CN110961778A - Method for automatically identifying welding area of welding workpiece, computer device and computer-readable storage medium - Google Patents

Method for automatically identifying welding area of welding workpiece, computer device and computer-readable storage medium Download PDF

Info

Publication number
CN110961778A
CN110961778A CN201911235163.7A CN201911235163A CN110961778A CN 110961778 A CN110961778 A CN 110961778A CN 201911235163 A CN201911235163 A CN 201911235163A CN 110961778 A CN110961778 A CN 110961778A
Authority
CN
China
Prior art keywords
welding
area
welded
workpiece
coordinates
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
Application number
CN201911235163.7A
Other languages
Chinese (zh)
Other versions
CN110961778B (en
Inventor
曹建华
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Zhuhai Pingzhu Technology Co Ltd
Original Assignee
Zhuhai Pingzhu Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Zhuhai Pingzhu Technology Co Ltd filed Critical Zhuhai Pingzhu Technology Co Ltd
Priority to CN201911235163.7A priority Critical patent/CN110961778B/en
Publication of CN110961778A publication Critical patent/CN110961778A/en
Application granted granted Critical
Publication of CN110961778B publication Critical patent/CN110961778B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • BPERFORMING OPERATIONS; TRANSPORTING
    • B23MACHINE TOOLS; METAL-WORKING NOT OTHERWISE PROVIDED FOR
    • B23KSOLDERING OR UNSOLDERING; WELDING; CLADDING OR PLATING BY SOLDERING OR WELDING; CUTTING BY APPLYING HEAT LOCALLY, e.g. FLAME CUTTING; WORKING BY LASER BEAM
    • B23K26/00Working by laser beam, e.g. welding, cutting or boring
    • B23K26/02Positioning or observing the workpiece, e.g. with respect to the point of impact; Aligning, aiming or focusing the laser beam
    • B23K26/03Observing, e.g. monitoring, the workpiece
    • BPERFORMING OPERATIONS; TRANSPORTING
    • B23MACHINE TOOLS; METAL-WORKING NOT OTHERWISE PROVIDED FOR
    • B23KSOLDERING OR UNSOLDERING; WELDING; CLADDING OR PLATING BY SOLDERING OR WELDING; CUTTING BY APPLYING HEAT LOCALLY, e.g. FLAME CUTTING; WORKING BY LASER BEAM
    • B23K26/00Working by laser beam, e.g. welding, cutting or boring
    • B23K26/20Bonding
    • B23K26/21Bonding by welding
    • B23K26/22Spot welding
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/0002Inspection of images, e.g. flaw detection
    • G06T7/0004Industrial image inspection
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00Scenes; Scene-specific elements
    • G06V20/10Terrestrial scenes

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Optics & Photonics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Plasma & Fusion (AREA)
  • Mechanical Engineering (AREA)
  • Multimedia (AREA)
  • Quality & Reliability (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Image Analysis (AREA)

Abstract

The invention provides a method for automatically identifying a welding area of a welding workpiece, a computer device and a computer readable storage medium, wherein the method comprises the steps of obtaining a color image shot by a color camera, and calibrating a plane coordinate of the welding workpiece according to the color image; acquiring a region with a preset color in the color image, and calibrating the region with the preset color as a welding region; acquiring a depth image of a workpiece to be welded, and calculating a height coordinate of a welding area; and calculating the motion trail of the welding equipment according to the plane coordinates and the height coordinates of the welding area. The invention also provides a computer device and a computer readable storage medium for realizing the method. The invention can weld the metal templates with different shapes and welding areas, is particularly suitable for the production and welding of small-batch multi-variety metal templates, and is also suitable for batch production with high welding precision and high welding efficiency.

Description

Method for automatically identifying welding area of welding workpiece, computer device and computer-readable storage medium
Technical Field
The invention relates to the technical field of intelligent manufacturing, in particular to a method for automatically identifying a welding area of a welding workpiece, a computer device for realizing the method and a computer readable storage medium.
Background
The construction industry uses aluminium template to carry out the construction in a large number, and current aluminium template is formed by bottom plate and polylith curb plate, baffle welding usually. If manual welding is used, on one hand, the welding quality cannot be guaranteed, and on the other hand, the manufacturing time of the aluminum template is long due to low manual welding efficiency, so that the processing efficiency of the template is influenced. Therefore, it is considered to use automated equipment to weld the aluminum forms, such as an automated welding machine.
The existing welding machines are used for welding workpieces with specific shapes, for example, the motion track of a welding gun is preset according to the shapes of the workpieces. After a welding workpiece is placed on a welding machine, the workpiece to be welded needs to be clamped and fixed by a fixing device, and a welding gun reciprocates on the workpiece according to a preset track and welds an area needing to be welded. However, this type of welding requires the shape and welding area of the workpiece to be welded to be determined in advance, and when the shape and welding area of the workpiece to be welded change, the trajectory of the movement of the welding gun needs to be reset. Since the movement track of the welding gun needs to be controlled by a preset program, once the shape of the workpiece to be welded or the welding area changes, reprogramming is needed, which brings inconvenience to welding. Because the shape of the aluminum template is more, many construction sites all need set up the aluminum template of specific shape according to actual need, this just leads to often adjusting the procedure of welding machine, is unfavorable for the automatic welding of many varieties of aluminum template of small batch.
In addition, the existing welding mode also needs to accurately clamp and fix the workpiece to be welded, and once the position of the workpiece to be welded in the welding machine deviates, the welding position is inaccurate, the welding is wrong, and even the workpiece to be welded is damaged. Because the surface of the aluminum template is smooth, the clamping of the clamping piece of the welding machine on the aluminum template is not very accurate, and the welding yield of the aluminum template is influenced.
Most existing welding machines with shooting devices can realize the function of automatic correction, such as correcting the motion track of welding equipment according to the shot images. However, these welding machines are not capable of automatically calculating the area to be welded on the welding workpiece, and further are not capable of automatically generating the motion trajectory of the welding equipment according to the calculated welding area, so that the motion trajectory of the welding equipment needs to be preset, and thus the requirement of automatic production of small-batch aluminum templates cannot be met.
Disclosure of Invention
The invention mainly aims to provide the automatic identification method of the welding area which is beneficial to producing the welding workpiece aiming at small-batch and multi-variety aluminum templates.
Another object of the present invention is to provide a computer device for implementing the above method for automatically identifying the welding area of the welding workpiece.
It is still another object of the present invention to provide a computer-readable storage medium for implementing the above-mentioned method for automatically identifying a welding area of a welding workpiece.
In order to realize the main purpose of the invention, the method for automatically identifying the welding area of the welding workpiece comprises the steps of obtaining a color image shot by a color camera, and calibrating the plane coordinates of the workpiece to be welded according to the color image; acquiring a region with a preset color in the color image, and calibrating the region with the preset color as a welding region; acquiring a depth image of a workpiece to be welded, and calculating a height coordinate of a welding area; and calculating the motion trail of the welding equipment according to the plane coordinates and the height coordinates of the welding area.
According to the scheme, when the aluminum template is welded, the plane coordinate and the height coordinate of the workpiece to be welded can be obtained through calculation by the color camera and the depth camera, so that the aluminum template with the specific shape can be welded, a model of the aluminum template does not need to be input into a welding machine before welding, the welding machine does not need to be programmed even if a new aluminum template is welded, and the welding workload is greatly reduced.
On the other hand, by identifying the region of the preset color, the welding region can be accurately identified. Therefore, before welding, the welding machine can automatically identify the area needing welding only by using strokes with specific colors in the area needing welding of the aluminum template, the welding of the aluminum template does not need manual participation, the welding efficiency can be improved, and the welding quality is guaranteed.
Preferably, the acquiring the region of the preset color in the color image includes: and acquiring a region of the chromatic value of the color image within a preset range.
Therefore, the chromatic value in the color image is preset, the welding area of the workpiece to be welded can be rapidly calculated, and the accuracy of identifying the welding area is improved.
Further, the step of calibrating the plane coordinates of the to-be-welded workpiece according to the color image comprises the following steps: and taking a preset point of the workpiece to be welded or a preset point on a welding machine as an original point of a plane coordinate system, and calibrating the plane coordinate of the workpiece to be welded by taking the original point as a reference.
Therefore, the edge of the workpiece to be welded, particularly the vertex area of the right angle is identified, the original point of the plane coordinate system is rapidly determined, or a certain preset point on the welding machine is directly used as the original point, so that the plane coordinate of the workpiece to be welded is determined.
Further, the calculating the height coordinate of the welding area comprises: and acquiring the height coordinate of the to-be-welded workpiece output by the depth camera, and acquiring the height coordinate of a welding area in the to-be-welded workpiece.
Therefore, the image of the whole workpiece to be welded is shot by using the depth camera, and after the welding area is identified, the height coordinate of the welding area is obtained, so that the height coordinate information of the welding area can be accurately calculated.
Further, after calculating the motion track of the welding device, the following steps are also executed: acquiring an image of the area to be welded, calculating the actual coordinates of the area to be welded, and adjusting the motion track of the welding equipment according to the actual coordinates of the area to be welded.
Therefore, after the three-dimensional coordinates of the workpiece to be welded are calculated through the color camera and the depth camera, the motion track of the welding equipment is continuously adjusted through acquiring the actual coordinates of the area to be welded in real time in the welding process, the motion track of the welding equipment can be accurately adjusted, and the welding accuracy and the welding quality are improved.
In a further aspect, the image of the area to be welded is acquired by a weld tracker, which is fixed to the welding apparatus.
Because the welding seam tracker can accurately calculate the actual coordinates of the area to be welded, and the welding seam tracker is fixed on the welding equipment, the image of the area to be welded can be more accurately obtained, the accurate actual coordinates of the area to be welded can be calculated, and accurate data can be provided for adjusting the movement track of the welding equipment.
Alternatively, calculating the height coordinate of the welding region comprises: and after the welding area is determined according to the color image, the depth coordinate of the welding workpiece is obtained by using a profile scanner so as to calculate the height coordinate of the welding area.
Because the profile scanner can replace a depth camera and can provide very accurate height coordinate data, the accuracy of welding can be improved by using the profile scanner to calculate the height coordinate of the workpiece to be welded.
Further, the step of obtaining the height coordinate of the welding area by using the profile scanner comprises: and when the workpieces to be welded are symmetrically arranged, acquiring the height coordinate of the welding area of one symmetrical area of the workpieces to be welded by using the profile scanner, and calculating the height coordinate of the welding area of the other symmetrical area.
According to the scheme, for the to-be-welded workpieces which are symmetrically designed, the height coordinate of the welding area of the other symmetric area can be calculated only by calculating the height coordinate of the welding area of one symmetric area, the calculation amount of the height coordinate of the to-be-welded workpieces is reduced, and the welding efficiency is improved.
In order to achieve the above-mentioned another object, the present invention provides a computer device comprising a processor and a memory, wherein the memory stores a computer program, and the computer program is executed by the processor to implement the steps of the automatic identification method for welding area of the welding workpiece.
To achieve the above-mentioned further object, the present invention provides a computer-readable storage medium having a computer program stored thereon, the computer program, when being executed by a processor, implementing the steps of the above-mentioned method for automatically identifying a welding area of a welding workpiece.
Drawings
Fig. 1 is a block diagram of a welding machine to which a first embodiment of the automatic identification method of the welding area of a welded workpiece of the present invention is applied.
Fig. 2 is a structural view of a welding machine in which the automatic identification method of the welding area of the welded workpiece according to the first embodiment of the present invention is applied after hiding a case.
Fig. 3 is a structural view of a to-be-welded workpiece to which a first embodiment of the automatic identification method of the welding area of the welded workpiece of the present invention is applied.
Fig. 4 is a flowchart of a first embodiment of a method of automatically identifying a welding area of a welding workpiece to which the present invention is applied.
Fig. 5 is a flowchart of a second embodiment of a welding area automatic identification method to which the present invention is applied to weld workpieces.
The invention is further explained with reference to the drawings and the embodiments.
Detailed Description
The method for automatically identifying the welding area of the welding workpiece is applied to a welding machine, and particularly the welding machine is a device for welding an aluminum template. Preferably, the welding machine is provided with a processor and a memory, the memory stores a computer program, and the processor realizes the automatic identification method of the welding area of the welding workpiece by executing the computer program.
The first embodiment of the automatic identification method of the welding area of the welding workpiece:
welding machine for realizing the present embodiment as shown in fig. 1 and 2, the welding machine has a base 10 on which a transmission assembly 11 is disposed, in the present embodiment, the transmission assembly 11 includes a plurality of cylindrical rollers. Of course, the transfer assembly 11 may also be implemented using a belt or a chain. The aluminum mold plate 30 to be welded may be placed on the transfer assembly 11. Preferably, can set up many cylinders of drive such as motor and rotate to wait that the aluminium template automatic conveying of welded is to the welding station on, and transmit to the discharge station after the welding finishes.
A welding gun 15 as a welding device is arranged above the base 10, a shell 13 is arranged outside the welding gun 15, and preferably, part of the shell 13 is made of transparent material, for example, acrylic material, so as to facilitate the observation of the welding condition from the outside. A color camera 20 is provided in the housing 13, and the color camera 20 can capture a color image of the aluminum mold 30 to be welded, for example, to form an RGB image. A depth camera 21 is provided at one side of the color camera 20, and in the present embodiment, the depth camera 21 may be a binocular color camera, a structured light camera, a TOF camera, or the like, for acquiring data of the height coordinates of the aluminum mold 30 to be welded.
In this embodiment, the welding gun 15 is driven by a robot arm, so that the welding gun 15 can move relative to the base 10. The color camera 20 and the depth camera 21 are fixed to the base 10, and therefore the color camera 20 and the depth camera 21 do not move relative to the base 10. A weld tracker 22 is fixed to the welding gun 15 or the robot arm, and the weld tracker 22 can capture an image of a welded weld and calculate the coordinates of the weld, so that the welding machine can adjust the movement locus of the welding gun 15 according to the coordinates of the weld, that is, correct the movement locus of the welding gun 15.
Referring to fig. 3, the aluminum mold plate 30 to be welded has a rectangular bottom plate 32, side plates 33 are disposed around the bottom plate 32, and four side plates 33 and the bottom plate 32 form a base 31 of the aluminum mold plate 30. Generally, the connection area between the bottom plate 32 and the side plate 33 is the area needing welding, for example, the area 36 is the connection area between the bottom plate 32 and the side plate 33.
The base 31 is further provided with a partition 34 and a partition 35, wherein the partition 34 is a partition extending along the longitudinal direction of the base 32, and the partition 35 is a partition extending along the width direction of the base 32, so that the partition 34 and the partition 35 are perpendicular to each other. Since the partition 34 and the partition 35 are not fixed to the bottom plate 32 or the side plate 33 by the fixing member, the connection region between the partition 34 and the bottom plate 32 and the connection region between the partition 35 and the bottom plate 32 are also regions to be welded, for example, the region 37 is the connection region between the partition 35 and the bottom plate 32 and the side plate 33.
However, since the shapes of the partition plates 34 and 35 are not fixed, and the shapes of the connection regions between the partition plates 34 and the side plates 33 and the bottom plate 32 are not fixed in consideration of the connection reliability, the shapes and positions of the welding regions on the aluminum mold plate 30 are not fixed, and thus, the welding requirements of the aluminum mold plates 30 of various types and shapes cannot be satisfied by using one set of computer program.
Therefore, the present embodiment provides a method for accurately welding aluminum templates with different shapes. The present embodiment is to identify a welding area based on an image of a workpiece to be welded, and calculate coordinates of the welding area, thereby calculating a movement locus of the welding apparatus, and further controlling the movement of the welding apparatus.
Before welding a workpiece to be welded, a mark of a specific color is drawn on an area to be welded, for example, a red ink pen is used to draw a mark on the area to be welded, so that the area to be welded is the area painted with red ink. Then, the work piece to be welded is placed on the transfer assembly and is transferred to the lower side of the color camera and the depth camera through the transfer assembly. Because color camera and depth camera all set up in the shell, consequently, at first will treat the work piece transmission of welding to the shell in to use anchor clamps will treat that the work piece centre gripping is fixed, avoid treating in the welding process and treat the condition that the work piece appears removing.
Referring to fig. 4, after the workpiece to be welded is clamped and fixed, step S1 is performed to capture a color image of the workpiece to be welded using a color camera. For example, a common color camera is used to capture an RGB image, where each pixel in the color image has a chromatic value composed of red, green, and blue, and the chromatic value of each color ranges from 0 to 255. Preferably, the color image shot by the color camera should cover the whole aluminum template to be welded, so that the plane coordinates of the aluminum template can be calibrated accurately through the color image.
For example, the color camera captures an image of the aluminum template at an angle of a top view, so that when calibrating the plane coordinates of the aluminum template, a preset point of the aluminum template may be used as an origin of the plane coordinate system, for example, a vertex of a lower left corner of the aluminum template is used as the origin of the plane coordinate system, and the plane coordinates of the aluminum template are calibrated based on the origin, that is, the X-axis coordinates and the Y-axis coordinates of the aluminum template are obtained. Because the color camera is fixed on the base, the distance between the color camera and the aluminum template is relatively fixed, and the actual size of the aluminum template can be calculated according to the size of the aluminum template in the color image, so that a basis is provided for the step length of a plane coordinate.
Of course, a certain preset point on the welding machine can be used as an origin, and the movement track of the welding equipment such as the welding gun can be calculated more accurately by taking the welding machine as a basis.
Then, step S2 is executed to acquire a region of a preset color in the color image. Because the required welding area on the workpiece to be welded is painted with red ink, the color of the aluminum template is usually silver gray, and the contrast between the two colors is very large, the area painted with the red ink can be calculated by calculating the chromatic value of each pixel point in the color image, so that the area required to be welded is determined.
Then, step S3 is performed, a depth image of the workpiece to be welded is acquired, and the height coordinates of the region to be welded are calculated. For example, a depth camera is used to capture an image of the entire aluminum template, thereby obtaining the height coordinates of the entire aluminum template. The depth camera captures an image of the aluminum template and calculates the height coordinate of the aluminum template from the captured image may be implemented using a known algorithm of the depth camera, which is not described herein again.
After the height coordinates of the aluminum mold plate are acquired from the image taken by the depth camera, the height coordinates of the area to be welded are acquired according to the area to be welded determined in step S2, that is, the height coordinates of the welded area portion are acquired from the entire image acquired by the depth camera, and the height coordinates of the area not to be welded are discarded.
Next, step S4 is executed to calculate the motion trajectory of the welding apparatus according to the plane coordinates and the height coordinates of the welding region. Since the three-dimensional coordinates of the area to be welded are calculated, the motion track of the welding equipment is the track required to pass through the welding area. The movement tracks of welding equipment such as a welding gun and the like can be calculated and obtained by using the conventional welding gun track calculation method according to the three-dimensional coordinates of the welding area, and are not repeated.
Then, step S5 is executed to output a control command to the welding equipment to operate the welding equipment. After the movement track of the welding gun is calculated in step S4, the mechanical arm drives the welding gun to move according to the calculated movement track, for example, according to the three-dimensional coordinates of the welding area, the movement path of the welding gun passing through the three-dimensional coordinates is calculated, including controlling the translation and rotation of the welding gun in the X-axis, Y-axis and Z-axis directions. And after the welding gun moves according to the calculated motion trail, a welding seam is formed in the area needing to be welded, so that the welding of the aluminum template is realized.
However, the coordinates of the to-be-welded area calculated by the depth camera are not very accurate due to the accuracy of the depth camera, so that after the welding device moves along the pre-calculated track during welding, the problem that the actual welding position is not the position actually required to be welded may occur. For this reason, the present embodiment introduces a correction mechanism that tracks the area to be welded using a seam tracker, calculates the actual coordinates of the area to be welded from the actually acquired image of the area to be welded, and thereby adjusts the movement trajectory of the welding apparatus. A seam tracker, also called a seam scanner, is a known device for monitoring a seam.
Therefore, after the welding apparatus starts welding, step S6 is performed, an image of the region to be welded is taken using the seam tracker, and the actual coordinates of the region to be welded are calculated. Since the seam tracker is fixed to the welding gun and the welding gun is moved according to a predetermined trajectory, i.e. the welding gun is moved to each position, the coordinates of the welding gun are known. Like this, when the welding gun motion, can calculate the coordinate of welding gun, can calculate the coordinate of welding seam tracker according to the position that welding seam tracker fixed on the welding gun, and then can calculate the actual coordinate of waiting to weld the region according to the photo that welding seam tracker shot.
Then, step S7 is performed to correct the movement locus of the welding apparatus according to the actual coordinates of the area to be welded calculated in step S6. For example, the area to be welded may be slightly bent, or the area to be welded may be raised or recessed, which requires modification of the movement path of the welding device to meet the welding requirement. Therefore, step S7 corrects the movement trajectory of the welding gun to ensure that the welding gun can move in accordance with the shape of the actual welding area, thereby ensuring the welding quality. It should be noted that steps S6 and S7 are used to correct the movement trajectory of the welding gun, and only to improve the welding quality, and in actual application, the movement trajectory of the welding gun may not be corrected, and it is understood that steps S6 and S7 are only preferred embodiments and are not necessarily performed.
The tracking of the welding area by using the seam tracker and the adjustment of the movement trajectory of the welding gun are known techniques, and the movement trajectory of the welding gun can be adjusted by using the existing seam tracker, which is not described herein again.
Finally, step S8 is executed to determine whether the welding of the workpieces to be welded is completed, for example, whether all the areas of the aluminum mold plate to be welded have been welded, if so, the welding operation is completed, and the welded aluminum mold plate is transported out of the housing through the transport assembly. If the welding is not finished, the process returns to step S5 to continue to obtain the control command and drive the welding gun to move until all the welding areas are welded.
If the length of the workpiece to be welded is long, the workpiece to be welded can be divided into multiple sections, and the above operation is performed once for each section, or multiple color cameras are used for shooting color images of the workpiece to be welded, then the images shot by the multiple color cameras are spliced, so that a complete image of the workpiece to be welded is obtained, and then welding is performed.
Second embodiment of the method for automatically identifying the welding area of a welding workpiece:
compared with the first embodiment, the depth camera adopted by the embodiment is a profile scanner, and the movement track of the welding gun does not need to be adjusted by using a seam tracker. The profile scanner has a higher accuracy than a depth camera such as a laser structured light camera, a binocular camera, etc., and generally calculates the height of a workpiece to be welded by emitting laser light and calculating the time for the laser light to return. The profile scanner may be fixed to the base of the welding machine, or of course, the profile scanner may be fixed to the robotic arm or to the welding gun to follow the movement of the robotic arm or welding gun relative to the base. In this embodiment, since the profile scanner is used, the movement locus of the welding apparatus does not need to be corrected by using a seam tracker.
Referring to fig. 5, after the workpiece to be welded is clamped and fixed, step S11 is performed to capture a color image of the workpiece to be welded using a color camera. The RGB image is acquired, for example, by shooting with a common color camera. Preferably, the color image shot by the color camera should cover the whole aluminum template to be welded, so that the plane coordinates of the aluminum template can be calibrated accurately through the color image. When calibrating the plane coordinates of the aluminum template, a preset point of the aluminum template can be used as an origin of a plane coordinate system, and the plane coordinates of the aluminum template are calibrated based on the origin, that is, the X-axis coordinates and the Y-axis coordinates of the aluminum template are obtained.
Then, step S12 is executed to acquire a region of a preset color in the color image. Because the required welding area on the workpiece to be welded is painted with red ink, the color of the aluminum template is usually silver gray, and the contrast between the two colors is very large, the area painted with the red ink can be calculated by calculating the chromatic value of each pixel point in the color image, so that the area required to be welded is determined.
Then, step S13 is performed to determine whether the workpieces to be welded are symmetrically arranged workpieces. Since the arrangement S11 has acquired a color image of the workpieces to be welded, it can be determined from the color image whether the workpieces to be welded are symmetrically arranged workpieces. For example, the workpieces to be welded are symmetrical along the X-axis direction, or symmetrical along the Y-axis direction. Preferably, a model library of the aluminum template may be preset, a plurality of common models of the aluminum template are stored in the model library, after a color image of the aluminum template is obtained by shooting, the obtained image of the aluminum template may be compared with the model of each aluminum template in the model library, whether the current aluminum template to be welded is the same as the model of one aluminum template in the model library is judged, if the current aluminum template is the same as the model of one aluminum template, the model of the aluminum template is directly used to calculate the plane coordinates of the area to be welded, and the model of the aluminum template is used to judge whether the workpiece to be welded is a symmetrically arranged workpiece.
If the workpieces to be welded are symmetrically arranged workpieces, step S14 is performed to acquire the height coordinates of the welding area of one of the symmetric areas. For example, if the workpieces to be welded are symmetrically arranged along the X-axis, the workpieces to be welded are divided into two symmetrical regions along the X-axis, and step S14 is to obtain the height coordinates of the welding region in one of the symmetrical regions.
The present embodiment acquires the height coordinates of the welding area using a profile scanner, which calculates the height coordinates of the area to be welded by emitting a laser beam and calculating the time of the returned laser beam, and the height coordinate calculation is very accurate. Because the width of each scanning of the profile scanner is narrow, for example, the profile scanner can only scan a width smaller than 5 cm in the X-axis direction when moving along the Y-axis direction, the profile scanner only scans the area to be welded, and the area not to be welded does not scan. Since the width of the area to be welded is also generally narrow, the profile scanner needs only to perform one movement along the Y-axis direction and perform scanning to satisfy the requirement of calculating the height coordinate of one welding area.
After the height coordinates of the welding area of one of the symmetric areas are acquired, step S15 is executed to calculate the height coordinates of the welding area of the other symmetric area. Since the height coordinate of the welding area of one symmetric area is obtained by calculation, when the coordinates of the welding area in the other symmetric area are calculated, the height coordinate of the welding area of one symmetric area which is already calculated only needs to be correspondingly and symmetrically calculated.
Then, step S16 is executed to calculate the motion trajectory of the welding apparatus according to the plane coordinates and the height coordinates of the welding region. Since the three-dimensional coordinates of the area to be welded are calculated, the motion track of the welding equipment is the track required to pass through the welding area. The movement tracks of welding equipment such as a welding gun and the like can be calculated and obtained by using the conventional welding gun track calculation method according to the three-dimensional coordinates of the welding area, and are not repeated. After the movement track of the welding equipment is calculated, a control instruction is output to the mechanical arm, so that the welding equipment is driven to act, and the aluminum template is welded.
If the result of the judgment of the step S13 is NO, a step S17 is performed in which all the areas to be welded of the entire aluminum mold plate are scanned using a profile scanner and the height coordinates of the areas to be welded are acquired. Preferably, the scanning width of the profile scanner is narrow, so that the scanning is only performed on a welding area, and the scanning is not performed on an area which does not need to be welded, so as to avoid an excessive calculation amount. After the height coordinate of the area to be welded is obtained, the running track of the welding equipment is calculated according to the plane coordinate and the height coordinate of the area to be welded, and the mechanical arm is driven to drive the welding equipment to move.
Finally, step S18 is executed to determine whether the welding of the workpieces to be welded is completed, for example, whether all the areas of the aluminum mold plate to be welded have been welded, if so, the welding operation is completed, and the welded aluminum mold plate is transported out of the housing through the transport assembly. If the welding is not finished, the process returns to the step S16 to continue to obtain the control command, and the robot arm drives the welding gun to move until all the welding areas are welded.
The method comprises the steps of shooting a color image of a workpiece to be welded, calculating the plane coordinate of the workpiece to be welded according to the color image, identifying a region with a preset color on the workpiece to be welded according to the color image, identifying a welding region, obtaining the height coordinate of the welding region, and calculating the motion track of the welding equipment. Therefore, the welding equipment can calculate the corresponding motion track of the welding equipment according to the shape of each workpiece to be welded and the position of the welding area, and the action of the welding equipment does not need to be controlled by performing corresponding programming on each workpiece to be welded in advance. Therefore, the aluminum templates produced in small batches can be welded through the welding machine, the aluminum templates do not need to be programmed before welding, the welding cost of the aluminum templates can be reduced, the automatic welding machine is used for welding, the welding quality can be improved, and the welding efficiency is also improved.
In addition, due to the fact that the ink with the specific color is coated on the welding area in advance, after the color image is shot by the color camera, the area where the ink is located can be rapidly identified, and therefore the coordinates of the welding area can be rapidly and accurately calculated.
In addition, the above embodiments have been described with reference to aluminum die plates as examples, and in actual use, the workpieces to be welded may be metal die plates made of steel, aluminum alloy, or the like.
Therefore, the welding machine provided by the invention is equipment capable of automatically welding the metal template, and provides a foundation for realizing intelligent manufacturing of the metal template.
The embodiment of the computer device comprises:
the computer device of the embodiment is a single chip microcomputer arranged in the welding machine, the computer device comprises a processor, a memory and a computer program which is stored in the memory and can run on the processor, and when the processor executes the computer program, the steps of the automatic identification method of the welding area of the welding workpiece are realized.
For example, a computer program may be partitioned into one or more modules that are stored in a memory and executed by a processor to implement the modules of the present invention. One or more of the modules may be a series of computer program instruction segments capable of performing certain functions, which are used to describe the execution of the computer program in the terminal device.
The Processor may be a Central Processing Unit (CPU), or may be other general-purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf Programmable Gate Array (FPGA) or other Programmable logic device, a discrete Gate or transistor logic device, a discrete hardware component, or the like. The general-purpose processor may be a microprocessor or the processor may be any conventional processor or the like, the processor being the control center of the terminal device and connecting the various parts of the entire terminal device using various interfaces and lines.
The memory may be used to store computer programs and/or modules, and the processor may implement various functions of the terminal device by running or executing the computer programs and/or modules stored in the memory and invoking data stored in the memory. The memory may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required by at least one function (such as a sound playing function, an image playing function, etc.), and the like; the storage data area may store data (such as audio data, a phonebook, etc.) created according to the use of the cellular phone, and the like. In addition, the memory may include high speed random access memory, and may also include non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), at least one magnetic disk storage device, a Flash memory device, or other volatile solid state storage device.
A computer-readable storage medium:
the computer program stored in the computer device may be stored in a computer-readable storage medium if it is implemented in the form of a software functional unit and sold or used as a separate product. Based on such understanding, all or part of the processes in the method according to the above embodiments may be implemented by a computer program, which may be stored in a computer readable storage medium and executed by a processor, so as to implement the steps of the automatic identification method for the welding area of the welding workpiece.
Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer readable medium may include: any entity or device capable of carrying computer program code, recording medium, U.S. disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution media, and the like. It should be noted that the computer readable medium may contain other components which may be suitably increased or decreased as required by legislation and patent practice in jurisdictions, for example, in some jurisdictions, in accordance with legislation and patent practice, the computer readable medium does not include electrical carrier signals and telecommunications signals.
Finally, it is emphasized that the present invention is not limited to the above-described embodiments, such as changes in the type of depth camera used, or changes in the method of calculating the motion trajectory of the welding equipment, etc., and such changes are also included in the scope of the present invention.

Claims (10)

1. The automatic identification method of the welding area of the welding workpiece comprises the following steps:
acquiring a color image shot by a color camera, and calibrating the plane coordinate of a workpiece to be welded according to the color image;
the method is characterized in that:
obtaining a region with a preset color in the color image, and calibrating the region with the preset color as a welding region;
acquiring a depth image of the workpiece to be welded, and calculating a height coordinate of the welding area;
and calculating the motion trail of the welding equipment according to the plane coordinates and the height coordinates of the welding area.
2. The automatic identification method of the welding area of the welding workpiece according to claim 1, characterized in that:
the acquiring of the region of the preset color in the color image comprises: and acquiring a region of the color image with the colorimetric value within a preset range.
3. The automatic identification method of the welding area of the welding workpiece according to claim 1, characterized in that:
the calibrating the plane coordinates of the workpiece to be welded according to the color image comprises: and taking the preset point of the workpiece to be welded or the preset point on the welding machine as the original point of a plane coordinate system, and calibrating the plane coordinate of the workpiece to be welded by taking the original point as a reference.
4. The automatic identification method of the welding area of the welding workpiece according to any one of claims 1 to 3, characterized in that:
calculating the height coordinates of the welding region comprises: and acquiring the height coordinate of the to-be-welded workpiece output by the depth camera, and acquiring the height coordinate of the welding area in the to-be-welded workpiece.
5. The automatic identification method of the welding area of the welding workpiece according to any one of claims 1 to 3, characterized in that:
after calculating the motion trail of the welding equipment, further executing the following steps: acquiring an image of the area to be welded, calculating the actual coordinates of the area to be welded, and adjusting the motion track of the welding equipment according to the actual coordinates of the area to be welded.
6. The automatic identification method of the welding area of the welding workpiece according to claim 5, characterized in that:
the image of the area to be welded is obtained by a weld tracker, which is fixed to the welding equipment.
7. The automatic identification method of the welding area of the welding workpiece according to any one of claims 1 to 3, characterized in that:
calculating the height coordinates of the welding region comprises: and after the welding area is determined according to the color image, a contour scanner is used for acquiring the height coordinate of the welding area.
8. The automatic identification method of the welding area of the welding workpiece according to claim 7, characterized in that:
acquiring the height coordinates of the welding region using the profile scanner comprises: and when the workpieces to be welded are confirmed to be symmetrically arranged workpieces, the contour scanner is applied to obtain the height coordinate of the welding area of one symmetrical area of the workpieces to be welded, and the height coordinate of the welding area of the other symmetrical area is calculated.
9. Computer arrangement, characterized in that it comprises a processor and a memory, said memory storing a computer program which, when being executed by the processor, carries out the steps of the method for automatic identification of a welding area of a welding workpiece according to any one of claims 1 to 8.
10. A computer-readable storage medium having stored thereon a computer program, characterized in that: the computer program, when being executed by a processor, realizes the steps of the method for automatically identifying a welding area of a welding workpiece according to any one of claims 1 to 8.
CN201911235163.7A 2019-12-05 2019-12-05 Method for automatically identifying welding area of welding workpiece, computer device and computer-readable storage medium Active CN110961778B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201911235163.7A CN110961778B (en) 2019-12-05 2019-12-05 Method for automatically identifying welding area of welding workpiece, computer device and computer-readable storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201911235163.7A CN110961778B (en) 2019-12-05 2019-12-05 Method for automatically identifying welding area of welding workpiece, computer device and computer-readable storage medium

Publications (2)

Publication Number Publication Date
CN110961778A true CN110961778A (en) 2020-04-07
CN110961778B CN110961778B (en) 2021-12-21

Family

ID=70032929

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201911235163.7A Active CN110961778B (en) 2019-12-05 2019-12-05 Method for automatically identifying welding area of welding workpiece, computer device and computer-readable storage medium

Country Status (1)

Country Link
CN (1) CN110961778B (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111644744A (en) * 2020-05-20 2020-09-11 南京航空航天大学 Multifunctional integrated welding equipment and method for double-laser-beam bilateral synchronous welding
CN115430956A (en) * 2022-08-19 2022-12-06 广州超音速自动化科技股份有限公司 Welding point positioning method, system, device and storage medium

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPS63317887A (en) * 1987-06-19 1988-12-26 Matsushita Electric Works Ltd Color image processing method
CN102059484A (en) * 2009-11-17 2011-05-18 孙杰 Color hose-based weld automatic identifying device
CN103252560A (en) * 2013-03-22 2013-08-21 广西机电职业技术学院 Automatic weld tracking method based on laser vision sensing
CN107424142A (en) * 2017-03-30 2017-12-01 上海万如科技发展有限公司 A kind of weld joint recognition method based on saliency detection
CN109352217A (en) * 2018-10-29 2019-02-19 上海船舶工艺研究所(中国船舶工业集团公司第十研究所) Robot on-line automatic welding equipment and weld job method are found by a kind of group
CN109903279A (en) * 2019-02-25 2019-06-18 北京深度奇点科技有限公司 The automatic teaching method and device of weld seam motion profile

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPS63317887A (en) * 1987-06-19 1988-12-26 Matsushita Electric Works Ltd Color image processing method
CN102059484A (en) * 2009-11-17 2011-05-18 孙杰 Color hose-based weld automatic identifying device
CN103252560A (en) * 2013-03-22 2013-08-21 广西机电职业技术学院 Automatic weld tracking method based on laser vision sensing
CN107424142A (en) * 2017-03-30 2017-12-01 上海万如科技发展有限公司 A kind of weld joint recognition method based on saliency detection
CN109352217A (en) * 2018-10-29 2019-02-19 上海船舶工艺研究所(中国船舶工业集团公司第十研究所) Robot on-line automatic welding equipment and weld job method are found by a kind of group
CN109903279A (en) * 2019-02-25 2019-06-18 北京深度奇点科技有限公司 The automatic teaching method and device of weld seam motion profile

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111644744A (en) * 2020-05-20 2020-09-11 南京航空航天大学 Multifunctional integrated welding equipment and method for double-laser-beam bilateral synchronous welding
CN115430956A (en) * 2022-08-19 2022-12-06 广州超音速自动化科技股份有限公司 Welding point positioning method, system, device and storage medium

Also Published As

Publication number Publication date
CN110961778B (en) 2021-12-21

Similar Documents

Publication Publication Date Title
CN110539109B (en) Robot automatic welding system and method based on single-binocular vision
CN110961778B (en) Method for automatically identifying welding area of welding workpiece, computer device and computer-readable storage medium
CN112620926B (en) Welding spot tracking method and device and storage medium
CN113305849B (en) Intelligent flat groove cutting system and method based on composite vision
CN109715307B (en) Bending machine with work area image capturing device and method for representing work area
CN108907526A (en) A kind of weld image characteristic recognition method with high robust
CN112456128B (en) Automatic loading and unloading method and system on production line based on machine vision
CN112719576B (en) Method, device and system for searching laser welding focus and storage medium
CN113146172A (en) Multi-vision-based detection and assembly system and method
CN109238135A (en) A kind of view-based access control model precise positioning expects the method for test box
CN107860773B (en) Automatic optical detection system for PCB and correction method thereof
CN110893525B (en) Method for identifying welding area of welding workpiece, computer device and computer readable storage medium
CN102172806A (en) Image recognition technology based full-automatic welding system and operation method thereof
CN113044349B (en) Product labeling control method and device based on robot arm
CN118397105A (en) Positioning calibration teaching method and system based on machine vision traversal
CN110977154A (en) Positioning marking method suitable for large breadth
CN112802029B (en) Welding spot positioning method and device
CN113182701A (en) Laser processing method, apparatus, device and storage medium
CN116030449B (en) Automatic sorting method and automatic sorting system for laser cutting pieces
CN116433604A (en) Chip identification method and pickup system
CN112743194B (en) Full-automatic welding process based on automatic path planning and slope point identification
CN114693679A (en) Deviation rectifying method, device and equipment
CN111563935B (en) Visual positioning method for honeycomb holes of honeycomb sectional material
KR20130073050A (en) Laser machining device and calibration data generating method
CN114289858B (en) Debugging and monitoring method, device, equipment and computer readable storage medium

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