CN112548265A - Intelligent welding method and equipment for container lock seat - Google Patents
Intelligent welding method and equipment for container lock seat Download PDFInfo
- Publication number
- CN112548265A CN112548265A CN202011184444.7A CN202011184444A CN112548265A CN 112548265 A CN112548265 A CN 112548265A CN 202011184444 A CN202011184444 A CN 202011184444A CN 112548265 A CN112548265 A CN 112548265A
- Authority
- CN
- China
- Prior art keywords
- door lock
- offset
- lock seat
- template
- image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000003466 welding Methods 0.000 title claims abstract description 160
- 238000000034 method Methods 0.000 title claims abstract description 41
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 21
- 239000013598 vector Substances 0.000 claims description 19
- 238000012545 processing Methods 0.000 claims description 12
- 238000004364 calculation method Methods 0.000 claims description 5
- 230000003993 interaction Effects 0.000 claims description 5
- 230000009467 reduction Effects 0.000 claims description 4
- 238000010606 normalization Methods 0.000 claims description 2
- 238000001514 detection method Methods 0.000 abstract description 13
- 238000004519 manufacturing process Methods 0.000 abstract description 3
- 230000008878 coupling Effects 0.000 abstract 1
- 238000010168 coupling process Methods 0.000 abstract 1
- 238000005859 coupling reaction Methods 0.000 abstract 1
- 230000000007 visual effect Effects 0.000 description 10
- 238000004590 computer program Methods 0.000 description 9
- 238000010586 diagram Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 238000003860 storage Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 239000000428 dust Substances 0.000 description 3
- 238000005259 measurement Methods 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000005855 radiation Effects 0.000 description 2
- 239000000523 sample Substances 0.000 description 2
- 239000000779 smoke Substances 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 238000005299 abrasion Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000013523 data management Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 239000012636 effector Substances 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000010891 electric arc Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B23—MACHINE TOOLS; METAL-WORKING NOT OTHERWISE PROVIDED FOR
- B23K—SOLDERING OR UNSOLDERING; WELDING; CLADDING OR PLATING BY SOLDERING OR WELDING; CUTTING BY APPLYING HEAT LOCALLY, e.g. FLAME CUTTING; WORKING BY LASER BEAM
- B23K9/00—Arc welding or cutting
-
- 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
- B23K9/00—Arc welding or cutting
- B23K9/12—Automatic feeding or moving of electrodes or work for spot or seam welding or cutting
- B23K9/127—Means for tracking lines during arc welding or cutting
-
- 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
- B23K9/00—Arc welding or cutting
- B23K9/32—Accessories
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Plasma & Fusion (AREA)
- Mechanical Engineering (AREA)
- Manipulator (AREA)
- Numerical Control (AREA)
Abstract
The invention is suitable for the technical field of container production, and provides an intelligent welding method and equipment for a container lock seat, wherein a workpiece coordinate system is generated according to image information of a door lock seat template by acquiring the door lock seat template of the door lock seat, and a track is taught; extracting characteristic points of a door lock seat template, and calculating a first offset and a first rotation amount of a door lock seat according to the characteristic points acquired after the door lock seat is offset and rotated and coordinate parameters of a central point of the door lock seat; according to a template matching algorithm of correlation, acquiring a second offset and a second rotation amount of a target image of a door lock seat relative to a template image, and calculating comparison information between the first offset and the first rotation amount; and if the comparison information meets the preset error condition, compensating the second offset at the teaching point of the welding robot so as to recalculate the motion track of the welding gun. Therefore, the welding track of the door lock seat can be corrected, and the problem of limiting detection precision by avoiding characteristic image coupling noise is solved.
Description
Technical Field
The invention relates to the technical field of container production, in particular to an intelligent welding method and equipment for a container lock seat.
Background
Because there are a large amount of noises, dust and arc light in the container production process, can cause the influence to welding personnel's health under this kind of environment for a long time, there are the amount of labour big in addition in the manual welding, inefficiency and quality can't guarantee the scheduling problem, robot welding has gradually obtained the application in the container trade at present, welding robot adopts the work of demonstration reappearing the mode usually, the process of teaching is accomplished through following mode: the robot end effector (e.g., a welding gun) is manually guided and the desired actions are stored in the form of points and commands that are invoked to achieve the desired actions of the robot.
In practical application, the manual spot welding positioning is needed in the front process of the welding robot, the manual spot welding positioning cannot guarantee the positioning precision, and a certain error exists between the actual position and the expected position, so that the teaching track of the robot cannot meet the actual track requirement. The same type of weldment provided by different welding suppliers has different sizes and shapes, and the periodical replacement of the welding suppliers causes the template to be inconsistent with the actual weldment, so that the teaching track of the welding robot cannot meet the actual track requirement.
To solve this problem, various welding sensors such as arc sensing, contact sensing, ultrasonic sensing, and visual sensing have come into play. The arc sensing influences the accuracy of welding seam signal detection because an accurate model between current change and arc length is difficult to establish; the contact type sensing requires that different probes are used corresponding to different types of grooves, the probes are large in abrasion and easy to deform, and fixed point obstacles are difficult to overcome; ultrasonic sensing requires that the sensor is close to the workpiece, so the ultrasonic sensing is strictly limited by welding methods, workpiece sizes and the like, and factors such as external vibration, propagation time and the like need to be considered, so the ultrasonic sensing has high requirements on the surface condition of the metal and limits the application range of the ultrasonic sensing. The visual sensing has the advantages of non-contact characteristic, rich acquired information and the like, and when a CCD (charge coupled device) camera is used for shooting a welding seam image, the image is easily degraded due to serious interference of noise such as electric arc and the like, so that the characteristic extraction is difficult.
As can be seen, the conventional method has many problems in practical use, and therefore, needs to be improved.
Disclosure of Invention
Aiming at the defects, the invention aims to provide an intelligent welding method and equipment for a container lock base, which solve the problems of low teaching reappearance type welding efficiency, poor universality and low flexibility in the welding process of the container door lock base and realize the welding work after the container door lock base is horizontally deviated.
In order to achieve the above object, the present invention provides an intelligent welding method for a container lock seat, comprising:
acquiring a door lock seat template of a door lock seat through an industrial camera, generating a workpiece coordinate system according to image information of the door lock seat template, and performing track teaching;
extracting any characteristic point of the door lock seat template, and calculating a first offset and a first rotation amount of the door lock seat according to the characteristic point acquired after the door lock seat is offset and rotated and coordinate parameters of the central point of the door lock seat;
according to a template matching algorithm of correlation, acquiring a second offset and a second rotation amount of a target image of the door lock seat relative to a template image, and calculating comparison information between the first offset and the first rotation amount;
and if the comparison information meets a preset error condition, compensating the second offset at a teaching point of the welding robot so as to recalculate the motion track of the welding gun.
Further, the step of obtaining the door lock seat template of the door lock seat through the industrial camera, generating a workpiece coordinate system according to the image information of the door lock seat template, and performing trajectory teaching further comprises:
and taking the circle center of the teaching standard circle of the welding robot as a reference point, and acquiring the relative position of the central point of the industrial camera in the coordinate system of the welding robot.
Further, the step of acquiring a door lock seat template of the door lock seat through an industrial camera, generating a workpiece coordinate system according to image information of the door lock seat template, and performing trajectory teaching includes:
capturing an image of the door lock seat through the industrial camera, and generating a door lock seat template after the image is preprocessed;
generating the workpiece coordinate system according to the position of the door lock seat central point in the welding robot coordinate system acquired from the image information;
and performing track teaching in the workpiece coordinate system according to preset welding information.
The step of generating the workpiece coordinate system according to the position of the door lock seat center point in the welding robot coordinate system obtained from the image information further comprises:
and calculating to obtain the position of the central point of the door lock seat in the coordinate system of the welding robot according to the offset between the central point of the door lock seat and the central point of the industrial camera.
Further, the step of obtaining a second offset amount and a second rotation amount of the target image of the door lock holder with respect to the template image according to the template matching algorithm of the correlation and calculating comparison information between the first offset amount and the first rotation amount may include:
and after the door lock base horizontally deviates and rotates, acquiring a door lock base image at the current position through the industrial camera, and performing image noise reduction and contrast enhancement processing on the door lock base image.
Further, the step of obtaining a second offset amount and a second rotation amount of the target image of the door lock holder with respect to the template image according to the template matching algorithm of the correlation, and calculating comparison information between the first offset amount and the first rotation amount includes:
a first difference between the first offset amount and the second offset amount and a second difference between the first rotation amount and the second rotation amount are calculated.
Further, if the comparison information meets a preset error condition, compensating the second offset to a teaching point of the welding robot so as to recalculate the motion trail of the welding gun, wherein the step includes:
and judging whether the first difference and the second difference are both smaller than a preset error threshold value, if so, compensating the second offset to a teaching point of the welding robot so as to recalculate the motion track of the welding gun.
Further, the step of acquiring the relative position of the center point of the industrial camera in the welding robot coordinate system by using the center of the teaching standard circle of the welding robot as a reference point comprises:
and collecting and extracting all pixel coordinates of the teaching standard circle, and calculating an average value of all the pixel coordinates to be used as a circle center coordinate of the teaching standard circle.
Further, the step of obtaining a second offset amount and a second rotation amount of the target image of the door lock holder with respect to the template image according to the template matching algorithm of the correlation, and calculating comparison information between the first offset amount and the first rotation amount includes:
according to a template matching algorithm of correlation, all pixels in the template image are subjected to normalization processing, and first feature vectors are obtained according to a column sequence;
acquiring a second feature vector matched with the first feature vector from the target image;
calculating to obtain the second offset and the second rotation amount according to the first feature vector and the second feature vector;
and respectively comparing the first offset and the first rotation amount with the second offset and the second rotation amount to obtain the comparison information.
The intelligent welding equipment for the container lock seat is also provided, and is applied to the intelligent welding method for realizing the container lock seat.
Intelligent welding equipment of container lock seat, including welding robot, vision collection equipment, controlgear and welder subassembly, welding robot with vision collection equipment pass through the ethernet line respectively with controlgear connects, vision collection equipment with the welder subassembly all is fixed in on welding robot's the terminal ring flange.
Further, controlgear is including welding robot switch board and the industrial control host computer that is used for image processing and calculates, the industrial control host computer with vision collection equipment is connected in order to be used for the storage the image information that vision collection equipment obtained, the industrial control host computer with welding robot switch board is connected, the industrial control host computer is connected with and is used for realizing the interactive display of human-computer.
Furthermore, the vision acquisition equipment comprises an industrial camera, a lens and a light source, wherein the lens is fixed on a flange plate at the tail end of the welding robot, and the light source is distributed around the lens.
According to the intelligent welding method and the intelligent welding equipment for the container lock seat, the door lock seat template of the door lock seat is obtained through the industrial camera, and a workpiece coordinate system is generated according to the image information of the door lock seat template and trajectory teaching is carried out; extracting characteristic points of a door lock seat template, and calculating a first offset and a first rotation amount of a door lock seat according to the characteristic points acquired after the door lock seat is offset and rotated and coordinate parameters of a central point of the door lock seat; according to a template matching algorithm of correlation, acquiring a second offset and a second rotation amount of a target image of a door lock seat relative to a template image, and calculating comparison information between the first offset and the first rotation amount; and if the comparison information meets the preset error condition, compensating the second offset at the teaching point of the welding robot so as to recalculate the motion track of the welding gun. Therefore, the welding track of the door lock seat can be corrected, and the problem that the detection precision is restricted due to the fact that a large amount of noise is coupled to the characteristic image caused by arc light radiation, high temperature, smoke dust and other factors is avoided through off-line detection; the welding work after the horizontal direction deviation of the container door lock base is realized.
Drawings
Fig. 1 is a flow chart illustrating steps of an intelligent welding method for a container lock seat according to a preferred embodiment of the present invention;
fig. 2 is a detailed flowchart of step S101 of the intelligent welding method for the container lock seat according to the preferred embodiment of the present invention;
fig. 3 is a flowchart illustrating the step S103 of the intelligent welding method for the container lock seat according to the preferred embodiment of the present invention;
fig. 4 is a schematic structural diagram of an intelligent welding device for a container lock base according to a preferred embodiment of the invention;
fig. 5 is a functional block diagram of an intelligent welding device for a container lock seat according to a preferred embodiment of the present invention;
fig. 6 is a control circuit diagram of the intelligent welding device for the container lock base according to the preferred embodiment of the invention;
fig. 7 is a control software structure diagram of the intelligent welding device for the container lock base according to the preferred embodiment of the invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
It should be noted that references in the specification to "one embodiment," "an example embodiment," etc., indicate that the embodiment described may include a particular feature, structure, or characteristic, but every embodiment may not necessarily include the particular feature, structure, or characteristic. Moreover, such phrases are not intended to refer to the same embodiment. Further, when a particular feature, structure, or characteristic is described in connection with an embodiment, it is submitted that it is within the knowledge of one skilled in the art to effect such feature, structure, or characteristic in connection with other embodiments whether or not explicitly described.
Moreover, where certain terms are used throughout the description and following claims to refer to particular components or features, those skilled in the art will understand that manufacturers may refer to a component or feature by different names or terms. This specification and the claims that follow do not intend to distinguish between components or features that differ in name but not function. In the following description and in the claims, the terms "include" and "comprise" are used in an open-ended fashion, and thus should be interpreted to mean "include, but not limited to. In addition, the term "connected" as used herein includes any direct and indirect electrical connection. Indirect electrical connection means include connection by other means.
Fig. 1 shows an intelligent welding method for a container lock seat according to a preferred embodiment of the invention, which comprises the following steps:
s101: acquiring a door lock seat template of a door lock seat through an industrial camera, generating a workpiece coordinate system according to image information of the door lock seat template, and performing track teaching;
s102: extracting any characteristic point of the door lock seat template, and calculating a first offset and a first rotation amount of the door lock seat according to the characteristic point acquired after the door lock seat is offset and rotated and coordinate parameters of the central point of the door lock seat;
s103: according to a template matching algorithm of correlation, acquiring a second offset and a second rotation amount of a target image of the door lock seat relative to a template image, and calculating comparison information between the first offset and the first rotation amount;
s104: and if the comparison information meets the preset error condition, compensating the second offset at the teaching point of the welding robot so as to recalculate the motion track of the welding gun.
Preferably, step S101 further includes:
and taking the circle center of the teaching standard circle of the welding robot as a reference point, and acquiring the relative position of the central point of the industrial camera in the coordinate system of the welding robot.
Specifically, the step of acquiring the relative position of the center point of the industrial camera in the coordinate system of the welding robot by using the center of the teaching standard circle of the welding robot as a reference point comprises:
and collecting and extracting all pixel coordinates of the teaching standard circle, and calculating an average value of all the pixel coordinates to be used as a circle center coordinate of the teaching standard circle.
Referring to fig. 2, the step S101 further includes:
s1011: capturing an image of the door lock seat through the industrial camera, and generating a door lock seat template after the image is preprocessed;
s1012: generating the workpiece coordinate system according to the position of the door lock seat central point in the welding robot coordinate system acquired from the image information;
s1013: and performing track teaching in the workpiece coordinate system according to preset welding information.
The step S102 further includes: and calculating to obtain the position of the central point of the door lock seat in the coordinate system of the welding robot according to the offset between the central point of the door lock seat and the central point of the industrial camera.
Preferably, step S103 includes, before: and after the door lock base horizontally deviates and rotates, acquiring a door lock base image at the current position through the industrial camera, and performing image noise reduction and contrast enhancement processing on the door lock base image.
Step S103 includes: a first difference between the first offset amount and the second offset amount and a second difference between the first rotation amount and the second rotation amount are calculated.
Further, step S104 includes: and judging whether the first difference and the second difference are both smaller than a preset error threshold value, if so, compensating the second offset to a teaching point of the welding robot so as to recalculate the motion track of the welding gun.
Preferably, referring to fig. 3, step S103 includes:
s1031: according to a template matching algorithm of correlation, all pixels in the template image are normalized, and a first feature vector is obtained according to a column sequence;
s1032: acquiring a second feature vector matched with the first feature vector from the target image;
s1033: calculating to obtain the second offset amount and the second rotation amount according to the first feature vector and the second feature vector;
s1034: and respectively comparing the first offset and the first rotation amount with the second offset and the second rotation amount to obtain the comparison information.
In summary, the specific steps of the intelligent welding method for the container lock seat in this embodiment are preferably as follows:
1. the relative position of the center point of the industrial camera in the coordinate system of the welding robot is obtained by teaching the center point of the standard circle as a reference point, and the relative position is set as (x)p,yp)；
2. Moving an industrial camera right above a door lock seat, capturing an image of the door lock seat, sending the image to an industrial control host, preprocessing the captured image by using an automatic generation template mode, generating a door lock seat template, numbering and storing the door lock seat template, calculating the offset of a center point of the door lock seat relative to a center point of the camera by taking pixels as units, and converting the offset into the offset (m) in a robot world coordinate system0,n0) And then the position of the central point of the door lock seat in the world coordinate system of the welding robot is as follows: (x)p+m0,yp+n0) Generating a workpiece coordinate system of the welding robot and performing track teaching in the workpiece coordinate system by taking the door lock seat central point O as the original point of a new coordinate system, the X-axis direction of the world coordinate system of the robot as the J-axis of the workpiece coordinate system and the Y-axis direction of the basic coordinate system of the robot as the K-axis of the workpiece coordinate system according to the image information of the door lock seat template, wherein the workpiece coordinate system of the welding robot is generated and the track teaching is performed in the workpiece coordinate system, and the position of the door lock seat central point in the workpiece coordinate system is (J)0,k0) Wherein j is0＝0,k0＝0；
3. Get arbitrary characteristic point I (j) in the lock seat1,k1) And is provided with
An included angle formed by the X-axis and the J-axis of the workpiece coordinate system is equal toFront rotation angle r0，
4. The center point of the welding gun tail end of the welding robot is aligned with the center point of the door lock seat after horizontal deviation rotation, and the center point is in the feature point I, and the coordinate parameters of the robot at the moment are recorded and recorded, and the parameters are respectively as follows: (x)r,yr)、(j2,k2) Obtaining the actual offset
Actual amount of rotation
5. After the door lock base horizontally deviates and rotates, acquiring an image of the door lock base at the current position through an industrial camera, processing the image by adopting an image noise reduction algorithm, and enhancing the image contrast;
6. obtaining the offset (m) of the welding image relative to the horizontal direction of the template image by adopting a template matching algorithm based on the correlation2,n2) Amount of rotation r2；
7. Comparison (m)1,n1) And (m)2,n2) A value of (d), comparing r2And r1According to the allowable error of the welding robot reproduction process, whether the precision of the machine vision detection meets the requirement is judged, namely whether the precision meets the requirement is judged
Wherein Δ m, Δ n, and Δ r are the allowable errors of the welding system; if the requirements are met, the system can be integrated into an industrial robot control system for application; if the measurement accuracy does not meet the requirements, analyzing the reasons of error generation, and optimizing the obtained image center coordinate, the image denoising processing algorithm and the template matching algorithm to improve the measurement accuracy so as to meet the use requirements;
8. offset (m) from the measurement2,n2) And amount of rotation r2Compensating the deviation amount toAnd (3) recalculating the movement track of the welding gun by the robot teaching point, and controlling the welding gun to move by the welding robot controller according to the track so as to ensure that the welding gun is always aligned with the welding seam and finish the correction of the welding track.
Wherein, image acquisition is carried out on the standard reference object (namely the standard circle adopted in the step 1), and all pixel coordinates of the standard reference object are extracted and recorded as: (x)i,yi) And i is the number of standard reference pixels and i is more than 0. Then respectively accumulating x and y and averaging to obtain the central coordinate (x) of the standard reference objectc,yc)： 
In addition, in order to avoid the problem that conventional template preparation needs to be accomplished by the developer, when gathering the image, can guide to put the lock seat to the region of making, save the image again, the template image will automatic generation, simultaneously, can be according to user's demand, change, increase the template in the row.
Specifically, a template matching algorithm based on correlation is adopted, all pixels in a template image are subjected to normalized correlation calculation, and a feature vector is obtained according to the sequence of columns
(e.g. in the object coordinate system
The vector is a row vector), and then searching and feature vectors in the detection target image
The most proximal part
(e.g. in the object coordinate system)
In the new image are
) And then through calculation
And
the included angle between the two is used to obtain the value of the correlation of matching, thereby determining the offset (m ') of the door lock seat relative to the template in the image coordinate system'2,n′2) And rotation amount r'2. The formula is as follows:
where γ is a correlation coefficient, and x and y are variable sequences of length n. When γ is ± 1, the welded workpiece template and the current welded workpiece image are completely matched, and the closer the absolute value of γ is to 1, the closer the welded workpiece template is to the welded workpiece image being detected.
Fig. 4 to 5 show an intelligent welding device for a container lock base according to a preferred embodiment of the present invention, which is applied to implement the above-mentioned intelligent welding method for a container lock base.
Intelligent welding equipment of container lock seat, including welding robot 3, vision collection equipment 1, controlgear and welder subassembly, welding robot 3 and vision collection equipment 1 pass through the ethernet line respectively with controlgear connects, vision collection equipment 1 and welder subassembly all are fixed in on welding robot's the terminal ring flange. Wherein vision collection equipment 1 passes through vision collection equipment fixed element to be fixed on 3 terminal ring flanges of welding robot, the welder subassembly is including welder, welder fixed element and supporting welding equipment etc. just welder passes through welder fixed element and installs on the terminal ring flange of welding robot 3, supporting welding equipment provides energy and material for the welding, controlgear can be according to actual need by the user increase by oneself, change image template.
In order to solve the problem of the door lock seat of the container during the welding process, the welding track of the door lock seat is corrected by adopting an off-line visual detection technology, as shown in fig. 4. The vision technology is that the vision acquisition equipment 1 is used for acquiring image information of a welding workpiece 2, transmitting the image information to an image processing system, and converting information such as brightness and distribution of pixels in an image into digital signals; and then the image system extracts required characteristic information from the digital signal through various visual algorithms, thereby determining and reproducing the welding track offset, and enabling the welding robot 3 to accurately weld the welding workpiece 2.
Preferably, the control device comprises a welding robot control cabinet and an industrial control host for image processing and calculation, the industrial control host is connected with the visual acquisition device 2 to store image information acquired by the visual acquisition device 2, the industrial control host is connected with the welding robot control cabinet, and the industrial control host is connected with a display for realizing human-computer interaction. The industrial control host is used for storing the image information acquired by the visual acquisition equipment, and performing image processing and calculation; the industrial camera sends image information to the industrial control host, and the industrial control host is connected with the welding robot control cabinet through an Ethernet cable and used for sending the offset and the rotation amount detected and calculated to the welding robot; and human-computer interaction can be achieved through the display.
The vision acquisition equipment comprises an industrial camera, a lens and a light source, wherein the lens and the industrial camera are fixed on a flange plate at the tail end of the welding robot, and the light source is distributed around the lens.
In this embodiment, the industrial camera is a black-and-white area-array camera with 200 ten thousand pixels, the model is acA1600-20gm, the resolution is 1600x1200, the pixel size is 4.4um in the horizontal direction and 4.4um in the vertical direction, the lens 10 is a megapixel lens with the model of M2514-MP2, and the focal length is 25 mm.
With reference to the device control circuit diagram shown in fig. 6, the industrial personal computer is connected to the industrial camera through an ethernet cable, and the industrial personal computer is connected to a display, so that human-computer interaction can be realized.
Referring to fig. 7, the industrial control host uses control system software, which is preferably developed by using a Microsoft Visual Studio 2017 platform and is divided into four layers, wherein the first layer is a driver library and is provided by each equipment supplier; the second layer is a communication and monitoring program, which comprises a monitoring module, a communication module and a fault diagnosis and alarm module, and is responsible for real-time communication and operation monitoring among the modules of the application program and diagnosing and alarming faults; the third level is a control program layer, which comprises a position detection module, a visual detection module and a human-computer interaction module and is the core of the whole control system; the fourth layer is a main control program layer and comprises a main control module and a file and data management module, wherein the first layer, the second layer and the third layer are real-time control modules, and the fourth layer is a coordination program and is a non-real-time control program.
In the embodiment, the offset detection of the welding track of the container door lock base in the horizontal direction can be completed based on a visual technology through the welding robot and the machine vision acquisition equipment, the detection result is evaluated and verified by using the industrial control host, and template images are added and changed; the method can be integrated into a welding robot control system for application when the precision requirement is met, the reason for error generation is analyzed when the precision requirement is not met, and an image processing method in a machine vision technology is continuously optimized, so that the aim of accurately detecting the welding track offset is fulfilled.
The present invention also provides a storage medium for storing a computer program of the intelligent welding method for the container lock seat as shown in fig. 1 to 3. Such as computer program instructions, which when executed by a computer, may invoke or otherwise provide methods and/or techniques in accordance with the present application through the operation of the computer. Program instructions which embody the methods of the present application may be stored on fixed or removable storage media and/or transmitted via a data stream on a broadcast or other signal-bearing medium and/or stored on storage media of a computer device operating in accordance with the program instructions.
It should be noted that the present application may be implemented in software and/or a combination of software and hardware, for example, implemented using Application Specific Integrated Circuits (ASICs), general purpose computers or any other similar hardware devices. In one embodiment, the software programs of the present application may be executed by a processor to implement the above steps or functions. Likewise, the software programs (including associated data structures) of the present application may be stored in a computer readable recording medium, such as RAM memory, magnetic or optical drive or diskette and the like. Additionally, some of the steps or functions of the present application may be implemented in hardware, for example, as circuitry that cooperates with the processor to perform various steps or functions.
The method according to the invention can be implemented on a computer as a computer-implemented method, or in dedicated hardware, or in a combination of both. Executable code or portions thereof for the method according to the invention may be stored on a computer program product. Examples of computer program products include memory devices, optical storage devices, integrated circuits, servers, online software, and so forth. Preferably, the computer program product comprises non-transitory program code means stored on a computer readable medium for performing the method according to the invention when said program product is executed on a computer.
In a preferred embodiment, the computer program comprises computer program code means adapted to perform all the steps of the method according to the invention when the computer program is run on a computer. Preferably, the computer program is embodied on a computer readable medium.
In summary, according to the intelligent welding method and the intelligent welding equipment for the container lock seat, the door lock seat template of the door lock seat is obtained through the industrial camera, and the workpiece coordinate system is generated according to the image information of the door lock seat template and the trajectory teaching is carried out; extracting characteristic points of a door lock seat template, and calculating a first offset and a first rotation amount of a door lock seat according to the characteristic points acquired after the door lock seat is offset and rotated and coordinate parameters of a central point of the door lock seat; acquiring a second offset amount and a second rotation amount of a target image of the door lock seat relative to a template image according to a template matching algorithm of correlation, and calculating comparison information between the first offset amount and the first rotation amount; and if the comparison information meets the preset error condition, compensating the second offset at the teaching point of the welding robot so as to recalculate the motion track of the welding gun. Therefore, the welding track of the door lock seat can be corrected, and the problem that the detection precision is restricted due to the fact that a large amount of noise is coupled to the characteristic image caused by arc light radiation, high temperature, smoke dust and other factors is avoided through off-line detection; the welding work after the horizontal direction deviation of the container door lock base is realized.
The present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof, and it should be understood that various changes and modifications can be effected therein by one skilled in the art without departing from the spirit and scope of the invention as defined in the appended claims.
Claims (13)
1. An intelligent welding method for a container lock seat is characterized by comprising the following steps:
acquiring a door lock seat template of a door lock seat through an industrial camera, generating a workpiece coordinate system according to image information of the door lock seat template, and performing track teaching;
extracting any characteristic point of the door lock seat template, and calculating a first offset and a first rotation amount of the door lock seat according to the characteristic point acquired after the door lock seat is offset and rotated and coordinate parameters of the central point of the door lock seat;
according to a template matching algorithm of correlation, acquiring a second offset and a second rotation amount of a target image of the door lock seat relative to a template image, and calculating comparison information between the first offset and the first rotation amount;
and if the comparison information meets the preset error condition, compensating the second offset at the teaching point of the welding robot so as to recalculate the motion track of the welding gun.
2. The intelligent welding method for container lock holders according to claim 1, wherein the step of obtaining the door lock holder template of the door lock holder by an industrial camera, generating a workpiece coordinate system according to the image information of the door lock holder template, and performing trajectory teaching further comprises:
and taking the circle center of the teaching standard circle of the welding robot as a reference point, and acquiring the relative position of the central point of the industrial camera in the coordinate system of the welding robot.
3. The intelligent welding method for container lock holders according to claim 2, wherein the step of obtaining the door lock holder template of the door lock holder by an industrial camera, generating a workpiece coordinate system according to the image information of the door lock holder template, and performing trajectory teaching comprises:
capturing an image of the door lock seat through the industrial camera, and generating a door lock seat template after the image is preprocessed;
generating the workpiece coordinate system according to the position of the door lock seat central point in the welding robot coordinate system acquired from the image information;
and performing track teaching in the workpiece coordinate system according to preset welding information.
4. The intelligent welding method for container lock holders according to claim 3, wherein the step of generating the workpiece coordinate system based on the position of the door lock holder center point in the welding robot coordinate system obtained from the image information further comprises:
and calculating to obtain the position of the central point of the door lock seat in the coordinate system of the welding robot according to the offset between the central point of the door lock seat and the central point of the industrial camera.
5. The intelligent welding method for container lock holders according to claim 1, wherein the step of obtaining a second offset amount and a second rotation amount of the target image of the door lock holder with respect to the template image according to the template matching algorithm of correlation and calculating the comparison information with the first offset amount and the first rotation amount is preceded by:
and after the door lock base horizontally deviates and rotates, acquiring a door lock base image at the current position through the industrial camera, and performing image noise reduction and contrast enhancement processing on the door lock base image.
6. The intelligent welding method for container lock holders according to claim 1, wherein the step of obtaining a second offset amount and a second rotation amount of the target image of the door lock holder with respect to the template image according to the template matching algorithm of correlation, and calculating the comparison information with the first offset amount and the first rotation amount comprises:
a first difference between the first offset amount and the second offset amount and a second difference between the first rotation amount and the second rotation amount are calculated.
7. The intelligent welding method for the container lock base according to claim 6, wherein the step of compensating the second offset to the teaching point of the welding robot to recalculate the movement track of the welding gun if the comparison information meets a preset error condition comprises:
and judging whether the first difference and the second difference are both smaller than a preset error threshold value, and if so, compensating the second offset to a teaching point of the welding robot so as to recalculate the motion track of the welding gun.
8. The intelligent welding method for the container lock base according to claim 2, wherein the step of obtaining the relative position of the center point of the industrial camera in the welding robot coordinate system with the center of the teaching standard circle of the welding robot as the reference point comprises:
and collecting and extracting all pixel coordinates of the teaching standard circle, and calculating the average value of all the pixel coordinates to be used as the center coordinates of the teaching standard circle.
9. The intelligent welding method for container lock holders according to claim 1, wherein the step of obtaining a second offset amount and a second rotation amount of the target image of the door lock holder with respect to the template image according to the template matching algorithm of correlation, and calculating the comparison information with the first offset amount and the first rotation amount comprises:
according to a template matching algorithm of correlation, all pixels in the template image are subjected to normalization processing, and first feature vectors are obtained according to a column sequence;
acquiring a second feature vector matched with the first feature vector from the target image;
calculating to obtain the second offset and the second rotation amount according to the first feature vector and the second feature vector;
and respectively comparing the first offset and the first rotation amount with the second offset and the second rotation amount to obtain the comparison information.
10. An intelligent welding device for a container lock base is characterized by being applied to the intelligent welding method for the container lock base according to any one of claims 1 to 9.
11. The intelligent welding device for the container lock base according to claim 10, comprising a welding robot, a vision collecting device, a control device and a welding gun assembly, wherein the welding robot and the vision collecting device are respectively connected with the control device through ethernet cables, and the vision collecting device and the welding gun assembly are both fixed on a terminal flange of the welding robot.
12. The intelligent welding device for the container lock seat according to claim 11, wherein the control device comprises a welding robot control cabinet and an industrial control host for image processing and calculation, the industrial control host is connected with the vision acquisition device for storing the image information acquired by the vision acquisition device, the industrial control host is connected with the welding robot control cabinet, and the industrial control host is connected with a display for realizing human-computer interaction.
13. The intelligent welding device for container lock base of claim 12, wherein the vision collecting device comprises an industrial camera, a lens and a light source, the lens and the industrial camera are fixed on the end flange of the welding robot, and the light source is distributed around the lens.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011184444.7A CN112548265A (en) | 2020-10-28 | 2020-10-28 | Intelligent welding method and equipment for container lock seat |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011184444.7A CN112548265A (en) | 2020-10-28 | 2020-10-28 | Intelligent welding method and equipment for container lock seat |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112548265A true CN112548265A (en) | 2021-03-26 |
Family
ID=75042706
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011184444.7A Pending CN112548265A (en) | 2020-10-28 | 2020-10-28 | Intelligent welding method and equipment for container lock seat |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112548265A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114309934A (en) * | 2021-12-29 | 2022-04-12 | 北京航星机器制造有限公司 | A method for automatic laser welding of frame skin box-like structures |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103846606A (en) * | 2014-02-17 | 2014-06-11 | 华南理工大学 | Special testing device and method for correcting welding track based on machine vision |
| CN104127204A (en) * | 2013-04-30 | 2014-11-05 | 佳能株式会社 | Object information acquiring apparatus and control method of object information acquiring apparatus |
| CN104175031A (en) * | 2014-08-20 | 2014-12-03 | 北京工业大学 | Welding robot with automatic correction function and welding method employing same |
| CN104552341A (en) * | 2014-12-29 | 2015-04-29 | 国家电网公司 | Single-point multi-view meter-hanging posture error detecting method of mobile industrial robot |
| CN106182004A (en) * | 2016-08-01 | 2016-12-07 | 上海交通大学 | The method of the industrial robot automatic pin hole assembling that view-based access control model guides |
| CN106981077A (en) * | 2017-03-24 | 2017-07-25 | 中国人民解放军国防科学技术大学 | Infrared image and visible light image registration method based on DCE and LSS |
| CN107808401A (en) * | 2017-10-30 | 2018-03-16 | 大族激光科技产业集团股份有限公司 | The hand and eye calibrating method of the one camera of mechanical arm tail end |
| CN108177150A (en) * | 2016-12-08 | 2018-06-19 | 广州映博智能科技有限公司 | Door of elevator positioning and grabbing device and the method for view-based access control model |
| CN108274092A (en) * | 2017-12-12 | 2018-07-13 | 北京石油化工学院 | Groove automatic cutting system and cutting method based on 3D vision and Model Matching |
-
2020
- 2020-10-28 CN CN202011184444.7A patent/CN112548265A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104127204A (en) * | 2013-04-30 | 2014-11-05 | 佳能株式会社 | Object information acquiring apparatus and control method of object information acquiring apparatus |
| CN103846606A (en) * | 2014-02-17 | 2014-06-11 | 华南理工大学 | Special testing device and method for correcting welding track based on machine vision |
| CN104175031A (en) * | 2014-08-20 | 2014-12-03 | 北京工业大学 | Welding robot with automatic correction function and welding method employing same |
| CN104552341A (en) * | 2014-12-29 | 2015-04-29 | 国家电网公司 | Single-point multi-view meter-hanging posture error detecting method of mobile industrial robot |
| CN106182004A (en) * | 2016-08-01 | 2016-12-07 | 上海交通大学 | The method of the industrial robot automatic pin hole assembling that view-based access control model guides |
| CN108177150A (en) * | 2016-12-08 | 2018-06-19 | 广州映博智能科技有限公司 | Door of elevator positioning and grabbing device and the method for view-based access control model |
| CN106981077A (en) * | 2017-03-24 | 2017-07-25 | 中国人民解放军国防科学技术大学 | Infrared image and visible light image registration method based on DCE and LSS |
| CN107808401A (en) * | 2017-10-30 | 2018-03-16 | 大族激光科技产业集团股份有限公司 | The hand and eye calibrating method of the one camera of mechanical arm tail end |
| CN108274092A (en) * | 2017-12-12 | 2018-07-13 | 北京石油化工学院 | Groove automatic cutting system and cutting method based on 3D vision and Model Matching |
Non-Patent Citations (4)
| Title |
|---|
| 丁式江等: "《海南省（岛）国土环境资源遥感应用研究》", 30 September 2008 * |
| 李春: "基于机器视觉的焊接工件识别与焊接轨迹校正方法研究", 《中国优秀博硕士学位论文全文数据库(硕士)·信息科技辑》 * |
| 李琳等: "基于机器视觉焊接轨迹搜索算法", 《焊接学报》 * |
| 陈建平等: "《月球地质研究与编图》", 31 October 2014, 地质出版社 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114309934A (en) * | 2021-12-29 | 2022-04-12 | 北京航星机器制造有限公司 | A method for automatic laser welding of frame skin box-like structures |
| CN114309934B (en) * | 2021-12-29 | 2024-11-12 | 北京航星机器制造有限公司 | A laser automatic welding method for frame skin box structure |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108982546B (en) | Intelligent robot gluing quality detection system and method | |
| CN103846606B (en) | Welding track based on machine vision corrects Special testing device and method | |
| CN206263418U (en) | A kind of real-time seam tracking system of six degree of freedom welding robot line laser | |
| CN103203526A (en) | Laser visual tracking system | |
| US9300852B2 (en) | Controlling robotic motion of camera | |
| CN112589232B (en) | A welding seam tracking method and device based on independent rectification deep learning | |
| US20100165116A1 (en) | Camera with dynamic calibration and method thereof | |
| CN108971704B (en) | Three-dimensional weld tracking method and system based on vision and rotating arc composite sensing | |
| US20120076428A1 (en) | Information processing device, information processing method, and program | |
| CN103231162A (en) | Device and method for visual detection of welding quality of robot | |
| CN110773840B (en) | Welding deviation determination method, device and automatic welding system | |
| CN114714029B (en) | Automatic arc welding method and device for aluminum alloy | |
| CN111299762B (en) | Laser real-time weld joint tracking method for separating strong noise interference | |
| US20120133215A1 (en) | Positioning method of movable apparatus and positioning system | |
| Rojtberg et al. | Efficient pose selection for interactive camera calibration | |
| Liu et al. | Seam tracking system based on laser vision and CGAN for robotic multi-layer and multi-pass MAG welding | |
| CN111570975B (en) | Welding deviation measurement method, device and automatic welding system based on synchronous mapping | |
| CN113510412A (en) | Detection system and detection method for identifying welding seam state and storage medium | |
| CN112548265A (en) | Intelligent welding method and equipment for container lock seat | |
| CN113634954A (en) | Method and system for welding seam trajectory tracking based on multi-sensor fusion | |
| Zhao et al. | A real-time seam tracking system based on extraction and restoration model in robotic GMAW | |
| Zhao et al. | Deepkp: A robust and accurate framework for weld seam keypoint extraction in welding robots | |
| JP3429194B2 (en) | Automatic tracking device | |
| CN116393982B (en) | Screw locking method and device based on machine vision | |
| CN114074321A (en) | Robot calibration method and device |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210326 |
|
| RJ01 | Rejection of invention patent application after publication |