Method for automatically creating robot program based on three-dimensional model

Abstract

The invention provides a method for automatically creating a robot program based on a three-dimensional model, which comprises the following steps of: correcting a hydraulic support three-dimensional model design BOM structure model into a process-level manufacturing BOM structure model, and constraining a welding robot positioner model according to an actual welding state and the process-level manufacturing BOM structure model; reading component basic information of a process-level manufacturing BOM structure model, and combining the identified weld form information, geometric constraint information and component model features into an information set based on a typical welding joint form knowledge base; on the basis of the identified information set, welding process parameters are defined, and welding process parameters corresponding to different welding seams are determined; according to the welding process parameters, welding seam sequence information necessary for a welding procedure is constructed; the motion trail of the welding robot is autonomously planned based on the welding seam sequence information, and welding gun pose information is iteratively optimized through kinematics solution and a collision detection algorithm; and generating a welding control program which can be recognized by the welding robot.

Description

Technical Field

[0001] The invention belongs to the technical field of welding process design, and in particular relates to a method for automatically creating a robot program based on a three-dimensional model. Background Art

[0002] As one of the key equipment in the comprehensive mining working face of coal mines, the hydraulic support has a large amount of welding work for its main steel structure parts. The industry usually adopts robot welding to produce it, but its products are highly customized and the production method belongs to typical discrete manufacturing. This puts higher requirements on the high-quality and efficient delivery of welding robot programs. It is urgent to explore a new method for creating welding robot programs.

[0003] The Chinese invention patent application with application number 202210858423.1, titled "An efficient dual-wire welding path generation system and path generation method", and publication date September 20, 2022, discloses the following scheme: The invention is based on a visual system to sequentially perform visual sensing detection on the workpiece, obtain image information, extract weld features, search the database, and call the weld model with the highest similarity and related welding process data. After workpiece identification and weld trajectory extraction, the extracted weld trajectory is used as the planning basis to plan the robot welding path and welding gun posture, realize the automatic generation of the robot welding program, form a "robot operation program" executable by the robot, and verify the robot's accessibility and anti-collision performance in the background.

[0004] Although this solution can automatically create a "robot running program" executable by the robot, it has the following three shortcomings: 1. This solution uses a machine vision recognition mode, and the hardware investment cost is high; 2. The main structural parts of the hydraulic support are usually box-type structural design patterns, and machine vision recognition has blind spots; 3. The accuracy of machine vision recognition is greatly affected by the production environment and assembly quality.

[0005] With the continuous development of the coal machinery industry, traditional robot program creation methods such as "on-site teaching" and "manual offline programming" have become bottlenecks restricting production efficiency. The increasing maturity of the digital factory concept supported by the integrated design and manufacturing solution of hydraulic support structural parts, as well as the increasing maturity of MBD (Model Based Definition) technology using 3D models as the only data source, make it possible to automatically create welding robot programs. Summary of the invention

[0006] The purpose of the present invention is to solve the problem of inefficiency of traditional robot program creation methods and to provide a method for automatically creating robot programs based on three-dimensional models, which can greatly shorten the robot program preparation time.

[0007] In a first aspect, the present invention provides a method for automatically creating a robot program based on a three-dimensional model, which is used in three-dimensional design software and includes the following steps: Step 1: Correct the BOM structure model of the hydraulic support 3D model design to the process-level manufacturing BOM structure model that conforms to the actual production on site, and constrain the welding robot positioner model according to the actual welding state and the process-level manufacturing BOM structure model; Step 2: Read the basic information of the components, weld shape information, geometric constraint information and component model features of the process-level manufacturing BOM structure model, and combine the identified weld shape information, geometric constraint information and component model features into an information set based on the typical welding joint form knowledge base; Step 3: Based on the identified information set, define the welding process parameters and determine the welding process parameters corresponding to different welds; Step 4: Based on the basic information of the parts and components of the process-level manufacturing BOM structure model and the defined welding process parameters, the weld sequence information including the initial point information and initial gun posture information required for the welding procedure is constructed; Step 5: Autonomously plan the motion trajectory of the welding robot based on the weld sequence information, and iteratively optimize the welding gun posture information through kinematic solution and collision detection algorithm; Step 6: Combine the welding robot programming specifications to generate a welding control program that the welding robot can recognize.

[0008] Based on the above, the method of correcting the hydraulic support three-dimensional model design BOM structure model to a process-level manufacturing BOM structure model that conforms to the actual on-site production is: after saving the hydraulic support three-dimensional model design BOM structure model as a design model, add tooling models including support models and fixture models according to the actual on-site production process requirements.

[0009] Based on the above, the method of constraining the welding robot positioner model according to the actual welding state and the process-level manufacturing BOM structure model is as follows: According to the different welding states of the workpiece, the process-level manufacturing BOM structure model is constrained according to the actual clamping position and the clamping mechanism of the welding robot positioner model.

[0010] Based on the above, in step 2: The basic information of the parts includes the name of the parts, the dimensions of the parts, the coordinate information of the parts' location in the assembly, and the topological information of the parts' surroundings; The knowledge base of typical welding joint forms includes plate lap joint, plate butt joint, plate T joint, plate corner joint and plate scarf joint; Weld shape information includes weld type, joint form, parent material, and component name; Geometric constraint information includes the lap groove weld angle formed between the part and its surrounding parts; Component model features include chamfer features, fillet features, and groove features; The information set is presented in a table, where different columns represent condition categories and different rows represent all possible situations for each condition category, thus forming an information set.

[0011] Based on the above, in step 3, based on the identified information set, the welding process parameters are defined, including: matching welds according to the conditions listed in the information set, and clarifying the process parameter information required for various types of welding including current, voltage, and layer arrangement for each weld.

[0012] Based on the above, the construction of the initial point information includes point type, point quantity and point coordinates; among them, the point type and point quantity are determined according to the identified weld trajectory according to the requirements of different weld text standards, and the point coordinates are determined according to the position coordinate information of the point in the process-level manufacturing BOM structure model; The construction of the initial gun posture information is jointly determined by the standard values ​​of W, P, and R of the welding gun and the topological information of the welding point manufacturing BOM structure model at the process level; the gun posture judgment rule is determined by looking up the identified weld type and weld angle size in the preset project inference table, and the inference result information of the gun posture is generated according to the lookup result.

[0013] Based on the above, step 5 is: based on the automatically inferred weld sequence information including point information and gun posture information, a subroutine for each weld is generated according to the standard program text architecture of different weld types, and the subroutine is called in the main program according to the weld trajectory sequence number, so as to realize the autonomous planning of the welding robot motion trajectory; Based on the existing point coordinate values ​​and the gun posture W, P, R values, that is, the torsion angle values ​​around each axis, combined with the workstation welding robot ground track layout position information, the angles of each axis of the welding robot are solved; The lightweight envelope model of each axis of the welding robot is loaded into the 3D design software and assembled in sequence according to the angles solved at each point. The interference detection function of the 3D design software is used to perform interference detection between the axis models of the welding robot and the structural parts. The gun posture WPR torsion angle is corrected according to the adjustment range specified in the process standard, the new angles of each axis of the welding robot are calculated, and the collision detection interface is called again to check the interference. If a collision exists, the above operations are repeated until there is no collision, thereby optimizing the welding gun posture information.

[0014] In a second aspect, the present invention provides a system for automatically creating a robot program based on a three-dimensional model, comprising: The reconstruction and constraint module is used to modify the hydraulic support three-dimensional model design BOM structure model to a process-level manufacturing BOM structure model that conforms to the actual production on site, and constrain the welding robot positioner model according to the actual welding state and the process-level manufacturing BOM structure model; The information collection module is used to read the basic information of parts, weld shape information, geometric constraint information and part model features of the process-level manufacturing BOM structure model, and combine the identified weld shape information, geometric constraint information and part model features into an information collection based on the typical welding joint form knowledge base; A process parameter determination module is used to define welding process parameters based on the identified information set and determine the welding process parameters corresponding to different welds; The welding procedure initial information construction module is used to construct the weld sequence information including initial point information and initial gun posture information required for the welding procedure based on the basic information of the parts and components of the process-level manufacturing BOM structure model and the defined welding process parameters; The welding gun posture information optimization module is used to autonomously plan the motion trajectory of the welding robot based on the weld sequence information, and iteratively optimize the welding gun posture information through kinematic solution and collision detection algorithm; The welding program output module is used to generate a welding control program that can be recognized by the welding robot in combination with the welding robot programming specifications.

[0015] In a third aspect, the present invention provides a computer device, comprising: one or more processors; a memory for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors are caused to perform the steps of the method for automatically creating a robot program based on a three-dimensional model.

[0016] In a fourth aspect, the present invention provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the method for automatically creating a robot program based on a three-dimensional model as described above.

[0017] Compared with the prior art, the present invention has outstanding substantive features and significant progress, specifically: 1. The present invention designs the BOM structure model based on the three-dimensional model of the hydraulic support, and automatically generates the robot program by constructing and calling the structured process database, etc., thereby ensuring that the quality of the welding program is not affected by the skill level of the personnel, and improving the accuracy and consistency of the welding program; 2. When preparing the welding procedure of the present invention, it takes 20 minutes to build the manufacturing BOM structure, 20 minutes to run the software to generate the program, and 20 minutes to check the generated results, which is shortened from the original 2 days to less than 1 hour, greatly improving the efficiency of technical data preparation; 3. The entire 3D model process from model creation to welding manufacturing of technical data has been realized. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 It is a three-dimensional assembly model diagram of the hydraulic support structural parts (taking the top beam model as an example) and the welding robot positioner. DETAILED DESCRIPTION

[0019] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0020] The standard values ​​of W, P, and R of the welding gun refer to the rotation angle of the rectangular coordinate system on the tool side around the relative X-axis, Y-axis, and Z-axis of the rectangular coordinate system in space in the rectangular coordinate system, that is, the value specification of the torsion angle around each axis. W, P, and R are mature standard definitions for robots.

[0021] Example 1 This embodiment proposes a method for automatically creating a robot program based on a three-dimensional model, which is used in three-dimensional design software such as CAD, and includes the following steps: Step 1: Modify the hydraulic support three-dimensional model design BOM structure model to conform to the process-level manufacturing BOM structure model of actual on-site production, and constrain the welding robot positioner model according to the actual welding state and the process-level manufacturing BOM structure model.

[0022] The method of correcting the hydraulic support three-dimensional model design BOM structure model to the process-level manufacturing BOM structure model that conforms to the actual production on site is as follows: after saving the hydraulic support three-dimensional model design BOM structure model as a design model, add tooling models including support models and fixture models according to the process requirements of the actual production on site. The process-level manufacturing BOM structure model is a manufacturing BOM structure model that can ensure production quality after adding tooling models such as support and fixtures to the hydraulic support three-dimensional model design BOM structure model according to the process standards.

[0023] Figure 1The 3D assembly model diagram of the hydraulic support structure (taking the top beam model as an example) and the welding robot positioner is shown. The method of constraining the welding robot positioner model according to the actual welding state and the process-level manufacturing BOM structure model is as follows: according to the different welding states of the workpiece, the process-level manufacturing BOM structure model is constrained according to the actual clamping position and the clamping mechanism such as the clamp of the welding robot positioner model.

[0024] Step 2: Read the basic information of parts, weld shape information, geometric constraint information and part model features of the process-level manufacturing BOM structure model; Based on the typical welding joint form knowledge base, the identified weld morphology information, geometric constraint information, and component model features are combined into an information set.

[0025] The basic information of the parts includes the name of the parts, the dimensions of the parts, the coordinate information of the parts' location in the assembly, and the topological information of the parts' surroundings; Weld shape information includes weld type, joint form, parent material, and component name; Geometric constraint information includes the lap groove weld angle formed between the part and its surrounding parts; Component model features include chamfer features, fillet features, and groove features.

[0026] The knowledge base of typical welding joint forms includes plate lap joints, plate butt joints, plate T-joints, plate corner joints and plate miter joints; an example of the structure of the knowledge base of typical welding joint forms is shown in Table 1 below.

[0027] Table 1 Typical welding joint form knowledge base sample table

[0028] The information set is presented in a table. Different columns in the table represent condition categories, and different rows represent all possible situations of each condition category. This combination forms an information set, as shown in Table 2. The specific information set sample table is shown in Table 3.

[0029] Table 2 Information collection sample table Serial number Condition 1 Condition 2 …… Output 1 Condition 1 Possible Situation 1 Condition 2 Possible Situation 1 …… Result 1 2 Condition 1 Possible situation 2 Condition 2 Possible Situation 2 …… Result 2 Table 3 Specific information set sample table Serial number Base material 1 name Base material 2 name Connector Type Welding seam form Welding position …… Weld code 1 Main reinforcement roof Plate T-joint Double-sided fillet weld Flat fillet welding …… JH_PB_1 2 …… …… …… …… …… …… …… Step 3: Based on the identified information set, define the welding process parameters and determine the welding process parameters corresponding to different welds.

[0030] Based on the identified information set, the definition of welding process parameters includes: matching welds according to the conditions listed in the information set, and clarifying the process parameter information required for various types of welding including current, voltage, and layer arrangement for each weld, as shown in Table 4.

[0031] Table 4 Process parameter definition sample table Serial number Weld code Welding angle size Number of weld layers Root welding current Root welding voltage …… Welding swing Dwell time 1 JH_PB_1 16 1 / 3 …… …… …… …… …… 2 …… …… …… …… …… …… …… …… Step 4: Based on the basic information of the components of the process-level manufacturing BOM structure model and the defined welding process parameters, construct the weld sequence information including the initial point information and initial gun posture information required for the welding procedure.

[0032] The construction of initial point information includes point type, point quantity and point coordinates; among them, the point type and point quantity are clarified according to the identified weld trajectory (weld trajectory, that is, the direction and shape of the weld, common direction shapes of welds include "straight line", "broken line", "arc", etc.) in accordance with different weld text standard requirements. For example, a straight line trajectory adds three points: "starting point", "middle point" and "end point"; an arc trajectory adds three points: "starting point", "passing point" and "end point"; the point coordinates are determined according to the position coordinate information of the point in the process-level manufacturing BOM structure model.

[0033] The construction of the initial gun posture information is jointly determined by the standard values ​​of the welding gun W, P, and R and the topological information of the welding point manufacturing BOM structure model at the process level. For example, the P value of the welding gun for the groove weld should divide the groove angle equally; the gun posture judgment rule is to look up the recognized weld type and weld angle size in the preset project reasoning table (the specific form is shown in Table 5), and generate the reasoning result information of the gun posture according to the lookup result. The lookup process locates according to the condition type of the column data and the weld information of the row data, and matches the result value of this item.

[0034] Table 5 Gun posture project reasoning example table Serial number Weld Type Model structure characteristics …… Welding gun W value Welding gun P value Welding gun R value 1 Fillet weld Open Architecture …… …… …… …… 2 …… …… …… …… …… …… Step 5: Autonomously plan the motion trajectory of the welding robot based on the weld sequence information, and iteratively optimize the welding gun posture information through kinematic solution and collision detection algorithm.

[0035] Step 5 is as follows: based on the automatically inferred weld sequence information including point information and gun posture information, a subroutine for each weld is generated according to the standard program text structure of different weld types, and the subroutine is called in the main program according to the weld trajectory sequence (the trajectory sequence refers to the welding sequence of different trajectories), so as to realize the autonomous planning of the motion trajectory of the welding robot; Based on the existing point coordinate values ​​and the gun posture W, P, R values, that is, the torsion angle values ​​around each axis, combined with the workstation welding robot ground track layout position information, the angles of each axis of the welding robot are solved; The lightweight envelope model of each axis of the welding robot is loaded into the 3D design software and assembled in sequence according to the angles solved at each point. The interference detection function of the 3D design software is used to perform interference detection between the axis models of the welding robot and the structural parts. The gun posture WPR torsion angle is corrected according to the adjustment range specified in the process standard, the new angles of each axis of the welding robot are calculated, and the collision detection interface of the 3D design software is called again to check the interference. If a collision exists, the above operations are repeated until there is no collision, thereby optimizing the welding gun posture information.

[0036] Step 6: Combine the welding robot programming specifications to generate a welding control program that the welding robot can recognize.

[0037] In other exemplary embodiments, the welding control program can be transmitted to a simulation platform that matches the welding robot; through simulation verification, the trajectory can be reviewed by integrating manual experience, and the program generation rules (including point positions, gun postures, etc.) can be corrected to obtain the optimal trajectory operation program of the welding robot. After the rules are stable, the manual review link can be removed.

[0038] Example 2 Based on the same inventive concept, the embodiment of the present application also provides a system for automatically creating robot programs based on three-dimensional models. The implementation solution provided by the system for automatically creating robot programs based on three-dimensional models is similar to the implementation solution described in the method of Example 1, so the specific limitations in one or more embodiments of the system for automatically creating robot programs based on three-dimensional models provided below can refer to the limitations on the method in Example 1, and will not be repeated here.

[0039] In an exemplary embodiment, a system for automatically creating a robot program based on a three-dimensional model is provided, comprising: The reconstruction and constraint module is used to modify the hydraulic support three-dimensional model design BOM structure model to a process-level manufacturing BOM structure model that conforms to the actual production on site, and constrain the welding robot positioner model according to the actual welding state and the process-level manufacturing BOM structure model; The information collection module is used to read the basic information of parts, weld shape information, geometric constraint information and part model features of the process-level manufacturing BOM structure model, and combine the identified weld shape information, geometric constraint information and part model features into an information collection based on the typical welding joint form knowledge base; A process parameter determination module is used to define welding process parameters based on the identified information set and determine the welding process parameters corresponding to different welds; The welding procedure initial information construction module is used to construct the weld sequence information including initial point information and initial gun posture information required for the welding procedure based on the basic information of the parts and components of the process-level manufacturing BOM structure model and the defined welding process parameters; The welding gun posture information optimization module is used to autonomously plan the motion trajectory of the welding robot based on the weld sequence information, and iteratively optimize the welding gun posture information through kinematic solution and collision detection algorithm; The welding program output module is used to generate a welding control program that can be recognized by the welding robot in combination with the welding robot programming specifications.

[0040] Example 3 Each module in the above system can be implemented in whole or in part by software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each module above.

[0041] In an exemplary embodiment, a computer device is provided, which may be a terminal. The computer device further includes a processor, a memory, an input / output interface, a communication interface, a display unit, and an input device. The processor, the memory, and the input / output interface are connected via a system bus, and the communication interface, the display unit, and the input device are connected to the system bus via 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 and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. 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 in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, the steps of the method for automatically creating a robot program based on a three-dimensional model are implemented. The display unit of the computer device is used to form a visually visible picture, which may be a display screen, a projection device, or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.

[0042] Those skilled in the art will appreciate that the structure of the above-mentioned computer device is only a partial 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, or combine certain components, or have a different arrangement of components.

[0043] In an exemplary embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of a method for automatically creating a robot program based on a three-dimensional model are implemented.

[0044] Those skilled 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 this 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), magnetoresistive 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. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0045] 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.

[0046] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A method for automatically creating a robot program based on a three-dimensional model, used in three-dimensional design software, characterized in that: The following steps are involved: Step 1: Correct the BOM structure model of the hydraulic support 3D model design to the process-level manufacturing BOM structure model that conforms to the actual production on site, and constrain the welding robot positioner model according to the actual welding state and the process-level manufacturing BOM structure model; Step 2: Read the basic information of the components, weld shape information, geometric constraint information and component model features of the process-level manufacturing BOM structure model, and combine the identified weld shape information, geometric constraint information and component model features into an information set based on the typical welding joint form knowledge base; Step 3: Based on the identified information set, define the welding process parameters and determine the welding process parameters corresponding to different welds; Step 4: Based on the basic information of the parts and components of the process-level manufacturing BOM structure model and the defined welding process parameters, the weld sequence information including the initial point information and initial gun posture information required for the welding procedure is constructed; Step 5: Autonomously plan the motion trajectory of the welding robot based on the weld sequence information, and iteratively optimize the welding gun posture information through kinematic solution and collision detection algorithm; Step 6: Combine the welding robot programming specifications to generate a welding control program that the welding robot can recognize.

2. The method for automatically creating a robot program based on a three-dimensional model according to claim 1, characterized in that: The method for correcting the hydraulic support three-dimensional model design BOM structure model to a process-level manufacturing BOM structure model that conforms to the actual on-site production is as follows: after saving the hydraulic support three-dimensional model design BOM structure model as a design model, add tooling models including support models and fixture models according to the actual on-site production process requirements.

3. The method for automatically creating a robot program based on a three-dimensional model according to claim 1, characterized in that: The method of constraining the welding robot positioner model according to the actual welding state and the process-level manufacturing BOM structure model is: According to the different welding states of the workpiece, the process-level manufacturing BOM structure model is constrained according to the actual clamping position and the clamping mechanism of the welding robot positioner model.

4. The method for automatically creating a robot program based on a three-dimensional model according to any one of claims 1 to 3, characterized in that: In step 2: The basic information of the parts includes the name of the parts, the dimensions of the parts, the coordinate information of the parts' location in the assembly, and the topological information of the parts' surroundings; The knowledge base of typical welding joint forms includes plate lap joint, plate butt joint, plate T joint, plate corner joint and plate scarf joint; Weld shape information includes weld type, joint form, parent material, and component name; Geometric constraint information includes the lap groove weld angle formed between the part and its surrounding parts; Component model features include chamfer features, fillet features, and groove features; The information set is presented in a table, where different columns represent condition categories and different rows represent all possible situations for each condition category, thus forming an information set.

5. The method for automatically creating a robot program based on a three-dimensional model according to claim 4, characterized in that: In step 3, based on the identified information set, the welding process parameters are defined, including: matching welds according to the conditions listed in the information set, and clarifying the process parameter information required for various types of welding, including current, voltage, and layer arrangement for each weld.

6. The method for automatically creating a robot program based on a three-dimensional model according to claim 4, characterized in that: The construction of the initial point information includes point type, point quantity and point coordinates; among them, the point type and point quantity are determined according to the identified weld trajectory and the requirements of different weld text standards, and the point coordinates are determined according to the position coordinate information of the point in the process-level manufacturing BOM structure model; The construction of the initial gun posture information is jointly determined by the standard values ​​of W, P, and R of the welding gun and the topological information of the welding point manufacturing BOM structure model at the process level; the gun posture judgment rule is determined by looking up the identified weld type and weld angle size in the preset project inference table, and the inference result information of the gun posture is generated according to the lookup result.

7. The method for automatically creating a robot program based on a three-dimensional model according to claim 6, characterized in that: Step 5 is: based on the automatically inferred weld sequence information including point information and gun posture information, a subroutine for each weld is generated according to the standard program text structure of different weld types, and the subroutine is called in the main program according to the weld trajectory sequence number, so as to realize the autonomous planning of the welding robot motion trajectory; Based on the existing point coordinate values ​​and the gun posture W, P, R values, that is, the torsion angle values ​​around each axis, combined with the workstation welding robot ground track layout position information, the angles of each axis of the welding robot are solved; The lightweight envelope model of each axis of the welding robot is loaded into the 3D design software and assembled in sequence according to the angles solved at each point. The interference detection function of the 3D design software is used to perform interference detection between the axis models of the welding robot and the structural parts. The gun posture WPR torsion angle is corrected according to the adjustment range specified in the process standard, the new angles of each axis of the welding robot are calculated, and the collision detection interface is called again to check the interference. If a collision exists, the above operations are repeated until there is no collision, thereby optimizing the welding gun posture information.

8. A system for automatically creating robot programs based on three-dimensional models, characterized in that: include: The reconstruction and constraint module is used to modify the hydraulic support three-dimensional model design BOM structure model to a process-level manufacturing BOM structure model that conforms to the actual production on site, and constrain the welding robot positioner model according to the actual welding state and the process-level manufacturing BOM structure model; The information collection module is used to read the basic information of parts, weld shape information, geometric constraint information and part model features of the process-level manufacturing BOM structure model, and combine the identified weld shape information, geometric constraint information and part model features into an information collection based on the typical welding joint form knowledge base; A process parameter determination module is used to define welding process parameters based on the identified information set and determine the welding process parameters corresponding to different welds; The welding procedure initial information construction module is used to construct the weld sequence information including initial point information and initial gun posture information required for the welding procedure based on the basic information of the parts and components of the process-level manufacturing BOM structure model and the defined welding process parameters; The welding gun posture information optimization module is used to autonomously plan the motion trajectory of the welding robot based on the weld sequence information, and iteratively optimize the welding gun posture information through kinematic solution and collision detection algorithm; The welding program output module is used to generate a welding control program that can be recognized by the welding robot in combination with the welding robot programming specifications.

9. A computer device, characterized in that: include: one or more processors; a memory for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors execute the steps of the method for automatically creating a robot program based on a three-dimensional model as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that: When the program is executed by a processor, the steps of the method for automatically creating a robot program based on a three-dimensional model as described in any one of claims 1 to 7 are implemented.

Images