Welded joint process parameter optimization system and method

Abstract

The invention belongs to the field of robot welding process planning, and discloses a welding joint process parameter optimization system and method, and the system comprises a welding system, a robot system and a computer control system; a welding power source in the welding system communicates with a robot controller in the robot system through a Device Net communication protocol, and a welding gun in the welding system is installed at the tail end of a six-axis mechanical arm. The robot controller sends a welding instruction through a Device Net communication protocol and monitors welding process parameters in the welding process at the same time; an upper computer in the computer control system serves as top equipment for operators to control the whole welding experiment equipment, communicates with the robot controller through the Ethernet, sends a welding task, controls the welding process and receives the welding state. The problems that the welding preparation work is complex, and the quality of a welding joint seriously depends on the experience of welding operators are solved, and the intelligent degree of robot welding is further improved.

Description

Technical Field

[0001] The present invention relates to the field of robot welding process planning, and in particular to a welding joint process parameter optimization system and method. Background Art

[0002] Robotic welding has the advantages of high degree of automation, stable quality of welded joints, and low labor intensity of welding operators. It is widely used in various fields of industrial manufacturing. However, before the welding robot performs the welding operation, the operator needs to formulate the welding process according to the welding requirements and welding scenarios. The welding preparation work is complicated and the quality of the welded joints is heavily dependent on the experience of the welding operator. At the same time, different application scenarios require welded joints to reach different quality levels. Without considering the application scenarios and quality level requirements, blindly using the optimal parameters will inevitably reduce production efficiency and cause a certain amount of resource waste. Therefore, it is particularly important to select welding parameters according to different application scenarios and the quality level required to be achieved.

[0003] The welding current, welding speed, welding gun inclination and nozzle height determine the quality of the welded joint. In order to obtain the process parameters of the required quality level, in previous engineering practices, a long period of trial production of welded parts is often used to find a combination of process parameters that meet the requirements. However, in the process of finding the optimal process parameters, there are conflicts between multiple goals, which increases the difficulty of finding suitable process parameters and wastes resources and man-hours.

[0004] "A system and method for intelligent planning of multi-layer and multi-pass GMAW welding process for thick plate V-groove", publication number: CN202410625562.9, the system establishes a basic process parameter set for medium and thick plate welds, and uses a long short-term memory deep network model (LSTM) to establish a relationship model between welding process parameters and weld formation dimensions, and realizes the prediction of welding process parameters based on weld formation dimensions. A line laser visual sensor device is used to obtain the image of the weld V-groove. After one layer of welding is completed, the groove is scanned again, the next layer of process is planned, and then welding is performed until the multi-layer and multi-pass welding of the thick plate V-groove is completed. However, the system only uses the wire feeding speed and welding speed as the output of the welding intelligent process planning, and the output parameters of the welding intelligent process planning are relatively few. Summary of the invention

[0005] In order to solve the above technical problems, the present invention provides a welding joint process parameter optimization system and method, which performs intelligent process planning through welding material information, geometric information and welding quality grade information input by the user, while reducing the dependence on welding operators, improving the intelligence level of robotized welding, manufacturing welding joints of different quality grades, and realizing robotized welding intelligent process planning. At the same time, in order to find process parameters suitable for different application scenarios and reduce the waste of resources and man-hours, the present invention adopts an improved multi-objective gray wolf optimization algorithm to solve the optimal welding process parameters. This method has strong convergence performance, simple structure and less parameter adjustment requirements, and is easy to implement.

[0006] The present invention provides a welding joint process parameter optimization system, the system comprising: a welding system, a robot system and a computer control system;

[0007] The welding system includes: welding power supply, welding gun and welding workbench; the robot system includes: robot controller, six-axis robot arm; the computer control system includes: host computer;

[0008] In the welding system, the welding power source and the robot controller communicate using the Device Net communication protocol, and the welding gun is installed at the end of the six-axis robotic arm; the robot controller sends welding instructions through the Device Net communication protocol and monitors the welding process parameters during the welding process; the host computer serves as the top-level device for the operator to control the entire welding experimental equipment, and communicates with the robot controller through Ethernet to send welding tasks, control the welding process, and receive welding status.

[0009] Preferably, the human-machine interaction interface of the host computer includes: a welding material information area, a welding process parameter area and a robot control area.

[0010] Preferably, in the welding material information area, the welding operator inputs welding material information, geometry information and welding quality grade information;

[0011] Among them, the operator selects the material information of the workpiece to be welded in the material information; inputs the thickness of the workpiece to be welded in the geometry information; and selects the welding quality grade according to the application scenario of the welding workpiece in the quality grade information;

[0012] Among them, welding quality grades include:

[0013] ,

[0014] ,

[0015] ,

[0016] in, Indicates the depth of penetration, Indicates the weld reinforcement on the parent material surface. Indicates the weld undercut height, Indicates the weld width. Indicates the back weld width of the weld joint. Indicates the weld toe angle, is the thickness of the workpiece being welded, Indicates the incomplete penetration height or the weld excess height on the lower surface of the parent material.

[0017] Preferably, the welding parameters involved in the welding process parameter area include welding current, welding speed, welding gun inclination angle and nozzle height, and the improved multi-objective gray wolf optimization algorithm is used to calculate the optimal welding process parameters according to the information input by the welding operator;

[0018] Among them, the improved multi-objective gray wolf optimization algorithm is used to calculate the optimal welding process parameters according to the information input by the welding operator, including:

[0019] Step 1: Initialize the gray wolf population parameters, including population size and convergence coefficient vector and And the total number of iterations ;

[0020] Step 2: Use chaos algorithm to randomly initialize the positions of individual wolves;

[0021] Step 3: Calculate the fitness value of each wolf and divide the wolf pack into , , and Four levels, updated 3 wolf leaders , , Location , , ;

[0022] Step 4: According to the three wolf leaders , , Location , , right The wolf position is updated;

[0023] Step 5: According to and Convergence coefficient vector and And the linear decreasing component Update, where and for A random number between

[0024] Step 6: Calculate the fitness of all wolves;

[0025] Step 7: 3 wolf leaders , , Location , , Make updates;

[0026] Step 8: Determine whether the iteration termination condition is met. If the condition is met, end the iteration and output the optimal solution; if not, return to step 4 to continue the iteration process.

[0027] Preferably, the robot control area includes six parts: connecting the robot, disconnecting the robot, powering on the motor, powering off the motor, starting and stopping; the robot control area can realize communication with the robot controller and the operation and stopping of the intelligent process planning process.

[0028] The present invention also provides a method for optimizing process parameters of a welding joint, which is implemented by applying the aforementioned system for optimizing process parameters of a welding joint, and the method comprises:

[0029] S1: The operator turns on the host computer, robot controller and welding power supply, starts the intelligent process planning process in the host computer, and clicks on the connected robot in the robot control area;

[0030] S2: The operator measures the geometric information of the workpiece to be welded, fixes the workpiece to be welded on the welding table, and determines the starting point and end point of the weld;

[0031] S3: input welding material information, geometric information and welding quality grade information into the welding material information area of ​​the human-computer interaction interface of the intelligent process planning host computer;

[0032] S4: Click the start part in the robot control area, and the welding parameter area will display the welding current, welding speed, welding gun inclination angle and nozzle height calculated by the intelligent process planning algorithm;

[0033] S5: After obtaining the optimal process parameters corresponding to the required welding quality level, click the motor power-on button in the host computer to achieve communication with the robot controller and complete the welding operation.

[0034] Preferably, the welding quality grades include:

[0035] ,

[0036] ,

[0037] ,

[0038] in, Indicates the depth of penetration, Indicates the weld reinforcement on the parent material surface. Indicates the weld undercut height, Indicates the weld width. Indicates the back weld width of the weld joint. Indicates the weld toe angle, is the thickness of the workpiece being welded, Indicates the incomplete penetration height or the weld excess height on the lower surface of the parent material.

[0039] Preferably, obtaining the optimal process parameters corresponding to the required welding quality level includes: using an improved multi-objective Grey Wolf optimization algorithm to calculate the optimal welding process parameters according to information input by a welding operator;

[0040] Step 1: Initialize the gray wolf population parameters, including population size and convergence coefficient vector and And the total number of iterations ;

[0041] Step 2: Use chaos algorithm to randomly initialize the positions of individual wolves;

[0042] Step 3: Calculate the fitness value of each wolf and divide the wolf pack into , , and Four levels, updated 3 wolf leaders , , Location , , ;

[0043] Step 4: According to the three wolf leaders , , Location , , right The wolf position is updated;

[0044] Step 5: According to and Convergence coefficient vector and And the linear decreasing component Update, where and for A random number between

[0045] Step 6: Calculate the fitness of all wolves;

[0046] Step 7: 3 wolf leaders , , Location , , Make updates;

[0047] Step 8: Determine whether the iteration termination condition is met. If the condition is met, end the iteration and output the optimal solution; if not, return to step 4 to continue the iteration process.

[0048] Compared with the prior art, the present invention has the following beneficial effects:

[0049] The present invention proposes a welding joint process parameter optimization system and method. The present invention will automatically calculate the welding process parameters (welding current, welding speed, welding gun inclination, nozzle height) according to the welding material information, geometric information and welding quality grade information input by the operator, and guide the welding execution device to weld along the taught weld according to the calculated welding process parameters, thereby solving the problem that the welding preparation work is complicated and the quality of the welding joint is seriously dependent on the experience of the welding operator, and further improving the intelligence level of robot welding.

[0050] The present invention designs constraint conditions by considering the variation range of welding process parameters and the quality grade of welding joints, uses an improved multi-objective grey wolf optimization algorithm to optimize the welding process parameters, and selects the only optimal welding process parameter combination based on the principle of maximizing efficiency, thereby solving the problem of waste of resources and working hours when searching for the optimal welding process parameters and improving the welding efficiency of the robot. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the technical solution of the present invention, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0052] Figure 1 A schematic diagram of a welding experimental platform according to an embodiment of the present invention;

[0053] Figure 2 A schematic diagram of the human-computer interaction software interface of the intelligent process planning host computer according to an embodiment of the present invention;

[0054] Figure 3 A schematic diagram of weld size established in an embodiment of the present invention;

[0055] Figure 4 It is a flow chart of an improved multi-objective grey wolf optimization algorithm according to an embodiment of the present invention;

[0056] Figure 5 A schematic flow chart of a method for optimizing process parameters of a welding joint according to an embodiment of the present invention.

[0057] Description of the drawings: 100 - welding power source; 200 - robot controller; 300 - host computer; 400 - six-axis robot arm; 500 - welding gun; 600 - welding workbench. DETAILED DESCRIPTION

[0058] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0059] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the embodiments of the present disclosure should be understood by people with ordinary skills in the field to which the present disclosure belongs. The "first", "second" and similar words used in the embodiments of the present disclosure do not indicate any order, quantity or importance, but are only used to distinguish different components. "Including" or "comprising" and similar words mean that the elements or objects appearing before the word cover the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0060] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0061] Embodiment 1

[0062] As can be seen from the background technology,

[0063] Before the welding robot performs the welding operation, the operator needs to formulate the welding process according to the welding requirements and welding scenarios. The welding preparation work is complicated and the quality of the welded joints is heavily dependent on the experience of the welding operator. At the same time, different application scenarios require different quality levels of welded joints. Without considering the application scenarios and quality level requirements, blindly using the optimal parameters will inevitably reduce production efficiency and cause a certain waste of resources. In the process of finding the optimal process parameters, there are conflicts between multiple goals, which increases the difficulty of finding suitable process parameters and leads to waste of resources and man-hours. Therefore, it is necessary to carry out intelligent process planning based on welding material information, geometric information and welding quality level information, and solve the optimal process parameters corresponding to welded joints of different quality levels, and guide the welding actuator to weld along the taught welds, so as to reduce the dependence on experienced technical workers, improve the efficiency of welding robots, and improve the intelligence of robot welding.

[0064] like Figure 1 As shown, an embodiment of the present invention provides a welding joint process parameter optimization system, which includes a welding system, a robot system and a computer control system. The welding system includes a welding power source 100, a welding gun 500 and a welding workbench 600. The robot system includes a robot controller 200 and a six-axis robot arm 400. The computer control system includes a host computer 300. In the welding system, the welding power source 100 and the robot controller 200 communicate using the Device Net communication protocol, and the welding gun 500 is installed at the end of the six-axis robot arm 400. The robot controller 200 can send welding instructions through the Device Net communication protocol and monitor the welding process parameters of the welding process. The host computer 300 is the top-level device for the operator to control the entire welding experimental equipment, and communicates with the robot controller 200 through Ethernet to send welding tasks, control the welding process and receive welding status.

[0065] First, the operator measures the geometric information (plate thickness) of the welded workpiece, fixes the welded workpiece on the welding table 600, and teaches the starting point and end point of the weld. The welding material information, geometric information, and welding quality grade information are input into the human-computer interaction software of the intelligent process planning host computer 300 written in C++ programming language, and the welding process parameters are calculated by the intelligent process planning algorithm (improved multi-objective gray wolf optimization algorithm). At the same time, the human-computer interaction software of the host computer 300 can communicate with the robot controller 200 to realize the welding operation.

[0066] The human-computer interaction software interface of the host computer 300 is as follows Figure 2 As shown, the software interface is divided into three areas, including welding material information area, welding parameter calculation area and robot control area.

[0067] The welding material information area includes three parts: material information, geometric information, and welding quality grade. In the welding material information area, the welding operator needs to input welding material information, geometric information, and welding quality grade information. The intelligent process planning algorithm will calculate the welding process parameters based on the information input by the welding operator. In the material information, the operator selects the material information of the workpiece to be welded; in the geometric information, the thickness of the workpiece to be welded is input; in the quality grade, the operator selects the appropriate welding quality grade according to the application scenario of the welding workpiece. Figure 3 As shown in the figure, the geometric dimensions of the weld seam are established by observing the weld joint of the pre-experiment after corrosion through a microscope camera, where Indicates the depth of penetration, Indicates the weld reinforcement on the parent material surface. Indicates the weld undercut height, Indicates the weld width. Indicates the back weld width of the weld joint. Indicates the weld toe angle, Indicates the parent material, Indicates the heat affected zone. The welding quality grade is formulated as B, C, and D according to ISO5817:2023 (E): Welding - Fusion welds of steel, nickel, titanium and their alloys (except beam welding) - Defect quality grade, as shown below:

[0068]

[0069]

[0070]

[0071] in, is the thickness of the workpiece being welded, Indicates the incomplete penetration height or the weld excess height on the lower surface of the parent material. In terms of appearance requirements, the weld should be uniform, the transition between the weld and the adjacent weld and the parent material should be smooth, and the welding slag and spatter should be cleaned up. For surface quality, Class B and Class C welds shall not have defects such as cracks, weld bumps, burn-throughs, and arc pits. Class D welds shall not have surface pores, slag inclusions, arc pits, cracks, and arc scratches. At the same time, Class B welds are also required to have no undercut or incomplete welding. Among the quality grades, Class B welds have the highest quality and are suitable for critical parts or structures that bear important loads. No defects are allowed at all; Class C welds have moderate quality and are suitable for structures with high strength requirements but non-critical loads; Class D welds have the lowest quality and are suitable for auxiliary structures.

[0072] The welding process parameter area is the welding process parameter calculated based on the information input by the operator. At the same time, the parameter can also be manually set and adjusted. The welding parameters involved in the welding process parameter area include welding current (A), welding speed (m / h), welding gun inclination (°) and nozzle height (mm). The welding power supply 100 adopts a unitary control mode. During the welding process, you only need to set the welding current. The welding voltage is automatically matched according to the welding current, and the wire feeding speed is proportional to the welding current. The shielding gas flow rate remains unchanged. In order to obtain welding joints of different quality levels, after consulting the welding process manual and multiple trial weldings, considering the loss of material and to obtain a good welding joint, the weld penetration depth The maximum value can be taken, the weld reinforcement on the parent material surface The minimum value that can be taken is the weld undercut height The minimum value possible, weld toe angle The maximum value can be taken. Since there are conflicts among the multiple objectives of the appearance size of the welding joint, the improved multi-objective gray wolf optimization algorithm is used to solve the optimal welding process parameters. In order to consider the welding operation efficiency, the solution with the highest welding speed is selected as the optimal solution among many feasible solutions. The algorithm flow chart is as follows Figure 4 The specific steps are as follows:

[0073] Step 1: Initialize the gray wolf population parameters, including population size and convergence coefficient vector and And the total number of iterations :

[0074]

[0075]

[0076] in, and for A random number between is a linearly decreasing component from 2 to 0.

[0077] Step 2: Use the chaos algorithm to randomly initialize the positions of individual wolves. The formula is:

[0078]

[0079] in, is the initial value, which is between A random number between is a parameter and ,Pick , then the individual positions of the wolf pack generated have the characteristics of non-periodicity and non-convergence.

[0080] Step 3: Calculate the fitness value of each wolf and divide the wolf pack into , , and Four levels, updated 3 wolf leaders , , Location , , The formula for calculating the gray wolf's fitness is as follows:

[0081]

[0082] in, is the distance between the gray wolf and its prey, is the current prey position vector, is the current gray wolf position vector. The gray wolf position update formula is as follows:

[0083]

[0084] in, is the gray wolf’s position vector at the next moment.

[0085] Step 4: According to the three wolf leaders , , Location , , right The wolf position is updated. First define Wolf and the three alpha wolves , , The distance between , , :

[0086]

[0087] During the iteration process, Wolf is defeated by three alpha wolves , , Position influence, adjust its own position, the position adjustment formula is:

[0088]

[0089] in, , , Respectively Wolf Arrives , , Wolf position update. The wolf position adjustment formula is:

[0090]

[0091] In the original multi-objective grey wolf algorithm, The wolves will evenly move towards the three alpha wolves. , , Learn, thereby updating its position. However, the position of each wolf leader is different, and its position relationship with the actual optimal solution is also different. Therefore, in order to improve the learning efficiency of individuals, we will learn from the three wolf leaders according to their different convergence levels. First, define the three wolf leaders , , The distance to the prey is , , :

[0092]

[0093] To the three wolves , , Distance to prey , , Normalization is performed and the result is recorded as , the smaller the value, the better the convergence performance. , , The convergence index is:

[0094]

[0095] Consider three alpha wolves , , The closer the gray wolf is to the prey, the greater its role in guiding the next generation of gray wolves, which is conducive to the gray wolf pack's rapid approach to the prey. , , , calculate the duty cycle of the three alpha wolves, the calculation formula is as follows:

[0096]

[0097] When the multi-objective gray wolf optimization algorithm is initially searching for the best solution, the individual positions of the gray wolves are relatively scattered, so a faster search speed is required in the initial stage of the search. In the later stage of the search, in order to avoid the local optimum, it is necessary to reduce the search speed to ensure the search for the global optimum. When updating the wolf position, consider the three alpha wolves , , The distance from the prey, the number of iterations, and the entropy between the wolves are used to introduce the convergence coefficient vector , the convergence coefficient vector The update formula is as follows:

[0098]

[0099] in, To consider the convergence coefficient of the discrete degree between wolf individuals, the formula is as follows:

[0100]

[0101] In the formula, Indicates the current wolf pack The distance from the wolf to the prey is given by , , and composition. is the average distance between all gray wolves and their prey. It is defined by the following formula:

[0102]

[0103] but The wolf position adjustment formula is:

[0104]

[0105] Step 5: According to the formula and formula Convergence coefficient vector and And the linear decreasing component Update, where and is a random number between [0,1].

[0106] Step 6: According to the formula Calculate the fitness of all wolves.

[0107] Step 7: According to the formula To the three wolves , , Location , , to update.

[0108] Step 8: Determine whether the iteration termination condition is met. If the condition is met, end the iteration and output the optimal solution; if not, return to step 4 to continue the iteration process.

[0109] The robot control area includes six parts: connecting the robot, disconnecting the robot, powering on the motor, powering off the motor, starting the program, and stopping the program. The robot control area can realize communication with the robot controller 200 and the operation and stop of the intelligent process planning program.

[0110] Embodiment 2

[0111] like Figure 5 As shown, the present invention also provides a method for optimizing process parameters of welding joints, which is implemented by applying the aforementioned welding joint process parameter optimization system, and the method includes:

[0112] S1: The operator turns on the host computer 300, the robot controller 200 and the welding power source 100, starts the intelligent process planning process in the host computer 300, and clicks on the connected robot in the robot control area;

[0113] S2: The operator measures the geometric information of the workpiece to be welded, fixes the workpiece to be welded on the welding table 600, and determines the starting point and the end point of the weld;

[0114] S3: input welding material information, geometric information and welding quality grade information into the welding material information area in the human-computer interaction interface of the intelligent process planning host computer 300;

[0115] S4: Click the start part in the robot control area, and the welding parameter area will display the welding current, welding speed, welding gun inclination angle and nozzle height calculated by the intelligent process planning algorithm;

[0116] S5: After obtaining the optimal process parameters corresponding to the required welding quality level, click on the motor power-on button in the host computer 300 to achieve communication with the robot controller 200 and complete the welding operation.

[0117] In this embodiment, the welding quality levels include:

[0118] ,

[0119] ,

[0120] ,

[0121] in, Indicates the depth of penetration, Indicates the weld reinforcement on the parent material surface. Indicates the weld undercut height, Indicates the weld width. Indicates the back weld width of the weld joint. Indicates the weld toe angle, is the thickness of the workpiece being welded, Indicates the incomplete penetration height or the weld excess height on the lower surface of the parent material.

[0122] In this embodiment, obtaining the optimal process parameters corresponding to the required welding quality level includes: using an improved multi-objective Grey Wolf optimization algorithm to calculate the optimal welding process parameters according to information input by a welding operator;

[0123] Step 1: Initialize the gray wolf population parameters, including population size and convergence coefficient vector and And the total number of iterations ;

[0124] Step 2: Use chaos algorithm to randomly initialize the positions of individual wolves;

[0125] Step 3: Calculate the fitness value of each wolf and divide the wolf pack into , , and Four levels, updated 3 wolf leaders , , Location , , ;

[0126] Step 4: According to the three wolf leaders , , Location , , right The wolf position is updated;

[0127] Step 5: According to and Convergence coefficient vector and And the linear decreasing component Update, where and for A random number between

[0128] Step 6: Calculate the fitness of all wolves;

[0129] Step 7: 3 wolf leaders , , Location , , Make updates;

[0130] Step 8: Determine whether the iteration termination condition is met. If the condition is met, end the iteration and output the optimal solution; if not, return to step 4 to continue the iteration process.

[0131] The embodiments of the present disclosure are intended to cover all such substitutions, modifications and variations that fall within the broad scope of the appended claims. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the embodiments of the present disclosure should be included in the scope of protection of the present disclosure.

Claims

1. A welding joint process parameter optimization system, characterized in that: The system comprises: a welding system, a robot system and a computer control system; The welding system includes: welding power supply, welding gun and welding workbench; the robot system includes: robot controller, six-axis robot arm; the computer control system includes: host computer; In the welding system, the welding power source and the robot controller communicate using the Device Net communication protocol, and the welding gun is installed at the end of the six-axis robotic arm; the robot controller sends welding instructions through the Device Net communication protocol and monitors the welding process parameters during the welding process; the host computer serves as the top-level device for the operator to control the entire welding experimental equipment, and communicates with the robot controller through Ethernet to send welding tasks, control the welding process, and receive welding status.

2. The system according to claim 1, characterized in that The human-computer interaction interface of the host computer includes: welding material information area, welding process parameter area and robot control area.

3. The system according to claim 2, characterized in that In the welding material information area, the welding operator enters welding material information, geometry information, and welding quality grade information; Among them, the operator selects the material information of the workpiece to be welded in the material information; inputs the thickness of the workpiece to be welded in the geometry information; and selects the welding quality grade according to the application scenario of the welding workpiece in the quality grade information; Among them, welding quality grades include: ， ， ， in, Indicates the depth of penetration, Indicates the weld reinforcement on the parent material surface. Indicates the weld undercut height, Indicates the weld width. Indicates the back weld width of the weld joint. Indicates the weld toe angle, is the thickness of the workpiece being welded, Indicates the incomplete penetration height or the weld excess height on the lower surface of the parent material.

4. The system according to claim 3, characterized in that The welding parameters involved in the welding process parameter area include welding current, welding speed, welding gun inclination and nozzle height. The improved multi-objective Grey Wolf optimization algorithm is used to calculate the optimal welding process parameters according to the information input by the welding operator. Among them, the improved multi-objective gray wolf optimization algorithm is used to calculate the optimal welding process parameters according to the information input by the welding operator, including: Step 1: Initialize the gray wolf population parameters, including population size and convergence coefficient vector and And the total number of iterations ; Step 2: Use chaos algorithm to randomly initialize the positions of individual wolves; Step 3: Calculate the fitness value of each wolf and divide the wolf pack into , , and Four levels, updated 3 wolf leaders , , Location , , ; Step 4: According to the three wolf leaders , , Location , , right The wolf position is updated; Step 5: According to and For the convergence coefficient vector and And the linear decreasing component To update, and for A random number between Step 6: Calculate the fitness of all wolves; Step 7: 3 wolf leaders , , Location , , Make updates; Step 8: Determine whether the iteration termination condition is met. If the condition is met, end the iteration and output the optimal solution; if not, return to step 4 to continue the iteration process.

5. The system according to claim 2, characterized in that The robot control area includes six parts: connecting the robot, disconnecting the robot, powering on the motor, powering off the motor, starting and stopping. The robot control area can realize communication with the robot controller and the operation and stopping of the intelligent process planning process.

6. A method for optimizing process parameters of a welding joint, characterized in that: The method is implemented by using the welding joint process parameter optimization system according to any one of claims 1 to 5, and comprises: S1: The operator turns on the host computer, robot controller and welding power supply, starts the intelligent process planning process in the host computer, and clicks on the connected robot in the robot control area; S2: The operator measures the geometric information of the workpiece to be welded, fixes the workpiece to be welded on the welding table, and determines the starting point and end point of the weld; S3: input welding material information, geometric information and welding quality grade information into the welding material information area of ​​the human-computer interaction interface of the intelligent process planning host computer; S4: Click the start part in the robot control area, and the welding parameter area will display the welding current, welding speed, welding gun inclination angle and nozzle height calculated by the intelligent process planning algorithm; S5: After obtaining the optimal process parameters corresponding to the required welding quality level, click the motor power-on button in the host computer to achieve communication with the robot controller and complete the welding operation.

7. The method according to claim 6, characterized in that Welding quality grades include: ， ， ， in, Indicates the depth of penetration, Indicates the weld reinforcement on the parent material surface. Indicates the weld undercut height, Indicates the weld width. Indicates the back weld width of the weld joint. Indicates the weld toe angle, is the thickness of the workpiece being welded, Indicates the incomplete penetration height or the weld excess height on the lower surface of the parent material.

8. The method according to claim 6, characterized in that Obtaining the optimal process parameters corresponding to the required welding quality level includes: using an improved multi-objective Grey Wolf optimization algorithm to calculate the optimal welding process parameters based on information input by a welding operator; Step 1: Initialize the gray wolf population parameters, including population size and convergence coefficient vector and And the total number of iterations ; Step 2: Use chaos algorithm to randomly initialize the positions of individual wolves; Step 3: Calculate the fitness value of each wolf and divide the wolf pack into , , and Four levels, updated 3 wolf leaders , , Location , , ; Step 4: According to the three wolf leaders , , Location , , right The wolf position is updated; Step 5: According to and For the convergence coefficient vector and And the linear decreasing component To update, and for A random number between Step 6: Calculate the fitness of all wolves; Step 7: 3 wolf leaders , , Location , , Make updates; Step 8: Determine whether the iteration termination condition is met. If the condition is met, end the iteration and output the optimal solution; if not, return to step 4 to continue the iteration process.

Images