Welding process procedure calling system and method with welding seam contour matching function

Abstract

The invention belongs to the technical field of welding, and discloses a welding process procedure calling system and method with a welding seam contour matching function. The method comprises the steps that the material mark of base metal is collected, indexing is conducted in a preset material database according to the material mark, the thermal expansion coefficient and the thermal conductivity coefficient corresponding to the base metal are obtained, welding materials are classified according to the thermal expansion coefficient and the thermal conductivity coefficient, and classification results are obtained; welding material matching is conducted on the base material according to the classification result, and the material mark of the welding material is obtained; based on the selected base metal and the welding material, a 3D finite element model is established, the thermal expansion coefficient and the heat conductivity coefficient of the material are collected and input, an optimization variable range is set, and the 3D finite element model is optimized; the optimization variables comprise current, voltage and welding speed; outputting the width and residual stress of the heat affected zone based on the optimized 3D finite element model; the welding quality, efficiency and automation level can be comprehensively improved, and standardization and normalization of the welding process are promoted.

Description

Technical Field

[0001] The present invention relates to the field of welding technology, and more specifically, to a welding process specification calling system and method with a weld profile matching function. Background Art

[0002] In modern manufacturing, welding, as a key joining process, is widely used in many fields such as aerospace, automotive manufacturing, and shipbuilding industries. With the continuous progress of industrial technology, the requirements for welding quality, efficiency, and automation are increasing day by day, and traditional welding processes face many challenges.

[0003] The patent application with the publication number CN117300466A discloses a welding process control method, device, computer device, and storage medium: obtaining welding parameters of a welding plate and an image of the weld groove cross-section; screening a welding process matching the welding parameters of the welding plate from a preset welding process library; calculating the filling droplet area based on the welding process and the weld groove cross-section image; calculating the working current during welding of the weld groove cross-section based on the filling droplet area. According to the calculated current offset, the initial welding current can be adjusted, and the initial welding current can be adjusted within a preset buffer length, so that the welding plate works in a welding process consistent with the welding parameters during welding, can pay attention to the overall situation of the weld groove of the welding plate, realizes the controllable adjustment of the current during the welding process, and improves the welding quality.

[0004] Although the above method can meet most scenarios, through research and practical application of the above method and the existing technology, it is found that the above method and the existing technology have at least the following partial defects:

[0005] It depends on a preset path or manual teaching and cannot adapt to the dynamic deformation of complex geometric welds; parameter selection depends on experience or fixed rules and cannot dynamically respond to material fluctuations;

[0006] In view of this, the present invention proposes a welding process specification calling system and method with a weld profile matching function to solve the above problems. Summary of the Invention

[0007] In order to overcome the above defects of the prior art and achieve the above object, the present invention provides the following technical solution: A welding process specification calling method with a weld profile matching function, including the following steps:

[0008] Collect the material grade of the base material, index in a preset material database according to the material grade, obtain the thermal expansion coefficient and thermal conductivity corresponding to the base material, classify the welding materials according to the thermal expansion coefficient and thermal conductivity respectively, and obtain the classification result; perform welding material matching on the base material according to the classification result to obtain the material grade of the welding material.

[0009] Based on the selected base material and welding materials, a 3D finite element model is established, the thermal expansion coefficient and thermal conductivity of the materials are collected and input, the range of optimization variables is set, and the 3D finite element model is optimized; the optimization variables include current, voltage, and welding speed; based on the optimized 3D finite element model, the width of the heat affected zone and the residual stress are output;

[0010] Obtain the contents of Cr element and Ni element in the molten pool, fit and establish the Cr / Ni element calibration equation, and trigger the feedback mechanism for adjusting the optimization variables when the detected Cr content is lower than the preset content threshold;

[0011] Collect the three-dimensional point cloud data of the weld, extract the weld profile features, match the weld profile features with the profiles in the preset profile library to obtain the weld profile matching result; correct the weld profile trajectory according to the weld profile matching result;

[0012] Construct a multi-level rule base based on welding material matching, optimization variable optimization, feedback adjustment of optimization variables, and weld profile matching, and define the process specifications according to the multi-level rule base for dynamic calling of process specifications in the later stage.

[0013] Furthermore, the method for optimizing the 3D finite element model includes:

[0014] Collect the shape and size of the welded structure and input them into the finite element preprocessing software to create a three-dimensional geometric model;

[0015] Obtain the thermophysical properties of the base material, and the thermophysical properties include density, specific heat capacity, thermal expansion coefficient, and thermal conductivity;

[0016] Input the thermophysical properties into the corresponding material regions and build the corresponding heat conduction equation;

[0017] Preset the value ranges of current, voltage, and welding speed, and set current, voltage, and welding speed as optimization variables;

[0018] Associate the optimization variables with the heat source model in the welding process, and divide the welding heat source into two ellipsoidal parts to build a double-ellipsoid heat source model;

[0019] Preset the constraint intervals for the width of the heat affected zone, residual stress, and energy efficiency; synchronously optimize the width of the heat affected zone, residual stress, and energy efficiency in the welding process through the NSGA-II algorithm to generate an optimal solution set, and select the parameter combination composed of the optimization variables with the highest comprehensive score in the optimal solution set;

[0020] Obtain the total heat power by integrating the double-ellipsoid heat source model , and then solve the heat conduction equation to obtain the temperature during the welding process;

[0021] The node displacements are obtained by establishing and solving a system of nonlinear equations; then the residual stresses are calculated based on the geometric equations and constitutive equations.

[0022] Furthermore, the method of selecting the parameter combination composed of the optimization variables with the highest comprehensive score in the optimal solution set includes:

[0023] Step 1: Define the objective functions of the 3D finite element model, which include the first objective function, the second objective function, and the third objective function;

[0024] Step 2: Randomly generate H individuals within the value ranges of current, voltage, and welding speed. Each individual represents a set of parameter combinations obtained by splicing current, voltage, and welding speed;

[0025] Step 3: Calculate the three objective function values corresponding to each individual;

[0026] Step 4: For any two individuals p and q, if the three objective function values of individual p are all less than or equal to the three objective function values corresponding to individual q, and at least one objective function value of individual p is less than the objective function value corresponding to individual q, then it is determined that individual p dominates individual q;

[0027] Step 5: Repeat Step 4 to obtain the first set of individuals composed of all individuals that are not dominated by other individuals, and divide the first set of individuals into the first rank;

[0028] Step 6: For the remaining individuals that have not been ranked, repeat the operations in Step 4 - Step 5 to sequentially obtain new sets of individuals that are not dominated by the remaining individuals, and divide them into the next rank until all individuals are divided into the corresponding ranks;

[0029] Step 7: Calculate the crowding degree of the individuals in each rank;

[0030] Step 8: Use the tournament selection method to randomly select K individuals from the population, and select the individual with the highest rank and a crowding degree higher than the preset crowding degree threshold as the parent;

[0031] Step 9: For the selected parent individuals and perform crossover operations to generate offspring individuals and ;

[0032] Step 10: Perform mutation operations on the offspring individuals to change the parameter values of the offspring individuals;

[0033] Step 11: Combine the parent population with a size of N and the mutated offspring population with a size of N to obtain a combined population with a size of 2N;

[0034] Step 12: Perform non-dominated sorting on the merged population, and select the top N individuals according to rank and crowding degree to form a new population;

[0035] Step 13: When the preset update requirement is met, stop the update of the new population; obtain the corresponding optimal solution set;

[0036] Step 14: Calculate the comprehensive score of each individual in the optimal solution set based on the comprehensive scoring function, and select the parameter combination composed of the optimization variables with the highest comprehensive score in the optimal solution set.

[0037] Further, the weld profile features include geometric features and topological features; the method for obtaining geometric features includes:

[0038] For the edge points in the three-dimensional point cloud data, find k neighborhood points through neighborhood search, construct a covariance matrix; perform eigenvalue decomposition on the covariance matrix; take the eigenvector corresponding to the minimum eigenvalue as the normal vector of the point; based on the normal vector and neighborhood points, calculate the curvature of the edge point; count the curvatures of all edge points to obtain a curvature set, and use the curvature set as geometric features.

[0039] Further, the method for obtaining topological features includes:

[0040] Step A: Select dimension R, and sort the three-dimensional point cloud data according to the values of the selected dimension;

[0041] Step B: Take the point corresponding to the median value of the sorting result as the root node, and divide the three-dimensional point cloud data into two parts, the left side and the right side, according to the root node;

[0042] Step C: Then repeat Step B for the two parts on the left side and the right side respectively to construct subtrees;

[0043] Step D: Repeat Step B - Step C until the two parts on the left side and the right side contain only one node;

[0044] Step E: Starting from the seed point perform region growing according to the normal vector similarity and distance threshold between points;

[0045] Step F: Obtain the boundary points of the growing region , that is, the weld profile points , calculate the normal vector angle between the weld profile point and its neighborhood point ; if is greater than the set normal vector similarity threshold, and the distance between point and point is less than the distance threshold; then point Add to the growth region and continue to perform the above operations on the newly added points until there are no points that meet the conditions to be added;

[0046] Step G: Count all the boundary points in the growth region to obtain a topological set, and use the topological set as the topological feature.

[0047] Furthermore, the method for obtaining the weld profile matching result includes:

[0048] Calculate the Euclidean distance between the geometric features of the weld profile and the geometric features of the profiles in the profile library, and at the same time calculate the similarity between the topological features of the weld profile and the topological features of the profiles in the profile library; make a comparison and judgment according to the preset distance matching threshold and similarity matching threshold:

[0049] If the Euclidean distance between the weld profile and the profile in the profile library is less than the distance matching threshold and the similarity is higher than the similarity matching threshold, it is determined that the weld profile is the same as the profile in the profile library to be matched;

[0050] If any of the following situations occur:

[0051] The matching result is more than one;

[0052] The Euclidean distance is greater than the distance matching threshold and the similarity is higher than the similarity matching threshold;

[0053] The Euclidean distance is greater than the distance matching threshold and the similarity is lower than the similarity matching threshold;

[0054] The Euclidean distance is less than the distance matching threshold and the similarity is lower than the similarity matching threshold;

[0055] Then select the profile in the profile library corresponding to the highest similarity as the final matching result;

[0056] The method for correcting the trajectory of the weld profile according to the weld profile matching result includes:

[0057] Obtain the weld offset during the welding process, and when the weld offset is greater than the preset offset threshold, correct the trajectory of the welding point.

[0058] Furthermore, the method for constructing a multi-level rule library includes:

[0059] Step a: Obtain the material grade of the base metal, the material grade of the welding material, the thermal expansion coefficient and thermal conductivity of the material, the width of the heat affected zone and the residual stress output based on the optimized 3D finite element model, the contents of Cr element and Ni element, the profile features, and the welding offset;

[0060] Step b: Design and store the rule logics for welding material matching, optimization variable optimization, feedback regulation of optimization variables, and weld profile matching during the welding process. The rule logics include basic rules, dynamic rules, and composite rules;

[0061] Step c: Use a rule engine to implement condition matching and action triggering.

[0062] Furthermore, the method for defining process specifications includes:

[0063] Real-time collect the material grade of the base material, the coefficient of thermal expansion and thermal conductivity of the material, the contents of Cr and Ni elements, and the three-dimensional point cloud data of the weld;

[0064] Compare and trigger the collected data with the condition fields in the rule logics defined in the multi-level rule library. If multiple rules are triggered simultaneously, execute them in the preset priority order;

[0065] Convert the corresponding action fields in the triggered rule logics into device instructions and send the device instructions to the corresponding devices, and the devices execute the device instructions;

[0066] If the device instruction is to adjust the feedback mechanism of the optimization variable and the trajectory correction rule, re-collect the contents of Cr and Ni elements and judge whether they return to the preset content threshold. If not, trigger the feedback mechanism until the contents of Cr and Ni elements return to the preset content threshold;

[0067] Rescan the adjusted weld profile and perform secondary matching with the preset profile library; if the matching fails continuously for E times, trigger an alarm and stop the machine, prompting for manual intervention; and store the adjustment data, rule trigger records, and quality inspection results in the preset call database.

[0068] Furthermore, the method for obtaining classification results includes:

[0069] Preset G thermal expansion coefficient thresholds, divide according to the preset G thermal expansion coefficient thresholds to obtain G + 1 thermal expansion coefficient intervals, and sequentially number each thermal expansion coefficient interval in ascending order; preset M thermal conductivity thresholds, divide according to the preset M thermal conductivity thresholds to obtain M + 1 thermal conductivity intervals, and sequentially number each thermal conductivity interval in ascending order; traverse and compare the thermal expansion coefficient and thermal conductivity of the welding material with the G + 1 thermal expansion coefficient intervals and M + 1 thermal conductivity intervals respectively, and obtain the thermal expansion coefficient interval number and thermal conductivity interval number to which the welding material belongs as the classification result.

[0070] Furthermore, the method for obtaining the material grade of the welding material includes:

[0071] Obtain the thermal expansion coefficient range number and thermal conductivity coefficient range number corresponding to the base material, and select the material corresponding to the material grade whose thermal expansion coefficient range number and thermal conductivity coefficient range number are the same as or adjacent to those of the base material as the material grade of the welding material.

[0072] A welding procedure specification calling system with a weld profile matching function, used to implement the welding procedure specification calling method with a weld profile matching function, including:

[0073] Material matching module: Collect the material grade of the base material, index it in the preset material database according to the material grade, obtain the thermal expansion coefficient and thermal conductivity coefficient corresponding to the base material, classify the welding materials respectively according to the thermal expansion coefficient and thermal conductivity coefficient, and obtain the classification result; perform welding material matching on the base material according to the classification result to obtain the material grade of the welding material.

[0074] Model prediction module: Based on the selected base material and welding material, establish a 3D finite element model, collect and input the thermal expansion coefficient and thermal conductivity coefficient of the material, set the optimization variable range, and optimize the 3D finite element model; the optimization variables include current, voltage and welding speed; output the heat affected zone width and residual stress based on the optimized 3D finite element model.

[0075] Feedback adjustment module: Obtain the contents of Cr element and Ni element in the molten pool, fit and establish a Cr / Ni element calibration equation, and trigger a feedback mechanism for adjusting the optimization variables when the detected Cr content is lower than the preset content threshold.

[0076] Profile matching module: Collect the three-dimensional point cloud data of the weld, extract the weld profile features, match the weld profile features with the profiles in the preset profile library to obtain the weld profile matching result; correct the trajectory of the weld profile according to the weld profile matching result.

[0077] Procedure calling module: Construct a multi-level rule library based on welding material matching, optimization variable optimization, feedback adjustment of optimization variables, and weld profile matching, define the welding procedure according to the multi-level rule library, and be used for dynamic calling of the welding procedure later.

[0078] The technical effects and advantages of the welding procedure specification calling system and method with a weld profile matching function of the present invention:

[0079] The present invention collects the material grades of the base materials, classifies and matches the welding materials according to the coefficient of thermal expansion and the coefficient of thermal conductivity, overcomes the limitations of traditional parameter selection relying on experience or fixed rules, can dynamically respond to the fluctuations of the characteristics of the base materials, ensures the coordination of the performance of the base materials and the welding materials during the welding process, guarantees the welding quality from the source, and improves the reliability and stability of the welded joints; uses a 3D finite element model to optimize variables, provides a scientific basis for the welding process, accurately predicts the physical phenomena during the welding process, optimizes the process parameters in advance, reduces welding defects, and improves the welding quality and production efficiency; monitors and feedback-adjusts in real time according to the element content in the molten pool, can monitor the quality changes during the welding process in real time, adjust the welding parameters in time, avoid quality problems caused by fluctuations in material composition, ensure the consistency and stability of the welding quality, realizes adaptive weld tracking by collecting the three-dimensional point cloud data of the weld, breaks through the bottleneck of the existing technology relying on preset paths or manual teaching and being unable to adapt to the dynamic deformation of complex geometric welds, can track the actual position and shape of the weld in real time, automatically adjust the welding trajectory, realize high-precision welding of complex welds, improve the automation and intelligent level of welding, and finally constructs a multi-level rule base to realize intelligent process calling, comprehensively improve the welding quality, efficiency and automation level, and promote the standardization and regularization of the welding process. BRIEF DESCRIPTION OF THE DRAWINGS

[0080] Figure 1 It is a schematic flow chart of a welding process specification calling method with a weld profile matching function according to the present invention;

[0081] Figure 2 It is a schematic flow chart of a method for constructing a multi-level rule base according to the present invention;

[0082] Figure 3 It is a schematic diagram of the double ellipsoid heat source model parameters according to the present invention;

[0083] Figure 4 It is a temperature field distribution diagram of the 3D finite element model according to the present invention;

[0084] Figure 5 It is a spatial distribution diagram of the temperature field distribution and welding residual stress according to the present invention;

[0085] Figure 6 It is a schematic diagram of the spatial distribution of the temperature field distribution, welding residual stress and deformation parameters according to the present invention;

[0086] Figure 7 It is a schematic structural diagram of a welding process specification calling system with a weld profile matching function according to the present invention;

[0087] Figure 8 It is a schematic diagram of the interface of a welding process specification calling system with a weld profile matching function according to the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0088] 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.

[0089] Example 1

[0090] The implementation conditions of this embodiment are as follows: a FANUC ARC Mate 120iD welding robot is used, with a maximum load of 20kg, a repeatability of ±0.08mm, a working range of 1443mm, support for six-axis linkage and offline programming (OLP), and a Fronius TPS 400i CMT cold metal transfer welder. An Ocean Optics LIBS 2500+ laser induced breakdown spectroscopy (LIBS) system is configured, with a laser wavelength of 1064nm, an adjustable pulse energy of 50-100mJ, a spectral range of 200-980nm, a 2048-pixel high-resolution CCD detector, a sampling frequency of 1-10Hz, and a SpectraSuite spectral analysis platform to support Cr / Ni element calibration curve fitting. The GOM ATOS Q 12M 3D point cloud scanning device was used, with a scanning accuracy of ±0.01mm, a resolution of 12 million pixels, and a full-width scanning speed of 1.5 seconds per frame. The point cloud data was preprocessed and the weld contour was matched with the GOM Inspect Pro software. The finite element analysis used ANSYS Mechanical APDL 2022 R1 software, and the 3D model of the welded structure was created through DesignModeler. The hexahedral dominant grid was used and locally encrypted to 0.5mm in the heat-affected zone to define the thermophysical parameters of the base material (12Cr1MoV) and the welding material (ER70S-6). The solver was the ANSYS TransientThermal transient thermal analysis module, and with the help of the NSGA-Ⅱ multi-objective genetic algorithm optimization integrated in ANSYS optiSLang, the double ellipsoid heat source model was used to simulate the welding heat source to ensure the coordinated support of equipment and software during the implementation process.

[0091] See also Figure 1 As shown, the welding procedure calling method with weld profile matching function described in this embodiment includes the following steps:

[0092] Collect the material grade of the base material, index it in the preset material database according to the material grade, obtain the thermal expansion coefficient and thermal conductivity corresponding to the base material, and classify the welding materials according to the thermal expansion coefficient range and thermal conductivity range respectively; obtain the welding materials by matching the welding materials to the base material according to the classification results. Collecting the material grade of the base material can index the preset database, obtain thermal physical properties parameters such as thermal expansion coefficient and thermal conductivity, assist in welding material matching, and ensure the coordination of material properties during the welding process; it can also help establish an accurate finite element model, input the corresponding material parameters, and make the simulation more in line with the actual situation; in addition, it also provides basic information for subsequent quality control and process analysis, helping to evaluate the welding quality and formulate reasonable process specifications. Obtaining the thermal expansion coefficient and thermal conductivity corresponding to the base material helps to accurately classify and match the welding materials according to their characteristics, ensuring the adaptability of welding; it provides key parameters for establishing a 3D finite element model, making the simulation closer to the actual welding process, thereby optimizing the welding parameters; it can help predict problems such as the width of the heat affected zone and residual stress that may occur during the welding process, providing a basis for controlling and improving the welding quality.

[0093] The methods for obtaining the classification results include:

[0094] Preset G thermal expansion coefficient thresholds, divide according to the preset G thermal expansion coefficient thresholds to obtain G + 1 thermal expansion coefficient ranges, and sequentially number each thermal expansion coefficient range in ascending order; preset M thermal conductivity thresholds, divide according to the preset M thermal conductivity thresholds to obtain M + 1 thermal conductivity ranges, and sequentially number each thermal conductivity range in ascending order; traverse and compare the thermal expansion coefficient and thermal conductivity of the welding materials with the G + 1 thermal expansion coefficient ranges and M + 1 thermal conductivity ranges respectively to obtain the thermal expansion coefficient range number and thermal conductivity range number to which the welding material belongs as the classification result.

[0095] The methods for obtaining the material grade of the welding material include:

[0096] Obtain the thermal expansion coefficient range number and thermal conductivity range number corresponding to the base material, and select the materials corresponding to the material grades with the thermal expansion coefficient range number and thermal conductivity range number both the same as or adjacent to those of the base material as the material grade of the welding material.

[0097] Based on the selected base material and welding material, establish a 3D finite element model, collect and input the thermal expansion coefficient and thermal conductivity of the material, set the optimization variable range, and optimize the 3D finite element model; the optimization variables include current, voltage, and welding speed; output the width of the heat affected zone and residual stress based on the optimized 3D finite element model;

[0098] The methods for optimizing the 3D finite element model include:

[0099] Collect the shape and size of the welded structure and input them into the finite element preprocessing software to create a three-dimensional geometric model;

[0100] Obtain the thermal physical properties of the base material. The thermal physical properties include density, specific heat capacity, coefficient of thermal expansion, and thermal conductivity;

[0101] Input the thermal physical properties into the corresponding material regions and establish the corresponding heat conduction equation ; where, is the density of the welding material; is the specific heat capacity; is the temperature; is the time; is the thermal conductivity; is the total heat power, is the distance that the heat source moves in the horizontal axis direction; is the distance that the heat source moves in the vertical axis direction; is the distance that the heat source moves in the vertical axis direction;

[0102] Preset the current , voltage and welding speed value ranges, and set the current , voltage and welding speed as optimization variables;

[0103] Associate the optimization variables with the heat source model in the welding process, establish a double ellipsoid heat source model, and divide the welding heat source into two ellipsoid parts, the front and the back, to establish the double ellipsoid heat source model. Specifically, refer to Figure 3 , which presents the geometric structure of the double ellipsoid heat source model and visually shows its three-dimensional form. The heat flux density of the front half of the double ellipsoid heat source model ; the heat flux density of the second half ; where, the total heat power Q is 3000W; is the arc thermal efficiency, such as Figure 3 0.85 in and are the semi-axis lengths of the front and rear ellipsoids in the horizontal axis direction, such as Figure 3 4mm and 8mm in is the semi-axis length of the front and rear ellipsoids in the vertical axis direction, such as Figure 3 3mm in , where the semi-axis lengths of the front and rear ellipsoids in the vertical axis direction are equal, that is, their extension ranges in the vertical axis direction are the same, which can achieve the purpose of simplifying the model; is the semi-axis length of the front and rear ellipsoids in the vertical axis direction, such as Figure 32mm in it, where the semi-axis lengths of the front and rear ellipsoids in the vertical axis direction are equal, that is, their extension ranges in the vertical axis direction are the same, and the purpose of simplifying the model can also be achieved; and are the energy distribution coefficients of the front and rear ellipsoids, such as Figure 3 0.6 and 0.4 in it;

[0104] Preset the width constraint interval of the heat affected zone (such as ≤5mm), the residual stress constraint interval (such as ≤300MPa), and the energy efficiency constraint interval (such as ≥80%); synchronously optimize the width of the heat affected zone, residual stress, and energy efficiency during the welding process through the NSGA-II algorithm to generate the optimal solution set, and select the parameter combination composed of the optimization variables with the highest comprehensive score in the optimal solution set;

[0105] The total heat power is obtained by integrating the double-ellipsoid heat source model , and then the heat conduction equation is solved to obtain the temperature during the welding process;

[0106] Establish and solve the non-linear equations to obtain the nodal displacements; where, is the stiffness matrix; is the nodal displacement; is the load vector; and then according to the geometric equation and the constitutive equation calculate to obtain the residual stress; where, is the strain vector; is the geometric matrix; is the stress vector, is the constitutive matrix; where, the stress vector is obtained by stress analysis calculation based on the mechanical equilibrium equation, and the mechanical equilibrium equation is as follows:

[0107] ;

[0108] ;

[0109] ;

[0110] where, is the stress component; is the body force component; is the shear stress component, indicating the magnitude of the shear force exerted on the material in different planes; , indicating the x-axis direction, y-axis direction, and z-axis direction.

[0111] The methods for selecting the parameter combination composed of the optimization variables with the highest comprehensive score in the optimal solution set include:

[0112] Step 1: Define the objective functions of the 3D finite element model, which include the first objective function, the second objective function, and the third objective function; among them, the first objective function ; where , , and are coefficients or exponents obtained by fitting experimental data; the second objective function ; where , , , and are coefficients obtained by fitting simulation data; the third objective function ; where is the heat transfer efficiency, determined by fitting experimental data; and are the heat dissipation coefficient and the splash energy loss coefficient respectively, obtained by fitting simulation data; and are coefficients related to electrode loss and the surface state of the welded part, determined by fitting experimental data; L is the weld length;

[0113] Step 2: Randomly generate H individuals within the value ranges of current, voltage, and welding speed. Each individual represents a set of parameter combinations obtained by splicing current, voltage, and welding speed, that is ;

[0114] Step 3: Calculate the values of the three objective functions corresponding to each individual;

[0115] Step 4: For any two individuals p and q, if the values of the three objective functions of individual p are all less than or equal to the values of the three objective functions corresponding to individual q, and at least one objective function value of individual p is less than the objective function value corresponding to individual q, then it is determined that individual p dominates individual q, denoted as p q.

[0116] Step 5: Repeat Step 4 to obtain the first set of individuals composed of all individuals that are not dominated by other individuals, and divide the first set of individuals into the first level;

[0117] Step 6: For the remaining individuals that have not been classified, repeat the operations in Step 4 - Step 5 to sequentially obtain new sets of individuals that are not dominated by the remaining individuals, and divide them into the next level until all individuals are classified into the corresponding levels;

[0118] Step 7: Calculate the crowding degree of individuals in each level ; where is the number of individuals, is the objective function, when represents the first objective function when represents the second objective function when represents the third objective function; and are respectively the th objective function values of adjacent individuals after sorting; and are respectively the maximum and minimum values of the objective function in the population; Set the crowding degree of the boundary individuals (the individuals with the largest and smallest objective function values) to infinity;

[0119] Step 8: Adopt the tournament selection method, randomly select K individuals from the population, and select the individual with the highest rank and crowding degree higher than the preset crowding degree threshold as the parent;

[0120] Step 9: Perform crossover operations on the selected parent individuals and to generate offspring individuals and :

[0121] ;

[0122] ;

[0123] where is a random number of crossover probability;

[0124] Step 10: Perform mutation operations on the offspring individuals to change the parameter values of the offspring individuals ; where is the parameter value of the mutated offspring individual; and are the value ranges of the parameter ; is a random number of mutation probability; is the parameter value of the offspring individual;

[0125] Step 11: Combine the parent population with a size of N and the offspring population with a size of N after mutation to obtain a combined population with a size of 2N;

[0126] Step 12: Perform non-dominated sorting on the combined population, and select the first N individuals according to the rank and crowding degree to form a new population.

[0127] Step 13: When the preset update requirement is met (such as reaching the preset maximum number of iterations or the change in the optimal solution for M1 consecutive generations is less than the preset change threshold), stop the update of the new population; Obtain the corresponding optimal solution set;

[0128] Step 14: Based on the comprehensive scoring function Calculate the comprehensive scores of each individual in the optimal solution set, and select the parameter combination composed of the optimization variables with the highest comprehensive scores in the optimal solution set; among them, , and are the weights of the first objective function, the second objective function, and the third objective function, which are determined according to actual needs and can be further optimized through natural inspiration optimization algorithms; and are respectively the maximum and minimum values of the first objective function in the Pareto optimal solution set; and are respectively the maximum and minimum values of the second objective function in the Pareto optimal solution set; and are respectively the maximum and minimum values of the third objective function in the Pareto optimal solution set;

[0129] Output the width of the heat affected zone and the residual stress based on the optimized 3D finite element model, and the specific results are as follows:

[0130] After the double ellipsoid heat source model is optimized, the temperature field distribution during the welding process is as Figure 4 shown, where the highest temperature reaches 1650 °C, the molten pool range (800 - 1500 °C) clearly presents the heat source concentration area, and the ambient temperature is 25 °C. The width of the heat affected zone is calculated by simulation to be 2.8 mm (the measured value is 2.8 ± 0.2 mm, and the error ≤ 3.7%), the weld depth is 3.5 mm, and the molten pool length is 8.6 mm. All parameters meet the preset constraint intervals (such as HAZ ≤ 5 mm). The temperature field distribution results verify the accurate simulation ability of the double ellipsoid heat source model for heat input.

[0131] The residual stress distribution during the welding process is as Figure 5 shown, the maximum stress is 380 MPa, mainly concentrated in the weld center area; the medium stress is distributed in the heat affected zone (180 - 280 MPa), and the minimum stress ≤ 100 MPa (located at the far end of the base metal). The error between the residual stress value (245 MPa) obtained by solving the nonlinear equations and the measured value by X-ray diffraction is ≤ 5%, meeting the requirements of the GB / T7704 - 2017 standard. The stress distribution nephogram intuitively reflects the welding deformation trend, proving the engineering feasibility of the residual stress constraint interval.

[0132] When simulating and analyzing the welding process through finite element software, as Figure 6 shown, Figure 6 the left side and the middle respectively correspond to the temperature field and the stress distribution, Figure 6The deformation parameters are obtained on the rightmost side. The deformation parameters show that the maximum deformation is 2.5 mm, the medium deformation is between 1.0 - 2.0 mm, and the minimum deformation is ≤ 0.5 mm. These data help to evaluate the influence of welding deformation on the weld formation and quality, provide a key reference for the dynamic adjustment and optimization of the subsequent welding procedure, and further reflect the technical advantages of the multi-dimensional control of welding quality in the present invention. Through Figure 6 the comprehensive analysis of these parameters in

[0133] the content of Cr element and Ni element in the molten pool is obtained, the calibration equation of Cr / Ni element is established by fitting. When the detected Cr content is lower than the preset content threshold, a feedback mechanism for adjusting the optimization variable is triggered; an LIBS system (Laser Induced Breakdown Spectroscopy system) is integrated to collect the spectral data of the molten pool in real time. Through spectral analysis, the content of Cr element and Ni element in the molten pool is obtained; obtaining the content of Cr element and Ni element in the molten pool, a calibration curve can be established by fitting, which is used as the basis for judging whether the composition is qualified. When the Cr content is abnormal, a feedback mechanism is triggered to adjust the welding process in time; the content of these elements will affect the weld performance and formation. Understanding their content helps to predict and control the weld quality; it can also provide data support for subsequent quality analysis and process optimization to ensure the reliability and stability of the welded structure.

[0134] The method for establishing the calibration equation of Cr / Ni element by fitting includes:

[0135] Standard samples with different Cr element and Ni element contents are obtained, and the spectra of the standard samples are collected; the characteristic peak positions of Cr element and Ni element in the spectra are respectively identified and obtained. By integrating the spectral intensity within the wavelength range where the characteristic peak is located, the integrated intensity of the characteristic peaks of Cr element and Ni element in each standard sample is obtained. Taking the known contents of Cr element and Ni element in the standard sample as the abscissa and the corresponding integrated intensity of the characteristic peak as the ordinate, the calibration equation is obtained by least squares fitting.

[0136] The method for triggering the feedback mechanism for adjusting the optimization variable includes:

[0137] The content of Cr element and Ni element is detected in real time and compared with the preset content threshold. When the content of Cr element or Ni element is lower than the preset content threshold, a feedback mechanism is triggered. The feedback mechanism includes increasing the wire feeding speed to the preset wire feeding speed threshold, reducing the welding speed to the preset welding speed threshold, and adjusting the shielding gas flow rate to the preset coverage rate threshold.

[0138] Collect the three-dimensional point cloud data of the weld seam, extract the weld seam contour features, match the weld seam contour features with the contours in the preset contour library to obtain the matching result; the weld seam contour features include geometric features and topological features; collecting the three-dimensional point cloud data of the weld seam can be used to extract the weld seam contour features, match with the preset contour library, judge whether the weld seam formation meets the standard, and then perform trajectory correction to ensure the weld seam quality; it can provide a data basis for the subsequent establishment of a multi-level rule library based on weld seam contour matching, facilitate the definition and invocation of process specifications; it can also visually present the three-dimensional shape of the weld seam, be used to analyze the causes of welding defects, and help optimize the welding process parameters.

[0139] The methods for obtaining geometric features include:

[0140] For the edge points in the three-dimensional point cloud data , find neighboring points through neighborhood search, and construct a covariance matrix ;

[0141] Among them, is the centroid of the neighboring point ; is the edge point in the three-dimensional point cloud data 's th neighboring point; is the transpose of the vector;

[0142] Perform eigenvalue decomposition on the covariance matrix ; among them, is the eigenvalue diagonal matrix; is the eigenvector matrix; take the eigenvector corresponding to the smallest eigenvalue as the normal vector of the point ; ;

[0143] Based on the normal vector and neighboring points, calculate the curvature of the edge point ; count the curvatures of all edge points to obtain a curvature set, and use the curvature set as the geometric feature.

[0144] The methods for obtaining topological features include:

[0145] Step A: Select a dimension R, and sort the three-dimensional point cloud data according to the values of the selected dimension;

[0146] Step B: Take the point corresponding to the median value of the sorting result as the root node, and divide the three-dimensional point cloud data into two parts, the left side and the right side, according to the root node;

[0147] Step C: Then repeat Step B for the two parts on the left side and the right side respectively to construct subtrees;

[0148] Step D: Repeat Step B - Step C until each of the left and right parts contains only one node;

[0149] Step E: Starting from the seed point perform region growing based on the normal vector similarity and distance threshold between points;

[0150] Step F: Obtain the boundary points of the growing region , i.e., the weld profile points , calculate the normal vector angle between the weld profile point and its neighborhood point ; where, is the normal vector of the weld profile point ; is the normal vector of the neighborhood point ; if is greater than the set normal vector similarity threshold, and the distance between the point and the point is less than the distance threshold; then add the point to the growing region and continue the above operations on the newly added point until there are no more qualifying points to add;

[0151] Step G: Count all the boundary points in the growing region to obtain a topological set, and use the topological set as a topological feature.

[0152] The method for obtaining the weld profile matching result includes:

[0153] Calculate the Euclidean distance between the geometric features of the weld profile and the geometric features of the profiles in the profile library (such as 50 standard profiles including V-groove, U-groove, J-groove, etc.), and at the same time calculate the similarity between the topological features of the weld profile and the topological features of the profiles in the profile library; make a comparison and judgment according to the preset distance matching threshold and similarity matching threshold:

[0154] If the Euclidean distance between the weld profile and the profile in the profile library is less than the distance matching threshold and the similarity is higher than the similarity matching threshold, then it is determined that the weld profile is the same as the profile being matched in the profile library;

[0155] If any of the following situations occur:

[0156] There is more than one matching result;

[0157] The Euclidean distance is greater than the distance matching threshold and the similarity is higher than the similarity matching threshold;

[0158] The Euclidean distance is greater than the distance matching threshold and the similarity is lower than the similarity matching threshold;

[0159] The Euclidean distance is less than the distance matching threshold and the similarity is lower than the similarity matching threshold;

[0160] Then, select the contour in the contour library corresponding to the highest similarity as the final matching result.

[0161] The method for trajectory correction of the weld contour according to the weld contour matching result includes:

[0162] Obtain the weld offset during the welding process. When the weld offset is greater than the preset offset threshold, use the welding point correction formula to perform trajectory correction on the welding point; where is the correction value of the welding point coordinates; is the empirical coefficient, generally taking 0.8, which can be calculated based on the response time of the welding robot; is the actual weld offset; is the preset offset threshold;

[0163] Construct a multi-level rule library based on welding material matching, optimization variable optimization, feedback regulation of optimization variables, and weld contour matching, and define the process specifications according to the multi-level rule library for dynamic invocation of process specifications in the later stage.

[0164] Refer to Figure 2 , and the method for constructing the multi-level rule library includes:

[0165] Step a: Obtain the material grade of the base metal, the material grade of the welding material, the coefficient of thermal expansion and thermal conductivity of the material, the width of the heat-affected zone and residual stress, the content of Cr and Ni elements, contour features, and welding offset output based on the optimized 3D finite element model;

[0166] Step b: Design and store the rule logics for welding material matching, optimization variable optimization, feedback regulation of optimization variables, and weld contour matching during the welding process. The rule logics include basic rules, dynamic rules, and composite rules;

[0167] Step c: Use the rule engine to achieve condition matching and action triggering;

[0168] The method for defining process specifications includes:

[0169] Real-time collect the material grade of the base metal, the coefficient of thermal expansion and thermal conductivity of the material, the content of Cr and Ni elements, and the three-dimensional point cloud data of the weld;

[0170] Compare and trigger the collected data with the condition fields in the rule logics defined in the multi-level rule library. If multiple rules are triggered simultaneously, execute them in the preset priority order;

[0171] Convert the action fields corresponding to the triggered rule logics into device instructions and send the device instructions to the corresponding devices, and the devices execute the device instructions.

[0172] If the device instruction is to adjust the feedback mechanism of the optimization variable and the trajectory correction rule, re-collect the contents of Cr element and Ni element, and judge whether it has returned to the preset content threshold. If it has not returned, trigger the feedback mechanism until the contents of Cr element and Ni element return to the preset content threshold;

[0173] Re-scan the adjusted weld profile and perform secondary matching with the preset profile library; if the matching fails continuously for E times, trigger an alarm and stop the machine, prompting for manual intervention; and store the adjustment data, rule trigger records, and quality inspection results in the preset call database.

[0174] Embodiment 2

[0175] Please refer to Figure 7 As shown, the welding process specification calling system with weld profile matching function described in this embodiment includes:

[0176] Material matching module: Collect the material grade of the base material, index it in the preset material database according to the material grade, obtain the thermal expansion coefficient and thermal conductivity corresponding to the base material, classify the welding materials respectively according to the thermal expansion coefficient and thermal conductivity, and obtain the classification result; perform welding material matching on the base material according to the classification result to obtain the material grade of the welding material;

[0177] Model prediction module: Based on the selected base material and welding material, establish a 3D finite element model, collect and input the thermal expansion coefficient and thermal conductivity of the material, set the optimization variable range, and optimize the 3D finite element model; the optimization variables include current, voltage, and welding speed; output the heat affected zone width and residual stress based on the optimized 3D finite element model;

[0178] Feedback adjustment module: Obtain the contents of Cr element and Ni element in the molten pool, fit and establish a Cr / Ni element calibration equation, and trigger the feedback mechanism for adjusting the optimization variable when the detected Cr content is lower than the preset content threshold;

[0179] Profile matching module: Collect the three-dimensional point cloud data of the weld, extract the weld profile features, match the weld profile features with the profiles in the preset profile library to obtain the weld profile matching result; perform trajectory correction on the weld profile according to the weld profile matching result;

[0180] Specification calling module: Construct a multi-level rule library based on welding material matching, optimization variable optimization, feedback adjustment of optimization variables, and weld profile matching, define the process specification according to the multi-level rule library, and be used for dynamic calling of the process specification in the later stage; in the later stage, the process specification stored in the multi-level rule library can be directly called through the specification calling module for weld profile matching.

[0181] Refer toFigure 8 In the material matching module, the base metal grade 12Cr1MoV is presented, which can be used to index key parameters such as its coefficient of thermal expansion and thermal conductivity in a preset material database, providing a basis for welding consumable classification and matching. As shown in Table 1, Table 2, and Table 3:

[0182] Table 1 Physical Property Parameters of the Base Metal (12Cr1MoV)

[0183]

[0184] Table 1 provides the core physical parameters of the base metal 12Cr1MoV. Among them, density, specific heat capacity, and thermal conductivity are directly used to solve the heat conduction equation of the finite element model, and the coefficient of thermal expansion and elastic modulus are used for residual stress and deformation analysis. The parameter test standards cover international general methods (such as ASTM, ISO) to ensure the authority of the data, providing basic input for establishing a 3D finite element model and supporting the technical characteristics of the output heat affected zone width and residual stress.

[0185] Table 2 Measured Data of the Base Metal (12Cr1MoV)

[0186]

[0187] Test environment: room temperature (25°C ± 1°C), humidity 50% ± 5%.

[0188] Sample numbers: MT-12Cr1MoV-001 to MT-12Cr1MoV-005 (5 groups of parallel samples).

[0189] Table 2 provides the measured data of the base metal 12Cr1MoV. Through high-precision testing methods such as the Archimedes drainage method and the laser flash method, the accuracy of the material parameters is verified. The errors between the measured data and the theoretical values (Table 1) are all within a reasonable range (such as a density error of ±0.02 g / cm³ and a thermal conductivity error of ±1.5%), proving the reliability of the experimental data, providing credible input parameters for the finite element model, and ensuring the accuracy of the heat conduction equation solution and residual stress calculation.

[0190] Table 3 Measured Data of Parallel Samples

[0191]

[0192] Table 3 shows the measured data of 5 groups of parallel samples. The test environment is room temperature (25°C ± 1°C) and humidity 50% ± 5%. The Archimedes drainage method, the laser flash method (LFA467), and the dilatometer method (Netzsch DIL402) are used to ensure the test accuracy; density ±0.02 g / cm³, thermal conductivity ±1.5%, coefficient of thermal expansion ±0.3×10 -6 / K are all within the allowable error range, proving the stability of the base metal properties. The above parallel sample data has good repeatability, ensuring the reliability of the input parameters (such as density and thermal conductivity) of the finite element model and being able to support the accuracy of establishing the 3D finite element model. The error between the measured value and the theoretical value (Table 1) is less than 3%, providing experimental verification for the simulation results of the width of the heat affected zone and the residual stress output.

[0193] The welding material matching results are visually presented through the material property comparison radar chart. The recommended welding material is ER70S-6, with a matching rate of 85%, which can ensure the synergistic effect of material properties during the welding process. As shown in Tables 4, 5, and 6:

[0194] Table 4 Physical Property Parameters of Welding Material (ER70S-6)

[0195]

[0196] Table 4 provides the core physical parameters of the welding material ER70S-6. Its coefficient of thermal expansion (13.2×10 -6 / K) is close to that of the base metal 12Cr1MoV (12.5×10 -6 / K, Table 1), and its thermal conductivity of 45 W / (m・K) matches that of the base metal of 42 W / (m・K), meeting the matching rule that the coefficient of thermal expansion range and the thermal conductivity range are the same or adjacent, ensuring controllable thermal stress at the welding interface.

[0197] Test standard description: The thermal conductivity is calculated from the thermal diffusivity (ASTM E1461), and other parameters are tested using international general standards.

[0198] Table 5 Measured Data of Welding Material (ER70S-6)

[0199]

[0200] Test environment: Room temperature (25°C ± 1°C), humidity 50% ± 5%.

[0201] Sample numbers: MT-ER70S6-001 to MT-ER70S6-005 (5 groups of parallel samples).

[0202] Table 5 presents the measured data of the welding material (ER70S-6), covering three key parameters: density, thermal conductivity, and coefficient of thermal expansion. The test was carried out in a strictly controlled environment, with a room temperature of 25°C ± 1°C and a humidity of 50% ± 5%, and 5 groups of parallel samples (MT-ER70S6-001 to MT-ER70S6-005) were used to ensure the reliability and repeatability of the data. Among them, the density was measured by the Archimedes drainage method, and the measured value was 7.86 g / cm 3 within the allowable error of ±0.02 g / cm 3Inside; the thermal conductivity was measured by the laser flash method (LFA467) with an error controlled within ±1.5%; the coefficient of thermal expansion (20 - 300 °C) was measured by the dilatometer method (Netzsch DIL402), and the result was 13.1×10 -6 / K, with an allowable error of ±0.3×10 -6 / K. The accurate measurement of these parameters provides a basis for evaluating the thermal match between the welding consumables and the base metal (Table 1), ensures that the width of the heat-affected zone and the residual stress are controllable during the welding process, and at the same time provides key inputs for the heat source calculation and thermo-mechanical analysis of the finite element model, strengthening the technical logic of matching the properties of the welding consumables and the base metal to improve the welding quality.

[0203] Furthermore, through the actual measurement of 5 groups of parallel samples (Table 6), the stability of the performance of the welding consumable ER70S-6 was verified. The fluctuation ranges of the sample density, thermal conductivity, and coefficient of thermal expansion were extremely small, indicating the stable quality of the welding consumables, providing a reliable basis for the material parameter for the subsequent formulation of the welding process specification. These data corroborate with Table 5, ensuring the accuracy of the thermophysical parameters in the finite element model, and further guaranteeing the reliability of the simulation results of the width of the heat-affected zone and the residual stress, reflecting the rigor and scientificity of the present invention in the acquisition and application of material parameters.

[0204] Table 6 Measured data of parallel samples

[0205]

[0206] Table 6 shows the measured data of 5 groups of parallel samples of the welding consumable (ER70S-6), covering density, thermal conductivity, and coefficient of thermal expansion, with the sample numbers ranging from MT-ER70S6-001 to MT-ER70S6-005. The test environment was the same as that in Table 5 (room temperature 25 °C ± 1 °C, humidity 50% ± 5%). Through the parallel sample test, the stability of the performance of the welding consumables was verified: the measured density values were between 7.85 - 7.87 g / cm 3 between, the thermal conductivity was between 44.8 - 45.0 W / (m·K), and the coefficient of thermal expansion was between 13.0 - 13.2×10 −6 / K. The fluctuations of each parameter were within a reasonable range, indicating the stable performance of the welding consumables. These data further supported the measured results in Table 5, providing a more sufficient basis for evaluating the match between the welding consumables and the base metal, ensuring the reliability of the input parameters of the finite element model, and thus accurately simulating the heat conduction, deformation, and stress distribution during the welding process.

[0207] In the optimization parameter region, three optimization variables, namely current (100 - 300 A), voltage (15 - 35 V), and welding speed (2 - 10 mm / s), and their corresponding variable ranges were set. Combining with the 3D finite element model, the optimization variables were optimized, and adjusting the optimization variables could optimize the welding process. The experimental data can be referred to Table 7:

[0208] Table 7 Comparison Table of Experimental Data

[0209]

[0210] Table 7 is a comparison table of experimental data, presenting the simulated and measured data of the heat affected zone width, residual stress, and energy efficiency under 8 groups of different welding parameters (current, voltage, welding speed), and also including the spatter rate and uniformity score.

[0211] As can be seen from Table 7, the error range between the simulated value and the measured value of the heat affected zone width in the 8 groups of experiments is 1.9% - 5.9%, the average error is 3.2%, and the standard deviation is 0.15 mm, meeting the requirements of the GB / T19869.1 standard. Among them, for the second group of experiments (current 150 A, voltage 22 V, welding speed 4.5 mm / s), the simulated value of the heat affected zone width is 2.8 mm, and the measured value is 2.9 mm, with an error of only 3.4%; the error of the eighth group of experiments (current 300 A, voltage 35 V, welding speed 10.0 mm / s) is 5.9%, which is the maximum error, but still lower than the 10% error standard allowed for industrial inspection. The simulation results are in good agreement with the measured data, proving that the 3D finite element model can accurately predict the heat affected zone width and provide a reliable basis for process parameter optimization.

[0212] The error range between the simulated value and the measured value of the residual stress is 6.4% - 8.6%, and the average error is 7.3%. Taking the fifth group of experiments (current 230 A, voltage 32 V, welding speed 8.0 mm / s) as an example, the error between the simulated value of 315 MPa and the measured value of 330 MPa is 4.5%, meeting the ±10% error requirement specified in GB / T7704 - 2017. The simulation accuracy of the model for residual stress meets the requirements of engineering applications, verifying the effectiveness of the double ellipsoidal heat source model and the nonlinear stress solution method.

[0213] When the current increases from 120 A to 300 A, the heat affected zone width increases from 2.5 mm to 4.0 mm, showing an approximately linear growth (the slope is 0.0078 mm / A). This is because the increase in current leads to an increase in heat input and an expansion of the high-temperature region of the molten pool. In scenarios where heat deformation needs to be controlled (such as welding of thin-walled structures), the heat affected zone width can be controlled within 3.0 mm by restricting the upper limit of the current (such as ≤200 A).

[0214] When the welding speed increases from 3.0 mm / s to 10.0 mm / s, the energy efficiency (simulation) increases from 82% to 92%, indicating that increasing the welding speed can reduce the heat input per unit weld length and lower the energy loss. However, if the welding speed is too fast (e.g., ≥8 mm / s), the spatter rate will increase significantly (from 3.0% to 4.2%), affecting the weld formation quality (the uniformity score drops from 3.5 to 3.0). Considering both the energy efficiency and the formation quality, the recommended welding speed range is 4.5 - 6.0 mm / s (corresponding to an energy efficiency of 85% - 88% and a spatter rate ≤2.5%).

[0215] By comparing the simulation results with the measured results, verify the accuracy of the finite element model in simulating the welding process, analyze the influence laws of various parameters on welding quality (heat affected zone width, residual stress), energy utilization (energy efficiency), and formation effect (spatter rate, uniformity score), and provide an experimental basis for optimizing welding process parameters based on the NSGA-II algorithm to ensure the effectiveness of the optimized parameters in actual welding. See Table 8:

[0216] Table 8 Partial data of the NSGA-II algorithm optimization process

[0217]

[0218] Table 8 shows partial data of the NSGA-II algorithm optimization process, including the welding parameters (current, voltage, welding speed) of 10 sets of solutions and the corresponding heat affected zone width, residual stress, energy efficiency, and comprehensive score.

[0219] The solution No. 2 in Table 8 (current 200 A, voltage 24 V, welding speed 5.0 mm / s) has the highest comprehensive score (S = 0.91), and its heat affected zone width (2.8 mm), residual stress (245 MPa), and energy efficiency (85%) are all at relatively good levels. In contrast, for solution No. 7 (current 220 A, voltage 26.5 V, welding speed 4.0 mm / s), although the heat affected zone width is the smallest (2.5 mm), the energy efficiency is only 80.5%, and the residual stress is as high as 290 MPa, resulting in poor comprehensive performance. Through non-dominated sorting and crowding degree calculation, the algorithm effectively balances the multi-objective conflicts and avoids the performance imbalance caused by optimizing a single index. During the optimization process, the average comprehensive score of the first 50 generations of the population is 0.78, which increases to 0.85 in the 100th generation and stabilizes at 0.88 - 0.91 in the 200th generation, indicating that the algorithm can converge to the optimal solution set within 200 iterations, and the calculation efficiency meets the requirements of real-time process optimization.

[0220] Through these data, the search process of the algorithm in multi-objective optimization (heat affected zone width, residual stress, energy efficiency) can be observed. The comprehensive score S reflects the quality of each group of solutions. For example, the comprehensive score of solution No. 2 is relatively high at 0.91. Its parameters (current 200A, voltage 24.0V, welding speed 5.0mm / s) result in a heat affected zone width of 2.80mm, a residual stress of 245MPa, and an energy efficiency of 85.0%, achieving a good multi-objective balance, providing a direct basis for screening the optimal process parameters, and fully demonstrating the algorithm's ability to balance and optimize multiple objectives in welding process optimization.

[0221] Obtaining the temperature distribution curve, heat affected zone width of 2.8mm, and residual stress of 245MPa output based on the optimized 3D finite element model can be used to monitor and evaluate welding quality, and also provide a reference basis for the subsequent dynamic adjustment and invocation of welding process specifications.

[0222] As described above, it is only the specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of changes or substitutions, which should all be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

[0223] Finally: The above description is only the preferred embodiment of the present invention and is not used to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A welding procedure calling method with a weld profile matching function, characterized in that: The steps include: Collect the material grade of the parent material, and index it in the preset material database according to the material grade, obtain the thermal expansion coefficient and thermal conductivity coefficient corresponding to the parent material, classify the welding materials according to the thermal expansion coefficient and thermal conductivity coefficient, and obtain the classification results; Match the welding materials to the parent materials according to the classification results to obtain the material grade of the welding materials; Based on the selected parent material and welding material, a 3D finite element model is established, the thermal expansion coefficient and thermal conductivity of the material are collected and input, the optimization variable range is set, and the 3D finite element model is optimized; the optimization variables include current, voltage and welding speed; based on the optimized 3D finite element model, the width of the heat affected zone and the residual stress are output; Obtain the contents of Cr and Ni in the molten pool, and establish a Cr / Ni element calibration equation by fitting. When the Cr content is detected to be lower than a preset content threshold, a feedback mechanism for adjusting the optimization variables is triggered. Collect the three-dimensional point cloud data of the weld, extract the weld contour features, match the weld contour features with the contours in the preset contour library, and obtain the weld contour matching results; perform trajectory correction on the weld contour according to the weld contour matching results; Construct a multi-level rule library based on welding material matching, optimization variable optimization, feedback adjustment of optimization variables, and weld contour matching. Define the process procedures according to the multi-level rule library for dynamic calling of the process procedures in the later stage.

2. The method for calling a welding procedure with a weld profile matching function according to claim 1, characterized in that: Methods for optimizing 3D finite element models include: Collect the shape and size of the welded structure and input it into the finite element pre-processing software to create a three-dimensional geometric model; Obtain the thermophysical parameters of the base material, including density, specific heat capacity, thermal expansion coefficient and thermal conductivity; Input the thermophysical property parameters into the corresponding material area and build the corresponding heat conduction equation; Preset the value range of current, voltage and welding speed, and set current, voltage and welding speed as optimization variables; The optimization variables are associated with the heat source model in the welding process, and the welding heat source is divided into two ellipsoid parts to build a double ellipsoid heat source model; Preset the heat-affected zone width constraint interval, residual stress constraint interval and energy efficiency constraint interval; use the NSGA-Ⅱ algorithm to simultaneously optimize the heat-affected zone width, residual stress and energy efficiency in the welding process, generate the optimal solution set, and select the parameter combination composed of the optimization variables with the highest comprehensive score in the optimal solution set; The total heat power is obtained by integrating the double ellipsoid heat source model , and then solve the heat conduction equation to obtain the temperature during welding; The node displacement is obtained by establishing and solving a group of nonlinear equations; the residual stress is then calculated based on the geometric equation and constitutive equation.

3. The welding procedure calling method with weld profile matching function according to claim 2 is characterized in that: Methods for selecting parameter combinations composed of optimization variables with the highest comprehensive scores in the optimal solution set include: Step 1, defining the objective function of the 3D finite element model, the objective function includes a first objective function, a second objective function and a third objective function; Step 2: Randomly generate H individuals within the range of current, voltage and welding speed, each individual represents a set of parameter combinations obtained by splicing current, voltage and welding speed; Step 3: Calculate the three objective function values ​​corresponding to each individual; Step 4: For any two individuals p and q, if the three objective function values ​​of individual p are less than or equal to the three objective function values ​​corresponding to individual q, and at least one objective function value of individual p is less than the objective function value corresponding to individual q, then it is judged that individual p dominates individual q; Step 5, repeat step 4 to obtain the first set of individuals consisting of all individuals that are not dominated by other individuals, and divide the first set of individuals into the first level; Step 6: Repeat the operations of step 4 to step 5 for the remaining individuals that have not been classified, obtain new sets of individuals that are not dominated by the remaining individuals, and divide them into the next level until all individuals are classified into the corresponding level; Step 7: Calculate the crowding degree of individuals in each level; Step 8: Use the tournament selection method to randomly select K individuals from the population, and select the individual with the highest rank and a crowding degree higher than the preset crowding degree threshold as the parent; Step 9: Select the parent individuals and Perform crossover operation to generate offspring individuals and ; Step 10, performing mutation operation on the offspring individuals to change the parameter values ​​of the offspring individuals; Step 11: merge the parent population of size N and the mutated offspring population of size N to obtain a merged population of size 2N; Step 12: Perform non-dominated sorting on the merged population, select the first N individuals according to the rank and crowding degree, and form a new population; Step 13: When the preset update requirement is reached, stop updating the new population; obtain the corresponding optimal solution set; Step 14: Calculate the comprehensive score of each individual in the optimal solution set based on the comprehensive scoring function, and select the parameter combination consisting of the optimization variables with the highest comprehensive score in the optimal solution set.

4. The welding procedure calling method with weld profile matching function according to claim 1 is characterized in that: The weld profile features include geometric features and topological features; Methods for obtaining geometric features include: For edge points in three-dimensional point cloud data, k neighboring points are found through neighborhood search to construct a covariance matrix; the covariance matrix is ​​decomposed by eigenvalue; the eigenvector corresponding to the minimum eigenvalue is taken as the normal vector of the point; the curvature of the edge point is calculated based on the normal vector and the neighborhood points; the curvature of all edge points is counted to obtain a curvature set, which is used as a geometric feature.

5. The method for calling welding procedure with weld profile matching function according to claim 4, characterized in that: Methods for obtaining topological features include: Step A: select dimension R, and sort the three-dimensional point cloud data according to the value of the selected dimension; Step B: taking the point corresponding to the middle value of the sorting result as the root node, and dividing the three-dimensional point cloud data into two parts, the left part and the right part, according to the root node; Step C, repeat step B for the left and right parts respectively to construct a subtree; Step D, repeat steps B to C until both the left and right parts contain only one node; Step E: From the seed point Initially, region growing is performed based on the normal vector similarity and distance threshold between points; Step F: Get the boundary points of the growth area , that is, the weld contour point , calculate the weld contour points With neighboring points The normal vector angle ;like is greater than the set normal vector similarity threshold, and the point With point If the distance is less than the distance threshold, then the point Add the growth area and continue to perform the above operations on the newly added points until there are no points that meet the conditions to be added; Step G: Count all the boundary points in the growing area to obtain a topological set, and use the topological set as a topological feature.

6. The method for calling welding procedure with weld profile matching function according to claim 5, characterized in that: Methods for obtaining weld profile matching results include: Calculate the Euclidean distance between the geometric features of the weld contour and the geometric features of the contours in the contour library, and calculate the similarity between the topological features of the weld contour and the topological features of the contours in the contour library; compare and judge based on the preset distance matching threshold and similarity matching threshold: If the Euclidean distance between the weld contour and the contour in the contour library is less than the distance matching threshold, and the similarity is higher than the similarity matching threshold, it is determined that the weld contour is the same as the matched contour in the contour library; If the following occurs: There is more than one matching result; The Euclidean distance is greater than the distance matching threshold and the similarity is greater than the similarity matching threshold; The Euclidean distance is greater than the distance matching threshold and the similarity is less than the similarity matching threshold; The Euclidean distance is less than the distance matching threshold and the similarity is less than the similarity matching threshold; The contour in the contour library corresponding to the highest similarity is selected as the final matching result; The method for correcting the weld contour trajectory according to the weld contour matching result includes: The weld offset during the welding process is obtained. When the weld offset is greater than a preset offset threshold, the welding point trajectory is corrected.

7. The method for calling welding procedure with weld profile matching function according to claim 1, characterized in that: Methods for building a multi-level rule base include: Step a, obtaining the material grade of the base material, the material grade of the welding material, the thermal expansion coefficient and the thermal conductivity of the material, and outputting the width and residual stress of the heat affected zone, the content of Cr and Ni elements, the contour characteristics, and the welding offset based on the optimized 3D finite element model; Step b, designing and storing rule logic for welding material matching, optimization variable optimization, feedback adjustment of optimization variables, and weld profile matching during welding, wherein the rule logic includes basic rules, dynamic rules, and composite rules; Step c: Use the rule engine to implement condition matching and action triggering.

8. The method for calling welding procedure with weld profile matching function according to claim 7, characterized in that: Methods for defining process specifications include: Real-time collection of the material grade of the base material, the thermal expansion coefficient and thermal conductivity of the material, the content of Cr and Ni elements, and the three-dimensional point cloud data of the weld; Compare the collected data with the condition fields in the rule logic defined in the multi-level rule library to trigger. If multiple rules are triggered at the same time, they are executed in the preset priority order; Convert the corresponding action field in the triggered rule logic into a device instruction, send the device instruction to the corresponding device, and the device executes the device instruction; If the device instruction is a feedback mechanism for adjusting the optimization variables and a trajectory correction rule, the contents of the Cr and Ni elements are collected again to determine whether they have recovered to the preset content threshold. If not, the feedback mechanism is triggered until the contents of the Cr and Ni elements are restored to the preset content threshold; Rescan the adjusted weld contour and perform a second match with the preset contour library; if E consecutive matches fail, an alarm is triggered and the machine is shut down, prompting manual intervention; and the adjustment data, rule trigger records, and quality inspection results are stored in the preset call database.

9. The method for calling welding procedure with weld profile matching function according to claim 1, characterized in that: Methods for obtaining classification results include: Preset G thermal expansion coefficient thresholds, divide according to the preset G thermal expansion coefficient thresholds, obtain G+1 thermal expansion coefficient intervals, and number each thermal expansion coefficient interval in sequence from small to large; preset M thermal conductivity coefficient thresholds, divide according to the preset M thermal conductivity coefficient thresholds, obtain M+1 thermal conductivity coefficient intervals, and number each thermal conductivity coefficient interval in sequence from small to large; traverse and compare the thermal expansion coefficient and thermal conductivity of the welding material with the G+1 thermal expansion coefficient intervals and the M+1 thermal conductivity coefficient intervals, respectively, to obtain the thermal expansion coefficient interval number and thermal conductivity interval number to which the welding material belongs as the classification result.

10. The welding procedure calling method with weld profile matching function according to claim 9, characterized in that: Methods for obtaining the material grade of welding materials include: The thermal expansion coefficient interval number and the thermal conductivity coefficient interval number corresponding to the base material are obtained, and the material corresponding to the material grade whose thermal expansion coefficient interval number and the thermal conductivity coefficient interval number are the same as or adjacent to the thermal expansion coefficient interval number and the thermal conductivity coefficient interval number of the base material is selected as the material grade of the welding material.

11. A welding procedure specification calling system with a weld profile matching function, used to implement a welding procedure specification calling method with a weld profile matching function as claimed in any one of claims 1 to 10, characterized in that: include: Material matching module: collects the material grade of the parent material, and indexes it in the preset material database according to the material grade, obtains the thermal expansion coefficient and thermal conductivity coefficient corresponding to the parent material, classifies the welding materials according to the thermal expansion coefficient and thermal conductivity coefficient, and obtains the classification results; Match the welding materials to the parent materials according to the classification results to obtain the material grade of the welding materials; Model prediction module: Based on the selected base material and welding material, a 3D finite element model is established, the thermal expansion coefficient and thermal conductivity of the material are collected and input, the optimization variable range is set, and the 3D finite element model is optimized; the optimization variables include current, voltage and welding speed; based on the optimized 3D finite element model, the width of the heat affected zone and the residual stress are output; Feedback adjustment module: obtains the contents of Cr and Ni in the molten pool, fits and establishes the Cr / Ni element calibration equation, and triggers the feedback mechanism for adjusting the optimization variables when the Cr content is detected to be lower than the preset content threshold; Contour matching module: collects 3D point cloud data of welds, extracts weld contour features, matches weld contour features with contours in a preset contour library, and obtains weld contour matching results; performs trajectory correction on weld contours based on weld contour matching results; Procedure calling module: Build a multi-level rule library based on welding material matching, optimization variable optimization, feedback adjustment of optimization variables, and weld contour matching. Define the process procedure according to the multi-level rule library for dynamic calling of the process procedure in the later stage.

Images