CN115070298A - A high-efficiency twin-wire welding path generation system and path generation method - Google Patents

Abstract

The invention discloses a high-efficiency double-wire welding path generation system and a path generation method, which relate to the technical field of welding and comprise the following steps: the welding line recognition, extraction and library adjustment module is used for sequentially carrying out visual sensing detection on the workpiece by the visual system, acquiring image information, extracting welding line characteristics, searching a database, and calling a welding line model with the highest similarity and relevant welding process data. The welding line model knowledge base and the welding line identification extraction need to be obtained through a large number of visual identification tests, the welding process database needs to be obtained through welding tests according to different groove forms and assembly conditions, the welding line identification extraction adjustment base, the welding line intelligent welding track path posture planning, the automatic generation of a robot welding program, the simulation issuing and the like need to be guaranteed through software algorithm design, and verification and optimization are carried out through tests, the welding quality and the welding precision of a double-wire welding path are guaranteed, the problems of dislocation and false welding are avoided, and the welding efficiency is improved to the maximum extent.

Description

A high-efficiency twin-wire welding path generation system and path generation method

technical field

The invention relates to the technical field of welding, in particular to a high-efficiency twin-wire welding path generation system and a path generation method.

Background technique

Welding: also known as welding, welding, is a manufacturing process and technology for joining metals or other thermoplastic materials such as plastics by heating, high temperature or high pressure. Welding achieves the purpose of joining through the following three ways: fusion welding - heating The workpiece to be joined is partially melted to form a molten pool. After the molten pool is cooled and solidified, it is joined. If necessary, a filler can be added to assist. It is suitable for welding of various metals and alloys without pressure. Pressure welding - welding The process must put pressure on the weldment, which belongs to the processing of various metal materials and some metal materials. Brazing - using a metal material with a lower melting point than the base metal as the brazing material, using the liquid brazing material to wet the base metal and filling the joint gap, It is suitable for welding of various materials, and also suitable for welding of different metals or dissimilar materials. There are many energy sources for modern welding, including gas flame, arc, laser, electron beam. , friction and ultrasonic etc.

The TCP of the traditional single-wire welding process torch is a point, and the TCP of the high-efficiency double-wire welding process torch is a line segment consisting of two points. It is relatively simple to fit a point and the weld trajectory. Fitting a line segment to the weld trajectory is relatively simple. The difficulty of precise welding is greatly increased, and a certain welding inclination angle is required for welding, and the difficulty is increased exponentially.

SUMMARY OF THE INVENTION

The purpose of the invention provided by the present invention is to provide a high-efficiency twin-wire welding path generation system and path generation method, so as to solve the above-mentioned problems in the background art.

In order to achieve the above purpose, the present invention is achieved through the following technical solutions: a high-efficiency twin-wire welding path generation system, comprising:

Weld seam identification, extraction and library adjustment module, the vision system performs visual sensor detection on the workpiece in turn, obtains image information, extracts weld seam features, searches the database, and calls the weld seam model with the highest similarity and related welding process data.

Weld seam model knowledge base and welding process database. Weld seam model knowledge base and welding process database include: Weld seam knowledge base and assembly welding seam function process database.

Welding seam intelligent welding trajectory path and attitude planning module, after workpiece identification and welding seam trajectory extraction, based on the extracted welding seam trajectory, the robot welding path and welding torch posture are planned.

Robot welding program automatic generation and simulation release module, after the robot welding program automatic generation and simulation release module forms a "robot welding series (or a complete) program", the system performs program conversion to form a robot executable "robot operation program", And the robot's operational accessibility and anti-collision verification are carried out in the background.

The signal connection between the weld seam identification, extraction and library adjustment module, the weld seam model knowledge base and the welding process database, the signal connection between the weld seam identification, extraction and library adjustment module and the weld seam intelligent welding trajectory path and attitude planning module, Two-way signal connection between the welding process database and the welding seam intelligent welding trajectory path and attitude planning module, and signal connection between the robot welding program automatic generation and simulation release module and the welding seam intelligent welding trajectory path and attitude planning module.

Further, the weld seam identification, extraction and library adjustment module sequentially performs visual sensing detection on the workpiece based on the vision system, obtains image information, extracts weld seam features, searches the database, and calls the weld seam model with the highest similarity and related welding process data. , at the same time, extract the welding seam contour image and welding seam trajectory, compare and verify with the data of the calling database, and confirm the welding seam trajectory of robot welding

Further, the weld model knowledge base and welding process database also have the ability to import, create, store and manage all three-dimensional models of welds or weld rules, and the best welding processes for various welds have been verified by batch production. Welding processes designed or verified by tests but not verified by batch production, as well as data such as welding design rules for assembling welds, this database module converts product models through algorithms, carries out parametric management, and serves as a visual scanning recognition system in the later stage. The basis for effective comparative analysis of actual workpiece and workpiece model data is also the basis for all trajectory, attitude, and path planning software.

Further, the welding seam intelligent welding trajectory path attitude planning module is also used to design the welding process and the welding process of each welding seam according to the "welding process" level given by the database, according to the data and the model-driven mode in combination with the retrieved welding process. parameters, and form a series of robot welding programs.

Further, the automatic generation and simulation release module of the robot welding program is also used to push the "robot operation program" to each robot controller to form the robot program to be executed.

A path generation method for a high-efficiency double-wire welding path generation system, applied to the high-efficiency double-wire welding path generation system described in any one of the above, includes the following steps:

Step 1: First, use the weld seam identification, extraction and library adjustment module to determine the path of the weld seam, and then interact with the extracted data with the weld seam model knowledge base and the welding process database to obtain the best welding process and weld model.

Step 2: Send the welding process and weld model data to the intelligent welding trajectory and posture planning module of the weld. After the workpiece is identified and the weld trajectory is extracted, the extracted weld trajectory is used as the planning basis to plan the robot welding path and welding torch posture. .

Step 3: Design the welding process and parameters of each weld according to the data and model-driven method, and form a series of robot welding programs.

Step 4: Send the path data planned by the welding seam intelligent welding trajectory path and attitude planning module to the robot welding program automatic generation and simulation release module to perform data simulation simulation, and send the data after passing the test.

Step 5. Push the "robot operation program" to each robot controller to form the robot program to be executed, and finally carry out the welding process.

Further, it includes the following steps: according to the operation steps in step 1, the welding seam trajectory obtained by the visual recognition of the welding seam identification extraction and library adjustment module becomes the motion trajectory of the welding gun, which requires not only special execution software, but also the welding seam trajectory. Through a special calibration method, the vision system, the robot external axis, and the robot TCP (torch end) are integrated into a common coordinate system to form a whole.

Further, it includes the following steps: according to the operation steps in step 2, the stereo vision measurement and recognition module based on the hand-eye calibration of the weld seam identification extraction and library adjustment module is the basis of high-precision three-dimensional measurement, and the module mainly includes high-resolution boards. Cameras, high-speed image acquisition boards, image processing control modules, etc., optimize the calibration process, and propose a space circle fitting method to perform hand-eye calibration of standard balls, so that the light plane can be any plane equation, improve the accuracy of standard ball hand-eye calibration, and expand the structure. For large and complex components, multi-frame reconstruction is performed in coordination with multi-module three-dimensional imaging, and then multi-view stitching is performed to obtain a panoramic appearance.

Further, it includes the following steps: according to the operation steps in step 4, 180 or 360 pieces of attitude data are compiled into the direction of the line segment formed by the two welding wires of the TCP and stored in the database, and when the intelligent welding trajectory path attitude planning module of the weld is executed, according to The algorithm automatically matches the optimal welding torch posture to generate the welding trajectory.

Further, it includes the following steps: according to the operation steps in step 5, the welding process adopts an adaptive laser sensor to process the high-resolution full-frame image and track the welding seam.

The invention provides a high-efficiency double-wire welding path generation system and path generation method. Has the following beneficial effects:

For the high-efficiency double-wire welding path generation system and method of use, the weld model knowledge base and weld seam identification and extraction need to be obtained through a large number of visual recognition tests, and the welding process database needs to be obtained through welding tests for different groove forms and assembly conditions. Seam recognition, extraction and adjustment of library, intelligent welding trajectory and attitude planning of seam, automatic generation and simulation of robot welding program, etc. need to be guaranteed by software algorithm design, and verified and optimized through experiments to ensure the welding quality and accuracy of double-wire welding path. Avoid the problems of misalignment and virtual welding, and maximize the efficiency of welding.

Description of drawings

1 is a general system diagram of a high-efficiency twin-wire welding path generation system and path generation method of the present invention;

FIG. 2 is a schematic diagram of a method for generating a high-efficiency twin-wire welding path generation system and a path generation method according to the present invention.

In Figure 1: 1. Weld seam recognition extraction and library adjustment module; 2. Weld seam model knowledge base and welding process database; 3. Weld seam intelligent welding trajectory path and attitude planning module; 4. Robot welding program automatic generation and simulation release module .

Detailed ways

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, but not all of the embodiments.

Examples of such embodiments are illustrated in the accompanying drawings, wherein the same or similar reference numerals refer to the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary, and are intended to explain the present invention and should not be construed as limiting the present invention.

Below in conjunction with accompanying drawing and embodiment, the present invention will be further described:

Referring to Figures 1-2, the present invention provides a technical solution: a high-efficiency dual-wire welding path generation system, including:

Weld seam identification, extraction and library adjustment module 1, the vision system performs visual sensing detection on the workpiece in turn, obtains image information, extracts weld seam features, searches the database, and calls the weld seam model with the highest similarity and related welding process data;

Weld Model Knowledge Base and Welding Process Database 2, Weld Model Knowledge Base and Welding Process Database 2 include: Weld Knowledge Base and Assembly Weld Function Process Database

Welding seam intelligent welding trajectory path and attitude planning module 3, after workpiece identification and welding seam trajectory extraction, based on the extracted welding seam trajectory, the robot welding path and welding torch posture are planned;

Robot welding program automatic generation and simulation release module 4, after the robot welding program automatic generation and simulation release module 4 forms a "robot welding series or a complete program", the system performs program conversion to form a robot executable "robot operation program", And verify the robot's accessibility and anti-collision in the background;

There is a signal connection between the weld seam identification, extraction and library adjustment module 1, the weld seam model knowledge base and the welding process database 2, and the signal connection between the weld seam identification, extraction and library adjustment module 1 and the weld seam intelligent welding trajectory path and attitude planning module 3. Two-way signal connection between the weld seam model knowledge base and welding process database 2 and the weld seam intelligent welding trajectory path attitude planning module 3, between the robot welding program automatic generation and simulation release module 4 and the weld seam intelligent welding trajectory path attitude planning module 3 Signal connection, a new wear-resistant composite steel plate (whole or part) is laid inside the bucket, and two types of welds will be formed between the steel plate and the steel plate. A small amount of gap is left as a weld), and this type of weld needs to be fully welded; the other type is a fillet groove, that is, a fillet weld formed by a single steel plate and the bottom plate, and a fillet weld needs to be welded. The above two types of welds require multi-layer and multi-pass welding, and the bottom of the bucket has an irregular arc, and the height of the entire bottom surface is different, which solves the problems of the weld groove state: complex size; complex measurement site environment, background object interference Seriously, it is difficult to distinguish the background object from the target in the captured image; the illumination factor is uncontrollable, and there is no obvious gray gradient change at the target boundary in the image. The above problems lead to difficult visual recognition and laser tracking.

Specifically, the weld seam identification, extraction and library adjustment module 1 sequentially performs visual sensing detection on the workpiece based on the vision system, obtains image information, extracts weld seam features, searches the database, and calls the weld seam model with the highest similarity and related welding process data. At the same time, extract the welding seam contour image and welding seam trajectory, compare and verify with the data of the calling database, and confirm the welding seam trajectory of the robot welding.

Specifically, the welding seam model knowledge base and the welding process database 2 also have the ability to import, create, store and manage all three-dimensional models of welding seams or welding seam rules. Or welding processes verified by tests but not verified by batch production, and data such as welding design rules for assembling welds; this database module converts product models through algorithms, carries out parametric management, and serves as a visual scanning The basis for effective comparative analysis of actual workpiece and workpiece model data is also the basis for all trajectory, attitude, and path planning software.

Specifically, the intelligent welding trajectory path and attitude planning module 3 of the welding seam is also used to design the welding process and parameters of each welding seam according to the "welding process" level given by the database, according to the data and the model-driven mode in combination with the recalled welding process. , and form a series of robot welding programs.

Specifically, the robot welding program automatic generation and simulation release module 4 is also used to push the "robot operation program" to each robot controller to form the robot program to be executed.

A path generation method for a high-efficiency double-wire welding path generation system, applied to any of the above-mentioned high-efficiency double-wire welding path generation systems, includes the following steps:

Step 1. First, use the weld seam identification, extraction and library adjustment module 1 to determine the path of the weld seam, and then interact with the extracted data with the weld seam model knowledge base and the welding process database 2 to obtain the best welding process and weld model. ;

Step 2: Send the welding process and weld model data to the intelligent welding trajectory and attitude planning module 3. After workpiece identification and weld trajectory extraction, the robot welding path and welding torch are planned based on the extracted weld trajectory. attitude;

Step 3: Design the welding process and parameters of each weld according to the data and model-driven method, and form a series of robot welding programs;

Step 4: Send the path data planned by the intelligent welding track path and attitude planning module 3 to the robot welding program automatic generation and simulation release module 4, perform data simulation simulation, and send data after passing the test;

Step 5. Push the "robot operation program" to each robot controller to form the robot program to be executed, and finally carry out the welding process.

Specifically, according to the operation steps in step 1, the welding seam trajectory obtained by the visual recognition of the welding seam identification extraction and library adjustment module 1 becomes the motion trajectory of the welding gun. In addition to special execution software, a special calibration method is also required. Integrate the vision system, the external axis of the robot, and the end of the robot TCP welding torch into a common coordinate system to form a whole.

Specifically, according to the operation steps in step 2, the stereo vision measurement and recognition module based on hand-eye calibration of the weld seam recognition extraction and library adjustment module 1 is the basis of high-precision 3D measurement. The modules mainly include high-resolution board cameras, high-speed image acquisition Boards, image processing control modules, etc., optimize the calibration process, and propose a space circle fitting method for the hand-eye calibration of the standard ball, so that the light plane can be any plane equation, improve the calibration accuracy of the standard ball's eye, and expand the adaptability of structural parts. Large and complex components can be reconstructed in multiple formats in coordination with multi-module 3D imaging, and then multi-view stitching can be performed to obtain a panoramic appearance.

Specifically, according to the operation steps in step 4, 180 or 360 attitude data are compiled into the direction of the line segment formed by the two welding wires of the TCP and stored in the database. The welding torch pose generates the welding trajectory.

Specifically, according to the operation steps in step 5, the welding process adopts an adaptive laser sensor to process high-resolution full-frame images and weld seam tracking, and the SLPr tracking system adopts the latest smart sensor, which integrates a megapixel high-resolution sensor. The high-speed camera, unique automatic laser control and special optical system ensure the high quality and stability of the generated welding seam laser fringe image, and the special digital image processing software and hardware inside the sensor ensures high-speed image processing and welding seam tracking.

The above are only the preferred embodiments of the present invention. It should be pointed out that for those of ordinary skill in the art, some modifications and improvements can be made without departing from the inventive concept of the present invention, which all belong to the present invention. protected range.

Claims (10)

1. A high-efficiency twin-wire welding path generation system, characterized in that, comprising: Weld seam identification, extraction and library adjustment module (1), the vision system sequentially performs visual sensing detection on the workpiece, obtains image information, extracts weld seam features, searches the database, and calls the weld seam model with the highest similarity and related welding process data; The weld model knowledge base and the welding process database (2), the weld model knowledge base and the welding process database (2) include: the weld knowledge base and the assembly weld function process database; Welding seam intelligent welding trajectory path and attitude planning module (3), after workpiece identification and welding seam trajectory extraction, based on the extracted welding seam trajectory, the robot welding path and welding torch posture are planned; Robot welding program automatic generation and simulation release module (4), robot welding program automatic generation and simulation release module (4) After forming a "robot welding series (or a complete) program", the system converts the program to form a robot executable. "Robot running program", and verify the accessibility and collision avoidance of the robot in the background; Signal connection between the weld seam identification, extraction and library adjustment module (1), the weld seam model knowledge base and the welding process database (2), and the weld seam identification, extraction and library adjustment module (1) and the weld seam intelligent welding track The signal connection between the path and attitude planning modules (3), the bidirectional signal connection between the welding process database (2) and the welding seam intelligent welding trajectory path and attitude planning module (3), the automatic generation of the robot welding program and the simulation release module (4) Signal connection with the intelligent welding track path and attitude planning module (3) of the welding seam. 2 . The high-efficiency twin-wire welding path generation system according to claim 1 , wherein the welding seam identification, extraction and library adjustment module (1) sequentially performs visual sensing detection on the workpiece based on a vision system, and obtains an image. 3 . information, extract weld features, search the database, call the most similar weld model and related welding process data, at the same time, extract the weld outline image and weld trajectory, compare and verify with the data called the database, and confirm the weld seam welded by the robot trajectory. 3. A high-efficiency twin-wire welding path generation system according to claim 1, characterized in that: the weld model knowledge base and the welding process database (2) also have the ability to import, create, store and manage all three-dimensional weld seams Model or weld rules, the best welding procedures for various welds verified by batch production, welding procedures that have been designed or verified by tests but not verified by batch production, etc., as well as data such as welding design rules for assembled welds ; This database module transforms the product model through an algorithm and performs parameterized management, which is used as the basis for the visual scanning and recognition system to effectively compare and analyze the actual workpiece and the workpiece model data in the later stage, and is also the basis for all trajectory, attitude, and path planning software. 4. A high-efficiency twin-wire welding path generation system according to claim 1, wherein the intelligent welding track and attitude planning module (3) for the welding seam is also used to combine the fetched welding process, according to the database According to the "welding process" level, the welding process and parameters of each weld are designed according to the data and model-driven method, and a series of robot welding programs are formed. 5. a kind of high-efficiency twin-wire welding path generation system according to claim 1, is characterized in that: described robot welding program automatic generation and simulation release module (4) is also used for pushing "robot operation program" to each The robot controller, which forms the robot program that will be executed. 6. A path generation method for a high-efficiency twin-wire welding path generation system, characterized in that, applied to the high-efficiency twin-wire welding path generation system described in any one of claims 1-5, comprising the following steps: S1. First, use the weld seam identification, extraction and library adjustment module (1) to determine the path of the weld seam, and then interact with the extracted data with the weld seam model knowledge base and the welding process database (2) to obtain the best welding process and weld model; S2. Send the welding process and the weld model data to the intelligent welding trajectory path and attitude planning module (3). After workpiece identification and weld trajectory extraction, the extracted weld trajectory is used as the planning basis to plan the robot welding path and trajectory. Welding gun attitude; S3. According to the data and model-driven method, design the welding process and parameters of each weld, and form a series of robot welding programs; S4, sending the path data planned by the intelligent welding trajectory path and attitude planning module (3) of the welding seam to the robot welding program automatic generation and simulation release module (4), to carry out data simulation simulation, and to send the data after passing the test; S5. Push the "robot running program" to each robot controller to form a robot program to be executed, and finally carry out the welding process. 7. The path generation method of a high-efficiency twin-wire welding path generation system according to claim 6, characterized in that it comprises the following steps: according to the operation steps in S1, the weld seam identification extraction and library adjustment module (1 ), the welding seam trajectory obtained by visual recognition becomes the motion trajectory of the welding torch. In addition to special execution software, it is also necessary to integrate the vision system, the robot external axis, and the robot TCP (the end of the welding torch) into a common coordinate system, forming a whole. 8. The path generation method of a high-efficiency twin-wire welding path generation system according to claim 6, characterized in that it comprises the following steps: according to the operation steps in S2, the weld seam identification extraction and library adjustment module (1 ) The stereo vision measurement and recognition module based on hand-eye calibration is the basis of high-precision 3D measurement. The modules mainly include high-resolution board cameras, high-speed image acquisition boards, image processing control modules, etc., optimize the calibration process, and propose a space circle fitting method Carry out the hand-eye calibration of the standard ball, so that the light plane can be any plane equation, improve the accuracy of the standard ball's hand-eye calibration, and expand the adaptability of the structure. Multi-view stitching can get panoramic appearance. 9 . The path generation method of a high-efficiency twin-wire welding path generation system according to claim 6 , comprising the following steps: according to the operation steps in S4 , the direction of the line segment formed by the two welding wires of the TCP is compiled. 10 . 180 or 360 attitude data are stored in the database. When the intelligent welding trajectory path attitude planning module (3) is executed, the optimal welding torch attitude is automatically matched according to the algorithm to generate the welding trajectory. 10. The path generation method of a high-efficiency twin-wire welding path generation system according to claim 6, characterized in that it comprises the following steps: according to the operation steps in S5, the welding process adopts an adaptive laser sensor to Resolution full frame image processing and seam tracking.

Images