Intelligent robot integration device based on direct digital-analog fusion and welding method

Abstract

The invention relates to an intelligent robot integration device based on direct digital-analog fusion and a welding method, and the method comprises the steps: directly reading a three-dimensional model and / or a two-dimensional drawing, and carrying out the geometric processing of the model; generating a welding seam, a scanning point, a welding gun angle and a robot running path through a generative path algorithm; optimizing a path track through dynamic virtual simulation; and the welding track and the technological parameters are compiled into codes which can be executed by the welding robot, and the welding robot is controlled to complete automatic welding operation. The method has the beneficial effects that the three-dimensional model of the steel structure and an intelligent welding system are integrated, the three-dimensional model is directly read, the intermediate drawing processing link is omitted, and the model directly drives the welding process operation; a welding process expert database, intelligent welding path programming, whole-process virtual simulation and an autonomous robot trajectory optimization algorithm are integrated.

Description

Technical Field

[0001] The present invention belongs to the field of intelligent construction technology, and in particular relates to an intelligent robot integration device and a welding method based on direct digital-analog fusion. Background Art

[0002] With the rapid development of computer and automation technology, intelligent welding robot systems have gained widespread application in the intelligent construction of building steel structures. However, existing welding robot systems often have limited application capabilities, such as intelligent robots that are only used for intersecting welding and multi-robot intelligent systems that are only used for collaborative operations. Furthermore, the automation and intelligence levels of existing welding robot systems are not high enough, and significant manual intervention is still required in both pre- and post-processing.

[0003] To further enhance the automation and intelligence of welding robot systems, building a welding process library, component library, and node library with massive data is an effective pre-processing solution. Automatically matching the database allows for rapid acquisition of effective welding process parameters. Integrating this database with visual recognition and intelligent path compilation is an effective post-processing solution. Visual recognition enables precise trajectory positioning, while intelligent compilation enables optimal path planning. However, these technologies are not currently integrated into existing welding robot systems to significantly reduce labor costs.

[0004] In summary, it is very necessary to study the intelligent robot integrated device and welding method based on direct digital-analog fusion, and to realize the integrated integrated device and welding method of fast and direct model reading of complex steel structures, integrated construction of welding process library, intelligent welding path programming, full process virtual simulation and intelligent robot trajectory optimization. Summary of the Invention

[0005] The purpose of the present invention is to overcome the deficiencies in the prior art and provide an intelligent robot integration device and a welding method based on direct digital-analog fusion.

[0006] In the first aspect, an intelligent robot welding method based on direct digital-analog fusion is provided, including:

[0007] S1. Direct digital-model integration: Connect to steel structure detailed design software to directly read 3D models and / or 2D drawings; build a database of steel components and steel nodes, automatically identify and classify components and nodes, automatically identify plate thickness and dimensions, and perform model geometry processing;

[0008] S2, intelligent automatic programming: Based on the model information data of S1, the welding process expert library is called to automatically match the welding process parameters and welding rules, and the weld seam, scanning point, welding gun angle and robot operation path are generated through the generative path algorithm;

[0009] S3, virtual simulation adaptive adjustment: automatic collision detection and interference detection of the S2 path, and optimization of the path trajectory through dynamic virtual simulation;

[0010] S4. Industrial control command automatic welding: compile the welding trajectory and process parameters into G code executable by the welding robot, and control the welding robot to complete the automatic welding operation.

[0011] Preferably, S1 includes:

[0012] S11. Model-drawing direct reading: Import a 3D model without welding process data and / or a 2D drawing containing welding process data, parse and match the production process data; the 3D model includes a model file in stp, stl, or ifc format, and the 2D drawing includes a drawing file in dxf or gen format;

[0013] S12. Geometric identification and classification processing: Build a database of steel components and steel nodes, identify and classify steel components and steel nodes, and extract geometric feature information. Steel components include I-beams, box steels, channels, cross steels, and steel pipes. Steel nodes include beam-column nodes and beam-beam nodes. The geometric feature information includes end plates, ribs, corbels, cross stiffeners, and yard plates.

[0014] Preferably, S2 includes:

[0015] S21. Construction of an integrated welding process library: An integrated steel structure welding process expert library is established. The structural welding process expert library includes welding process parameters and welding rules for fillet welds, single-sided groove welds, double-sided groove welds, butt welds, and intersecting welds; the library automatically calculates weld leg dimensions, sets welding rules, and automatically matches welding current and voltage parameters.

[0016] S22. Visual recognition automated programming: Using image and depth recognition visual positioning technology, the 3D point cloud depth recognition algorithm of the 3D vision camera is combined with the 2D camera image edge extraction algorithm to locate the geometric boundaries of the steel structure and extract the weld position. At the same time, the weld points and through-weld holes are identified, and the arc starting and ending positions are located. The generative path algorithm is used to automatically generate welds and scanning points, automatically calculate the welding gun angle, robot operation trajectory and weld layer weld size, and solve the fastest, shortest, collision-free and infinite-position welding path for intelligent automatic programming.

[0017] Preferably, S3 includes:

[0018] S31. Full-process virtual simulation: Through full-process virtual simulation, automatic collision detection and interference detection are performed, and a generative optimal path algorithm is used to avoid welding collisions between the welding gun and steel structures when welding complex metal structures;

[0019] S32, Autonomous robot trajectory optimization: Through visual dynamic virtual simulation of the entire welding process, the effectiveness of the path simulation is tested, and the path trajectory is optimized, and adaptive adjustments are made to complex position relationships.

[0020] Preferably, S4 includes:

[0021] S41, automatic compilation of industrial control instructions: compile welding trajectory and process parameters into G code executable by welding robots and import it into intelligent robot welding workstation;

[0022] S42. Intelligent robot automatic welding: The intelligent robot welding workstation controls the welding robot through G code to automatically perform welding operations.

[0023] In a second aspect, an intelligent robot integrated device based on direct digital-analog fusion is provided, which is used to perform any of the methods described in the first aspect, including: a welding robot 1, a welding motor 2, a robot ground rail 3, a displacement mechanism 4, a positioning line laser 5, and a visual recognition system 6;

[0024] The G code is imported into the console of the intelligent robot integrated device and executed to control the welding robot 1 to perform automatic welding operations; the welding motor 2 provides power to the welding robot 1 and controls the welding robot 1 to perform multi-directional movement in space; the welding robot 1 is controlled to move longitudinally on the robot ground rail 3 to expand the longitudinal welding range of the structural part; the rotation of the displacement mechanism 4 is controlled to rotate the weld seam of the structural part to within a suitable angle range to avoid collision between the welding gun of the welding robot 1 and the structural part; the positioning line laser 5 is used to automatically calibrate the position of the structural part and the rib plate, and the visual recognition system 6 is used to automatically identify the geometric boundaries of the structural part and the micro features of the weld points and through-weld holes.

[0025] In a third aspect, an intelligent robot welding system based on direct digital-analog fusion is provided, which is used to execute any of the methods described in the first aspect, including:

[0026] A fusion module is used to connect to steel structure detailed design software and directly read 3D models and / or 2D drawings; it builds a database of steel components and steel nodes, automatically identifies and classifies components and nodes, automatically identifies plate thickness and dimensions, and performs model geometry processing;

[0027] The programming module is used to call the welding process expert library to automatically match welding process parameters based on the model information data of the fusion module, and generate welds, scanning points, welding gun angles and robot operation paths through the generative path algorithm;

[0028] The simulation module is used to automatically detect collisions and interferences on the path of the programming module and optimize the path trajectory through dynamic virtual simulation;

[0029] The welding module is used to compile the welding trajectory and process parameters into G code executable by the welding robot, and control the welding robot to complete automatic welding operations.

[0030] According to a fourth aspect, a computer storage medium is provided, wherein a computer program is stored in the computer storage medium; when the computer program is run on a computer, the computer executes any one of the methods described in the first aspect.

[0031] According to a fifth aspect, an electronic device is provided, including:

[0032] Memory, used to store computer programs;

[0033] A processor is used to execute the computer program to implement any method as described in the first aspect.

[0034] The beneficial effects of the present invention are:

[0035] 1) The intelligent robot integrated device and welding method based on direct digital-analog drive provided by the present invention realize direct digital-analog integration through direct model-drawing reading and geometric recognition and classification processing, skipping the processing drawing link, omitting process marking time, and improving work efficiency; through the integration of the welding process expert library, rapid matching of welding process parameters and welding rules is achieved; through image and depth recognition visual positioning, precise positioning of the geometric boundaries of steel structures and precise extraction of weld positions are achieved; through generative path algorithms, intelligent automatic programming is achieved; through full-process virtual simulation, collision detection and avoidance and path trajectory optimization are achieved; through the integrated welding workstation, automatic compilation of industrial control instructions and automatic welding by intelligent robots are achieved.

[0036] 2) Compared with traditional welding robots, the intelligent robot integrated device and welding method based on direct digital-analog drive provided by the present invention integrates a three-dimensional model of the steel structure and an intelligent welding system. It directly reads the three-dimensional model, omitting the intermediate processing drawing link, and the welding process operation is directly driven by the model; it integrates a welding process expert library, intelligent welding path programming, full-process virtual simulation and an autonomous robot trajectory optimization algorithm. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 This is a schematic diagram of the overall process of the intelligent robot welding method based on direct digital-analog drive of the present invention;

[0038] Figure 2 This is a schematic structural diagram of an intelligent robot integrated device based on direct digital-analog drive according to the present invention;

[0039] Figure 3a It is a schematic diagram that directly reads the 3D model without process data;

[0040] Figure 3bIt is a schematic diagram that can be directly read from a two-dimensional drawing containing process annotations;

[0041] Figure 4 It is a schematic diagram of the geometric characteristic information of the steel structure;

[0042] Figure 5 It is a schematic diagram of the image and depth recognition visual positioning process;

[0043] Figure 6 This is a schematic diagram of the depth recognition weld positioning result;

[0044] Figure 7 It is a schematic diagram of simulation path collision detection and generative optimal path algorithm avoidance;

[0045] Figure 8 It is a schematic diagram of the optimal simulation path solved by the generative algorithm;

[0046] Figure 9a This is a schematic diagram of a welding case of a weld seam of an intelligent robot integrated device;

[0047] Figure 9b This is a schematic diagram of the second welding case of the intelligent robot integrated device.

[0048] Explanation of the accompanying symbols: 1-welding robot; 2-welding motor; 3-robot ground rail; 4-positioning mechanism; 5-positioning line laser; 6-visual recognition system. DETAILED DESCRIPTION

[0049] The present invention will be further described below with reference to the following examples. The following examples are provided only to facilitate understanding of the present invention. It should be noted that, without departing from the principles of the present invention, it is possible for a person skilled in the art to make various modifications to the present invention, and such improvements and modifications fall within the scope of the claims of the present invention.

[0050] Example 1:

[0051] In order to solve the problems of the prior art, Example 1 of the present application provides an intelligent robot welding method based on direct digital-analog fusion, such as Figure 1 Shown, including:

[0052] S1. Direct digital-model integration: Connect to steel structure in-depth design software, directly read 3D models and / or 2D drawings, without additional settings for the design model, skip the steel structure processing drawing link, and save a lot of process marking time; build a database of steel components and steel nodes, automatically identify components and nodes and classify them, automatically identify plate thickness and dimensions, and perform model geometry processing.

[0053] S1 includes:

[0054] S11. Model-drawing direct reading: Import 3D models without welding process data and / or 2D drawings with welding process data, analyze and match them with production process data.

[0055] Specifically, such as Figure 3a-Figure 3b As shown, when reading the 3D model, import the 3D model file, including stp, stl, ifc and other format model files, decompose the plate components of the steel structure 3D model, generate the process data of plate welding assembly, and match the production process data ( Figure 3a ); When reading 2D drawings, import 2D drawing files, including dxf, gen and other format drawing files, merge the drawing data with the annotation, and match the production process data ( Figure 3b ).

[0056] When directly reading models and drawings, the fusion module directly connects to the steel structure design deepening software, quickly and directly reads the original data of various types of two-dimensional drawings and three-dimensional models, automatically identifies two-dimensional drawings, generates annotation information of three-dimensional models, and matches the corresponding production process data; the fusion module skips the traditional processing drawing link, does not require steel component deepening processing drawings, omits a lot of process annotation time, and effectively improves work efficiency.

[0057] S12, geometric recognition and classification processing: Figure 4 As shown, a steel component and steel node database is integrated to identify and classify steel components and steel nodes, and to extract geometric feature information as the data basis for corresponding automatic process processing.

[0058] Specifically, steel components include I-beams, box steels, channels, cross steels, and steel pipes; steel nodes include beam-column nodes and beam-beam nodes; steel components and steel nodes constitute steel structural parts; and the geometric feature information of steel structural parts includes end plates (such as conventional end plates and special-shaped end plates), stiffeners (such as full-length stiffeners and non-full-length stiffeners), corbels, cross stiffeners, and code plates.

[0059] S2, intelligent automatic programming: Based on the model information data of S1, the welding process expert library is called to automatically match the welding process parameters and welding rules, and the weld, scanning point, welding gun angle and robot operation path are generated through the generative path algorithm.

[0060] S2 includes:

[0061] S21. Construction of integrated welding process library: An integrated steel structure welding process expert library is established, which includes welding process parameters and welding rules for fillet welds, single-sided groove welds, double-sided groove welds, butt welds and intersecting welds; the weld leg size is automatically calculated, welding rules are set, and welding current and voltage parameters are automatically matched.

[0062] S22, Visual recognition automation programming: Figure 5-Figure 6 As shown, it adopts image and depth recognition visual positioning technology, through the three-dimensional point cloud depth recognition algorithm of the 3D vision camera, combined with the 2D camera image edge extraction algorithm, it has strong anti-interference ability, accurately locates the geometric boundaries of steel structures and extracts the weld position, and simultaneously identifies micro features such as weld spots and through-weld holes, accurately locates the arc starting and arc ending positions; and through the generative path algorithm, automatically generates welds and scanning points, automatically calculates the welding gun angle, robot operation trajectory and weld layer weld size, quickly solves the fastest, shortest, collision-free, unlimited position welding path, and performs intelligent automatic programming.

[0063] S3, virtual simulation adaptive adjustment: automatic collision detection and interference detection of the S2 path, and optimization of the path trajectory through dynamic virtual simulation.

[0064] S3 includes:

[0065] S31, full process virtual simulation: Figure 7 As shown, through virtual simulation of the entire process, automatic collision detection and interference are performed, and a generative optimal path algorithm is used to avoid welding collisions between welding guns and steel structures when welding complex metal structures. Compared with the traditional template lifting path to avoid collisions, it is more convenient and efficient. The external expansion mode of the steel structure is used to avoid collisions caused by assembly errors.

[0066] S32, Autonomous robot trajectory optimization: Figure 8 As shown, through the visualization of dynamic virtual simulation of the entire welding process, the effectiveness of the path simulation is tested, the path trajectory is optimized, and adaptive adjustments are made to complex positional relationships.

[0067] S4. Industrial control command automatic welding: compile the welding trajectory and process parameters into G code executable by the welding robot, and control the welding robot to complete the automatic welding operation.

[0068] S4 includes:

[0069] S41, automatic compilation of industrial control instructions: compile welding trajectory and process parameters into G code executable by welding robots and import it into intelligent robot welding workstation;

[0070] S42. Intelligent robot automatic welding: The intelligent robot welding workstation controls the welding robot through G code to automatically perform welding operations.

[0071] Specifically, Figure 9a-9b Shown are two actual case welding and processes performed with different welds.

[0072] Example 2:

[0073] Based on Example 1, Example 2 of the present application provides an intelligent robot integration device based on direct digital-analog fusion, such as Figure 2 As shown, it includes: a welding robot 1, a welding motor 2, a robot ground rail 3, a displacement mechanism 4, a positioning line laser 5 and a visual recognition system 6;

[0074] The G code is imported into the console of the intelligent robot integrated device and executed to control the welding robot 1 to perform automatic welding operations; the welding motor 2 provides power to the welding robot 1 and controls the welding robot 1 to perform multi-directional movement in space; the welding robot 1 is controlled to move longitudinally on the robot ground rail 3 to expand the longitudinal welding range of the structural part; the rotation of the displacement mechanism 4 is controlled to rotate the weld seam of the structural part to within a suitable angle range to avoid collision between the welding gun of the welding robot 1 and the structural part; the positioning line laser 5 is used to automatically calibrate the position of the structural part and the rib plate, and the visual recognition system 6 is used to automatically identify the geometric boundaries of the structural part and the micro features of the weld points and through-weld holes.

[0075] Specifically, the welding robot is set to 6-axis positioning, the two positioners are set to 4-axis positioning, and the robot ground rail is set to 1-axis positioning; the rotation angle of the positioner is -90° to 90°; the maximum size of the formed part is 14m×3.8m×3.6m.

[0076] It should be noted that the device provided in this embodiment is a corresponding device of the method provided in Example 1. Therefore, the parts in this embodiment that are the same or similar to those in Example 1 can be referenced to each other and will not be repeated in this application.

[0077] Example 3:

[0078] Based on Example 1, Example 3 of the present application provides an intelligent robot welding system based on direct digital-analog fusion, including:

[0079] A fusion module is used to connect to steel structure detailed design software and directly read 3D models and / or 2D drawings; it builds a database of steel components and steel nodes, automatically identifies and classifies components and nodes, automatically identifies plate thickness and dimensions, and performs model geometry processing;

[0080] The programming module is used to call the welding process expert library to automatically match welding process parameters based on the model information data of the fusion module, and generate welds, scanning points, welding gun angles and robot operation paths through the generative path algorithm;

[0081] The simulation module is used to automatically detect collisions and interferences on the path of the programming module and optimize the path trajectory through dynamic virtual simulation;

[0082] The welding module is used to compile the welding trajectory and process parameters into G code executable by the welding robot, and control the welding robot to complete automatic welding operations.

[0083] It should be noted that the system provided in this embodiment is a corresponding system of the method provided in Example 1. Therefore, the parts in this embodiment that are the same or similar to those in Example 1 can be referenced to each other and will not be repeated in this application.

[0084] In summary, the intelligent robot integrated device and welding method based on direct digital-analog drive provided by the present invention achieves direct digital-analog integration through direct model-drawing reading and geometric recognition and classification processing. Rapid matching of welding process parameters and welding rules is achieved through an integrated welding process expert library. Precise positioning of the geometric boundaries of steel structures and accurate extraction of weld positions are achieved through image and depth recognition visual positioning. Intelligent automatic programming is achieved through a generative path algorithm. Collision detection and avoidance, as well as path optimization, are achieved through full-process virtual simulation. Furthermore, an integrated welding workstation enables automated compilation of industrial control instructions and automated welding by intelligent robots. The present method has been verified to be effective in practice.

Claims

1. An intelligent robot welding method based on direct digital-analog fusion is characterized in that: include: S1. Direct digital-model integration: Connect to steel structure detailed design software to directly read 3D models and / or 2D drawings; build a database of steel components and steel nodes, automatically identify and classify components and nodes, automatically identify plate thickness and dimensions, and perform model geometry processing; S2, intelligent automatic programming: Based on the model information data of S1, the welding process expert library is called to automatically match the welding process parameters and welding rules, and the weld seam, scanning point, welding gun angle and robot operation path are generated through the generative path algorithm; S3, virtual simulation adaptive adjustment: automatic collision detection and interference detection of the S2 path, and optimization of the path trajectory through dynamic virtual simulation; S4. Industrial control command automatic welding: compile the welding trajectory and process parameters into G code executable by the welding robot, and control the welding robot to complete the automatic welding operation.

2. The intelligent robot welding method based on direct digital-analog fusion according to claim 1 is characterized in that: S1 includes: S11. Model-drawing direct reading: Import a 3D model without welding process data and / or a 2D drawing containing welding process data, parse and match the production process data; the 3D model includes a model file in stp, stl, or ifc format, and the 2D drawing includes a drawing file in dxf or gen format; S12. Geometric identification and classification processing: Build a database of steel components and steel nodes, identify and classify steel components and steel nodes, and extract geometric feature information. Steel components include I-beams, box steels, channels, cross steels, and steel pipes. Steel nodes include beam-column nodes and beam-beam nodes. The geometric feature information includes end plates, ribs, corbels, cross stiffeners, and yard plates.

3. The intelligent robot welding method based on direct digital-analog fusion according to claim 2, characterized in that S2 include: S21. Construction of an integrated welding process library: An integrated steel structure welding process expert library is established. The structural welding process expert library includes welding process parameters and welding rules for fillet welds, single-sided groove welds, double-sided groove welds, butt welds, and intersecting welds; the library automatically calculates weld leg dimensions, sets welding rules, and automatically matches welding current and voltage parameters. S22. Visual recognition automated programming: Using image and depth recognition visual positioning technology, the 3D point cloud depth recognition algorithm of the 3D vision camera is combined with the 2D camera image edge extraction algorithm to locate the geometric boundaries of the steel structure and extract the weld position. At the same time, the weld points and through-weld holes are identified, and the arc starting and ending positions are located. The generative path algorithm is used to automatically generate welds and scanning points, automatically calculate the welding gun angle, robot operation trajectory and weld layer weld size, and solve the fastest, shortest, collision-free and infinite-position welding path for intelligent automatic programming.

4. The intelligent robot welding method based on direct digital-analog fusion according to claim 3 is characterized in that S3 include: S31. Full-process virtual simulation: Through full-process virtual simulation, automatic collision detection and interference detection are performed, and a generative optimal path algorithm is used to avoid welding collisions between the welding gun and steel structures when welding complex metal structures; S32, Autonomous robot trajectory optimization: Through visual dynamic virtual simulation of the entire welding process, the effectiveness of the path simulation is tested, and the path trajectory is optimized, and adaptive adjustments are made to complex position relationships.

5. The intelligent robot welding method based on direct digital-analog fusion according to claim 4 is characterized in that S4 include: S41, automatic compilation of industrial control instructions: compile welding trajectory and process parameters into G code executable by welding robots and import it into intelligent robot welding workstation; S42. Intelligent robot automatic welding: The intelligent robot welding workstation controls the welding robot through G code to automatically perform welding operations.

6. Intelligent robot integration device based on direct digital-analog fusion, characterized in that: Used to perform the method according to any one of claims 1 to 5, comprising: a welding robot 1, a welding motor 2, a robot ground rail 3, a displacement mechanism 4, a positioning line laser 5 and a visual recognition system 6; The G code is imported into the console of the intelligent robot integrated device and executed to control the welding robot 1 to perform automatic welding operations; the welding motor 2 provides power to the welding robot 1 and controls the welding robot 1 to perform multi-directional movement in space; the welding robot 1 is controlled to move longitudinally on the robot ground rail 3; the rotation of the displacement mechanism 4 is controlled; the position of the structural parts and the ribs is automatically calibrated by the positioning line laser 5, and the geometric boundaries of the structural parts and the micro features of the weld points and through-weld holes are automatically identified by the visual recognition system 6.

7. Intelligent robot welding system based on direct digital-analog fusion, characterized by: Used to perform the method according to any one of claims 1 to 5, comprising: A fusion module is used to connect to steel structure detailed design software and directly read 3D models and / or 2D drawings; it builds a database of steel components and steel nodes, automatically identifies and classifies components and nodes, automatically identifies plate thickness and dimensions, and performs model geometry processing; The programming module is used to call the welding process expert library to automatically match welding parameters based on the model information data of the fusion module, and generate welds, scanning points, welding gun angles and robot operation paths through a generative path algorithm; The simulation module is used to automatically detect collisions and interferences on the path of the programming module and optimize the path trajectory through dynamic virtual simulation; The welding module is used to compile the welding trajectory and process parameters into G code executable by the welding robot, and control the welding robot to complete automatic welding operations.

8. A computer storage medium, characterized in that The computer storage medium stores a computer program; when the computer program is run on a computer, the computer executes the method according to any one of claims 1 to 5.

9. An electronic device, characterized in that: include: Memory, used to store computer programs; A processor, configured to execute the computer program to implement the method according to any one of claims 1 to 5.

Images