118023683B (en) | 2024-04-12 | 2024-04-12 | Welding quality real-time control method and system based on visual detection |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410438671.XA CN118023683B (en) | 2024-04-12 | 2024-04-12 | Welding quality real-time control method and system based on visual detection |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118023683A CN118023683A (en) | 2024-05-14 |
| CN118023683B true CN118023683B (en) | 2024-06-28 |
Family
ID=90984437
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410438671.XA Active CN118023683B (en) | 2024-04-12 | 2024-04-12 | Welding quality real-time control method and system based on visual detection |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118023683B (en) |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114740006A (en) * | 2022-03-15 | 2022-07-12 | 安徽工程大学 | Weldment surface defect online detection method and device based on 3D visual sensing |
Family Cites Families (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB2020799B (en) * | 1978-05-11 | 1982-09-15 | Atomic Energy Authority Uk | Detecting flaws in welds |
| JPH087158B2 (en) * | 1989-12-12 | 1996-01-29 | 川崎製鉄株式会社 | Welding quality judgment method for seam welded joint of steel strip |
| US5961859A (en) * | 1997-10-23 | 1999-10-05 | Trw Inc. | Method and apparatus for monitoring laser weld quality via plasma size measurements |
| JP4267789B2 (en) * | 2000-01-24 | 2009-05-27 | 日立建機株式会社 | Method and apparatus for detecting weld bead shape |
| AT508696B1 (en) * | 2009-09-11 | 2015-06-15 | Fronius Int Gmbh | MONITORING MODULE FOR MONITORING A PROCESS WITH A LIGHT ARCH |
| CN103084746A (en) * | 2013-02-09 | 2013-05-08 | 傅凤义 | Novel method for removing welding deformation at bottom of metallic oil tank |
| CN103231162A (en) * | 2013-04-17 | 2013-08-07 | 柳州市自动化科学研究所 | Device and method for visual detection of welding quality of robot |
| US10427239B2 (en) * | 2015-04-02 | 2019-10-01 | Illinois Tool Works Inc. | Systems and methods for tracking weld training arc parameters |
| WO2017122391A1 (en) * | 2016-01-14 | 2017-07-20 | 日産自動車株式会社 | Method for detecting hole in laser-welded portion and laser welding device |
| CN106583961B (en) * | 2017-03-01 | 2023-10-24 | 湖南泰嘉新材料科技股份有限公司 | Continuous welding seam monitoring probe, welding seam monitoring system and method |
| US11389908B2 (en) * | 2018-08-02 | 2022-07-19 | Dexter Stamping Company, Llc | Systems and methods for detecting weld bead conformity |
| CN111215800B (en) * | 2020-02-10 | 2021-02-02 | 武汉理工大学 | Maintenance amount detection device and detection method for welding maintenance robot |
| CN112958956B (en) * | 2021-02-05 | 2021-11-02 | 燕山大学 | Automatic welding method and device |
| CN113953668B (en) * | 2021-10-29 | 2023-05-26 | 神龙汽车有限公司 | Laser welding method and device for large-penetration gear |
| CN114161048B (en) * | 2021-12-30 | 2023-11-21 | 常熟理工学院 | 3D vision-based parameterized welding method and device for tower legs of iron tower |
| CN116309292A (en) * | 2022-12-30 | 2023-06-23 | 沈阳派得林科技有限责任公司 | Intelligent weld defect identification method based on visual conversion layer and instance segmentation |
| CN117808814B (en) * | 2024-03-01 | 2024-05-28 | 深圳市新技智能设备有限公司 | Welding defect detection and identification method and system based on machine vision |
-
2024
- 2024-04-12 CN CN202410438671.XA patent/CN118023683B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114740006A (en) * | 2022-03-15 | 2022-07-12 | 安徽工程大学 | Weldment surface defect online detection method and device based on 3D visual sensing |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118023683A (en) | 2024-05-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Grasso et al. | In-process monitoring of selective laser melting: spatial detection of defects via image data analysis | |
| CN109886298B (en) | Weld quality detection method based on convolutional neural network | |
| CN111462110A (en) | Welding seam quality detection method, device and system and electronic equipment | |
| CN104020222B (en) | Fully-automatic supersonic aluminum wire press welder weld quality prediction system | |
| CN114119470B (en) | Electric core seal nail weld appearance detection algorithm and system based on deep learning | |
| CN118023683B (en) | Welding quality real-time control method and system based on visual detection | |
| CN116091404A (en) | Welding line defect detection and pattern recognition method based on image-point cloud information fusion | |
| CN118023791B (en) | Welding method and system for precise shell | |
| CN114119595A (en) | GMAW welding quality on-line monitoring and evaluating method based on integrated deep learning | |
| CN114170176A (en) | Automatic detection method for steel grating welding seam based on point cloud | |
| CN113641155A (en) | High-temperature forging detection control system | |
| CN114646665A (en) | Arc welding defect real-time detection method and system | |
| CN115106617A (en) | Scanning and tracking method for long weld joint in narrow space | |
| CN115032200A (en) | Method and system for detecting 3D defects of sealing weld at top of new energy cylindrical battery | |
| CN118123316A (en) | Method and system for detecting cold joint by ultrasonic welding of battery connecting sheet | |
| CN117079100B (en) | Weld defect recognition system based on deep learning | |
| CN107796818B (en) | The method of on-line checking bi-metal bandsaw blades welding quality | |
| CN206662523U (en) | A kind of spot welding on-line detecting system | |
| JP2021535836A (en) | Weld bead forming control device and method | |
| CN109239301B (en) | Anchor chain flash welding quality online evaluation method | |
| CN118081171B (en) | Abnormal intelligent identification method and system applied to metal plate welding | |
| CN118023657B (en) | Control method for maintenance gouging robot | |
| JP3787230B2 (en) | Welding state monitoring apparatus and method | |
| CN116402762A (en) | Automatic detection method for blank part of automobile brake system | |
| CN117218188B (en) | Deep learning positioning optimization method for can body processing |
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 |