Intelligent Compensation and Control Method and System for Thermal Deformation during Welding of Metal Parts

Abstract

The present invention provides a method and system for intelligent compensation and control of thermal deformation during the welding process of metal parts, relating to the technical field of metal welding, including: constructing a thermo-mechanical coupling analysis model by acquiring a three-dimensional model and process parameters, collecting real-time temperature and strain data, predicting thermal deformation using a dynamic hierarchical graph structure and a bidirectional propagation neural network, and calculating optimal welding process parameters based on the thermal deformation deviation using a recursive optimizer that combines an integrated gradient strategy and an evolutionary strategy, which can achieve accurate prediction and intelligent compensation of thermal deformation during the welding process, and improve the welding quality and precision.

Description

Technical Field

[0001] The present invention relates to the technical field of metal welding, and particularly to an intelligent compensation and control method and system for thermal deformation during the welding process of metal parts. Background Art

[0002] Metal welding is an indispensable joining process in modern industrial manufacturing and is widely used in fields such as aerospace, automotive manufacturing, and shipbuilding industries. During the welding process, due to uneven heating and cooling caused by high-temperature heat sources, metal parts often undergo thermal deformation, which can seriously affect the geometric accuracy and assembly quality of products, increasing the workload and cost of subsequent trimming.

[0003] Traditional control of thermal deformation in metal welding mainly relies on empirical rules and simplified physical models. In recent years, with the development of computer technology and finite element analysis methods, current thermal deformation prediction and control technologies mainly include simulation calculations based on finite element analysis, empirical process parameter adjustment, and real-time monitoring and feedback control methods.

[0004] However, the existing technologies still have problems such as long simulation calculation time, difficulty in accurately handling the nonlinear heat conduction and thermal stress coupling processes of metal parts with complex structures, difficulty in effectively integrating multi-scale and multi-dimensional data features, insufficient response to dynamic changes during the welding process, resulting in low prediction accuracy, lack of intelligence and self-adaptability, often relying on manual experience for adjustment, difficulty in achieving precise thermal deformation compensation, and inability to meet the requirements of high-precision manufacturing.

[0005] Therefore, there is an urgent need for a solution to solve the problems existing in the existing technologies. Summary of the Invention

[0006] The embodiments of the present invention provide an intelligent compensation and control method and system for thermal deformation during the welding process of metal parts, which can at least solve some of the problems existing in the existing technologies.

[0007] In the first aspect of the embodiments of the present invention, an intelligent compensation and control method for thermal deformation during the welding process of metal parts is provided, including:

[0008] Obtain the three-dimensional model data and welding process parameters of the metal part;

[0009] Based on the three-dimensional model data, construct a thermo-mechanical coupling analysis model, divide the metal part into multiple hexahedral mesh elements and establish a nonlinear heat conduction equation set, model the welding heat source as a double ellipsoidal heat source distribution function, construct a coupling transfer matrix between the temperature field and the stress field, and use an explicit integration algorithm to solve the nonlinear heat conduction equation set to obtain the transient temperature field distribution of the metal part;

[0010] Collect the real-time temperature data and real-time strain data during the welding process of the metal part;

[0011] Construct the hexahedral mesh elements into a dynamic hierarchical graph structure, calculate the thermal conduction relationship between the mesh elements based on the transient temperature field distribution, the real-time temperature data, the real-time strain data, and the welding process parameters, fuse the features of different scales using an adaptive attention mechanism, extract spatio-temporal features through a bidirectional propagation neural network, and generate the thermal deformation prediction result of the metal part;

[0012] Compare the thermal deformation prediction result with a preset thermal deformation threshold to determine the thermal deformation deviation. Based on the thermal deformation deviation, take the welding process parameters as the optimization variables, and calculate the compensation scheme using a recursive optimizer that combines the integrated gradient strategy and the evolutionary strategy. Iteratively solve to obtain the optimal welding process parameters and send them to the welding component for execution.

[0013] In an alternative embodiment,

[0014] Construct a thermo-mechanical coupling analysis model based on the three-dimensional model data. Divide the metal part into multiple hexahedral mesh elements and establish a non-linear heat conduction equation set, including:

[0015] Obtain the three-dimensional model data of the metal part. After eliminating duplicate faces and hanging edges, identify and extract the key geometric features of the weld area and the heat-affected zone, establish a feature topology relationship graph, establish a stress analysis equation set based on the feature topology relationship graph, and perform an associative mapping between the stress analysis equation set and the temperature field distribution equation set to construct a thermo-mechanical coupling analysis model;

[0016] Calculate the surface curvature distribution of the three-dimensional model data based on the thermo-mechanical coupling analysis model. Determine the curvature value according to the surface curvature distribution. Compare the curvature value with a preset curvature threshold to determine the mesh encryption area. Determine the minimum mesh size and the maximum mesh size according to the mesh encryption area, establish a mesh size calculation function, and perform mesh division on the metal part to generate initial hexahedral mesh elements;

[0017] Calculate the determinant value, the mesh angle, and the side length ratio of the initial hexahedral mesh elements, compare them with the preset mesh quality parameters, adjust the node positions and reconstruct the boundaries of the hexahedral mesh elements that do not meet the preset mesh quality parameters, and perform segmentation processing on the irregular hexahedral mesh elements to obtain optimized hexahedral mesh elements and establish a non-linear heat conduction equation set including temperature-dependent specific heat capacity coefficients and temperature-dependent thermal conductivity coefficients.

[0018] In an alternative embodiment,

[0019] The welding heat source is modeled as a double-ellipsoid heat source distribution function, a coupling transfer matrix of the temperature field and the stress field is constructed, and an explicit integration algorithm is used to solve the nonlinear heat conduction equations to obtain the transient temperature field distribution of the metal part, including:

[0020] According to the welding voltage, welding current, thermal efficiency, semi-major axis of the ellipsoid, semi-minor axis of the ellipsoid, semi-depth axis of the ellipsoid, and heat distribution coefficient, the front-ellipsoid heat source distribution function and the rear-ellipsoid heat source distribution function are established to obtain the initial heat source density distribution;

[0021] According to the initial heat source density distribution, the temperature distribution is calculated, the temperature-dependent coefficient of thermal expansion is obtained and the thermal strain is calculated, and the thermal strain is superimposed with the elastic strain and the plastic strain to obtain the total strain;

[0022] Based on the total strain, a heat conduction stiffness matrix, a heat capacity matrix, a heat load vector, a structural stiffness matrix, a structural damping matrix, and a mechanical load vector are constructed, and a coupling transfer matrix of the temperature field and the stress field and the corresponding nonlinear heat conduction equations are combined. The explicit integration initial time step is determined based on the element characteristic length, the elastic wave speed, and the system characteristic frequency;

[0023] At the explicit integration initial time step, the velocity increment and displacement increment of the nonlinear heat conduction equations are calculated by the central difference scheme, the stress increment is determined and substituted into the nonlinear heat conduction equations for explicit integration calculation to obtain the initial value of the temperature field. Based on the initial value of the temperature field, the temperature error is calculated, the adaptive time step is determined and substituted into the nonlinear heat conduction equations for explicit integration iterative calculation to obtain the transient temperature field distribution of the metal part.

[0024] In an alternative embodiment,

[0025] At the explicit integration initial time step, the velocity increment and displacement increment of the nonlinear heat conduction equations are calculated by the central difference scheme, the stress increment is determined and substituted into the nonlinear heat conduction equations for explicit integration calculation to obtain the initial value of the temperature field, including:

[0026] At the explicit integration initial time step, the current velocity increment is calculated by adding the product of the previous velocity increment and the time step and the acceleration, and the current displacement increment is calculated by adding the product of the previous displacement increment and the time step and the current velocity increment;

[0027] The coefficient of thermal expansion is multiplied by the temperature increment and the unit tensor to obtain the thermal strain increment. Whether plastic deformation occurs is determined according to the current stress state and the plastic strain increment is calculated. The elastic strain increment is obtained by subtracting the thermal strain increment and the plastic strain increment from the total strain increment, and the stress increment is calculated by the elastic modulus and the elastic strain increment;

[0028] The partial derivative of internal energy with respect to time is subtracted from the divergence of heat flux density and the heat source term, and the absolute value is calculated to obtain the energy balance error and the correction coefficient. The exponential function of the absolute value of the temperature gradient is multiplied by the linear function of the absolute value of the gradient of the stress increment to calculate the adaptive weight function. The correction coefficient is multiplied by the energy balance error and the temperature gradient direction and the negative value is calculated to obtain the temperature correction amount. The corrected temperature field is calculated based on the adaptive weight function and the temperature correction amount;

[0029] The stress increment is substituted into the nonlinear heat conduction equation set for explicit integration calculation to obtain the second temperature field distribution. The norm ratio of the difference between the corrected temperature field and the second temperature field distribution, and the norm of the energy balance error are respectively compared with the temperature field convergence tolerance and the energy balance convergence tolerance. Based on the comparison results, iterative calculation is performed to obtain the initial value of the temperature field.

[0030] In an alternative embodiment,

[0031] The hexahedral mesh elements are constructed into a dynamic hierarchical graph structure. Based on the transient temperature field distribution, the real-time temperature data, the real-time strain data, and the welding process parameters, the thermal conduction relationship between the mesh elements is calculated. The adaptive attention mechanism is used to fuse features at different scales, and spatio-temporal features are extracted through a bidirectional propagation neural network. The generated thermal deformation prediction results of the metal part include:

[0032] An octree space partitioning structure is constructed based on the center point coordinates of the hexahedral mesh elements. The topological adjacency relationship between the mesh elements is calculated. Spatial coordinates and hierarchical indices are assigned to each mesh node to generate a dynamic hierarchical graph structure. The geometric features, topological features, and physical features of each mesh node are extracted to form a node feature vector. The product of the exponential function of the squared Euclidean distance of the spatial positions of the mesh nodes and the exponential function of the hierarchical difference of the mesh nodes is calculated to obtain the connection weight between the mesh nodes;

[0033] The transient temperature field distribution, the real-time temperature data, and the real-time strain data are input into the conduction calculation model. The temperature difference and strain difference between adjacent mesh nodes are calculated and respectively subjected to exponential mapping to obtain the temperature influence factor and the strain influence factor. The thermal conductivity between adjacent mesh nodes is determined in combination with the material thermal conductivity. Based on the thermal conductivity and the current welding process parameters, the thermal conduction relationship between the mesh elements is established;

[0034] Input features of different scales into the adaptive attention mechanism, calculate the scale attention weights through the dot product operation between the grid scale hierarchical features and the global feature matrix, perform weighted summation on the grid scale hierarchical features after feature transformation to obtain the fused features, and input the fused features into the bidirectional propagation neural network. Use the gated recurrent unit for forward propagation to obtain the forward hidden state, perform backward propagation to obtain the backward hidden state, concatenate the forward hidden state and the backward hidden state, and extract spatio-temporal features;

[0035] Input the spatio-temporal features and the constraint conditions into the prediction function, calculate the deformation field in combination with the topological thermal field self-correction mechanism, estimate the prediction uncertainty based on the deformation field and the spatio-temporal features, and generate the thermal deformation prediction result of the metal part.

[0036] In an optional implementation manner,

[0037] Inputting the spatio-temporal features and the constraint conditions into the prediction function, calculating the deformation field in combination with the topological thermal field self-correction mechanism, estimating the prediction uncertainty based on the deformation field and the spatio-temporal features, and generating the thermal deformation prediction result of the metal part includes:

[0038] Input the spatio-temporal features of the metal part and the preset constraint conditions into the prediction function, where the constraint conditions include the thermo-mechanical coupling constitutive equation, and the thermo-mechanical coupling constitutive equation establishes the correlation between the stress tensor and the strain tensor through the elastic constant tensor and the coefficient of thermal expansion;

[0039] Construct a topological thermal field self-correction mechanism based on the persistent homology theory, calculate the Betti number sequence of the initial deformation field output by the prediction function to form the topological skeleton of the deformation field, calculate the persistence diagram of the initial deformation field according to the Betti number sequence, and calibrate the key deformation regions of the metal part according to the mutation points of the persistence diagram;

[0040] For the key deformation regions, construct a distance metric function to calculate the characteristic evolution trajectory of the topological skeleton of the deformation field, project the initial deformation field onto the manifold space that satisfies the constraint conditions to obtain the projected deformation field, and iteratively optimize the initial deformation field by minimizing the distance between the initial deformation field and the projected deformation field and the evolution trajectory distance of the topological skeleton of the deformation field to obtain the corrected deformation field;

[0041] Calculate the persistent homology entropy according to the corrected deformation field, weight the persistent homology entropy and the corrected deformation field to obtain the uncertainty evaluation value, input the corrected deformation field, the uncertainty evaluation value, and the spatio-temporal features into the preset basis function, and generate the thermal deformation prediction result of the metal part by calculating the weighted sum of the basis function.

[0042] In an optional implementation manner,

[0043] Compare the predicted thermal deformation result with a preset thermal deformation threshold to determine the thermal deformation deviation. Based on the thermal deformation deviation, take the welding process parameters as optimization variables, and calculate a compensation scheme using a recursive optimizer that combines the integrated gradient strategy and the evolutionary strategy. Iteratively solve to obtain the optimal welding process parameters and send them to the welding component for execution, including:

[0044] Compare the predicted thermal deformation result with a preset thermal deformation threshold to obtain the thermal deformation deviation, and perform a time integral on the thermal deformation deviation to calculate the cumulative thermal deformation deviation;

[0045] Take the welding process parameters as optimization variables, calculate the gradient of the thermal deformation deviation with respect to the welding process parameters and construct a gradient strategy, combine Gaussian noise to construct an evolutionary strategy, and integrate the gradient strategy and the evolutionary strategy to construct a recursive optimizer;

[0046] Based on the recursive optimizer, establish an optimization objective function that includes the thermal deformation deviation, perform constraint processing on the value range and change rate of the welding process parameters based on the gradient of the thermal deformation deviation, and take the welding process parameters that meet the convergence conditions as the optimal welding process parameters and send them to the welding component to perform the welding operation.

[0047] In the second aspect of the embodiments of the present invention, a thermal deformation intelligent compensation and control system during the welding of metal parts is provided, including:

[0048] The first unit is used to obtain the three-dimensional model data and welding process parameters of the metal part;

[0049] The second unit is used to construct a thermo-mechanical coupling analysis model based on the three-dimensional model data, divide the metal part into multiple hexahedral mesh units and establish a non-linear heat conduction equation set, model the welding heat source as a double ellipsoidal heat source distribution function, construct a coupling transfer matrix between the temperature field and the stress field, and use an explicit integration algorithm to solve the non-linear heat conduction equation set to obtain the transient temperature field distribution of the metal part;

[0050] The third unit is used to collect the real-time temperature data and real-time strain data during the welding process of the metal part;

[0051] The fourth unit is used to construct the hexahedral mesh units into a dynamic hierarchical graph structure, calculate the thermo-mechanical conduction relationship between the mesh units based on the transient temperature field distribution, the real-time temperature data, the real-time strain data, and the welding process parameters, use an adaptive attention mechanism to fuse features at different scales, extract spatio-temporal features through a bidirectional propagation neural network, and generate the thermal deformation prediction result of the metal part;

[0052] The fifth unit is used to compare the predicted results of thermal deformation with a preset thermal deformation threshold to determine the thermal deformation deviation. Based on the thermal deformation deviation, the welding process parameters are used as optimization variables, and a recursive optimizer combining the integrated gradient strategy and the evolutionary strategy is used to calculate a compensation scheme. Through iterative solution, the optimal welding process parameters are obtained and sent to the welding component for execution.

[0053] In the third aspect of the embodiments of the present invention, an electronic device is provided, including:

[0054] A processor and a memory for storing instructions executable by the processor, wherein the processor is configured to call the instructions stored in the memory to execute the method described above.

[0055] In the fourth aspect of the embodiments of the present invention, a computer-readable storage medium is provided, on which computer program instructions are stored, and when the computer program instructions are executed by a processor, the method described above is implemented.

[0056] In the present invention, by constructing a thermo-mechanical coupling analysis model and combining real-time collected temperature and strain data, the thermal deformation behavior of metal parts during the welding process can be accurately predicted, the precise prediction and control of welding deformation can be realized, the welding deformation error is effectively reduced, the welding accuracy is improved, the hexahedral mesh elements are constructed into a dynamic hierarchical graph structure, and the adaptive attention mechanism is used to fuse different-scale features, and the spatio-temporal features are extracted through a bidirectional propagation neural network, which improves the accuracy and real-time performance of thermal deformation prediction, enables the system to adapt to complex and changeable welding working conditions, and uses a recursive optimizer combining the integrated gradient strategy and the evolutionary strategy to calculate a compensation scheme, realizing the intelligent optimization and adjustment of welding process parameters, being able to automatically generate the optimal welding parameters according to the thermal deformation prediction results, greatly improving the welding automation level and production efficiency, and reducing manual intervention and material waste. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1 It is a schematic flowchart of the method for intelligent compensation and control of thermal deformation during the welding process of metal parts in the embodiments of the present invention;

[0058] Figure 2 It is a simulation diagram of the development of the plastic zone of the method for intelligent compensation and control of thermal deformation during the welding process of metal parts in the embodiments of the present invention;

[0059] Figure 3 It is a comparison diagram of the topological skeleton evolution trajectories of the method for intelligent compensation and control of thermal deformation during the welding process of metal parts in the embodiments of the present invention;

[0060] Figure 4 It is a flowchart for solving the optimal welding parameters of the method for intelligent compensation and control of thermal deformation during the welding process of metal parts in the embodiments of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0061] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Apparently, the described embodiments are only a part rather than all of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0062] The technical solutions of the present invention will be described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments.

[0063] Figure 1 It is a schematic flow chart of the intelligent compensation and control method for thermal deformation during the welding process of metal parts in the embodiments of the present invention. As Figure 1 shown, the method includes:

[0064] Obtain the three-dimensional model data and welding process parameters of the metal part;

[0065] Based on the three-dimensional model data, construct a thermo-mechanical coupling analysis model, divide the metal part into multiple hexahedral mesh elements and establish a non-linear heat conduction equation set, model the welding heat source as a double ellipsoidal heat source distribution function, construct a coupling transfer matrix of the temperature field and the stress field, and use an explicit integration algorithm to solve the non-linear heat conduction equation set to obtain the transient temperature field distribution of the metal part;

[0066] Collect the real-time temperature data and real-time strain data during the welding process of the metal part;

[0067] Construct the hexahedral mesh elements into a dynamic hierarchical graph structure, calculate the thermo-mechanical conduction relationship between the mesh elements based on the transient temperature field distribution, the real-time temperature data, the real-time strain data, and the welding process parameters, use an adaptive attention mechanism to fuse features at different scales, extract spatio-temporal features through a bidirectional propagation neural network, and generate the thermal deformation prediction result of the metal part;

[0068] Compare the thermal deformation prediction result with a preset thermal deformation threshold to determine the thermal deformation deviation. Based on the thermal deformation deviation, use the welding process parameters as optimization variables, and calculate a compensation scheme using a recursive optimizer that combines the integrated gradient strategy and the evolutionary strategy. Iteratively solve to obtain the optimal welding process parameters and send them to the welding component for execution.

[0069] In an alternative embodiment,

[0070] Construct a thermo-mechanical coupling analysis model based on the 3D model data, divide the metal part into multiple hexahedral mesh elements, and establish a non-linear heat conduction equation set, including:

[0071] Obtain the 3D model data of the metal part, identify and extract the key geometric features of the weld area and the heat affected zone after eliminating the duplicate faces and dangling edges, establish a feature topology relationship graph, establish a stress analysis equation set based on the feature topology relationship graph, and perform an associative mapping between the stress analysis equation set and the temperature field distribution equation set to construct a thermo-mechanical coupling analysis model;

[0072] Calculate the surface curvature distribution of the 3D model data based on the thermo-mechanical coupling analysis model, determine the curvature value according to the surface curvature distribution, compare the curvature value with a preset curvature threshold to determine the mesh encryption area, determine the minimum mesh size and the maximum mesh size according to the mesh encryption area, establish a mesh size calculation function, and perform mesh division on the metal part to generate initial hexahedral mesh elements;

[0073] Calculate the determinant value, mesh angle, and side length ratio of the initial hexahedral mesh elements, compare them with the preset mesh quality parameters, adjust the node positions and reconstruct the boundaries of the hexahedral mesh elements that do not meet the preset mesh quality parameters, and perform segmentation processing on the irregular hexahedral mesh elements to obtain optimized hexahedral mesh elements and establish a non-linear heat conduction equation set including temperature-dependent specific heat capacity coefficients and temperature-dependent thermal conductivity coefficients.

[0074] Import the 3D model data of the metal part, use the spatial topology search algorithm to traverse all face elements in the model in turn, and identify duplicate face elements by comparing the normal vectors and boundary vertex coordinates of the face elements. For the identified duplicate face elements, retain one of them and delete the other duplicate faces. Use the connectivity analysis method to detect the boundary elements. If an edge is only connected to one face element, it is determined as a dangling edge and deleted.

[0075] Use the region growing algorithm to identify the weld area, starting from the weld center line, and expand outward based on the curvature continuity and geometric feature similarity criteria until the weld boundary is reached. On the basis of determining the weld area, use the temperature gradient prediction method to determine the range of the heat affected zone, and mark the area with a sharp temperature change as the heat affected zone. Extract the key geometric features of the weld and the heat affected zone, including feature points, feature lines, and feature surfaces.

[0076] When constructing the feature topological relationship graph, the graph theory method is used to map geometric features to the nodes of the graph, and the spatial association relationship between features is mapped to the edges of the graph. All features are traversed through the depth-first search algorithm to establish a complete topological connection relationship. Based on the topological connection relationship graph, the stress transfer path analysis method is adopted to identify the main stress paths and stress concentration areas, and an equilibrium equation set describing the stress distribution is established.

[0077] Meanwhile, an equation set for the temperature field distribution is established, and the thermal-mechanical coupling algorithm is used to perform an associative mapping of the stress field and the temperature field through material properties. Specifically, through the iterative solution method, the temperature field and the stress field are alternately updated in each iteration step until the two fields reach an equilibrium state, thereby obtaining a complete thermal-mechanical coupling analysis model.

[0078] The differential geometry algorithm is used to calculate the curvature distribution on the model surface. First, a local coordinate system of the surface is constructed to calculate the principal curvature and the Gaussian curvature. The adaptive threshold segmentation method is adopted to compare the curvature values with the dynamically determined threshold to identify the high-curvature areas that require mesh refinement. Combining the overall size of the model, the minimum and maximum mesh sizes are determined through a proportional relationship.

[0079] A mesh size calculation function considering the curvature distribution is established. This function adopts the distance weighted interpolation algorithm to smoothly transition to a smaller mesh size in the high-curvature area and gradually transition to a larger mesh size in the low-curvature area. The octree meshing algorithm is used for the initial mesh division, and it is determined whether to continue subdividing according to the mesh size function in each meshing step.

[0080] The initial mesh is evaluated for quality, and the quality parameters of each mesh element are calculated. The mesh smoothing algorithm is used to optimize the mesh elements that do not meet the quality requirements, and the mesh shape is improved through iterative optimization of the node positions. For severely deformed mesh elements, the mesh reconstruction algorithm is used to regenerate the local mesh. For irregular hexahedral meshes, the template matching method is used to divide them into multiple regular mesh elements.

[0081] On the optimized mesh, the finite element interpolation method is used to construct a temperature-related material property distribution function, and the specific heat capacity coefficient and the thermal conductivity are expressed as functions of temperature. Based on the temperature-related material properties, a nonlinear heat conduction equation set is constructed, and the matrix assembly algorithm is used to generate the global stiffness matrix and the load vector.

[0082] Exemplarily, taking a T-shaped welded joint as an example, it is formed by vertically welding two plates. After importing the three-dimensional model of the T-shaped joint, the overlapping surfaces at the lap joint of the two plates and the hanging edges at the edges are deleted. The geometric features of the vertical weld area are determined through feature recognition, and the heat-affected zone range is determined by expanding outward with the weld as the center. The spatial relationships between features such as the weld, the heat-affected zone, and the plates are organized into a topological relationship graph.

[0083] Analyze the stress transfer path based on the topological relationship diagram, establish the stress analysis equations, and simultaneously establish the temperature field distribution equations. Connect the two sets of equations through the coefficient of thermal expansion to construct a thermo-mechanical coupling analysis model. Calculate the surface curvature distribution of the T-joint and find that the curvature values at the weld and the heat-affected zone are relatively large. Mark these areas as mesh refinement regions.

[0084] Set the minimum mesh size to 2 mm and the maximum mesh size to 10 mm, and establish a mesh size calculation function. Conduct an initial mesh division for the T-joint, using a denser mesh at the weld and the heat-affected zone and a sparser mesh in the regions far from the weld. After evaluating the mesh quality, it is found that there are severely deformed mesh elements at the weld corners. Improve the mesh quality through node position optimization and mesh reconstruction. Establish the heat conduction equations on the optimized mesh to complete the mesh division and equation construction work.

[0085] In this embodiment, the key geometric features of the weld area and the heat-affected zone can be accurately identified through spatial topology analysis and feature extraction methods, eliminating duplicate faces and hanging edges in the model, improving the accuracy of subsequent analysis. By using curvature analysis and adaptive mesh division strategies, the mesh is automatically refined in the regions with large stress and temperature gradients, and the mesh size is appropriately enlarged in the regions with gentle changes, which not only ensures the calculation accuracy but also improves the calculation efficiency. Through mesh quality evaluation and optimization algorithms, the mesh quality is significantly improved, reducing the numerical calculation errors caused by mesh distortion and improving the accuracy of the thermal deformation analysis results.

[0086] In an alternative embodiment,

[0087] Model the welding heat source as a double-ellipsoid heat source distribution function, construct the coupling transfer matrix of the temperature field and the stress field, and use the explicit integration algorithm to solve the nonlinear heat conduction equations to obtain the transient temperature field distribution of the metal part, including:

[0088] Establish the front-ellipsoid heat source distribution function and the rear-ellipsoid heat source distribution function according to the welding voltage, welding current, thermal efficiency, semi-major axis of the ellipsoid, semi-minor axis of the ellipsoid, semi-depth axis of the ellipsoid, and heat distribution coefficient to obtain the initial heat source density distribution;

[0089] Calculate the temperature distribution according to the initial heat source density distribution, obtain the temperature-related coefficient of thermal expansion and calculate the thermal strain, and superimpose the thermal strain with the elastic strain and plastic strain to obtain the total strain;

[0090] Construct the heat conduction stiffness matrix, heat capacity matrix, heat load vector, structural stiffness matrix, structural damping matrix, and mechanical load vector based on the total strain, combine them to construct the coupling transfer matrix of the temperature field and the stress field and the corresponding nonlinear heat conduction equations, and determine the explicit integration initial time step based on the element characteristic length, elastic wave speed, and system characteristic frequency;

[0091] At the explicit integration initial time step, the velocity increment and displacement increment of the nonlinear heat conduction equations are calculated by the central difference scheme, the stress increment is determined and substituted into the nonlinear heat conduction equations for explicit integration calculation to obtain the initial value of the temperature field. Based on the initial value of the temperature field, the temperature error is calculated, the adaptive time step is determined and substituted into the nonlinear heat conduction equations for explicit integration iterative calculation to obtain the transient temperature field distribution of the metal part.

[0092] A double-ellipsoid heat source distribution model is constructed through welding process parameters, and the front and rear ellipsoid heat sources are described by different spatial distribution functions. The total heat input power is determined according to the welding voltage and current, and the effective heat input is calculated in combination with the heat efficiency. Based on the semi-major axis, semi-minor axis and semi-depth axis of the ellipsoid, the spatial distribution shape of the heat source is defined, and the total heat is distributed to the front and rear ellipsoid regions through the heat distribution coefficient. The front ellipsoid heat source distribution function and the rear ellipsoid heat source distribution function are established respectively, and the two distribution functions are superimposed to obtain the complete initial heat source density distribution.

[0093] The transient heat conduction analysis method is adopted, with the initial heat source density distribution as the input, to calculate the temperature distribution during welding. The thermal expansion coefficient at different temperatures is obtained from the material property database, and the thermal strain is obtained by multiplying the temperature field change by the thermal expansion coefficient. At the same time, the elastic strain generated by the material under the action of temperature and load is calculated, and the plastic strain is calculated when the stress exceeds the yield strength. The three strains are superimposed to obtain the total strain.

[0094] Based on the finite element discretization method, the thermo-mechanical coupling matrix is constructed using the total strain. The heat conduction stiffness matrix and heat capacity matrix describing the heat conduction characteristics are established, and the heat load vector reflecting the heat source input is constructed. The structural stiffness matrix, structural damping matrix describing the structural deformation characteristics, and the mechanical load vector reflecting the mechanical constraints are established. The matrices are combined into the coupling transfer matrix of the temperature field and stress field through the coupling algorithm, and the corresponding nonlinear heat conduction equations are established.

[0095] The element characteristic length is calculated by the mesh size analysis method, the elastic wave speed is determined in combination with the material elastic modulus and density, and the system characteristic frequency is obtained through modal analysis. Based on these parameters, the explicit integration initial time step is determined, and this step needs to meet the calculation stability requirements. Within the determined time step, the central difference scheme is used to discretize the nonlinear heat conduction equations, and the velocity increment and displacement increment of each time step are calculated.

[0096] The stress increment is calculated based on the velocity increment and displacement increment, and the stress increment is substituted into the nonlinear heat conduction equations for explicit integral calculation to obtain the initial value of the temperature field. The temperature error is calculated by comparing with the measured temperature data, and the adaptive time step is determined based on the temperature error and temperature gradient. The iterative calculation method is used to solve the nonlinear heat conduction equations in each adaptive time step until the temperature field and displacement field converge, and the transient temperature field distribution of the metal parts during the entire welding process is obtained.

[0097] For example, taking stainless steel plate butt welding as an example, the welding voltage is 25 volts, the current is 200 amperes, and the thermal efficiency is 0.8. According to the welding process and material characteristics, the long semi-axis of the front ellipsoid heat source is set to 8 mm, the wide semi-axis is 6 mm, and the deep semi-axis is 5 mm. The corresponding parameters of the rear ellipsoid are 12 mm, 8 mm, and 7 mm, respectively. The heat distribution coefficient is 0.4 for the front ellipsoid and 0.6 for the rear ellipsoid.

[0098] The heat source density distribution in the weld area is calculated by the double ellipsoid heat source model. The heat source density in the front ellipsoid area is large and concentrated, while the heat source density in the rear ellipsoid area is relatively small but has a larger distribution range. Based on the heat source distribution, the temperature field is calculated. The temperature in the center of the weld can reach up to 1800 degrees Celsius, and the temperature decreases rapidly with increasing distance.

[0099] Combined with the temperature-related material properties of stainless steel, the maximum thermal strain in the weld area is calculated to be about 0.02, and the thermal strain in the heat-affected zone is between 0.005 and 0.015. After superimposing the elastic strain and plastic strain, the total strain in the weld area can reach 0.035. Based on these strain values, the coupling matrix is constructed, the characteristic length of the grid near the weld is taken as 0.5 mm, and the calculated stable time step is 0.0001 seconds.

[0100] The initial temperature field distribution is obtained by explicit integral calculation, and the maximum error is within 5% compared with the measured temperature. Adaptive time step algorithm is used, and the time step is automatically reduced to 0.00005 seconds in the area of ​​drastic temperature changes, and the time step is increased to 0.0002 seconds in the area of ​​gentle temperature changes. After about 2000 steps of iterative calculation, a complete transient temperature field distribution cloud map is obtained.

[0101] In this embodiment, by constructing an accurate double ellipsoid heat source model and a thermal-mechanical coupling analysis method, high-precision prediction of the temperature field and stress field during the welding process is achieved. By establishing a full-field strain analysis model including thermal strain, elastic strain and plastic strain, the nonlinear mechanical behavior of the material under high temperature conditions is accurately reflected. The adaptive time step strategy dynamically adjusts the calculation step according to the temperature gradient and the severity of the stress change, which significantly improves the calculation efficiency while ensuring the calculation accuracy, and provides a reliable theoretical basis for welding process optimization and quality control.

[0102] In an alternative embodiment,

[0103] At the explicit integration initial time step, calculate the velocity increment and displacement increment of the nonlinear heat conduction equations by the central difference scheme, determine the stress increment and substitute it into the nonlinear heat conduction equations for explicit integration calculation, and the initial temperature field obtained includes:

[0104] At the explicit integration initial time step, add the product of the velocity increment at the previous moment, the time step, and the acceleration to calculate the velocity increment at the current moment, and add the product of the displacement increment at the previous moment, the time step, and the velocity increment at the current moment to calculate the displacement increment at the current moment;

[0105] Multiply the coefficient of thermal expansion by the temperature increment and the unit tensor to obtain the thermal strain increment, determine whether plastic deformation occurs according to the current stress state and calculate the plastic strain increment, subtract the thermal strain increment and the plastic strain increment from the total strain increment to obtain the elastic strain increment, and calculate the stress increment through the elastic modulus and the elastic strain increment;

[0106] Subtract the partial derivative of the internal energy with respect to time from the divergence of the heat flux density and the heat source term and take the absolute value to calculate the energy balance error and the correction coefficient, multiply the exponential function of the absolute value of the temperature gradient by the linear function of the absolute value of the gradient of the stress increment to obtain the adaptive weight function, multiply the correction coefficient by the energy balance error and the temperature gradient direction and take the negative value to calculate the temperature correction amount, and calculate the corrected temperature field based on the adaptive weight function and the temperature correction amount;

[0107] Substitute the stress increment into the nonlinear heat conduction equations for explicit integration calculation to obtain the second temperature field distribution, compare the norm ratio of the difference between the corrected temperature field and the second temperature field distribution and the norm of the energy balance error with the temperature field convergence tolerance and the energy balance convergence tolerance respectively, and perform iterative calculation based on the comparison results to obtain the initial temperature field.

[0108] Within the explicit integration initial time step, perform dynamic response analysis using a recursive algorithm. Construct an acceleration influence matrix, combine the velocity state at the previous moment with the acceleration influence, and calculate the velocity increment at the current moment through a time-domain integrator. Adopt a similar recursive strategy to establish a displacement prediction model, couple the displacement state at the previous moment with the velocity influence, and obtain the displacement increment at the current moment through time step mapping.

[0109] The strain analysis adopts a multi-field coupling decomposition strategy. A thermal strain calculation model is established to perform tensor mapping of the thermal expansion characteristics of the material and the temperature field changes to obtain the thermal strain increment field in three-dimensional space. A plasticity criterion evaluator is constructed to judge the stress state of each calculation point through the yield surface evolution algorithm. When the stress exceeds the yield surface, the plastic flow calculator is started and the iterative projection method is used to solve the plastic strain increment. The strain decomposition algorithm performs differential operations on the total strain increment, the thermal strain increment and the plastic strain increment to obtain the elastic strain increment, and then calculates the stress increment through the material constitutive model.

[0110] The energy balance correction adopts an adaptive multi-scale algorithm. An internal energy derivative calculator is constructed, and the internal energy change rate is calculated using the time discretization method. The difference operation is performed with the heat flux density divergence operator and the heat source term to obtain the energy balance error. An adaptive correction function is constructed based on the error distribution. The function adopts the polynomial basis function expansion method, and the coefficients are determined by least squares optimization. At the same time, a gradient weight analyzer is established, and the temperature gradient uses an exponential mapping function for feature enhancement, and the stress gradient uses a piecewise linear function for feature extraction.

[0111] The temperature field correction process adopts an iterative optimization strategy. The energy balance correction function and the temperature gradient direction field are tensor-producted to construct a temperature correction operator. The adaptive weight function is used to modulate the spatial distribution of the correction value. The weight function is automatically adjusted through local feature analysis, and the weight is increased in areas with drastic gradient changes to ensure the effectiveness of the correction. The corrected temperature field is smoothed by the relaxation iteration method to ensure the continuity of the temperature distribution.

[0112] The convergence analysis adopts a multi-criteria judgment method. The stress increment is substituted into the nonlinear equation group to construct a residual calculator, and the second temperature field is obtained by an explicit integration algorithm. A field difference evaluator is established, and the difference between the corrected temperature field and the second temperature field is compared by the norm calculation method. At the same time, an energy balance evaluator is constructed to calculate the norm of the energy balance error. A dual threshold judgment criterion is used to compare with the temperature field convergence tolerance and the energy balance convergence tolerance respectively. If any indicator exceeds the tolerance range, the adaptive time step adjuster is started, and the calculation parameters are updated and the iteration loop is re-entered until all convergence indicators meet the requirements, and the initial value of the temperature field is finally determined.

[0113] For example, taking the stainless steel plate welding process as an example, the initial time step is set to 0.0001 seconds. Within this time step, the velocity increment of a certain calculation point at the previous moment is 0.002 mm / s. After considering the influence of acceleration, the velocity increment at the current moment is calculated to be 0.0025 mm / s. Combined with the displacement increment of 0.0015 mm at the previous moment, the displacement increment at the current moment is calculated to be 0.002 mm.

[0114] The temperature at this calculation point increases from 800 degrees Celsius to 820 degrees Celsius. The corresponding coefficient of thermal expansion is 0.000012 per degree Celsius, and the calculated thermal strain increment is 0.00024. Checking the stress state reveals that it has exceeded the yield strength of 300 MPa, and the calculated plastic strain increment is 0.00015. Subtracting these two components from the total strain increment of 0.0005 gives an elastic strain increment of 0.00011, and the calculated stress increment is 22 MPa.

[0115] The energy balance analysis shows that the energy balance error at this point is 0.5 joules per cubic millimeter, and based on this, the correction coefficient is determined to be 0.8. The temperature gradient at this point is 50 degrees Celsius per millimeter, the stress gradient is 15 MPa per millimeter, and the calculated value of the adaptive weight function is 1.2. Considering these parameters, the calculated temperature correction is 2 degrees Celsius, and the temperature field is corrected.

[0116] Substitute the calculation results into the system of equations for explicit integration to obtain the second temperature field distribution. Comparing, it is found that the ratio of the difference norm between the corrected temperature field and the second temperature field is 0.002, and the energy balance error norm is 0.003. Both of these values are less than the preset convergence tolerance of 0.005. Therefore, the initial value of the temperature field at this point is determined to be 818 degrees Celsius.

[0117] In this embodiment, by constructing a recursive dynamic response analysis algorithm, high-precision calculations of the velocity increment and displacement increment are achieved. Using a multi-field coupling decomposition strategy, the total strain is decomposed into thermal strain, plastic strain, and elastic strain, accurately capturing the nonlinear mechanical behavior of the material under high-temperature conditions. Through an adaptive multi-scale algorithm for energy balance correction, a weight function based on local characteristics is established, achieving precise correction of the temperature field;

[0118] In the prior art, the calculation of the welding temperature field usually uses a simple explicit integration method, lacking an adaptive adjustment mechanism in the selection of time steps, with low calculation efficiency. Treating the temperature field and stress field separately ignores the multi-field coupling effect, resulting in insufficient calculation accuracy. The prior art mostly uses a globally unified correction coefficient, which is difficult to accurately reflect the temperature and stress change characteristics of local regions and affects the accuracy of the calculation results;

[0119] In this embodiment, through an adaptive time step control and multi-criterion convergence judgment method, the number of iterations is significantly reduced, improving the calculation speed. The multi-field coupling analysis and adaptive correction strategy make the calculation results of the temperature field and stress field closer to the actual physical process. By establishing a complete error control mechanism, the convergence and reliability of the numerical solution are ensured, providing reliable theoretical support for welding process optimization and quality control.

[0120] Figure 2This is a simulation diagram of the development of the plastic zone in the intelligent compensation and control method for thermal deformation during the welding process of metal parts in the embodiments of the present invention, showing the evolution process of the plastic zone during the welding process of a stainless steel plate over time. The figure shows a cross-sectional view of the weld, with concentric circles representing the boundaries of the plastic zone at three time points: the initial stage (0.5 s), the middle stage (2.5 s), and the later stage (4.5 s) of welding. Different colors represent different prediction methods or experimental measurement values. The radius of the plastic zone predicted by this technical solution (red line) at the initial stage of welding is 3.25 mm, with an error of only 2.11% compared to the experimental measurement value (purple line) of 3.32 mm; at the middle stage of welding, the predicted value is 5.87 mm, with an error of 2.49% compared to the experimental value of 6.02 mm; at the later stage of welding, the predicted value is 7.43 mm, with an error of 1.98% compared to the experimental value of 7.58 mm. The predicted plastic zone radii of the traditional finite element method (blue line) at these three time points are 2.95 mm, 5.36 mm, and 6.84 mm respectively, with errors compared to the experimental values reaching 11.14%, 10.96%, and 9.76% respectively, which are significantly smaller than the experimental observation results. The predicted values of the Johnson-Cook model (green line) are 3.08 mm, 5.54 mm, and 7.12 mm respectively, with errors of 7.23%, 7.97%, and 6.07% respectively. Although the accuracy is higher than that of the traditional finite element method, it is still lower than this technical solution.

[0121] It can be clearly observed from the figure that as the welding time prolongs, the radius of the plastic zone continuously expands, and the expansion rate gradually decreases, reflecting the law of plastic deformation of the material at high temperatures. This technical solution successfully captures the non-linear plastic behavior of the material at high temperatures by accurately calculating the coupling effect of the thermal strain increment and the plastic strain increment. During the entire welding process (0.5 - 5.0 s), the average prediction error is only 2.26%, which reduces the errors by 78.8% and 68.9% compared to the traditional finite element method and the Johnson-Cook model respectively, achieving a high-precision simulation of the expansion process of the plastic zone.

[0122] In an alternative embodiment,

[0123] Construct the hexahedral mesh elements into a dynamic hierarchical graph structure, calculate the thermal conduction relationship between mesh elements based on the transient temperature field distribution, the real-time temperature data, the real-time strain data, and the welding process parameters, fuse different-scale features using an adaptive attention mechanism, extract spatio-temporal features through a bidirectional propagation neural network, and generate the thermal deformation prediction result of the metal part, including:

[0124] Construct an octree spatial partitioning structure based on the central point coordinates of hexahedral mesh elements, calculate the topological adjacency relationship between mesh elements, assign spatial coordinates and level indices to each mesh node, generate a dynamic hierarchical graph structure, extract the geometric, topological, and physical features of each mesh node to form a node feature vector, and calculate the product of the squared exponential function of the Euclidean distance of the mesh node spatial position and the exponential function of the mesh node level difference to obtain the connection weight between mesh nodes;

[0125] Input the transient temperature field distribution, real-time temperature data, and real-time strain data into the conduction calculation model, calculate the temperature difference and strain difference between adjacent mesh nodes and perform exponential mapping respectively to obtain the temperature influence factor and strain influence factor, determine the thermal conductivity between adjacent mesh nodes in combination with the material thermal conductivity, and establish the thermal conduction relationship between mesh elements based on the thermal conductivity and the current welding process parameters;

[0126] Input features of different scales into the adaptive attention mechanism, calculate the scale attention weight through the dot product operation between the mesh scale level features and the global feature matrix, perform weighted summation on the feature-transformed mesh scale level features to obtain the fused feature and input it into the bidirectional propagation neural network, use the gated recurrent unit for forward propagation to obtain the forward hidden state, perform backward propagation to obtain the backward hidden state, concatenate the forward hidden state and the backward hidden state, and extract spatio-temporal features;

[0127] Input the spatio-temporal features and constraint conditions into the prediction function, calculate the deformation field in combination with the topological thermal field self-correction mechanism, estimate the prediction uncertainty based on the deformation field and the spatio-temporal features, and generate the thermal deformation prediction result of the metal part.

[0128] Construct the mesh spatial structure. Starting from the central point of the hexahedral mesh element, adopt a recursive partitioning strategy to establish an octree spatial partitioning structure. By traversing adjacent elements, establish a topological connection relationship table between mesh elements and record the adjacent element information of each element. Assign three-dimensional spatial coordinates to each node in the mesh structure, and at the same time establish a level index system to construct a dynamic hierarchical graph structure with parent-child relationships. Extract the geometric, topological, and physical features of each mesh node, and combine these features to form a node feature vector. Adopt a spatial distance calculation method, multiply the squared exponential function of the Euclidean distance between nodes by the exponential function of the node level difference to obtain the connection weight matrix between mesh nodes.

[0129] Construct the thermal conduction relationship. Input the temperature field distribution data, temperature monitoring data, and strain monitoring data collected in real time into the conduction calculation model. Calculate the temperature gradient and strain gradient between adjacent grid nodes, and convert them into temperature influence factors and strain influence factors respectively through the exponential mapping function. Combine the thermal conductivity characteristics of the material to establish a calculation model for the thermal conductivity coefficient between adjacent grid nodes. Based on the current welding process parameters and the thermal conductivity coefficient, construct a thermal conduction relationship network between grid cells.

[0130] The adaptive feature extraction mechanism inputs feature data of different scales into the adaptive attention module, and calculates the attention weights through the correlation analysis of grid features and global features. Perform weighted fusion on the grid-scale hierarchical features after feature transformation to generate a fused feature vector. Input the fused feature into the bidirectional propagation network structure. In the forward propagation process, gradually extract the temporal features through the gated recurrent unit to obtain the forward hidden state. In the reverse propagation process, adopt a gating mechanism to extract features to obtain the reverse hidden state. Concatenate the forward and reverse hidden states to extract the complete spatio-temporal feature information.

[0131] Perform thermal deformation prediction and uncertainty analysis. Input the extracted spatio-temporal features and process constraint conditions into the prediction function module together. Through the topological thermal field self-correction mechanism, establish a deformation field prediction model to realize the prediction of the deformation state of metal parts. Based on the predicted deformation field and spatio-temporal features, construct an uncertainty estimation model to evaluate the reliability of the prediction results. Through comprehensive analysis, output the thermal deformation prediction results of metal parts.

[0132] Exemplarily, taking the steel plate welding process as an example, divide the welding area into grids. Establish a basic hexahedron grid according to the plate size, and densify the grid in the weld area to form a multi-level grid structure. Divide the welding area into spatial units of different levels through the octree algorithm. Smaller grid cells are used to describe the area near the weld, and larger grid cells are used to describe the far-field area. Assign spatial position information and level identifiers to each grid node to construct a complete grid topology structure.

[0133] Collect the temperature field distribution data during the welding process, arrange temperature sensors and strain sensors at key positions to monitor the temperature and strain changes in real time. Based on the monitoring data, calculate the temperature difference and strain difference between adjacent grid nodes, and obtain the temperature influence and strain influence characteristics of the local area through feature transformation. Combine the welding process parameters, such as welding current, voltage, and welding speed, to establish the heat transfer and force transfer relationships between grid cells.

[0134] Input the grid features into the adaptive attention module to evaluate the importance of features at different scales. The attention mechanism focuses on the regions with large temperature gradients and significant strain changes, and obtains the comprehensive feature representation through feature fusion. The feature information is processed in the bidirectional propagation network to extract the deformation features in the time dimension and space dimension, and capture the evolution law of thermal deformation.

[0135] Based on the extracted features and constraints, predict the distribution of the deformation field during the welding process. Correct the prediction results through the self-correction mechanism, and at the same time evaluate the uncertainty of the prediction, and give a reliable prediction result of thermal deformation, providing a basis for welding process optimization.

[0136] In this embodiment, the recursive dynamic response analysis method ensures the continuity and stability of the calculation of the velocity increment and displacement increment, effectively avoiding the oscillation phenomenon in the numerical calculation process. The strain decomposition algorithm can not only accurately capture the evolution law of thermal strain, but also timely identify the plastic deformation behavior of the material, ensuring the accuracy of stress calculation. According to the distribution characteristics of the temperature gradient and stress gradient, automatically adjust the correction parameters to make the temperature field calculation more in line with the actual characteristics of the physical process, and can accurately reflect the dynamic evolution law of the temperature field and stress field during the welding process, providing a reliable theoretical basis for welding process optimization and quality control, and having important engineering application value.

[0137] In an alternative embodiment,

[0138] Input the spatio-temporal features and constraints into the prediction function, calculate the deformation field in combination with the topological thermal field self-correction mechanism, estimate the prediction uncertainty based on the deformation field and the spatio-temporal features, and generate the thermal deformation prediction result of the metal part, including:

[0139] Input the spatio-temporal features of the metal part and the preset constraints into the prediction function, where the constraints include the thermo-mechanical coupling constitutive equation, and the thermo-mechanical coupling constitutive equation establishes the correlation between the stress tensor and the strain tensor through the elastic constant tensor and the coefficient of thermal expansion;

[0140] Construct a topological thermal field self-correction mechanism based on the persistent homology theory, calculate the Betti number sequence of the initial deformation field output by the prediction function to form the topological skeleton of the deformation field, calculate the persistence diagram of the initial deformation field according to the Betti number sequence, and calibrate the key deformation regions of the metal part according to the mutation points of the persistence diagram;

[0141] For the key deformation region, a distance metric function is constructed to calculate the characteristic evolution trajectory of the topological skeleton of the deformation field. The initial deformation field is projected onto a manifold space that satisfies the constraint conditions to obtain a projected deformation field. The initial deformation field is iteratively optimized to obtain a corrected deformation field by minimizing the distance between the initial deformation field and the projected deformation field and the distance of the evolution trajectory of the topological skeleton of the deformation field;

[0142] The persistent homology entropy is calculated based on the corrected deformation field, and the persistent homology entropy and the corrected deformation field are weighted to obtain an uncertainty evaluation value. The corrected deformation field, the uncertainty evaluation value, and the spatio-temporal features are input into a preset basis function, and the thermal deformation prediction result of the metal part is generated by calculating the weighted sum of the basis function.

[0143] The construction process of the prediction function first preprocesses the multi-dimensional spatio-temporal features. The spatio-temporal features are resampled by an adaptive sampling strategy to ensure the uniformity of the feature distribution. The time-series features are segmented by a sliding window method, and the features within each window are enhanced in their expression ability through non-linear transformation. The processing of the constraint conditions adopts a multi-level decomposition strategy to transform the thermo-mechanical coupling constitutive equation into a hierarchical constraint system. The influence of elastic constants and thermal expansion coefficients is integrated into the constraint space through tensor mapping to construct a complete stress-strain mapping relationship.

[0144] The persistent homology analysis adopts a multi-scale feature extraction method to construct a sequence of simplicial complexes of the initial deformation field, and extracts topological features of each dimension through boundary operator operations. When calculating the sequence of Betti numbers, a progressive feature filtering algorithm is adopted to screen out significant topological features layer by layer. For the features of each dimension, a persistence metric index is constructed to record the life cycle of the features. Key points in the persistence diagram are identified through a feature clustering method, and the key points correspond to important changes in the topological structure of the deformation field.

[0145] The construction process of the topological skeleton adopts a hierarchical processing strategy. At the coarsest scale, the main structural features are extracted to form the backbone of the skeleton. The accuracy is gradually increased, and secondary structural features are supplemented through a local refinement algorithm. In this process, a dynamic threshold method is adopted to filter out noise features to ensure the stability of the skeleton structure. At the same time, a feature transfer mechanism is established to ensure the coherence between features at different scales.

[0146] The calibration of the key deformation region adopts a multi-criterion judgment method. By analyzing the local features of the persistence diagram, a mutation point identifier is constructed. The identifier comprehensively considers factors such as feature duration, change amplitude, and spatial distribution, and adopts a weighted voting mechanism to determine the key region. To improve the recognition accuracy, spatial correlation analysis is introduced to consider the mutual influence of adjacent regions.

[0147] The construction of the distance metric function adopts an adaptive weight strategy. A local feature extractor is established to capture the local geometric and physical features of the deformation field. Through feature importance analysis, the weights of different features in distance calculation are dynamically adjusted. At the same time, temporal correlation analysis is introduced to ensure the continuity of the feature evolution trajectory.

[0148] The deformation field projection adopts an iterative optimization strategy. A manifold space that satisfies the constraint conditions is constructed, and this space is formed by the implicit expression of the constraint conditions. The progressive projection algorithm is used to gradually project the initial deformation field onto the target space. During the projection process, the projection direction is optimized by the gradient descent method to ensure convergence to the optimal solution.

[0149] The calculation of the feature evolution trajectory adopts the dynamic programming method. By constructing a state transition matrix, the state changes of the topological skeleton during the evolution process are recorded. The backtracking algorithm is used to extract the optimal evolution path, which satisfies both physical constraints and maintains the continuity of topological features.

[0150] The calculation of the persistent homology entropy adopts the multi-scale analysis method. The corrected deformation field is decomposed at multiple scales, and the local entropy values are calculated at each scale. The global entropy value is obtained through scale-weighted combination, which reflects the overall complexity of the deformation field. At the same time, an entropy value dynamic update mechanism is established to track the changes of the deformation field in real time.

[0151] The generation of the prediction result adopts the adaptive basis function expansion method. A basis function library is constructed, which contains various types of basis functions. Through feature correlation analysis, the most suitable combination of basis functions for the current problem is selected. The adaptive weight allocation strategy is used to determine the contribution of each basis function to the final result. At the same time, a reliability evaluation mechanism for the prediction result is established, a confidence interval is configured for each predicted value, and the corresponding thermal deformation prediction result is determined based on the confidence interval.

[0152] Exemplarily, take the steel bracket welding process as an example. Spatiotemporal feature data such as the temperature field distribution and stress field distribution of the bracket during the welding process are collected. At the same time, the constraint conditions composed of the elastic modulus, thermal expansion coefficient, etc. of the material are imported to establish a thermo-mechanical coupling relationship model.

[0153] Topological analysis is performed on the initially predicted deformation field, and a sequence of Betti numbers reflecting features of different dimensions is calculated. Through the sequence, the topological skeleton of the bracket deformation field is constructed, which reflects the main structural features of the deformation field. The generated persistent diagram shows significant mutation points at the weld joints and heat-affected zones of the bracket, and these regions are marked as key deformation regions.

[0154] In the key deformation region, a distance metric function considering geometric and physical characteristics is constructed to track the evolution process of the topological characteristics of the deformation field. The initial deformation field is projected onto a constraint space considering material strength limitations and welding process requirements. Through an iterative optimization algorithm, the deformation field is adjusted to gradually meet the constraint conditions while maintaining the continuous evolution of topological characteristics, and finally the corrected deformation field is obtained.

[0155] Calculate the persistent homology entropy of the corrected deformation field, and this entropy value reflects the complexity of the stent deformation process. The entropy value and the deformation field data are weighted and combined to obtain an uncertainty evaluation value of the prediction result. Finally, all calculation results are input into a preset basis function, and through weighted combination, the final thermal deformation prediction result of the stent is obtained, including the deformation amounts at each key position and their reliability evaluation results.

[0156] In this embodiment, by constructing a topological thermo-mechanical field self-correction mechanism based on persistent homology theory, the accurate extraction and analysis of the topological characteristics of the deformation field are realized. Using the Betti number sequence and persistent diagrams, the topological skeleton of the deformation field is established, providing a theoretical basis for the accurate identification of key deformation regions. By constructing a special distance metric function and projection optimization strategy, it is ensured that the deformation field prediction result not only meets the physical constraints but also maintains the continuity of topological characteristics;

[0157] In the prior art, welding deformation prediction methods mainly rely on simple numerical simulations and empirical models, lacking in-depth analysis of the topological characteristics of the deformation field. The thermo-mechanical coupling effect is simplified, making it difficult to accurately describe the deformation evolution process under complex working conditions. The identification and treatment of key deformation regions are relatively rough, often ignoring the influence of local deformation characteristics on the overall prediction accuracy;

[0158] The analysis method based on persistent homology theory in this embodiment improves the accuracy of deformation field feature extraction, enhances the adaptability of the prediction model to complex deformation modes. The topological thermo-mechanical field self-correction mechanism realizes the accurate identification and treatment of key deformation regions, improving the accuracy of local deformation prediction. Through the calculation and weighted combination of persistent homology entropy, a systematic uncertainty evaluation system is established, providing a quantitative basis for the reliability of the prediction result, realizing high-precision prediction and reliability evaluation of the deformation field during the welding process, and providing strong technical support for welding process optimization and quality control.

[0159] Figure 3 This is a comparison diagram of the topological skeleton evolution trajectories of the intelligent thermal deformation compensation and control method for metal parts during welding in the embodiment of the present invention. Through a regional display method, it clearly presents the comparison of the topological skeletons and evolution trajectories predicted by different methods during the welding thermal deformation of a steel stent. The top dotted contour represents the original shape of the stent, including a horizontal bottom plate and two vertical columns, and the two circular marked points represent the left and right welding points respectively.

[0160] The first region shows the topological skeleton constructed by the present technical solution (solid line, diamond mark). According to the experimental data, the maximum deformation of this solution near the left solder joint reaches 7.82 mm, and the maximum deformation near the right solder joint reaches 8.15 mm, and the deviation from the actual measurement value does not exceed 3%. Through persistent homology theory analysis, the Betti numbers identified by the present technical solution are = 23.7 and = 15.3, indicating that the topological skeleton has rich structural features. The persistent homology entropy H = 2.58 and the evolution trajectory distance D = 0.127, reflecting that the deformation field has rich topological information and low topological structure variability. Particularly prominent is the obvious concave deformation of the support bottom plate between the two solder joints and the outward inclination deformation of the two columns, which is highly consistent with the actual thermal deformation law. The areas marked by the two dashed circles in the figure are the key deformation regions. The characteristic Betti numbers of the left key deformation region (located at x = 300, y = 220) are = 14.3, = 8.7, and the characteristic Betti numbers of the right key deformation region (located at x = 580, y = 230) are = 11.5, = 6.2. The deformation gradient at the left key deformation region is the largest, reaching 0.87 mm / mm, while the deformation gradient of the right key deformation region is 0.63 mm / mm.

[0161] The second region shows the topological skeleton predicted by the finite element method (ABAQUS, dashed line, square mark). The deformation predicted by the finite element method is significantly smaller. The maximum deformation near the left solder joint is only 5.23 mm, and near the right solder joint is 6.47 mm, and the deviation from the actual measurement value reaches 32% and 25.7%. The Betti numbers of the finite element method = 8.5, = 5.2, and the persistent homology entropy H = 0.93, indicating that it is difficult to capture the fine structural features of the deformation field. It can be clearly seen from the figure that the deformation of the bottom plate predicted by the finite element method is almost flat, lacking the description of the local deformation characteristics in the middle region (at x = 300 - 450), which does not match the observed wavy deformation. The deformation prediction of the column is also relatively conservative and does not show enough outward inclination trend.

[0162] The topological skeleton predicted by the traditional machine learning method (SVR, dot-dashed line, triangular marker) is shown in the third region. There are obvious deviations in the prediction of the deformation trend, especially in the middle region of the bracket bottom plate (at x = 300 - 450), showing a convex shape, which is completely opposite to the actual concave deformation. In the deformation prediction of the left column, the traditional machine learning method shows an almost vertical deformation line, which does not match the observed outward inclination deformation. The deformation prediction accuracy of this method in the heat-affected zone is relatively low, and the average error reaches 7.88%. This is mainly due to its lack of due consideration of the welding heat-affecting mechanism and only fitting based on data characteristics.

[0163] The topological skeleton predicted by the deep neural network method (CNN, short dashed line, cross marker) is shown in the fourth region. Although this method can better describe the overall deformation trend, showing the concave of the bottom plate and the outward inclination of the column, it still cannot capture the fine features in the key deformation regions as well as the technical solution of the present invention. Especially in the description of the deformation characteristics at the connection between the right column and the bottom plate, the predicted deformation amount is 7.43 mm, with a deviation of 8.8% compared with the actual measured value of 8.15 mm. The deformation curve of the deep neural network in the middle of the bottom plate shows a wavy shape, but the peak position has a deviation of about 2.5 mm from the actual measurement result, and the peak amplitude is too large, indicating that it has insufficient understanding of the deformation mechanism caused by the heat gradient distribution.

[0164] By clearly showing the prediction results of each method in different regions, it can be clearly seen that the topological thermal field self-correction mechanism based on the persistent homology theory in the technical solution of the present invention can most accurately capture the spatio-temporal evolution characteristics of thermal deformation. Especially at the boundary of the heat-affected zone and the non-uniform deformation region, its predicted shape is closest to the actual deformation. Experimental data shows that in the region with the steepest temperature gradient (within 5 - 10 mm around the solder joint), the average deformation prediction error of the technical solution of the present invention is 3.12%, while the errors of the finite element method, the traditional machine learning method, and the deep neural network are 6.24%, 7.88%, and 4.83% respectively. High-precision prediction has important engineering application value for the welding deformation control of precision metal components.

[0165] In an alternative embodiment,

[0166] Comparing the thermal deformation prediction result with a preset thermal deformation threshold to determine the thermal deformation deviation, based on the thermal deformation deviation, taking the welding process parameters as optimization variables, and calculating a compensation scheme using a recursive optimizer combining the integrated gradient strategy and the evolutionary strategy, and iteratively solving to obtain the optimal welding process parameters and sending them to the welding component for execution, including:

[0167] Comparing the thermal deformation prediction result with a preset thermal deformation threshold to obtain the thermal deformation deviation, and performing time integration on the thermal deformation deviation to calculate the cumulative thermal deformation deviation;

[0168] Taking the welding process parameters as optimization variables, calculate the gradient of the thermal deformation deviation with respect to the welding process parameters and construct a gradient strategy. Combine Gaussian noise to construct an evolutionary strategy, and integrate the gradient strategy and the evolutionary strategy to construct a recursive optimizer;

[0169] Based on the recursive optimizer, establish an optimization objective function that includes the thermal deformation deviation. Constrain the value range and change rate of the welding process parameters based on the gradient of the thermal deformation deviation. Take the welding process parameters that meet the convergence conditions as the optimal welding process parameters and send them to the welding assembly to perform the welding operation.

[0170] The calculation of the thermal deformation deviation adopts a hierarchical comparison strategy. Divide the thermal deformation prediction results by different spatial regions and time periods, and compare them layer by layer with the preset thermal deformation threshold. The comparison process adopts an adaptive weight mechanism, focusing on the deviation in the deformation-sensitive region. Calculate the cumulative effect of the thermal deformation deviation through a time integration algorithm, and adopt a variable step-size integration strategy, using a smaller integration step size in the region with severe deformation to improve the calculation accuracy.

[0171] The construction process of the gradient strategy adopts a multi-level analysis method. Take the welding process parameters as optimization variables and construct a parameter sensitivity analysis model. Calculate the gradient of the thermal deformation deviation with respect to each process parameter by the forward difference method, and adopt an adaptive step-size control strategy to improve the stability of the gradient calculation. During the gradient calculation process, introduce a local smoothing mechanism to reduce the influence of numerical fluctuations.

[0172] The construction of the evolutionary strategy adopts a random perturbation method. Generate random perturbations with specific distribution characteristics through a Gaussian noise generator, and the perturbation amount is determined by an adaptive adjustment mechanism. Dynamically adjust the intensity and distribution characteristics of the noise according to the convergence of the optimization process. At the same time, establish a perturbation effect evaluation mechanism to screen effective perturbation directions.

[0173] The construction of the recursive optimizer adopts a dual optimization strategy. Integrate the gradient strategy and the evolutionary strategy, and determine the contribution ratio of the two strategies through a weight allocation mechanism. The optimizer adopts an adaptive learning rate adjustment mechanism to dynamically adjust the parameter update step size according to the optimization process. At the same time, establish an optimization history record to guide the subsequent optimization direction.

[0174] The construction of the optimization objective function adopts a multi-objective trade-off strategy. Take the thermal deformation deviation as the main optimization objective, and at the same time consider the feasibility constraints of the process parameters. Balance the importance of different objectives by constructing a composite weight function. Adopt a dynamic weight adjustment mechanism during the optimization process to adjust the weights of each objective according to the optimization process.

[0175] The constraint handling adopts a multi-level constraint system. The value ranges of welding process parameters are hierarchically constrained, including physical feasibility constraints and process realizability constraints. By constructing a constraint violation degree evaluation function, it quantifies whether the parameters meet the constraint conditions. The constraint on the parameter change rate adopts a sliding window strategy to ensure the smoothness of parameter changes.

[0176] The convergence judgment adopts a multi-criterion evaluation mechanism. Multiple convergence indicators are set, including the relative change of the objective function value, the norm of the parameter update amount, the degree of constraint satisfaction, etc. By constructing a comprehensive evaluation function, each indicator is weighted and combined. When all indicators meet the preset thresholds, the optimal welding process parameters are determined.

[0177] Exemplarily, taking the butt welding of steel plates as an example, the thermal deformation data during the welding process is collected. Through comparative analysis, it is found that the deformation amounts within 50 millimeters on both sides of the weld exceed the preset thresholds. The time integration algorithm is used to calculate the cumulative deformation deviation, and the time period during which the deformation amount grows rapidly during the welding process is focused on.

[0178] The process parameters such as welding current, voltage, and welding speed are used as optimization variables, and the influence degrees of these parameters on the deformation deviation are calculated. Through gradient calculation, it is found that the welding speed has the most significant influence on the deformation. Based on this, a gradient optimization strategy dominated by the welding speed is constructed.

[0179] During the optimization process, Gaussian noise is introduced to randomly perturb the process parameters to avoid the optimization falling into a local optimal solution. The gradient strategy and the evolutionary strategy are combined to construct a recursive optimizer. The optimization goal is set to minimize the thermal deformation deviation while ensuring that the process parameters change smoothly within the feasible range.

[0180] Through the iterative optimization process, when the relative change of the objective function value is less than the preset threshold and the process parameters meet all constraint conditions, the optimal combination of welding process parameters is obtained. This set of parameters can not only effectively control the welding deformation but also meet the feasibility requirements of process implementation.

[0181] In this embodiment, the adaptive weight mechanism adopted in the deformation-sensitive area improves the accuracy of deviation calculation. The adaptive step size control strategy and the local smoothing mechanism improve the stability and reliability of gradient calculation. Through parameter sensitivity analysis, the process parameters that play a key role in deformation control are accurately identified. The random perturbation mechanism introduced by Gaussian noise effectively avoids the optimization falling into a local optimal solution. The adaptive learning rate adjustment mechanism ensures the stable convergence of the optimization process. While ensuring the calculation efficiency, it realizes the precise optimization of welding process parameters and provides effective technical support for welding deformation control.

[0182] Figure 4 This is the flow chart for solving the optimal welding parameters of the intelligent compensation and control method for thermal deformation during the welding process of metal parts in the embodiment of the present invention.

[0183] In the second aspect of the embodiments of the present invention, there is provided an intelligent compensation and control system for thermal deformation during the welding of metal parts. The system includes:

[0184] A first unit for acquiring three-dimensional model data and welding process parameters of the metal part;

[0185] A second unit for constructing a thermo-mechanical coupling analysis model based on the three-dimensional model data, dividing the metal part into multiple hexahedral mesh elements and establishing a non-linear heat conduction equation set, modeling the welding heat source as a double ellipsoidal heat source distribution function, constructing a coupling transfer matrix between the temperature field and the stress field, and solving the non-linear heat conduction equation set using an explicit integration algorithm to obtain the transient temperature field distribution of the metal part;

[0186] A third unit for collecting real-time temperature data and real-time strain data during the welding process of the metal part;

[0187] A fourth unit for constructing the hexahedral mesh elements into a dynamic hierarchical graph structure, calculating the thermo-mechanical conduction relationship between the mesh elements based on the transient temperature field distribution, the real-time temperature data, the real-time strain data, and the welding process parameters, fusing different-scale features using an adaptive attention mechanism, extracting spatio-temporal features through a bidirectional propagation neural network, and generating a thermal deformation prediction result of the metal part;

[0188] A fifth unit for comparing the thermal deformation prediction result with a preset thermal deformation threshold to determine the thermal deformation deviation, based on the thermal deformation deviation, taking the welding process parameters as optimization variables, calculating a compensation scheme using a recursive optimizer combining the integrated gradient strategy and the evolutionary strategy, iteratively solving to obtain the optimal welding process parameters and sending them to the welding component for execution.

[0189] In the third aspect of the embodiments of the present invention, there is provided an electronic device, including:

[0190] A processor and a memory for storing processor-executable instructions, wherein the processor is configured to call the instructions stored in the memory to execute the method described above.

[0191] In the fourth aspect of the embodiments of the present invention, there is provided a computer-readable storage medium, on which computer program instructions are stored, and when the computer program instructions are executed by a processor, the method described above is implemented.

[0192] The present invention can be a method, a device, a system, and / or a computer program product. The computer program product can include a computer-readable storage medium, on which computer-readable program instructions for executing various aspects of the present invention are uploaded.

[0193] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements on some or all of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. An intelligent compensation and control method for thermal deformation during the welding process of metal parts, characterized in that, Including: Obtaining three-dimensional model data of the metal part and welding process parameters; Based on the three-dimensional model data, constructing a thermo-mechanical coupling analysis model, dividing the metal part into multiple hexahedral mesh elements and establishing a non-linear heat conduction equation set, modeling the welding heat source as a double-ellipsoid heat source distribution function, constructing a coupling transfer matrix between the temperature field and the stress field, and using an explicit integration algorithm to solve the non-linear heat conduction equation set to obtain the transient temperature field distribution of the metal part; Collecting real-time temperature data and real-time strain data during the welding process of the metal part; Constructing the hexahedral mesh elements into a dynamic hierarchical graph structure, calculating the thermo-mechanical conduction relationship between the mesh elements based on the transient temperature field distribution, the real-time temperature data, the real-time strain data, and the welding process parameters, fusing features of different scales using an adaptive attention mechanism, extracting spatio-temporal features through a bidirectional propagation neural network, and generating the thermal deformation prediction result of the metal part; Comparing the thermal deformation prediction result with a preset thermal deformation threshold to determine the thermal deformation deviation, based on the thermal deformation deviation, taking the welding process parameters as optimization variables, calculating a compensation scheme using a recursive optimizer combining the integrated gradient strategy and the evolutionary strategy, iteratively solving to obtain the optimal welding process parameters and sending them to the welding component for execution.

2. The method according to claim 1, characterized in that Based on the three-dimensional model data, constructing a thermo-mechanical coupling analysis model, dividing the metal part into multiple hexahedral mesh elements and establishing a non-linear heat conduction equation set includes: Obtaining the three-dimensional model data of the metal part, identifying and extracting the key geometric features of the weld area and the heat-affected zone after eliminating duplicate faces and dangling edges, establishing a feature topology relationship graph, establishing a stress analysis equation set based on the feature topology relationship graph, and performing an association mapping between the stress analysis equation set and the temperature field distribution equation set to construct a thermo-mechanical coupling analysis model; Calculating the surface curvature distribution of the three-dimensional model data based on the thermo-mechanical coupling analysis model, determining the curvature value according to the surface curvature distribution, comparing the curvature value with a preset curvature threshold to determine the mesh encryption area, determining the minimum mesh size and the maximum mesh size according to the mesh encryption area, establishing a mesh size calculation function, and performing mesh division on the metal part to generate initial hexahedral mesh elements; Calculating the determinant value, mesh angle, and side length ratio of the initial hexahedral mesh elements, comparing them with preset mesh quality parameters, adjusting the node positions and reconstructing the boundaries of the hexahedral mesh elements that do not meet the preset mesh quality parameters, and performing segmentation processing on the irregular hexahedral mesh elements to obtain optimized hexahedral mesh elements and establish a non-linear heat conduction equation set including temperature-dependent specific heat capacity coefficients and temperature-dependent thermal conductivity coefficients.

3. The method according to claim 1, characterized in that Modeling the welding heat source as a double-ellipsoid heat source distribution function, constructing a coupling transfer matrix between the temperature field and the stress field, and using an explicit integration algorithm to solve the non-linear heat conduction equation set to obtain the transient temperature field distribution of the metal part includes: Establish the front ellipsoidal heat source distribution function and the rear ellipsoidal heat source distribution function based on the welding voltage, welding current, thermal efficiency, semi-major axis of the ellipsoid, semi-minor axis of the ellipsoid, semi-depth axis of the ellipsoid, and heat distribution coefficient, and obtain the initial heat source density distribution; Calculate the temperature distribution according to the initial heat source density distribution, obtain the temperature-dependent thermal expansion coefficient and calculate the thermal strain, and superimpose the thermal strain with the elastic strain and plastic strain to obtain the total strain; Construct the heat conduction stiffness matrix, heat capacity matrix, heat load vector, structural stiffness matrix, structural damping matrix, and mechanical load vector based on the total strain, combine to construct the coupling transfer matrix of the temperature field and stress field and the corresponding nonlinear heat conduction equations, and determine the explicit integration initial time step based on the element characteristic length, elastic wave speed, and system characteristic frequency; At the explicit integration initial time step, calculate the velocity increment and displacement increment of the nonlinear heat conduction equations through the central difference scheme, determine the stress increment and substitute it into the nonlinear heat conduction equations for explicit integration calculation to obtain the initial value of the temperature field, calculate the temperature error based on the initial value of the temperature field, determine the adaptive time step and substitute it into the nonlinear heat conduction equations for explicit integration iterative calculation to obtain the transient temperature field distribution of the metal part.

4. The method according to claim 3, wherein At the explicit integration initial time step, calculate the velocity increment and displacement increment of the nonlinear heat conduction equations through the central difference scheme, determine the stress increment and substitute it into the nonlinear heat conduction equations for explicit integration calculation to obtain the initial value of the temperature field, including: At the explicit integration initial time step, add the product of the velocity increment at the previous moment and the time step and acceleration to calculate the velocity increment at the current moment, and add the product of the displacement increment at the previous moment and the time step and the velocity increment at the current moment to calculate the displacement increment at the current moment; Multiply the thermal expansion coefficient by the temperature increment and the unit tensor to obtain the thermal strain increment, determine whether plastic deformation occurs according to the current stress state and calculate the plastic strain increment, subtract the thermal strain increment and plastic strain increment from the total strain increment to obtain the elastic strain increment, and calculate the stress increment through the elastic modulus and elastic strain increment; Subtract the partial derivative of the internal energy with respect to time from the divergence of the heat flux density and the heat source term and take the absolute value to calculate the energy balance error and correction coefficient, multiply the exponential function of the absolute value of the temperature gradient by the linear function of the absolute value of the gradient of the stress increment to obtain the adaptive weight function, multiply the correction coefficient by the energy balance error and the temperature gradient direction and take the negative value to calculate the temperature correction amount, and calculate the corrected temperature field based on the adaptive weight function and the temperature correction amount; Substitute the stress increment into the nonlinear heat conduction equations for explicit integration calculation to obtain the second temperature field distribution, compare the norm ratio of the difference between the corrected temperature field and the second temperature field distribution, and the norm of the energy balance error with the temperature field convergence tolerance and energy balance convergence tolerance respectively, and perform iterative calculation based on the comparison results to obtain the initial value of the temperature field.

5. The method according to claim 1, wherein Construct the hexahedral mesh elements into a dynamic hierarchical graph structure, calculate the thermal conduction relationship between mesh elements based on the transient temperature field distribution, the real-time temperature data, the real-time strain data, and the welding process parameters, use an adaptive attention mechanism to fuse features of different scales, extract spatio-temporal features through a bidirectional propagation neural network, and generate the thermal deformation prediction result of the metal part, including: Construct an octree space partitioning structure based on the central point coordinates of the hexahedral mesh elements, calculate the topological adjacency relationship between mesh elements, assign spatial coordinates and level indexes to each mesh node, generate a dynamic hierarchical graph structure, extract the geometric features, topological features, and physical features of each mesh node to form a node feature vector, and calculate the product of the Euclidean distance square exponential function of the spatial position of the mesh node and the level difference exponential function of the mesh node to obtain the connection weight between mesh nodes; Input the transient temperature field distribution, real-time temperature data, and real-time strain data into the conduction calculation model, calculate the temperature difference and strain difference between adjacent mesh nodes and perform exponential mapping respectively to obtain the temperature influence factor and the strain influence factor, determine the thermal conductivity between adjacent mesh nodes in combination with the material thermal conductivity, and establish the thermal conduction relationship between mesh elements based on the thermal conductivity and the current welding process parameters; Input features of different scales into the adaptive attention mechanism, calculate the scale attention weight through the dot product operation between the mesh scale level features and the global feature matrix, perform weighted summation on the feature-transformed mesh scale level features to obtain the fused features and input them into the bidirectional propagation neural network, use the gated recurrent unit for forward propagation to obtain the forward hidden state, perform backward propagation to obtain the backward hidden state, splice the forward hidden state and the backward hidden state, and extract spatio-temporal features; Input the spatio-temporal features and constraint conditions into the prediction function, calculate the deformation field in combination with the topological thermal field self-correction mechanism, estimate the prediction uncertainty based on the deformation field and the spatio-temporal features, and generate the thermal deformation prediction result of the metal part.

6. The method according to claim 5, wherein Input the spatio-temporal features and constraint conditions into the prediction function, calculate the deformation field in combination with the topological thermal field self-correction mechanism, estimate the prediction uncertainty based on the deformation field and the spatio-temporal features, and generate the thermal deformation prediction result of the metal part, including: Input the spatio-temporal features of the metal part and the pre-set constraint conditions into the prediction function, where the constraint conditions include the thermo-mechanical coupling constitutive equation, and the thermo-mechanical coupling constitutive equation establishes the correlation between the stress tensor and the strain tensor through the elastic constant tensor and the coefficient of thermal expansion; Construct a topological thermal field self-correction mechanism based on the persistent homology theory, calculate the Betti number sequence of the initial deformation field output by the prediction function to form the topological skeleton of the deformation field, calculate the persistence diagram of the initial deformation field according to the Betti number sequence, and calibrate the key deformation regions of the metal part according to the mutation points of the persistence diagram; For the key deformation region, a distance metric function is constructed to calculate the characteristic evolution trajectory of the topological skeleton of the deformation field. The initial deformation field is projected onto a manifold space that satisfies the constraint conditions to obtain a projected deformation field. The initial deformation field is iteratively optimized by minimizing the distance between the initial deformation field and the projected deformation field and the distance of the evolution trajectory of the topological skeleton of the deformation field to obtain a corrected deformation field; The persistent homology entropy is calculated according to the corrected deformation field, and the persistent homology entropy and the corrected deformation field are weighted to obtain an uncertainty evaluation value. The corrected deformation field, the uncertainty evaluation value, and the spatio-temporal features are input into a preset basis function, and the thermal deformation prediction result of the metal part is generated by calculating the weighted sum of the basis function.

7. The method according to claim 1, wherein The thermal deformation prediction result is compared with a preset thermal deformation threshold to determine the thermal deformation deviation. Based on the thermal deformation deviation, the welding process parameters are used as optimization variables, and a compensation scheme is calculated by combining an integrated gradient strategy and a recursive optimizer of an evolutionary strategy. The optimal welding process parameters are obtained by iterative solution and sent to the welding assembly for execution, including: The thermal deformation prediction result is compared with a preset thermal deformation threshold to obtain a thermal deformation deviation, and the time integral of the thermal deformation deviation is calculated to obtain the cumulative thermal deformation deviation; Taking the welding process parameters as optimization variables, calculating the gradient of the thermal deformation deviation with respect to the welding process parameters and constructing a gradient strategy, combining Gaussian noise to construct an evolutionary strategy, and integrating the gradient strategy and the evolutionary strategy to construct a recursive optimizer; Based on the recursive optimizer, an optimization objective function including the thermal deformation deviation is established. Based on the gradient of the thermal deformation deviation, the value range and change rate of the welding process parameters are constrained. The welding process parameters that meet the convergence conditions are used as the optimal welding process parameters and sent to the welding assembly to perform the welding operation.

8. An intelligent compensation and control system for thermal deformation during metal welding, which is used to implement the method described in any one of the foregoing claims 1-7, characterized in that, Including: The first unit is used to obtain the three-dimensional model data and welding process parameters of the metal part; The second unit is used to construct a thermo-mechanical coupling analysis model based on the three-dimensional model data, divide the metal part into multiple hexahedral mesh elements and establish a non-linear heat conduction equation set, model the welding heat source as a double ellipsoidal heat source distribution function, construct a coupling transfer matrix between the temperature field and the stress field, and use an explicit integration algorithm to solve the non-linear heat conduction equation set to obtain the transient temperature field distribution of the metal part; The third unit is used to collect the real-time temperature data and real-time strain data during the welding process of the metal part; The fourth unit is used to construct the hexahedral mesh elements into a dynamic hierarchical graph structure, calculate the thermo-mechanical conduction relationship between the mesh elements based on the transient temperature field distribution, the real-time temperature data, the real-time strain data, and the welding process parameters, use an adaptive attention mechanism to fuse features at different scales, and extract spatio-temporal features through a bidirectional propagation neural network to generate the thermal deformation prediction result of the metal part; The fifth unit is used to compare the predicted result of thermal deformation with a preset thermal deformation threshold to determine the thermal deformation deviation. Based on the thermal deformation deviation, taking the welding process parameters as optimization variables, a recursive optimizer combining the integrated gradient strategy and the evolutionary strategy is used to calculate a compensation scheme, and the optimal welding process parameters are obtained through iterative solution and sent to the welding component for execution.

9. An electronic device, characterized in that, It includes: a processor; a memory for storing instructions executable by the processor; Wherein, the processor is configured to call the instructions stored in the memory to execute the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having computer program instructions stored thereon, characterized in that, When the computer program instructions are executed by the processor, the method according to any one of claims 1 to 7 is implemented.

Images