Robot laser welding system, method and equipment capable of automatically planning track

Abstract

The invention discloses a robot laser welding system, method and equipment capable of automatically planning a track, and relates to the technical field of laser welding, the robot laser welding system capable of automatically planning the track comprises a 3D camera, a laser welding mechanical arm, an operation unit and a control unit; the 3D camera is arranged at the tail end of the laser welding mechanical arm; the 3D camera, the laser welding mechanical arm and the operation unit are all connected with the control unit. The operation unit is used for sequentially sending a welding track planning control instruction and an automatic welding control instruction to the control unit; and the control unit is used for controlling the 3D camera to acquire a 3D image of the target workpiece and planning a welding track based on the 3D image when receiving the welding track planning control instruction, and controlling the laser welding mechanical arm to weld the target workpiece according to the planned welding track when receiving the automatic welding control instruction. The welding efficiency of automatic laser welding is improved, and the application range of automatic laser welding is widened.

Description

Technical Field

[0001] The present application relates to the field of laser welding technology, and in particular to a robot laser welding system, method and equipment for automatically planning trajectories. Background Art

[0002] Laser welding is an efficient and precise welding method that uses a high-energy-density laser beam as a heat source. The laser beam can be guided by an optical element, and then the beam is projected onto the weld by a reflective focusing element or lens. It is a non-contact welding method. The optical properties of the laser determine that when it is focused by an optical element, it will have an energy center point, namely the laser focus. When using laser welding, it is necessary to ensure that the laser focus is at the weld joint, which determines the working characteristics of laser welding that requires focus finding and focusing. As a high-precision and high-efficiency welding technology, laser welding has been widely used in modern industrial production. At present, there are many types of intelligent welding technologies, which generally adopt two methods. One is the method of real-time measurement and correction of weld trajectory, namely weld tracking technology. However, this technology has problems such as difficulty in debugging, high professional requirements, inability to track short-distance welds, and real-time tracking is easily affected by laser radiation and affects the measurement accuracy of optical cameras. The other method is mostly offline programming plus 3D visual correction. The welding trajectory is planned by software 3D modeling, and the trajectory deviation value of the object is measured and calculated by 3D camera to calculate the compensation value. This method requires a lot of modeling work in the early stage. For small batches of various types of welding workpieces, it is necessary to repeatedly create digital models and repeat the debugging steps, which is not suitable. In addition, the workpiece clamping accuracy is high, the workpiece loading and unloading tooling positioning device design is difficult and costly, the overall equipment manufacturing and debugging cycle is long, and the scope of application is small.

[0003] Therefore, the current laser welding method requires manual teaching of the robot. When manually teaching the robot welding system, on the one hand, because there is no physical object at the focus, it is difficult for the human eye to identify the focus, resulting in a long focusing time and high labor costs. On the other hand, it also leads to insufficient focusing accuracy, which affects the final welding quality, welding trajectory deviation, pores, cracks and other welding defects, which is not only inefficient, but also difficult to ensure the stability of welding quality. In addition, due to the complexity of the shape, size and welding environment of the workpiece, the current laser welding method is often difficult to automatically generate welding trajectories, and requires a complex modeling process, which limits the application scope of laser welding technology. Summary of the invention

[0004] The purpose of this application is to provide a robot laser welding system, method and equipment with automatic trajectory planning, which can improve the welding efficiency of automatic laser welding and expand the scope of application of automatic laser welding.

[0005] To achieve the above objectives, this application provides the following solutions.

[0006] In the first aspect, the present application provides a robot laser welding system with automatic trajectory planning, the robot laser welding system with automatic trajectory planning is used to weld a target workpiece, the target workpiece is a workpiece to be welded that has been marked with a weld seam, and the robot laser welding system with automatic trajectory planning includes: a 3D camera, a laser welding robot arm, an operating unit and a control unit; the 3D camera is arranged at the end of the laser welding robot arm; the 3D camera, the laser welding robot arm and the operating unit are all connected to the control unit; the operating unit is used to send a planned welding trajectory control instruction and an automatic welding control instruction to the control unit in sequence; the control unit is used to control the 3D camera to obtain a 3D image of the target workpiece when receiving a planned welding trajectory control instruction, plan a welding trajectory based on the 3D image, obtain a planned welding trajectory, and when receiving an automatic welding control instruction, control the laser welding robot arm to weld the target workpiece according to the planned welding trajectory.

[0007] In a second aspect, a robot laser welding method with automatic trajectory planning is applied to the control unit described above, and the robot laser welding method with automatic trajectory planning includes: acquiring a 3D image of a target workpiece; performing image enhancement on the 3D image to obtain an enhanced 3D image; performing weld recognition based on the enhanced 3D image, and screening out marked weld image dot matrix; and planning a welding trajectory using the marked weld image dot matrix to obtain a planned welding trajectory.

[0008] In a third aspect, the present application provides a computer device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement any one of the above-described robotic laser welding methods for automatically planning trajectories.

[0009] According to the specific embodiments provided in this application, this application discloses the following technical effects:

[0010] This application controls the 3D camera to obtain the 3D image of the target workpiece and plans the welding trajectory based on the 3D image when the control unit receives the control instruction for planning the welding trajectory; when the automatic welding control instruction is received, the laser welding robot arm is controlled to weld the target workpiece according to the planned welding trajectory. This application uses the 3D image of the target workpiece to automatically plan the welding trajectory, replacing the process of manually teaching the robot the weld points, reducing the manual workload, lowering the requirements for the workers' skill level and the welding difficulty, and improving the welding efficiency of automatic laser welding. In addition, this application does not require the creation of workpiece digital models and offline programming, does not require real-time measurement and tracking, reduces the design workload, adapts to the processing of more small non-standard workpieces, and expands the scope of application of automatic laser welding. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0012] Figure 1 A schematic diagram of the structural connections of a robot laser welding system with automatic trajectory planning provided in an embodiment of the present application.

[0013] Figure 2 A schematic flow chart of a robot laser welding method with automatic trajectory planning provided in an embodiment of the present application.

[0014] Figure 3 A schematic diagram of the structure of a computer device provided in an embodiment of the present application.

[0015] Explanation of symbols:

[0016] 3D camera-1; laser welding robot arm-2; operation unit-3; control unit-4; laser welding head-21; robot arm-22; vision control module-41; robot control module-42 and workbench-5. DETAILED DESCRIPTION

[0017] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0018] Embodiment 1, as Figure 1 As shown, this embodiment provides a robot laser welding system with automatic trajectory planning. The robot laser welding system with automatic trajectory planning is used to weld a target workpiece. The target workpiece is a workpiece to be welded that has been welded. The robot laser welding system with automatic trajectory planning includes: a 3D camera 1, a laser welding robot arm 2, an operating unit 3 and a control unit 4; the weld mark of the target workpiece includes: a starting point mark, an end point mark and an inflection point mark.

[0019] The 3D camera 1 is arranged at the end of the laser welding robot arm 2; the 3D camera 1, the laser welding robot arm 2 and the operating unit 3 are all connected to the control unit 4; the operating unit 3 is used to send a planned welding trajectory control instruction and an automatic welding control instruction to the control unit 4 in sequence; the control unit 4 is used to control the 3D camera 1 to obtain a 3D image of the target workpiece when receiving the planned welding trajectory control instruction, plan the welding trajectory based on the 3D image, obtain the planned welding trajectory, and when receiving the automatic welding control instruction, control the laser welding robot arm 2 to weld the target workpiece according to the planned welding trajectory.

[0020] Among them, the type of weld is not limited in this embodiment, and the weld is marked by marking points of the target workpiece to identify the weld position to be welded. It is marked by the characteristics of the preset marking points, such as the "X" symbol, the "O" symbol or other symbols, or by marking points of different colors. When the weld is a straight weld, just mark the starting point and the end point (starting point mark and end point mark). When the weld is a bending line, in addition to the starting point and the end point, make a mark at the middle bend (starting point mark, end point mark and inflection point mark). When the weld is a curve, in addition to the starting point and the end point, make more marks on the arc to connect the marking points into a curve that approximates the weld (inflection point mark). When the 3D camera 1 recognizes, it will automatically capture the weld near the marking point. Mark the weld position of the workpiece with a marker pen, such as marking an "X" mark at the starting point, the end point, and the inflection point (the position where the feature changes in the middle of the weld).

[0021] Optionally, the 3D camera 1 is a 3D structured light camera or a 3D binocular vision camera.

[0022] Optionally, the recognition accuracy of the 3D camera 1 is within 0.5 mm.

[0023] In actual application, the 3D camera 1 can collect light with a coded pattern reflected from the surface of the target workpiece. Due to the different shapes and depths of the surface of the target workpiece, the coded pattern will be distorted. By analyzing and calculating the collected distorted pattern through a specific algorithm, the position and depth information of each point on the surface of the target workpiece can be obtained. The 3D camera 1 collects the characteristic stripe image carrying the weld information on the surface of the target workpiece, and transmits the image data to the control unit 4 in real time through the Gigabit Industrial Ethernet interface.

[0024] Optionally, since the 3D scanning measurement takes pictures according to the field of view of the 3D camera 1, when the target workpiece is too large or too long, the 3D image cannot be collected in one go. The target workpiece can be photographed multiple times using a multi-position photo puzzle by moving the laser welding robot 2.

[0025] Furthermore, the laser welding robot arm 2 specifically includes: a laser welding head 21 and a robot arm 22; the laser welding head 21 is arranged at the end of the robot arm 22, and the laser welding head 21 and the robot arm 22 are both connected to the control unit 4; the robot arm 22 is used to drive the welding head 21 to weld the target workpiece.

[0026] Furthermore, the control unit 4 includes a visual control module 41 and a robot control module 42; the visual control module 41 is connected to the operating unit 3 and the 3D camera 1 respectively; the visual control module 41 is used to control the 3D camera 1 to obtain a 3D image of the target workpiece when receiving a control instruction for planning a welding trajectory, and to plan the welding trajectory based on the 3D image to obtain a planned welding trajectory.

[0027] The robot control module 42 is connected to the visual control module 41, the operating unit 3, the laser welding head 21 and the robotic arm 22 respectively; the robot control module 42 is used to control the robotic arm 22 to drive the welding head 21 to weld the target workpiece according to the planned welding trajectory when receiving the automatic welding control instruction.

[0028] Further, the camera TCP coordinates of the 3D camera 1 and the marking welding focus TCP coordinates of the laser welding head 21 are the same.

[0029] Furthermore, the operating unit 3 specifically includes: a planned welding trajectory start button, a welding trajectory planning completion indicator light, an automatic welding start button, an automatic welding completion indicator light and an operating panel.

[0030] The planned welding trajectory start button, the welding trajectory planning completion indicator light, the automatic welding start button and the automatic welding completion indicator light are all set on the operation panel; the planned welding trajectory start button, the welding trajectory planning completion indicator light, the automatic welding start button and the automatic welding completion indicator light are all connected to the control unit 4 through the operation panel; the planned welding trajectory start button is used to issue a planned welding trajectory control instruction; the automatic welding start button is used to issue an automatic welding control instruction.

[0031] During actual application, a welding trajectory planning control instruction is sent to the control unit 4 through a welding trajectory planning start button, the control unit 4 controls the 3D camera 1 to trigger the camera photo function, the control unit 4 automatically identifies the weld position based on the 3D image and plans the welding trajectory, and the control unit 4 controls the welding trajectory planning completion indicator light up; an automatic welding control instruction is sent to the control unit 4 through an automatic welding start button, the control unit 4 controls the laser welding robot 2 to weld the target workpiece, and after the welding is completed, the control unit 4 controls the welding trajectory planning completion indicator light up.

[0032] Furthermore, the robot laser welding system with automatic trajectory planning also includes: a workbench 5; the workbench 5 is used to place the target workpiece.

[0033] Optionally, the target workpiece of this embodiment does not need to be placed in a fixed position. A new trajectory is automatically generated each time a photo is taken and recognized, and no digital-analog comparison is required. The welding trajectory of each operation is generated based on the target workpiece, and there is no need to save the trajectory program.

[0034] Optionally, this embodiment does not require manual debugging of the robot arm 22 to focus the weld, teach the weld trajectory, and does not require manual programming. All weld positions are automatically identified based on image scanning and processing, and the program logic is automatically generated based on the control system, including the idle movement of the robot arm 22, focusing, starting the laser welding system, emitting laser, the robot arm 22 moving along the trajectory to weld, turning off the laser, and the robot arm 22 returning to the waiting position.

[0035] The technical effects of this application are as follows.

[0036] This application controls the 3D camera to obtain the 3D image of the target workpiece when the control unit receives the control instruction for planning the welding trajectory, and plans the welding trajectory based on the 3D image; when receiving the automatic welding control instruction, the laser welding robot arm is controlled to weld the target workpiece according to the planned welding trajectory. This application uses the 3D image of the target workpiece to automatically plan the welding trajectory, replacing the process of manually teaching the robot the welding points, because teaching a weld requires at least moving the robot to find several welding points. For welds with turns, transitions, and offsets, more should be added. Generally, a single weld takes at least several minutes. This application reduces the manual workload, reduces the requirements for workers' skill levels and welding difficulty, and improves the welding efficiency of automatic laser welding. In addition, this application does not require the creation of workpiece digital models and offline programming, does not require real-time measurement and tracking, reduces the design workload, adapts to the processing of more small non-standard workpieces, and expands the scope of application of automatic laser welding. This application does not require real-time measurement, and the measurement accuracy is not affected by laser radiation. 3D scanning measurement takes pictures according to the field of view of the 3D camera. It can be adapted to small workpieces and can also be applied to large workpiece processing by taking pictures in multiple positions and assembling them. There is no need to use a large-format scanning system for workpiece scanning and modeling. The device of this application does not require workpiece modeling and offline programming, reduces the difficulty of equipment manufacturing and debugging, adapts to small batch and multi-type workpiece processing scenarios, simplifies the operation process, and reduces the difficulty of operating automated equipment while replacing manual welding. This application increases the accuracy of the weld trajectory. Since traditional teaching relies on naked eye recognition and debugging experience, the accuracy is difficult to guarantee, and this application can ensure the consistency of focusing accuracy. The whole machine of this application is easier to run welding, and it can be started with one button after the recognition is completed, without too much manual operation. The workbench of this application does not require special fixtures for the workpiece, and there is no requirement for the placement position. There is no need to place the workpiece in the same position for multiple uses, as long as it is on the workbench. This application is suitable for workpieces with poor consistency. Separate photos and calculations are performed separately, with short time, fast response, and high processing efficiency.

[0037] Embodiment 2, as Figure 2 As shown, the present application also provides a robot laser welding method with automatic trajectory planning. The robot laser welding method with automatic trajectory planning is applied to the above control unit. The robot laser welding method with automatic trajectory planning includes the following steps.

[0038] S1. Obtain a 3D image of the target workpiece.

[0039] S2. Perform image enhancement on the 3D image to obtain an enhanced 3D image.

[0040] Furthermore, the image enhancement includes at least one of contrast enhancement, median filtering and binarization.

[0041] In practical applications, the purpose of image enhancement for 3D images is to remove noise from the 3D images, making them clearer and with more obvious edge features. For example, contrast enhancement is used to increase the contrast of 3D images, median filtering is used to remove noise from 3D images, and binarization is used to extract the target image (the image of the target workpiece) from the 3D image. In subsequent processing, a practical method is used to extract the center line of the micro-light band and detect feature points, which can accurately detect the feature points of the weld.

[0042] S3. Perform weld identification based on the image-enhanced 3D image and filter out the marked weld image dots.

[0043] Step S3 specifically includes: extracting the marking points of the target workpiece based on the 3D image after image enhancement, retaining the welds with the marking points, deleting the welds without the marking points, and screening out the marked weld image dot matrix.

[0044] S4. Plan a welding trajectory using the marked weld image dot matrix to obtain a planned welding trajectory.

[0045] Step S4 specifically includes: converting the marked weld image dot matrix into three-dimensional spatial coordinate data with the robot arm as a reference point; planning a welding trajectory based on the three-dimensional spatial coordinate data to obtain a planned welding trajectory.

[0046] Embodiment 3, the present application also provides a computer device, which may be a server or a terminal, and its internal structure diagram may be as follows: Figure 3As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a robot laser welding method with automatic trajectory planning is implemented.

[0047] Those skilled in the art will understand that Figure 3 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0048] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0049] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0050] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A robot laser welding system with automatic trajectory planning, the robot laser welding system with automatic trajectory planning is used to weld a target workpiece, the target workpiece is a workpiece to be welded that has been marked with a weld seam, and is characterized in that: The robot laser welding system with automatic trajectory planning includes: a 3D camera, a laser welding robot arm, an operating unit and a control unit; The 3D camera is arranged at the end of the laser welding robot arm; The 3D camera, the laser welding robot arm and the operating unit are all connected to the control unit; the operating unit is used to send a planned welding trajectory control instruction and an automatic welding control instruction to the control unit in sequence; the control unit is used to control the 3D camera to obtain a 3D image of the target workpiece when receiving the planned welding trajectory control instruction, plan the welding trajectory based on the 3D image, obtain the planned welding trajectory, and when receiving the automatic welding control instruction, control the laser welding robot arm to weld the target workpiece according to the planned welding trajectory.

2. The robot laser welding system with automatic trajectory planning according to claim 1, characterized in that: The laser welding robot arm specifically includes: a laser welding head and a robot arm; The laser welding head is arranged at the end of the mechanical arm, and both the laser welding head and the mechanical arm are connected to the control unit; the mechanical arm is used to drive the welding head to weld the target workpiece.

3. The robot laser welding system with automatic trajectory planning according to claim 2 is characterized in that: The control unit includes a visual control module and a robot control module; The visual control module is connected to the operating unit and the 3D camera respectively; the visual control module is used to control the 3D camera to obtain the 3D image of the target workpiece when receiving the control instruction for planning the welding trajectory, and plan the welding trajectory based on the 3D image to obtain the planned welding trajectory; The robot control module is connected to the visual control module, the operating unit, the laser welding head and the robotic arm respectively; the robot control module is used to control the robotic arm to drive the welding head to weld the target workpiece according to the planned welding trajectory when receiving the automatic welding control instruction.

4. The robot laser welding system with automatic trajectory planning according to claim 2, characterized in that: The camera TCP coordinates of the 3D camera are the same as the marking welding focus TCP coordinates of the laser welding head.

5. The robot laser welding system with automatic trajectory planning according to claim 1, characterized in that: The operating unit specifically includes: a planned welding trajectory start button, a welding trajectory planning completion indicator light, an automatic welding start button, an automatic welding completion indicator light and an operating panel; The planned welding trajectory start button, the welding trajectory planning completion indicator light, the automatic welding start button and the automatic welding completion indicator light are all arranged on the operation panel; the planned welding trajectory start button, the welding trajectory planning completion indicator light, the automatic welding start button and the automatic welding completion indicator light are all connected to the control unit through the operation panel; the planned welding trajectory start button is used to issue a planned welding trajectory control instruction; the automatic welding start button is used to issue an automatic welding control instruction.

6. The robot laser welding system with automatic trajectory planning according to claim 1, characterized in that: The robot laser welding system with automatic trajectory planning also includes: a workbench; The workbench is used for placing the target workpiece.

7. The robot laser welding system with automatic trajectory planning according to claim 1, characterized in that: The weld mark of the target workpiece includes: a starting point mark, an end point mark and an inflection point mark.

8. A robot laser welding method with automatic trajectory planning, the robot laser welding method with automatic trajectory planning being applied to the control unit according to any one of claims 1 to 7, characterized in that: The robot laser welding method with automatic trajectory planning includes: Acquire the 3D image of the target workpiece; Performing image enhancement on the 3D image to obtain an image-enhanced 3D image; Weld seam recognition is performed based on the image-enhanced 3D image, and the marked weld seam image dot matrix is ​​screened out; The marked weld image dot matrix is ​​used to plan a welding trajectory to obtain a planned welding trajectory.

9. The robot laser welding method with automatic trajectory planning according to claim 8, characterized in that: The image enhancement includes at least one of contrast enhancement, median filtering and binarization.

10. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the robot laser welding method for automatically planning trajectories as described in any one of claims 8 to 9.

Images