CN111673749A - Adjustment method of vision welding robot and vision welding robot - Google Patents

Abstract

Embodiments of the present application disclose a method for adjusting a vision welding robot and a vision welding robot, wherein the vision welding robot has a camera, and the method includes: synchronizing a control coordinate system of a vision welding robot control system with a base coordinate system of the vision welding robot ; Obtain the image of the workpiece to be welded collected by the camera to extract the weld track in the image of the workpiece to be welded, and extract the feature points of the weld track; obtain the coordinates of the feature points of the weld track in the robot base coordinate system; The seam trajectory and the coordinates of the feature points in the robot base coordinate system control the camera to move along the welding seam trajectory; adjust the position of the camera of the visual welding robot according to the pictures captured by the camera moving along the welding seam trajectory. The technical method of the present application can ensure that the robot body and related components are not damaged during the debugging process when automatically adjusting the visual welding robot, and also ensure the safety of the debugging personnel.

Description

Adjustment method of vision welding robot and vision welding robot

technical field

The present application relates to the technical field of robot calibration, and in particular, to a calibration method for a visual welding robot, a calibration method device for a visual welding robot, an electronic device, and a computer-readable storage medium.

Background technique

At present, the robot adjustment technology has not yet formed a unified operating standard. Therefore, in the process of adjusting the robot, the robot body and control system may be damaged during the debugging process.

It should be noted that the information disclosed in the above Background section is only for enhancing understanding of the background of the application, and therefore may include information that does not form the prior art known to a person of ordinary skill in the art.

SUMMARY OF THE INVENTION

To solve the above problems, embodiments of the present application provide a method for adjusting a visual welding robot, an apparatus for adjusting a visual welding robot, an electronic device, and a computer-readable storage medium.

Wherein, the adjustment method of a kind of visual welding robot adopted in this application is:

Synchronize the control coordinate system of the visual welding robot control system with the base coordinate system of the visual welding robot; acquire the image of the workpiece to be welded collected by the camera to extract the weld track in the image of the workpiece to be welded, and extract the feature points of the weld track ; Obtain the coordinates of the feature points of the welding seam trajectory in the robot base coordinate system; control the camera to move along the welding seam trajectory according to the welding seam trajectory and the coordinates of the feature points in the robot base coordinate system; according to the camera along the welding seam trajectory Adjust the position of the camera of the visual welding robot according to the picture captured by the movement.

In another embodiment, based on the aforementioned solution, synchronizing the control coordinate system of the visual welding robot control system with the base coordinate system of the visual welding robot includes: detecting the position signal of the visual welding robot; if a preset position signal is detected, then Make sure that the visual welding robot has returned to the mechanical origin, the mechanical origin is the origin of the robot base coordinate system, and the preset position signal is the position signal when the visual welding robot returns to the mechanical origin; when it is determined that the visual welding robot has returned to the mechanical origin, set the control coordinate system , to synchronize the control coordinate system with the robot base coordinate system.

In another embodiment, based on the foregoing solution, controlling the camera to move along the welding seam trajectory according to the welding seam trajectory and the coordinates of the feature points in the robot base coordinate system, including: taking the position of the feature point as the origin of the workpiece coordinate system , to obtain the coordinate data of each point of the welding seam trajectory in the workpiece coordinate system; according to the coordinates of the feature points in the robot base coordinate system and the coordinate data of each point of the welding seam trajectory in the workpiece coordinate system, control the camera to follow the welding seam trajectory to move.

In another embodiment, based on the aforementioned solution, the visual welding robot has a welding gun, and the method further includes: controlling the camera to move to capture the feature point; when the feature point is located in the center of the image captured by the camera, recording the camera in the robot base coordinate system control the welding torch to move to move the welding torch to the position with the preset arc starting distance from the feature point; obtain the coordinates of the welding torch in the robot base coordinate system; determine the coordinates of the camera and the welding torch in the robot base coordinate system The offset distance between the welding torch and the camera.

In another embodiment, based on the aforementioned solution, the visual welding robot has multiple axes, and the multiple axes are used to control the welding torch to move, and the welding torch is controlled to move so that the welding torch is moved to a distance from the feature point to a preset arc starting distance. Before the position, the method further includes: debugging the motion of the welding torch, and controlling multiple axes of the visual welding robot to run at the first speed limit for the first time period after the debugging starts; after reaching the first time period, controlling the multiple axes of the visual welding robot. Axes run under the second limit speed, and the second limit speed is greater than the first limit speed.

In another embodiment, based on the foregoing solution, the method further includes: controlling the welding torch to perform simulated profiling welding according to the welding seam trajectory, to obtain the motion trajectory of the welding gun; comparing the motion trajectory of the welding torch and the welding seam trajectory to obtain a first comparison result; Weld according to the welding seam track, and control the welding track of the welding gun to keep the offset distance from the camera and the welding gun; obtain the second comparison result according to the welding track and the welding seam track; determine according to the first comparison result and the second comparison result For the adjustment result of the adjustment of the visual welding robot, if the first comparison result matches the second comparison result, it is determined that the adjustment result of the vision welding robot is successful, if either the first comparison result or the second comparison result is successful. If the result is a mismatch, it is determined that the adjustment result of the vision welding robot is a failure.

In another embodiment, based on the foregoing solution, after the motion of the welding torch is debugged, the method further includes: confirming whether the motion of each axis of the visual welding robot is smooth, and confirming whether the motion trajectory of the welding torch is smooth; when determining the motion of each axis After the movement trajectory of the welding torch is stable and smooth, the welding process and the welding path of the welding torch are planned according to the welding seam trajectory and the offset distance; if the welding process and the planning of the welding path meet the preset conditions, the vision welding robot is determined. The welding process and the debugging results of the welding path were successful.

In another embodiment, based on the foregoing solution, before obtaining the image of the workpiece to be welded by the camera, the method further includes: shooting a plurality of images of the workpiece to be welded; Commissioning includes one or more of determining the exposure time, determining the sampling frequency, selecting an image processing strategy, and selecting a feature extraction strategy.

In another embodiment, based on the foregoing solution, before shooting a plurality of images of the workpiece to be welded, the method further includes: confirming whether the robot body of the visual welding robot is deformed, and confirming whether the electrical control installation wiring of the visual welding robot is correct and Whether there is looseness; if it is confirmed that there is no deformation of the robot body and that the electrical control installation wiring is correct and not loose, take various images of the parts to be welded.

Based on another aspect of the present application, the present application also provides a visual welding robot, which is characterized by comprising: a robot body; the robot body has a plurality of axes; a camera mechanism has a camera, and the camera mechanism is connected to the robot body; welding equipment , connected with the robot body, the welding equipment includes a welding torch; the controller is connected with the robot body, the camera mechanism and the welding equipment, and is used to control the camera mechanism and the welding equipment to perform the steps of the aforementioned adjustment method of the visual welding robot.

Based on another aspect of the present application, the present application also provides a device for adjusting a vision welding robot, the vision welding robot having a camera, including:

The synchronization unit is used to synchronize the control coordinate system of the visual welding robot control system with the base coordinate system of the visual welding robot;

an extraction unit, configured to acquire the image of the workpiece to be welded collected by the camera, to extract the weld track in the image of the to-be-welded workpiece, and to extract the feature points of the weld track;

The obtaining unit is used to obtain the coordinates of the feature points of the welding seam trajectory in the robot base coordinate system;

The control unit is used to control the camera to move along the welding seam trajectory according to the welding seam trajectory and the coordinates of the feature points in the robot base coordinate system;

The adjustment unit is used to adjust the position of the camera of the visual welding robot according to the picture captured by the camera moving along the welding seam track.

Based on another aspect of the present application, the present application also provides

A calibration device for a visual welding robot, comprising a processor and a memory, on which computer-readable instructions are stored, and when the computer-readable instructions are executed by the processor, the above-mentioned adjustment of the visual welding robot is realized. school method.

A computer-readable storage medium on which computer-readable instructions are stored, when the computer-readable instructions are executed by a processor of a computer, the computer is made to execute the above-mentioned adjustment method of a visual welding robot.

The technical solutions provided by the application embodiments may include the following beneficial effects:

The technical method of the present application can ensure that the robot body and related components are not damaged during the debugging process when automatically adjusting the visual welding robot, and also ensure the safety of the debugging personnel.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not limiting of the present application.

Description of drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the application and together with the description serve to explain the principles of the application. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained from these drawings without creative effort. In the attached image:

FIG. 1 is a flowchart of a method for adjusting a vision welding robot according to an exemplary embodiment;

FIG. 2 is a flowchart of step S110 in another embodiment of the embodiment shown in FIG. 1;

FIG. 3 is a flowchart of step S140 in another embodiment of the embodiment shown in FIG. 1;

FIG. 4 is a flowchart of a method for adjusting a vision welding robot according to another exemplary embodiment;

FIG. 5 is a flowchart of a method for adjusting a vision welding robot according to another exemplary embodiment;

FIG. 6 is a flowchart of a method for adjusting a vision welding robot according to another exemplary embodiment;

FIG. 7 is a flowchart of a method for adjusting a vision welding robot according to another exemplary embodiment;

FIG. 8 is a flowchart of a method for adjusting a vision welding robot according to another exemplary embodiment;

FIG. 9 is a flowchart of a method for adjusting a vision welding robot according to another exemplary embodiment;

10 is a flowchart of a method for adjusting a vision welding robot according to an embodiment of the present application;

FIG. 11 is a block diagram of a calibration device 1100 for a visual welding robot according to an exemplary embodiment;

Fig. 12 is a schematic diagram of the hardware structure of a calibration device for a vision welding robot according to an exemplary embodiment.

Detailed ways

Exemplary embodiments will be described in detail herein, examples of which are illustrated in the accompanying drawings. Where the following description refers to the drawings, the same numerals in different drawings refer to the same or similar elements unless otherwise indicated. The implementations described in the illustrative examples below are not intended to represent all implementations consistent with this application. Rather, they are merely examples of apparatus and methods consistent with some aspects of the present application as recited in the appended claims.

Fig. 1 is a flow chart of a method for adjusting a vision welding robot according to an exemplary embodiment. As shown in FIG. 1 , in an exemplary embodiment, the adjustment method of the visual welding robot may include the following steps S110 to S150 .

First of all, it should be noted that the adjustment process of the visual welding robot includes adjustment and calibration of the camera, and the adjustment of the camera can be realized through the following steps S110 to S150.

In step S110, the control coordinate system of the visual welding robot control system is synchronized with the base coordinate system of the visual welding robot.

A coordinate system that defines a plane or space through axes from a fixed point of origin. The control system of the visual welding robot performs measurement and positioning through each axis of the coordinate system. The control of the visual welding robot has multiple coordinate systems, wherein the control coordinate system is the coordinate system used by the control system, and the coordinate system can be set to The base coordinate system of the visual welding robot is synchronized, and the base coordinate system is a coordinate system located at the base of the visual welding robot, which is convenient for the visual welding robot to move from one position to another.

By synchronizing the control coordinate system of the visual welding robot control system with the base coordinate system of the visual welding robot, it is possible to more conveniently control each part of the visual welding robot to move.

In step S120, the image of the workpiece to be welded collected by the camera is acquired, so as to extract the welding seam trajectory in the image of the to-be-welded workpiece, and extract the feature points of the welding seam trajectory.

A weldment is a workpiece waiting for a weldment with a weld trace on it to indicate the point or line where the weldment is required.

The image of the workpiece to be welded can be collected by a camera to extract the welding track in the image. In another embodiment, a sensor can also be used to obtain the image of the workpiece to be welded. When the image of the forehead to be welded is collected, the image The processing component preprocesses the image, such as image binarization, median filtering, image morphological refinement, etc., and then sends the preprocessed image to the controller of the visual welding robot control system for processing.

The feature points of the weld track can be defined in advance. For example, the plane coordinates of the feature point are the coordinates of the first turning point of the center line of the weld, and the coordinates of the feature point of the T-shaped fillet weld are the center of the right stripe of the two fracture stripes. The coordinates of the first point where the extension line or the left stripe touches, there is no restriction here.

It should be understood that, according to the welding seam trajectory and the feature points of the welding seam trajectory in the collected image, the positional relationship between the welding seam trajectory feature point and the visual welding robot can be obtained.

In this embodiment, the extracted feature points of the welding seam trajectory, the welding seam trajectory and the positional relationship implied therein can be used to adjust the position of the camera of the visual welding robot.

In step S130, the coordinates of the feature points of the welding seam trajectory in the robot base coordinate system are obtained.

As mentioned earlier, the base coordinate system is the coordinate system located at the base of the vision welding robot. Through step S220, the positional relationship between the feature points of the welding seam trajectory and the visual welding robot can be obtained. Then, it is easy to understand that the coordinates of the feature points of the welding seam trajectory in the robot base coordinate system can be obtained.

Step S140, controlling the camera to move along the welding seam trajectory according to the welding seam trajectory and the coordinates of the feature points in the robot base coordinate system.

According to the coordinates of the feature points of the weld track and the image of the weld track, the coordinates of all points of the weld track in the base coordinate system of the visual welding robot can be obtained. According to the obtained coordinates of all points of the welding seam trajectory in the base coordinate system of the visual welding robot, the camera installed on the visual welding robot can be controlled to move along the welding seam trajectory.

In step S150, the position of the camera of the visual welding robot is adjusted according to the picture captured by the camera moving along the trajectory of the welding seam.

The camera based on binocular vision can be automatically corrected. The automatic camera correction based on binocular vision is that the camera of the visual welding robot in the teaching automatically adjusts the position of the camera according to the position of the captured weld track in the shooting screen.

It should be noted that in the process of adjusting the visual welding robot, if an abnormality occurs, the power supply can be forcibly turned off. The abnormality can be preset by the debugger and detected by the sensors installed in various parts of the visual welding robot.

Therefore, the position of the camera of the robot can be automatically adjusted by the control system of the visual welding robot, which can ensure the safety of the debugging personnel, and ensure that the robot body and the control system are not damaged during the debugging process, saving labor costs.

Fig. 2 is a flowchart of step S110 in another embodiment of the embodiment shown in Fig. 1. In this embodiment, the control coordinate system of the visual welding robot control system is synchronized with the base coordinate system of the visual welding robot, including step S210 Go to step S230.

Step S210, detecting the position signal of the visual welding robot.

The position signal can be a preset switch signal when the vision welding robot returns to the mechanical origin.

Step S220, if a preset position signal is detected, it is determined that the visual welding robot has returned to the mechanical origin, the mechanical origin is the origin of the robot base coordinate system, and the preset position signal is the position signal when the visual welding robot returns to the mechanical origin.

When the switch signal is detected, it can be determined that the visual welding robot has returned to the mechanical origin, and the robot can be better controlled based on the mechanical origin.

Step S230, when it is determined that the visual welding robot returns to the mechanical origin, the control coordinate system is set, so that the control coordinate system is synchronized with the robot base coordinate system.

When it is determined that the visual welding robot has returned to the mechanical origin, the origin of the control coordinate system of the control system can be set to the position of the mechanical origin, so that the synchronization of the control coordinate system and the base coordinate system can be realized.

FIG. 3 is a flow chart of step S140 in another embodiment of the embodiment shown in FIG. 1 . In this embodiment, step S140 is to control the camera along the trajectory of the welding seam and the coordinates of the feature points in the base coordinate system of the robot. The movement of the welding seam trajectory may include the following steps S310 and S320.

In step S310, the position of the feature point is taken as the origin of the workpiece coordinate system, and the coordinate data of each point of the welding seam trajectory in the workpiece coordinate system is obtained.

The workpiece coordinate system is a coordinate system composed of a workpiece origin and a coordinate axis, and the coordinate data of the workpiece coordinate system is the coordinate data of the workpiece coordinate system relative to the base coordinate system.

Step S320 , according to the coordinates of the feature points in the robot base coordinate system and the coordinate data of each point of the welding seam trajectory in the workpiece coordinate system, the camera is controlled to move along the welding seam trajectory.

In this way, the welding seam trajectory can be photographed by the camera to form multiple pictures, and the position of the camera can be automatically adjusted by analyzing the positions of the feature points of the welding seam trajectory in each picture.

Fig. 4 is a flow chart of a method for adjusting a vision welding robot according to another exemplary embodiment. As shown in FIG. 4 , in an exemplary embodiment, the vision welding robot has a welding torch, and the adjustment method of the vision welding robot may further include the following steps S410 to S450 .

Step S410, controlling the movement of the camera to capture feature points;

Step S420, when the feature point is located at the center of the picture captured by the camera, record the coordinates of the camera in the robot base coordinate system;

Step S430, controlling the welding torch to move, so that the welding torch is moved to a position with a preset arc starting distance from the feature point;

Step S440, obtaining the coordinates of the welding torch in the robot base coordinate system;

Step S450: Determine the offset distance between the welding torch and the camera according to the coordinates of the camera and the welding torch in the robot base coordinate system.

The adjustment process of the visual welding robot also includes setting the offset distance between the welding torch and the camera. Specifically, the position of the feature point of the welding seam is used as the reference point, and the position of the camera is adjusted to make the camera move within a suitable range, and finally the feature point is located in the center of the picture captured by the camera. After the position of the camera is determined, Move the welding torch so that the distance between the welding torch and the feature point is the preset arc starting distance. Thus, the offset distance between the welding torch and the camera is obtained, so that the camera can photograph the welding process based on the principle of structured light.

In another embodiment, the feature point may also be located at the far left or the far right of the picture captured by the camera, which may be specifically set by the adjuster according to the specific situation, which is not limited here.

It should be noted that the preset arc starting distance, arc starting voltage and arc starting current will all affect the welding effect of the visual welding robot. Therefore, in another embodiment, the adjustment process of the visual welding robot may further include the setting of arc starting parameters, and the arc starting parameters include arc starting distance, arc starting voltage and arc starting current.

Fig. 5 is a flowchart showing a method for adjusting a visual welding robot according to another exemplary embodiment. On the basis of the adjusting method for a visual welding robot described in Fig. 4, the visual welding robot has multiple axes, A plurality of axes are used to control the welding torch to move. Before step S430, the method further includes steps S510 and S520.

Step S510, debug the motion of the welding torch, and control multiple axes of the visual welding robot to run at a first speed limit for a first time period after the debugging starts;

In step S520, after the first time period is reached, the axes of the visual welding robot are controlled to run at a second speed limit, and the second speed limit is greater than the first speed limit.

The visual welding robot has multiple axes, that is, the visual welding robot is a multi-axis robot, and the multi-axis robot is a multi-purpose manipulator that can realize automatic control, repeatable programming, multiple degrees of freedom, and movement degrees of freedom to establish a spatial right-angle relationship. According to the number of axes of the manipulator, multi-axis robots can be divided into 4-axis, 5-axis, 6-axis and other robots. That is, it can move freely in 4, 5 or 6 directions, respectively.

The adjustment process of the vision welding robot also includes the adjustment of the movement of each axis.

Specifically, in the early stage of the motion debugging of each axis, that is, for the first time after the debugging starts, each axis is controlled to run at the first speed limit. With the continuous progress of debugging and the continuous optimization of debugging results, each axis The speed can be gradually increased to the second speed limit. In this way, the safety of the equipment can be improved, the safety of the debugging personnel can be ensured, and the robot body and the hardware of the control system are not damaged during the debugging process.

Fig. 6 is a flowchart showing a method for adjusting a visual welding robot according to another exemplary embodiment. On the basis of the adjusting method for a visual welding robot shown in Fig. 5, in this embodiment, the Steps S610 to S650 are included.

Step S610, controlling the welding torch to perform simulated profiling welding according to the welding seam trajectory to obtain the motion trajectory of the welding torch;

Step S620, comparing the motion trajectory of the welding torch and the welding seam trajectory to obtain a first comparison result;

Step S630, controlling the welding torch to perform welding according to the welding seam track, and controlling the welding track of the welding torch welding captured by the camera and the welding torch at an offset distance;

Step S640, obtaining a second comparison result according to the welding track and the welding seam track;

Step S650, according to the first comparison result and the second comparison result, determine the adjustment result for the adjustment of the visual welding robot, if both the first comparison result and the second comparison match, then determine that the adjustment result for the vision welding robot is: Success, if any of the first comparison result and the second comparison result does not match, it is determined that the adjustment result of the visual welding robot is a failure.

The adjustment process of the vision welding robot also includes the welding test. In order to better observe the operation of the visual welding robot and the influence of the external environment on the performance of the welding robot during the welding process, the welding test process is divided into two stages. In the first stage, the welding torch is controlled to simulate profiling welding according to the welding seam trajectory, and the motion trajectory of the welding torch is obtained. The motion trajectory is the motion trajectory of the welding torch to simulate welding without arcing. It can also be obtained by other arbitrary methods. By comparing the motion trajectory with the welding seam trajectory, the first comparison result can be obtained. By analyzing the comparison results, the control system of the welding torch can be obtained. If the motion trajectory If the check value of the welding seam trajectory is less than the preset value, it can be determined that the control system can accurately control the welding torch. Above, the control effect of the control system on welding can be obtained through profiling welding, which can save solder. The second stage is the actual welding process. After the actual welding is recorded by the camera, the generated welding trajectory can not only verify the adjustment result of the camera, but also the actual welding effect, and can realize the test of the welding process of the visual welding robot. The test results can also verify the adjustment effect of the vision welding robot.

Fig. 7 is a flowchart showing a method for adjusting a visual welding robot according to another exemplary embodiment. On the basis of the adjusting method for a visual welding robot shown in Fig. 5, in step S510, the movement of the welding torch is adjusted. After debugging, in this embodiment, the following steps may also be included:

Step S710, confirming whether the motion of each axis of the visual welding robot is smooth, and confirming whether the motion trajectory of the welding torch is smooth;

Step S720, after determining that the motion of each axis is stable and the motion trajectory of the welding torch is smooth, plan the welding process and the welding path of the welding torch according to the welding seam trajectory and the offset distance;

Step S730, if the planning of the welding process and the welding path satisfy the preset conditions, it is determined that the debugging result of the welding process and the welding path of the visual welding robot is successful.

In this embodiment, based on the aforementioned method, after the motion of the welding torch is debugged, the debugging process of the visual welding robot may further include determining whether the motion of each axis of the visual welding robot is smooth and determining whether the motion trajectory of the welding torch is smooth. After confirming that the motion of each axis of the visual welding robot is smooth and the motion trajectory of the welding torch is smooth, parameters can be manually selected through the control panel of the control system, or data such as welding seam type and process can be obtained according to the sensor, and the corresponding module in the control system can be used to image the image. Process, realize the welding process and the planning of the welding path.

Fig. 8 is a flow chart showing a method for adjusting a visual welding robot according to another exemplary embodiment. On the basis of the adjusting method for a visual welding robot shown in Fig. 1, before step S120, in this implementation In this example, the following steps may also be included:

Step S810, photographing a plurality of images of the workpiece to be welded;

Step S820, debug the camera according to the image information of the multiple images of the workpiece to be welded. The debugging of the camera includes one or more of determining the exposure time, determining the sampling frequency, selecting an image processing strategy and selecting a feature extraction strategy.

The debugging of the visual welding robot also includes the debugging of the camera shooting parameters, and the shooting parameters include one or more of exposure time, sampling frequency, image processing strategy and feature extraction strategy. Specifically, different exposure times or combinations of different sampling frequencies or exposure times and frequencies can be used to photograph the image of the workpiece to be welded, and the photographed image is transmitted to the control system, which determines the final image according to the image quality standard. According to the exposure time and sampling frequency, different image processing strategies and feature extraction strategies are used for image processing. In order to determine the various shooting parameters of the camera according to the characteristics of different parts to be welded and the brightness of the environment.

Fig. 9 is a flowchart showing a method for adjusting a visual welding robot according to another exemplary embodiment. On the basis of the adjusting method for a visual welding robot shown in Fig. 8, before step S810, in this implementation In this example, the following steps may also be included:

Step S910, confirming whether the robot body of the visual welding robot is deformed, and confirming whether the electrical control installation connection of the visual welding robot is correct and whether it is loose;

In step S920, if it is determined that the robot body is not deformed and that the electrical control installation wiring is correct and not loose, various images of the parts to be welded are captured.

In this embodiment, before taking a plurality of images of the workpiece to be welded, the debugging process of the visual welding robot may further include determining whether the robot body of the visual welding robot is deformed or not and confirming the electrical control installation connection of the visual welding robot Whether it is correct and whether it is loose, if it is confirmed that the robot body is not deformed and that the electrical control installation wiring is correct and not loose, start to take multiple images of the workpiece to be welded.

For ease of understanding, the following describes the inventive concept of the present application through a specific adjustment process of a visual welding robot.

FIG. 10 is a flowchart of a method for adjusting a vision welding robot according to an embodiment of the present application. As shown in Figure 10, in this embodiment, the adjustment process of the visual welding robot sequentially includes robot body debugging 1001, electrical control installation and debugging 1002, camera acquisition and debugging 1003, setting the working stroke range of each axis 1004, setting axis direction, pulse Vector 1005, returning to the mechanical origin 1006, camera follow-up profiling and centering debugging 1007, setting the offset distance between the camera and the welding torch 1008, adjusting the speed of each axis 1009, smoothing the torch trajectory 1010, welding torch path welding process planning 1011, given Arc starting voltage, arc starting current and arc starting distance 1012, welding test 1013.

Among them, the robot body debugging 1001 includes manufacturing mechanical parts in strict accordance with the design, simulation analysis and mechanical assembly paper, and assembling the parts to ensure that the assembly is correct and firm, there are no missing parts, and there is no impact deformation during the assembly process. , damage, etc., check whether the lubrication of the lead screw, slide rail and rack of each part of the body is appropriate, check whether the transmission screw is stuck, and ensure that the movement direction of each axis is unobstructed. If you are sure the installation is correct. If the robot body is not deformed, go to the next step.

Electrical control installation and debugging 1002, including checking whether the installation and connection of each electrical component is correct, whether there is a loose connection, whether the communication between components is normal; whether the connection of the electrical circuit is normal, the installation and performance of each insurance limit Whether it is safe and reliable, check whether the electrical output and settings are normal; check the input signal indicating LED light of the terminal board, and interfere with the origin switch by simulating. If the state of the corresponding LED light changes, it means that the origin signal has been sent to the terminal board. The wiring of the welding robot drive control, limit position and zero point is correct, which can greatly shorten the debugging time. Use the "port" online debugging module of the host computer software to determine whether the signal transmission of each port is normal. When the dot is green, it means that the signal is valid at this time, and the red dot means that the signal is invalid at this time (no input or output). If the electrical components are installed correctly and are not loose, go to the next step.

The camera acquisition and debugging 1003 includes debugging the exposure time, sampling frequency, image processing method and feature proposal strategy, so that the obtained welding seam information is more accurate and better applied to welding control. After the setting is complete, go to the next step.

Setting the working stroke range 1004 of each axis includes, based on the actual size of the visual welding robot, setting the working stroke range of each axis by using the soft limit function. After the setting is complete, go to the next step.

Set the axis direction and pulse vector 1005, including moving each axis of the robot to determine whether the motion direction of each axis is correct. If the motion direction is incorrect, you can modify the axis direction 1 or -1 through the host computer, or set the relevant parameters of the servo drive; The smaller the pulse equivalent, the higher the control resolution, and the value of the pulse equivalent directly affects the maximum feed rate.

Returning to the mechanical origin 1006 includes, if a preset position signal is detected, determining that the visual welding robot has returned to the mechanical origin, the mechanical origin is the origin of the robot base coordinate system, and the preset position signal is the position when the visual welding robot returns to the mechanical origin Signal.

Camera follow-up profiling and centering debugging 1007, including: acquiring the image of the workpiece to be welded collected by the camera, to extract the welding seam trajectory in the image of the to-be-welded workpiece, and extracting the feature points of the welding seam trajectory; obtaining the characteristics of the welding seam trajectory The coordinates of the point in the robot base coordinate system; according to the welding seam trajectory and the coordinates of the feature points in the robot base coordinate system, the camera is controlled to move along the welding seam trajectory; Check the position of the camera of the vision welding robot.

Set the offset distance 1008 between the camera and the welding gun, including: controlling the camera to move to shoot the feature point; when the feature point is located in the center of the picture captured by the camera, record the coordinates of the camera in the robot base coordinate system; control the welding gun to move to make The welding torch is moved to the position with the preset arc starting distance from the feature point; the coordinates of the welding torch in the robot base coordinate system are obtained; the offset distance between the welding torch and the camera is determined according to the coordinates of the camera and the welding torch in the robot base coordinate system.

The speed adjustment 1009 of each axis includes debugging the motion of the welding torch, and controlling the multiple axes of the visual welding robot to run at the first speed limit for the first time after the debugging starts; after reaching the first time, controlling the visual welding robot A plurality of axes of , run under a second speed limit, and the second speed limit is greater than the first speed limit.

The welding gun trajectory smoothing 1010 includes, according to the specific welding seam trajectory, setting the initial path of the welding gun, and optimizing the initial path through a smoothing strategy, so as to set the welding gun trajectory satisfying the smoothing condition.

The welding process planning 1011 of the welding torch path includes planning and adjusting the welding path and welding process of the welding torch according to the characteristics of the welding seam, such as the width of the gap, thermal deformation, coordinate distance and other factors.

Given the arcing voltage, arcing current and arcing distance 1012, including debugging on the basis of the arcing voltage, arcing current and arcing distance given by the control system, to determine the final arcing voltage according to the actual situation , arc starting current and arc starting distance.

The welding test 1013 includes controlling the welding torch to perform simulating profiling welding according to the welding seam trajectory to obtain the motion trajectory of the welding gun; comparing the motion trajectory of the welding gun and the welding seam trajectory to obtain the first comparison result; controlling the welding gun to perform welding according to the welding seam trajectory, and controlling the camera The welding track of the welding torch taken at an offset distance from the welding torch; according to the welding track and the welding seam track, the second comparison result is obtained; according to the first comparison result and the second comparison result, the adjustment result for the adjustment of the visual welding robot is determined .

If both the first comparison result and the second comparison result match, it is determined that the adjustment result of the visual welding robot is successful; The adjustment result of the robot is failed.

In this way, it is possible to ensure the safety of debugging personnel, ensure that the robot body and control system hardware are not damaged during the debugging process, save welding materials, reduce costs, and enhance the safety of the equipment in terms of slow-to-fast movement speed.

An embodiment of the present application also shows a visual welding robot. The visual welding robot includes: a robot body; the robot body has a plurality of axes; a camera mechanism has a camera, and the camera mechanism is connected to the robot body; a welding device is connected to the robot body , the welding equipment includes a welding torch; a controller, connected with the robot body, the camera mechanism and the welding equipment, is used to control the camera mechanism and the welding equipment to execute the steps of the aforementioned adjustment method of the visual welding robot.

FIG. 11 is a block diagram of a calibration device 1100 for a visual welding robot according to an exemplary embodiment. As shown in FIG. 11 , the calibration device for a visual welding robot includes a synchronization unit 1101 , an extraction unit 1102 , and an acquisition unit 1103 , the control unit 1104 and the adjustment unit 1105 .

The synchronization unit 1101 is used to synchronize the control coordinate system of the visual welding robot control system with the base coordinate system of the visual welding robot;

The extraction unit 1102 is configured to acquire the image of the workpiece to be welded collected by the camera, so as to extract the welding seam trajectory in the image of the to-be-welded workpiece, and extract the feature points of the welding seam trajectory;

Obtaining unit 1103, for obtaining the coordinates of the feature points of the welding seam trajectory in the robot base coordinate system;

The control unit 1104 is configured to control the camera to move along the welding seam trajectory according to the welding seam trajectory and the coordinates of the feature points in the robot base coordinate system;

The adjustment unit 1105 is configured to adjust the position of the camera of the visual welding robot according to the picture captured by the camera moving along the welding seam trajectory.

It should be noted that the apparatus provided by the above embodiments and the methods provided by the above embodiments belong to the same concept, and the specific manners in which each module and unit perform operations have been described in detail in the method embodiments, which will not be repeated here. .

In another exemplary embodiment, the present application also provides a calibration device for a visual welding robot, including a processor and a memory, wherein the memory stores computer-readable instructions, and the computer-readable instructions are processed by the processor When executed, the aforementioned adjustment method of the vision welding robot is implemented.

Please refer to FIG. 12 , which is a schematic diagram of a hardware structure of a calibration device for a visual welding robot according to an exemplary embodiment.

It should be noted that this device is only an example adapted to the present application, and should not be considered as providing any limitation on the scope of use of the present application. Nor should the apparatus be construed as requiring one or more components in a tuning apparatus that relies on or must have the exemplary vision welding robot shown in FIG. 12 .

The hardware structure of the device may vary greatly due to different configurations or performances. As shown in FIG. 12 , the device includes: a power supply 1210 , an interface 1230 , at least one memory 1250 , and at least one central processing unit (CPU, Central Processing). Units) 1270.

Among them, the power supply 1210 is used to provide working voltage for each hardware device on the device.

The interface 1230 includes at least one wired or wireless network interface 1231, at least one serial-parallel conversion interface 1233, at least one input/output interface 1235, and at least one USB interface 1237, etc., for communicating with external devices.

The memory 1250 is used as a carrier for resource storage, which can be a read-only memory, random access memory, magnetic disk or optical disk, etc. The resources stored on it include the operating system 1251, the application program 1253 or the data 1255, etc., and the storage method can be short-term storage or permanent storage. . Among them, the operating system 1251 is used to manage and control the hardware devices and application programs 1253 on the device, so as to realize the calculation and processing of the data 1255 by the central processing unit 1270, which can be WindowsServerTM, Mac OS XTM, UnixTM, LinuxTM and so on. The application program 1253 is a computer program based on the operating system 1251 to complete at least one specific task, and it may include at least one module, and each module may respectively contain a series of computer-readable instructions for the device.

The central processing unit 1270 may include one or more processors, and is configured to communicate with the memory 1250 through a bus for computing and processing the data 1255 in the memory 1250 .

As described in detail above, the adjustment equipment for the visual welding robot applicable to the present application will complete the aforementioned visual welding robot through the central processing unit 1270 reading a series of computer-readable instructions stored in the memory 1250. adjustment method.

In addition, the present application can also be implemented by a hardware circuit or a hardware circuit combined with software instructions. Therefore, the implementation of the present application is not limited to any specific hardware circuit, software, or combination of the two.

In another exemplary embodiment, the present application also provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, realizes the aforementioned adjustment of the visual welding robot method. The computer-readable storage medium may be included in the adjustment device of the visual welding robot described in the above-mentioned embodiments, or may exist alone without being assembled into the adjustment device of the vision welding robot.

The above contents are only preferred exemplary embodiments of the present application, and are not intended to limit the embodiments of the present application. Those of ordinary skill in the art can easily make corresponding changes or modifications according to the main concept and spirit of the present application. Therefore, the protection scope of this application shall be subject to the protection scope required by the claims.

Claims (10)

1. the adjustment method of a vision welding robot, is characterized in that, described vision welding robot has camera, and described method comprises: Synchronizing the control coordinate system of the control system of the visual welding robot with the base coordinate system of the visual welding robot; acquiring the image of the workpiece to be welded collected by the camera, to extract the weld track in the image of the to-be-welded workpiece, and extract the feature points of the weld track; obtaining the coordinates of the feature points of the welding seam trajectory in the robot base coordinate system; controlling the camera to move along the welding seam trajectory according to the welding seam trajectory and the coordinates of the feature point in the robot base coordinate system; Adjust the position of the camera of the visual welding robot according to the picture captured by the camera moving along the welding seam trajectory. 2. The method according to claim 1, characterized in that, synchronizing the control coordinate system of the control system of the visual welding robot with the base coordinate system of the visual welding robot, comprising: detecting the position signal of the visual welding robot; If a preset position signal is detected, it is determined that the visual welding robot has returned to the mechanical origin, the mechanical origin is the origin of the robot base coordinate system, and the preset position signal is that the visual welding robot has returned to the The position signal at the mechanical origin; When it is determined that the vision welding robot returns to the mechanical origin, the control coordinate system is set so that the control coordinate system is synchronized with the robot base coordinate system. 3 . The method according to claim 1 , wherein, according to the welding seam trajectory and the coordinates of the feature points in the robot base coordinate system, the camera is controlled to perform the welding seam trajectory along the welding seam trajectory. 4 . sports, including: The position of the feature point is used as the origin of the workpiece coordinate system, and the coordinate data of each point of the weld track in the workpiece coordinate system is obtained; According to the coordinates of the feature point in the robot base coordinate system and the coordinate data of each point of the weld track in the workpiece coordinate system, the camera is controlled to move along the weld track . 4. The method of claim 1, wherein the vision welding robot has a welding torch, the method further comprising: controlling the movement of the camera to capture the feature point; When the feature point is located at the center of the picture captured by the camera, record the coordinates of the camera in the robot base coordinate system; controlling the welding torch to move, so that the welding torch is moved to a position with a preset arc starting distance from the feature point; obtaining the coordinates of the welding torch in the robot base coordinate system; According to the coordinates of the camera and the welding torch in the robot base coordinate system, the offset distance between the welding torch and the camera is determined. 5. The method according to claim 4, wherein the visual welding robot has multiple axes, and the multiple axes are used to control the welding torch to move, and the welding torch is controlled to move so as to make the welding torch move. Before the welding torch is moved to a position with a preset arc starting distance from the feature point, the method further includes: Debug the motion of the welding torch, and control multiple axes of the visual welding robot to run at a first speed limit for a first time period after the debugging starts; After the first time period is reached, the axes of the visual welding robot are controlled to run at a second speed limit, where the second speed limit is greater than the first speed limit. 6. The method of claim 5, further comprising: Controlling the welding torch to perform simulated profiling welding according to the welding seam trajectory to obtain the motion trajectory of the welding torch; Comparing the motion trajectory of the welding torch and the welding seam trajectory to obtain a first comparison result; controlling the welding gun to perform welding according to the welding seam trajectory, and controlling the welding trajectory of the welding gun welding captured by the camera and the welding gun maintaining the offset distance; obtaining a second comparison result according to the welding track and the welding seam track; According to the first comparison result and the second comparison result, the adjustment result of the adjustment of the visual welding robot is determined, and if the first comparison result and the second comparison are both matched, it is determined The adjustment result of the visual welding robot is successful, and if any result of the first comparison result and the second comparison result is mismatched, it is determined that the adjustment result of the visual welding robot is a failure. 7. The method according to claim 5, characterized in that, after the adjustment of the movement of the welding torch, the method further comprises: Confirm whether the motion of each axis of the visual welding robot is smooth, and confirm whether the motion trajectory of the welding torch is smooth; After determining that the motion of each axis is smooth and the motion trajectory of the welding torch is smooth, plan the welding process and the welding path for the welding path of the welding torch according to the welding seam trajectory and the offset distance; If the planning of the welding process and the welding path meets the preset conditions, it is determined that the debugging result of the welding process and the welding path of the visual welding robot is successful. 8. The method according to claim 1, wherein before the controlling the camera to capture the image of the workpiece to be welded, the method further comprises: photographing a plurality of images of the workpiece to be welded; Debug the camera according to the image information of the images of the workpiece to be welded, and the debugging of the camera includes determining the exposure time, determining the sampling frequency, selecting one of the image processing strategy and the selected feature extraction strategy or variety. 9 . The method according to claim 8 , wherein before the shooting of the plurality of images of the workpiece to be welded, the method further comprises: 10 . Confirm whether the robot body of the visual welding robot is deformed, and confirm whether the electrical control installation connection of the visual welding robot is correct and whether it is loose; If it is determined that there is no deformation of the robot body and that the electrical control installation wiring is correct and not loose, a variety of images of the parts to be welded are taken. 10. A vision welding robot, characterized in that, comprising: a robot body; the robot body has a plurality of axes; a camera mechanism with a camera, the camera mechanism is connected with the robot body; welding equipment, connected with the robot body, the welding equipment includes a welding torch; a controller, connected with the robot body, the camera mechanism and the welding equipment, for controlling the camera mechanism and the welding equipment to perform the adjustment of the visual welding robot according to any one of claims 1 to 9 steps of the method.

Images