An automated welding system and method for liquefied natural gas ship pipe fabrication

Abstract

The application provides an automatic welding system and method for liquefied natural gas ship pipe manufacturing, wherein the welding area of the liquefied natural gas ship pipe is divided into multiple welding sub-areas through surface topography data of the welding area of the liquefied natural gas ship pipe; the posture reachable space of the arc welding gun end effector in the Cartesian space is determined, and multiple process control points of the ship pipe welding area are calibrated according to the feature correlation relationship between the weld geometric features of each welding sub-area in combination with the posture reachable space, and then the heat affected zone of each process control point under the thermal state is predicted; the preheating regulation and control parameters when the welding area of the ship pipe is welded are determined through the interaction relationship of the heat affected zones between adjacent process control points; the welding area is guided by heat energy according to the preheating regulation and control parameters, and then the weld fusion work of the welding area after the heat energy guidance is completed. The above scheme can avoid local thermal burn-through of the weld during welding based on the preheating regulation and control parameters.

Description

Technical Field

[0001] This application relates to the field of industrial welding technology, and more specifically, to an automated welding system and method for manufacturing liquefied natural gas ship pipe fittings. Background Technology

[0002] Industrial welding is an indispensable key process in modern manufacturing. With the rapid development of industry, the requirements for welding quality and efficiency are getting higher and higher. Traditional welding methods can no longer meet the joining needs of complex structures and high-performance materials. In recent years, automated welding technology has emerged rapidly. With the help of robots and CNC equipment, high-precision and high-efficiency welding operations have been achieved, which greatly reduces labor costs and labor intensity. In addition, intelligent monitoring and quality inspection technologies for the welding process are also constantly improving, providing strong guarantees for the stability and reliability of welding quality.

[0003] Current industrial welding mainly involves heating or pressurizing, or both, to create atomic or molecular bonding forces between two separate objects, thereby achieving a connection. During the welding process, a welding heat source is typically used to heat the welding material and the workpiece to a molten state, forming a weld pool. As the weld pool cools and solidifies, a strong weld is formed. However, in the welding process of liquefied natural gas ship pipe fittings, when continuous welding operations are performed on the weld seam in the welding area, the heat diffusion of the current weld point will overlap with the welding heat source of the next weld point, causing local heat accumulation. This leads to localized heat burn-through defects in the weld. Therefore, how to avoid localized heat burn-through in the weld seam under localized heat accumulation has become a difficult problem for the industry. Summary of the Invention

[0004] This application provides an automated welding system and method for manufacturing liquefied natural gas (LNG) ship pipe fittings, which can prevent localized heat burn-through defects in the weld seam under localized heat accumulation.

[0005] In a first aspect, this application provides a method for guiding heat energy during welding of liquefied natural gas (LNG) ship pipe fittings. This method, used in an automated welding system for manufacturing LNG ship pipe fittings, guides heat energy to the welding area during the welding process. The method includes the following steps:

[0006] Dynamic scanning was performed on the welding area of ​​the liquefied natural gas ship pipe fittings to obtain the surface morphology data of the welding area;

[0007] Based on the surface topography data, the welding area is divided into multiple welding sub-regions with different surface morphologies, and the weld geometry features of the pipe fitting welds in each welding sub-region are extracted.

[0008] The attitude reachable space of the end effector of the arc welding gun in Cartesian space is determined. Then, based on the feature correlation between the geometric features of each weld and the attitude reachable space, multiple process control points of the welding area of ​​the ship pipe fitting are calibrated. Based on the preset welding heat transfer model, the heat-affected zone of each process control point under thermal state is predicted.

[0009] The preheating control parameters for welding the welding area of ​​the ship pipe fittings are determined by the interaction relationship between the heat-affected zones of adjacent process control points.

[0010] The welding area is guided by the preheating control parameters, and then the arc welding gun completes the weld fusion operation of the welding area after the heat energy is guided.

[0011] In some embodiments, dividing the welding area into multiple welding sub-regions with different surface morphologies based on the surface topography data specifically includes:

[0012] A three-dimensional surface model of the welding area is constructed based on the surface morphology data.

[0013] The three-dimensional surface model is meshed to obtain the local curvature distribution of the welding area;

[0014] Based on the local curvature distribution, the welding area is clustered using a region growing algorithm to obtain multiple welding sub-regions with different surface morphologies.

[0015] In some embodiments, extracting the weld geometry features of the pipe fitting welds within each welding sub-region specifically includes:

[0016] Extract the weld contour of the pipe fitting weld in each welding sub-region;

[0017] Select a welding sub-region as the selected welding sub-region, and extract the initial weld curve corresponding to the selected welding sub-region based on the weld contour of the selected welding sub-region.

[0018] The initial weld curve is smoothed and optimized, and the weld geometry of the pipe fitting weld in the selected welding sub-region is determined by the smoothed and optimized initial weld curve.

[0019] Continue to determine the weld geometry of the pipe fittings within the remaining welding sub-regions.

[0020] In some embodiments, determining the attitude reachability space of the arc welding torch end effector in Cartesian space specifically includes:

[0021] Establish a forward kinematic model of the end effector of the arc welding gun;

[0022] The effective end-effector posture set of the arc welding gun end effector is extracted based on the positive kinematics model;

[0023] The attitude reachable space of the arc welding gun end effector in Cartesian space is determined based on the set of effective end attitudes.

[0024] In some embodiments, determining multiple process control points for the welding area of ​​the ship fitting based on the feature correlation between various weld geometric features and the attitude reachability space specifically includes:

[0025] Determine the feature relationships between the geometric features of each weld;

[0026] The constraint identification parameters for welding constraints of the welding area of ​​the ship fittings are constructed based on all feature relationships.

[0027] Obtain the initial weld curve corresponding to each welding sub-region in the welding area of ​​the ship pipe fitting;

[0028] For each welding sub-region, calculate the curvature deviation at different sampling points in the initial weld curve corresponding to each welding sub-region, and extract multiple candidate process control points from all sampling points based on all curvature deviations and the constraint identification parameters;

[0029] Based on the attitude reachability space, multiple process control points for the welding area of ​​the ship fittings are selected from all candidate process control points.

[0030] In some embodiments, the prediction of the heat-affected zone at each process control point under thermal conditions based on a preset welding heat transfer model specifically includes:

[0031] The preset welding heat transfer model is invoked, and heat conduction simulation calculations are performed for each process control point to generate the temperature gradient distribution corresponding to each process control point.

[0032] For each process control point, the heat-affected zone of the process control point is determined based on the temperature gradient distribution of the process control point.

[0033] In some embodiments, a laser scanner is used to dynamically scan the welding area along the liquefied natural gas ship pipe fittings to obtain surface morphology data of the welding area.

[0034] Secondly, this application provides an automated welding system for manufacturing liquefied natural gas (LNG) ship pipe fittings, which includes a heat energy guiding unit, the heat energy guiding unit comprising:

[0035] The scanning module is used to dynamically scan the welding area of ​​liquefied natural gas ship pipe fittings to obtain surface morphology data of the welding area;

[0036] The processing module is used to divide the welding area into multiple welding sub-regions with different surface morphologies based on the surface topography data, and extract the weld geometric features of the pipe fitting weld in each welding sub-region.

[0037] The processing module is also used to determine the attitude reachable space of the end effector of the arc welding gun in Cartesian space, and then, based on the feature correlation between the geometric features of each weld and the attitude reachable space, to calibrate multiple process control points in the welding area of ​​the ship pipe fitting, and to predict the heat-affected zone of each process control point under thermal conditions based on a preset welding heat transfer model.

[0038] The processing module is also used to determine the preheating control parameters when welding the welding area of ​​the ship pipe fittings by means of the interaction relationship between the heat-affected zones of adjacent process control points.

[0039] The execution module is used to guide the heat energy of the welding area according to the preheating control parameters, and then the arc welding gun completes the weld fusion operation of the welding area after the heat energy is guided.

[0040] Thirdly, this application provides a computer device including a memory and a processor, the memory storing code, and the processor being configured to acquire the code and execute the above-described heat-guided welding method for liquefied natural gas ship pipe fittings.

[0041] Fourthly, this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method for guiding heat energy during welding of liquefied natural gas ship pipe fittings.

[0042] The technical solutions provided by the embodiments disclosed in this application have the following beneficial effects:

[0043] The automated welding system and method for manufacturing liquefied natural gas (LNG) ship pipe fittings provided in this application firstly involves dynamically scanning the welding area of ​​the LNG ship pipe fitting to obtain surface morphology data of the welding area; secondly, based on the surface morphology data, the welding area is divided into multiple welding sub-regions with different surface morphologies, and the weld geometry features of the pipe fitting welds in each welding sub-region are extracted; furthermore, the attitude reachable space of the end effector of the arc welding torch in Cartesian space is determined, and then multiple process control points of the welding area of ​​the ship pipe fitting are calibrated based on the feature correlation between the various weld geometry features and the attitude reachable space; then, the heat-affected zone of each process control point under thermal conditions is predicted based on a preset welding heat transfer model, and the preheating control parameters for welding the welding area of ​​the ship pipe fitting are determined through the interaction relationship of the heat-affected zones between adjacent process control points; finally, the welding area is guided by the preheating control parameters, and then the arc welding torch completes the weld fusion operation of the heat-guided welding area.

[0044] Therefore, this application can avoid localized heat burn-through in welds under localized heat accumulation. First, a laser scanner dynamically scans the welding area of ​​the liquefied natural gas (LNG) ship pipe fittings to obtain surface morphology data, providing a data foundation for subsequent welding of the pipe fitting area. Second, based on the surface morphology data, the welding area is divided into multiple welding sub-regions with different surface morphologies, and the weld geometry features of the pipe fitting welds within each sub-region are extracted to accurately describe the weld state changes within the sub-region, providing crucial geometric guidance information for the automated welding system and further identifying the heat-affected state of localized welding areas. Furthermore, the attitude reachability space of the arc welding torch end effector in Cartesian space is determined, and multiple process controls for the ship pipe fitting welding area are calibrated based on the feature correlation between various weld geometry features and the attitude reachability space. The system establishes several control points to ensure the continuity of the welding trajectory, providing constraints for the spatial geometric control and thermal guidance of the automated welding system. Then, based on a pre-set welding heat transfer model, it predicts the heat-affected zone (HAZ) of each process control point under thermal conditions. The interaction relationship between the HAZ of adjacent process control points determines the preheating control parameters for welding the ship fittings, reflecting the relative amount of heat required during the preheating stage. This guides the control of the preheating temperature in actual welding operations, allowing the welding material to gradually adapt to subsequent welding heat input and avoiding thermal stress concentration or embrittlement caused by localized heat accumulation. Finally, the preheating control parameters guide the heat energy of the welding area, and the arc welding torch completes the weld fusion operation of the heat-guided area. In summary, the technical solution provided in this application can prevent localized heat burn-through in welds under localized heat accumulation. Attached Figure Description

[0045] Figure 1 This is an exemplary flowchart of a heat energy guiding method for welding liquefied natural gas ship pipe fittings according to some embodiments of this application;

[0046] Figure 2 A schematic diagram of the application scenario architecture of the heat energy guiding method for welding liquefied natural gas ship pipe fittings, as shown in some embodiments of this application;

[0047] Figure 3 This is an exemplary flowchart illustrating the determination of multiple welding sub-regions according to some embodiments of this application;

[0048] Figure 4 This is an exemplary flowchart illustrating the determination of the attitude reachable space according to some embodiments of this application;

[0049] Figure 5 This is a schematic diagram of the structure of a heat energy guiding unit according to some embodiments of this application;

[0050] Figure 6 This is a schematic diagram of the structure of a computer device for implementing a heat energy guiding method for welding liquefied natural gas ship pipe fittings, according to some embodiments of this application. Detailed Implementation

[0051] To better understand the technical solution of this application, the technical solution of this application will be described in detail below with reference to the accompanying drawings and specific embodiments.

[0052] refer to Figure 1 The figure is an exemplary flowchart of a heat conduction method for welding liquefied natural gas (LNG) ship pipe fittings according to some embodiments of this application. The heat conduction method 100 for welding LNG ship pipe fittings mainly includes the following steps:

[0053] In step 101, the welding area of ​​the liquefied natural gas ship pipe fittings is dynamically scanned to obtain the surface morphology data of the welding area.

[0054] In practice, a laser scanner can be used to dynamically scan the welding area of ​​liquefied natural gas (LNG) ship pipe fittings to obtain surface morphology data of the welding area. Figure 2 This is a schematic diagram of an application scenario for the thermal energy guiding method for welding liquefied natural gas (LNG) ship pipe fittings, as shown in some embodiments of this application. The laser scanner interacts with the server through a communication network to complete the dynamic scanning of the welding area of ​​the LNG ship pipe fittings. The server stores the surface morphology data of the scanned welding area into a data storage system for subsequent thermal energy guiding analysis.

[0055] It should be noted that the surface morphology data in this application refers to the point cloud information of the surface of the welding area obtained by a laser scanner, which is used to describe the actual structural features of the surface of the welding area of ​​the liquefied natural gas ship pipe fittings. By determining the surface morphology data, a data basis can be provided for the subsequent welding of the welding area of ​​the ship pipe fittings.

[0056] In step 102, the welding area is divided into multiple welding sub-regions with different surface morphologies based on the surface topography data, and the weld geometry features of the pipe fitting welds in each welding sub-region are extracted.

[0057] It should be noted that the surface of the liquefied natural gas ship pipe fittings in this application is in an arc state. Therefore, the welding area of ​​the ship pipe fittings is in an arc-aligned state, that is, the welding area is also in an arc state, and the welding area has different surface morphologies (i.e., differences in surface curvature).

[0058] In some embodiments, reference Figure 3 As shown in the figure, this is an exemplary flowchart illustrating the determination of multiple welding sub-regions according to some embodiments of this application. In this embodiment, dividing the welding area into multiple welding sub-regions with different surface morphologies based on the surface topography data can be achieved by the following steps:

[0059] First, in step 1021, a three-dimensional surface model of the welding area is constructed based on the surface morphology data;

[0060] Then, in step 1022, the three-dimensional surface model is meshed to obtain the local curvature distribution of the welding area;

[0061] Finally, in step 1023, based on the local curvature distribution, the welding area is clustered using a region growing algorithm to obtain multiple welding sub-regions with different surface morphologies.

[0062] In specific implementation, firstly, the existing Delaunay triangulation algorithm projects all point clouds in the surface topography data onto a two-dimensional parameterized plane, generating a triangular mesh that satisfies the empty circle property (i.e., the circumcircle of any triangle does not contain other points) within the two-dimensional parameterized plane. Then, the connection relationships between the triangular meshes are mapped back to three-dimensional space, forming a three-dimensional surface model composed of triangular facets. This three-dimensional surface model is used as the three-dimensional surface model of the welding area. Next, the existing triangular network is used to mesh the three-dimensional surface model, and the local curvature (e.g., Gaussian curvature) of each mesh unit is calculated using discrete differential geometry methods (e.g., quadratic surface fitting based on vertex neighborhood). The local curvature of each mesh unit is then combined to form the welding area. The local curvature distribution of the region will not be elaborated here. Finally, the local curvature of each grid cell in the local curvature distribution is obtained, and a local curvature difference threshold is set. Starting from the initial seed point (such as the local curvature maximum or minimum point), the region growing algorithm gradually merges adjacent grid cells that meet the conditions (i.e., adjacent grid cells whose local curvature difference does not exceed the local curvature difference threshold are considered to be of the same type). Finally, the welding area is divided into multiple welding sub-regions with different surface morphologies. For example, regions with abrupt changes in local curvature will be clustered into independent sub-regions, while gentle sections will be merged into continuous regions. The local curvature difference threshold can be set according to actual needs. For example, it can be set by learning a large number of local curvature differences through machine learning. There is no limitation here.

[0063] It should be noted that the three-dimensional surface model in this embodiment is a digital model representing the surface geometry of the welding area of ​​the liquefied natural gas ship pipe fittings; the local curvature distribution in this embodiment represents a distribution field composed of the local curvature of different grid units. The local curvature distribution reflects the changes in the degree of surface curvature at different locations in the welding area and highlights the geometric deformation characteristics of the welding surface at the microscale; the welding sub-region in this application represents a sub-region with different surface morphology divided from the welding area. By determining the welding sub-region, the original complex and geometrically drastic overall welding area can be divided into several sub-regions with relatively uniform local structures and consistent curvature characteristics, thereby significantly improving the accuracy and stability of subsequent weld centerline extraction, welding path planning, welding torch posture adjustment, and thermal control strategies.

[0064] In some embodiments, extracting the weld geometry features of the pipe fitting welds within each welded sub-region can be achieved using the following steps:

[0065] Extract the weld contour of the pipe fitting weld in each welding sub-region;

[0066] Select a welding sub-region as the selected welding sub-region, and extract the initial weld curve corresponding to the selected welding sub-region based on the weld contour of the selected welding sub-region.

[0067] The initial weld curve is smoothed and optimized, and the weld geometry of the pipe fitting weld in the selected welding sub-region is determined by the smoothed and optimized initial weld curve.

[0068] Continue to determine the weld geometry of the pipe fittings within the remaining welding sub-regions.

[0069] It should be noted that, in this application, the weld geometric features represent the morphological characteristics of the pipe weld in three-dimensional space within the welding sub-region. The weld geometric features are used to accurately describe the state changes of the weld in the sub-region. The weld geometric features are the basic data for welding path planning and welding torch posture control. By extracting the weld geometric features, the state changes of the weld in the sub-region can be accurately described, thereby providing key geometric guidance information for the automated welding system and further identifying the heat-affected zone of the local welding area in the welding region.

[0070] In specific implementation, firstly, for each welding sub-region, based on the surface topography data of the welding sub-region, the weld contour of the pipe fitting weld within the welding sub-region is extracted using an existing boundary detection algorithm (such as the Alpha Shape Algorithm). Specifically, the sawtooth contour composed of triangles extracted by the Alpha Shape Algorithm is used as the weld contour, which will not be elaborated here. Secondly, the weld contour of the selected welding sub-region is interpolated using an existing interpolation method to obtain the initial weld curve corresponding to the selected welding sub-region, which will not be elaborated here. Then, the initial weld curve is smoothed and optimized, and the smoothed and optimized initial weld curve is used to determine the weld geometric features of the pipe fitting weld within the selected welding sub-region, i.e., using a cubic B-sample. The initial weld curve is smoothly fitted by a curve, and the average curvature value of the smoothed and optimized initial weld curve describes the weld geometry of the pipe fitting weld in the selected welding sub-region. This will not be elaborated further here. Generally, the geometric state of the weld edge is related to curvature; the greater the curvature, the more prominent the geometric shape. Therefore, the average curvature value of the initial weld curve can describe the weld geometry of the pipe fitting weld in the selected welding sub-region. Finally, the weld geometry of the pipe fitting weld in the remaining welding sub-regions is determined using the method of "smoothing and optimizing the initial weld curve based on the minimum curvature variational principle, and determining the weld geometry of the pipe fitting weld in the selected welding sub-region based on the smoothed and optimized initial weld curve."

[0071] It should be noted that in this embodiment, the weld contour represents the boundary of the pipe weld within the welding sub-region, used to characterize the boundary shape of the geometric contour of the weld on the three-dimensional surface; in this embodiment, the initial weld curve represents a geometric central axis along the weld extension direction obtained by preliminary fitting of the pipe weld within the welding sub-region, used to approximately represent the direction of the weld path in three-dimensional space, and is the initial estimation result for extracting the geometric features of the weld.

[0072] In step 103, the attitude reachable space of the end effector of the arc welding gun in Cartesian space is determined. Then, based on the feature correlation between the geometric features of each weld and the attitude reachable space, multiple process control points of the welding area of ​​the ship pipe fitting are calibrated. Based on the preset welding heat transfer model, the heat-affected zone of each process control point under thermal conditions is predicted.

[0073] It should be noted that, in this application, the attitude reachable space refers to the spatial range in which the welding torch end effector can reach the welding area in various different attitudes. For example, in welding, if the welding torch needs to weld along the normal direction of the curved surface of the pipe, it is necessary to ensure that the normal direction falls within the reachable attitude range of the welding torch at that position (e.g., no collision with the robotic arm linkage within ±30° of the welding torch tilt angle). If it exceeds this range, the path needs to be adjusted or additional degrees of freedom (e.g., positioner assistance) needs to be introduced. By determining the attitude reachable space, a collision-free welding torch attitude that conforms to mechanical constraints can be planned for the welding torch, ensuring the feasibility of the welding path of the welding torch in complex geometric structures (e.g., curved surfaces of pipe fittings). In this application, the arc welding torch end effector refers to the position portion of the arc welding torch end.

[0074] In some embodiments, reference Figure 4 As shown, this figure is an exemplary flowchart illustrating the determination of the attitude reachability space according to some embodiments of this application. In this embodiment, the determination of the attitude reachability space of the arc welding torch end effector in Cartesian space can be achieved by the following steps:

[0075] First, in step 1031, a forward kinematic model of the end effector of the arc welding gun is established;

[0076] Then, in step 1032, the effective end pose set of the arc welding gun end effector is extracted based on the positive kinematics model;

[0077] Finally, in step 1033, the attitude reachable space of the arc welding gun end effector in Cartesian space is determined based on the effective end attitude set.

[0078] In specific implementation, firstly, a forward kinematics model of the arc welding gun end effector is established based on existing welding robot link parameters (such as Denavit-Hartenberg parameters), which will not be elaborated here. Secondly, based on the forward kinematics model, the effective end-effector posture set of the arc welding gun end effector is extracted, that is: obtaining the preset welding path of the arc welding gun end effector; for discrete points on the welding path, the theoretical posture vectors corresponding to each discrete point are substituted into the forward kinematics model, and inverse kinematics is solved using existing Newton iteration techniques to obtain all effective joint angle combinations. The effective joint angle combination refers to the set of welding robot joint angle configurations that can satisfy the forward kinematics model. The theoretical attitude vectors corresponding to each effective joint angle combination are used as effective end-effector poses. All effective end-effector poses are then combined to form the effective end-effector pose set of the arc welding gun end effector, which contains multiple effective end-effector poses. Finally, the attitude reachable space of the arc welding gun end effector in Cartesian space is determined based on the effective end-effector pose set. That is, each effective end-effector pose (including position and orientation) in the effective end-effector pose set is discretized in Cartesian space to obtain the attitude reachable space of the arc welding gun end effector in Cartesian space. The discretization expression refers to the process of digitally representing a continuous mathematical object (such as an attitude) through a finite number of sampling points.

[0079] It should be noted that, in this embodiment, the forward kinematics model represents a mathematical model for calculating the position and orientation of the end effector in Cartesian space using the joint parameters of the welding robot; in this embodiment, the end effector pose set represents the set of valid end effectors of the welding robot that satisfy the constraints in Cartesian space, and the end effector pose set contains multiple valid end effectors.

[0080] In some embodiments, determining multiple process control points in the welding area of ​​the ship fitting based on the feature correlation between the geometric features of each weld and the attitude reachable space can be achieved by the following steps:

[0081] Determine the feature relationships between the geometric features of each weld;

[0082] The constraint identification parameters for welding constraints of the welding area of ​​the ship fittings are constructed based on all feature relationships.

[0083] Obtain the initial weld curve corresponding to each welding sub-region in the welding area of ​​the ship pipe fitting;

[0084] For each welding sub-region, calculate the curvature deviation at different sampling points in the initial weld curve corresponding to each welding sub-region, and extract multiple candidate process control points from all sampling points based on all curvature deviations and the constraint identification parameters;

[0085] Based on the attitude reachability space, multiple process control points for the welding area of ​​the ship fittings are selected from all candidate process control points.

[0086] It should be noted that, in this application, process control points refer to key spatial points that ensure the stability of the welding process. Specifically, process control points refer to a set of key control points with clear geometric position and posture requirements selected on the weld centerline during the welding path planning process to ensure the continuity of the welding trajectory. These points are usually located on the weld centerline and represent the local path direction and spatial posture changes during the welding process. In automated welding systems, process control points have the dual functions of spatial geometric control and process constraint control, and are a key bridge connecting path design, posture adjustment and thermal control strategies.

[0087] In specific implementation, firstly, the feature correlation relationships between various weld geometric features are determined. That is, for every two weld geometric features, the feature correlation relationship between the two weld geometric features can be described by the absolute difference between the two weld geometric features, thus obtaining the feature correlation relationships between each weld geometric feature. Secondly, in the welding of the pipe fitting welding area, the weld usually has tiny edge burrs. To extract the points where the edge burrs are more prominent, the curvature of the weld can be quantified to identify the points where the edge burrs are prominent. Therefore, the mean of all feature correlation relationships can be used as the constraint identification parameter when performing welding constraints on the welding area of ​​the ship pipe fitting. Then, for each welding sub-region, the curvature deviation at different sampling points in the initial weld curve corresponding to each welding sub-region is calculated. The curvature deviation can be determined by the absolute difference between the mean curvature and the curvature value at the sampling point. Specifically, multiple candidate process control points are extracted from all sampling points based on all curvature deviations and the constraint identification parameters. That is, each curvature deviation is compared with the constraint identification parameters, and sampling points with curvature deviations greater than the constraint identification parameters are extracted as candidate process control points, thus obtaining multiple candidate process control points. Finally, multiple process control points for the welding area of ​​the ship fitting are selected from all candidate process control points based on the attitude reachable space. That is, for each candidate process control point, if the welding torch attitude (e.g., tilt angle 45°) corresponding to the normal direction of the candidate process control point (calculated from the surface curvature) exceeds the attitude reachable space (e.g., the maximum allowable tilt angle is 30°), then the candidate process control point is determined as the process control point for the welding area of ​​the ship fitting, thus obtaining multiple process control points for the welding area of ​​the ship fitting.

[0088] It should be noted that, in this embodiment, the feature correlation relationship represents an index that measures the correlation between the geometric features of the weld; in this embodiment, the constraint identification parameter represents a quantitative parameter used to identify the constraints that need to be applied to each welding sub-region during the welding process, so as to screen out control points that have a key guiding role in the welding process; in this embodiment, the candidate process control point represents a pre-selected welding control point. Specifically, the candidate process control point is a spatial point that has potential control significance but has not yet been screened for attitude reachability during the automated path planning and attitude analysis of the weld of the ship pipe fitting. These points are usually distributed in the weld path at the location where the weld morphology changes significantly.

[0089] In some embodiments, predicting the heat-affected zone at each process control point under thermal conditions based on a preset welding heat transfer model can be achieved through the following steps:

[0090] The preset welding heat transfer model is invoked, and heat conduction simulation calculations are performed for each process control point to generate the temperature gradient distribution corresponding to each process control point.

[0091] For each process control point, the heat-affected zone of the process control point is determined based on the temperature gradient distribution of the process control point.

[0092] It should be noted that, in this application, the heat-affected zone refers to the range of heat diffusion when the welded area is heated. Accurate prediction of the heat-affected zone is helpful in setting preheating strategies and avoiding welding defects caused by thermal deformation or stress concentration.

[0093] In specific implementation, firstly, a preset welding heat transfer model (such as an existing three-dimensional transient heat conduction finite element model) is invoked. Welding process parameters (such as arc power and welding speed) and material thermal property parameters (such as thermal conductivity and specific heat capacity) are input into the welding heat transfer model. Each process control point is used as the center point of the heat source, and a finite element mesh is constructed for each process control point to perform heat conduction simulation. The instantaneous temperature distribution field output by the welding heat transfer model under the action of welding heat input is used as the temperature gradient distribution corresponding to the process control point, thereby generating the temperature gradient distribution corresponding to each process control point. This will not be elaborated here. Then, for each process control point, the region where the temperature exceeds the threshold is extracted based on the temperature gradient distribution of the process control point as the heat-affected zone of the process control point. The threshold can be set according to actual needs. For example, the critical phase transformation temperature of the welded pipe material (such as 650℃) can be used as the threshold.

[0094] It should be noted that, in this embodiment, the temperature gradient distribution represents the gradient field of temperature change with spatial position around the process control point. The temperature gradient distribution describes the rate and direction of temperature change per unit length at different locations in this region under the action of the welding heat source. This temperature gradient distribution reflects the trend and range of heat diffusion inside the pipe material during the welding process and can be used to delineate the boundary of the heat-affected zone.

[0095] In step 104, the preheating control parameters for welding the welding area of ​​the ship fittings are determined by the interaction relationship between the heat-affected zones of adjacent process control points.

[0096] In some embodiments, determining the preheating control parameters for welding the welding area of ​​the ship fittings based on the interaction relationship between the heat-affected zones of adjacent process control points can be achieved through the following steps:

[0097] Determine the interaction relationship between the heat-affected zones of adjacent process control points;

[0098] The thermal coupling zone of the welding area of ​​the ship fittings is constructed based on all the interaction relationships;

[0099] Thermal field simulation and prediction are performed on the thermal coupling zone to obtain preheating control parameters for welding the welding area of ​​the ship pipe fitting.

[0100] It should be noted that the preheating control parameters in this application refer to parameters used to control the preheating intensity during welding of the welding area. Specifically, the preheating control parameters reflect the relative amount of heat required to be applied during the preheating stage of the welded pipe fitting. They are used to guide the control of the preheating temperature of each welding point in actual operation. The preheating control parameters can dynamically adjust the preheating scheme to avoid material thermal stress concentration or welding defects caused by temperature superposition, thereby optimizing the overall welding quality and structural performance, allowing the material to gradually adapt to the subsequent welding heat input, and avoiding uneven structural expansion or embrittlement of the structure caused by local drastic temperature rise.

[0101] In the welding of liquefied natural gas (LNG) ship pipe fittings, to improve welding quality and reduce residual stress, preheating control parameters can be scientifically formulated based on the interaction relationship between the heat-affected zones (HAZs) of adjacent process control points. Specifically, firstly, the interaction relationship between the HAZs of adjacent process control points is determined: the interaction region between the HAZs of adjacent process control points is extracted, and this interaction region describes the current interaction relationship between the HAZs of adjacent process control points. Furthermore, when there is no interaction region between the HAZs of adjacent process control points, the HAZs corresponding to each adjacent process control point are extracted as thermally independent sub-regions. These thermally independent sub-regions represent individual HAZs and describe the current interaction relationship between the HAZs of adjacent process control points. Then, based on all the interaction relationships, the thermal coupling zone of the ship pipe fitting welding area is constructed, i.e. The process involves: acquiring the interaction regions or thermally independent sub-regions corresponding to each interaction relationship; combining all interaction regions and thermally independent sub-regions into the thermal coupling zone of the welding area of ​​the ship fitting; finally, performing thermal field simulation and prediction on the thermal coupling zone to obtain the preheating control parameters for welding the welding area of ​​the ship fitting, namely: applying preheating parameters (e.g., linearly decreasing from 120℃ / cm to 50℃ / cm) to the thermal coupling zone using the existing technology based on the finite difference method heat conduction model; iteratively adjusting the preheating parameters using an inverse problem optimization algorithm (e.g., the Levenberg-Marquardt algorithm) to ensure that the maximum residual stress in the thermal coupling zone during welding is lower than the yield strength (e.g., 550MPa for 9% nickel steel); and finally quantifying the optimized preheating parameters as the preheating control parameters for welding the welding area of ​​the ship fitting.

[0102] It should be noted that, in this embodiment, the interaction relationship refers to the temperature field interaction relationship between the heat-affected zones of different process control points. Specifically, when a process control point generates a heat-affected zone, the heat in that area will not only affect the material around it, but may also diffuse into the heat-affected zones of adjacent welding points, resulting in a coupling characteristic between the temperature changes of the two welding points. Therefore, the preheating control parameters during welding can be scientifically formulated through the interaction relationship between the heat-affected zones of adjacent process control points. In this embodiment, the thermal coupling zone represents an interrelated temperature field formed between the heat-affected zones of multiple process control points.

[0103] In step 105, the welding area is guided by the preheating control parameters, and then the arc welding gun completes the weld fusion operation of the welding area after the heat energy is guided.

[0104] In some embodiments, the process of guiding heat energy into the welding area according to the preheating control parameters, and then having the arc welding torch complete the weld fusion operation on the heat-guided welding area, can be achieved by the following steps:

[0105] The preheating control parameters are converted into heat source execution commands, and the heat source execution commands drive the heating module to perform scanning heating on the welding area;

[0106] The temperature feedback value of the welding area is collected in real time. When the temperature feedback value reaches the preset temperature range, the heat energy of the welding area is guided and the arc welding gun completes the weld fusion operation of the welding area after the heat energy is guided.

[0107] In specific implementation, firstly, the preheating control parameters are converted into heat source execution commands, and the heat source execution commands drive the heating module to apply gradient preheating to the welding area through closed-loop temperature control (such as PID regulation) at a temperature gradient rate (such as 80℃ / cm) corresponding to the preheating control parameters (for example, increasing the temperature of the weld center from 50℃ to both sides to 200℃) to complete the scanning heating of the welding area; secondly, a distributed thermocouple array is used to monitor the temperature feedback value of the welding area in real time. When the temperature feedback value reaches the preset temperature range, the heat energy is guided to the welding area, and the arc welding gun is triggered to complete the weld fusion operation of the heat-guided welding area according to the set welding path.

[0108] It should be noted that in this embodiment, gradient preheating refers to the preheating temperature applied to the welding area before welding. Through gradient preheating, a controllable temperature gradient distribution can be formed along a predetermined path by the arc welding torch. In this application, the heating value represents the temperature value after preheating the welding area. The preset temperature range in this embodiment is usually determined according to the material type and welding process standards, and is not limited here. For example, carbon steel needs to be preheated to 150~200℃ to prevent cracking. In this embodiment, the heating module refers to the module used for applying temperature.

[0109] It should also be noted that, in this application, thermal energy guidance refers to the process of preheating the welding area. Specifically, thermal energy guidance of the welding area is performed according to the preheating control parameters, that is: the preheating control parameters are converted into heat source execution commands, and the heat source execution commands drive the heating module to perform scanning heating of the welding area; the temperature feedback value of the welding area is collected in real time, and when the temperature feedback value reaches the preset temperature range, the thermal energy guidance of the welding area is completed.

[0110] In another aspect, in some embodiments, this application provides an automated welding system for manufacturing liquefied natural gas (LNG) ship pipe fittings, the system including a heat guiding unit, referenced... Figure 5The figure is a schematic diagram of the structure of a thermal energy guiding unit according to some embodiments of this application. The thermal energy guiding unit 200 includes: a scanning module 201, a processing module 202, and an execution module 203, which are described below:

[0111] The scanning module 201 in this application is mainly used to dynamically scan the welding area of ​​liquefied natural gas ship pipe fittings to obtain the surface morphology data of the welding area.

[0112] Processing module 202, in this application, is mainly used to divide the welding area into multiple welding sub-regions with different surface morphologies based on the surface topography data, and to extract the weld geometric features of the pipe fitting weld in each welding sub-region.

[0113] The processing module 202 is also used to determine the attitude reachable space of the end effector of the arc welding gun in Cartesian space, and then, based on the feature correlation between the geometric features of each weld and the attitude reachable space, to calibrate multiple process control points of the welding area of ​​the ship pipe fitting, and to predict the heat-affected zone of each process control point under the thermal state based on the preset welding heat transfer model.

[0114] In addition, the processing module 202 is also used to determine the preheating control parameters when welding the welding area of ​​the ship pipe fittings by means of the interaction relationship between the heat-affected zones of adjacent process control points.

[0115] The execution module 203 in this application is mainly used to guide the heat energy of the welding area according to the preheating control parameters, and then the arc welding gun completes the weld fusion operation of the welding area after the heat energy is guided.

[0116] In addition, this application also provides a computer device, the computer device including a memory and a processor, the memory storing code, the processor being configured to acquire the code and execute the above-described heat energy guiding method for welding liquefied natural gas ship pipe fittings.

[0117] In some embodiments, reference Figure 6 The figure is a schematic diagram of a computer device for implementing a heat energy guiding method for welding liquefied natural gas (LNG) ship pipe fittings according to some embodiments of this application. The heat energy guiding method for welding LNG ship pipe fittings in the above embodiments can be achieved through… Figure 6 The computer device shown is used to implement this, and the computer device 300 includes at least one processor 301, a communication bus 302, a memory 303, and at least one communication interface 304.

[0118] The processor 301 may be a general-purpose central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more devices used to control the execution of the heat energy guiding method for welding liquefied natural gas ship pipe fittings in this application.

[0119] The communication bus 302 can be used to transmit information between the aforementioned components.

[0120] The memory 303 may be a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, or electrically erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital versatile optical discs, Blu-ray discs, etc.), magnetic disks or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto. The memory 303 may exist independently and be connected to the processor 301 via the communication bus 302. The memory 303 may also be integrated with the processor 301.

[0121] The memory 303 stores program code for executing the scheme of this application, and its execution is controlled by the processor 301. The processor 301 executes the program code stored in the memory 303. The program code may include one or more software modules. In the above embodiments, the determination of the heat energy guiding method for welding liquefied natural gas ship pipe fittings can be implemented by the processor 301 and one or more software modules in the program code in the memory 303.

[0122] Communication interface 304 uses any transceiver-like device to communicate with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area networks (WLAN), etc.

[0123] In a specific implementation, as one example, a computer device may include multiple processors, each of which may be a single-core (single-CPU) processor or a multi-core (multi-CPU) processor. Here, a processor may refer to one or more devices, circuits, and / or processing cores used to process data (e.g., computer program instructions).

[0124] The aforementioned computer device can be a general-purpose computer device or a special-purpose computer device. In specific implementations, the computer device can be a desktop computer, a portable computer, a network server, a handheld digital assistant (PDA), a mobile phone, a tablet computer, a wireless terminal device, a communication device, or an embedded device. This application does not limit the type of computer device.

[0125] In addition, this application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described heat energy guiding method for welding liquefied natural gas ship pipe fittings.

[0126] Although preferred embodiments of this application have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of this application.

[0127] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.

Claims

1. A method for guiding heat energy during welding of liquefied natural gas (LNG) ship pipe fittings, used in an automated welding system for manufacturing LNG ship pipe fittings to guide heat energy to the welding area during welding, characterized in that, The method includes the following steps: Dynamic scanning was performed on the welding area of ​​the liquefied natural gas ship pipe fittings to obtain the surface morphology data of the welding area; Based on the surface topography data, the welding area is divided into multiple welding sub-regions with different surface morphologies, and the weld geometry features of the pipe fitting welds in each welding sub-region are extracted. The process involves determining the reachable attitude space of the arc welding torch end effector in Cartesian space, and then calibrating multiple process control points in the welding area of ​​the ship fitting based on the feature correlations between various weld geometric features and the reachable attitude space. Specifically, this calibration includes: determining the feature correlations between various weld geometric features; constructing constraint identification parameters for welding constraints in the welding area of ​​the ship fitting based on all feature correlations; obtaining the initial weld curves corresponding to each welding sub-region in the welding area of ​​the ship fitting; for each welding sub-region, calculating the curvature deviation at different sampling points in the initial weld curve corresponding to each welding sub-region, and extracting multiple candidate process control points from all sampling points based on all curvature deviations and the constraint identification parameters; selecting multiple process control points for the welding area of ​​the ship fitting based on the reachable attitude space, and predicting the heat-affected zone of each process control point under thermal conditions based on a preset welding heat transfer model. The preheating control parameters for welding the welding area of ​​the ship pipe fittings are determined by the interaction relationship between the heat-affected zones of adjacent process control points. The welding area is then guided by the preheating control parameters, and the arc welding gun completes the weld fusion operation of the heat-guided welding area.

2. The method as described in claim 1, characterized in that, Based on the surface morphology data, the welding area is divided into multiple welding sub-regions with different surface morphologies, specifically including: A three-dimensional surface model of the welding area is constructed based on the surface morphology data. The three-dimensional surface model is meshed to obtain the local curvature distribution of the welding area; Based on the local curvature distribution, the welding area is clustered using a region growing algorithm to obtain multiple welding sub-regions with different surface morphologies.

3. The method as described in claim 1, characterized in that, Extracting the weld geometry features of the pipe fitting welds within each welding sub-region specifically includes: Extract the weld contour of the pipe fitting weld in each welding sub-region; Select a welding sub-region as the selected welding sub-region, and extract the initial weld curve corresponding to the selected welding sub-region based on the weld contour of the selected welding sub-region. The initial weld curve is smoothed and optimized, and the weld geometry of the pipe fitting weld in the selected welding sub-region is determined by the smoothed and optimized initial weld curve. Continue to determine the weld geometry of the pipe fittings within the remaining welding sub-regions.

4. The method as described in claim 1, characterized in that, Determining the reachable space of the arc welding torch end effector in Cartesian space specifically includes: Establish a forward kinematic model of the end effector of the arc welding gun; The effective end-effector posture set of the arc welding gun end effector is extracted based on the positive kinematics model; The attitude reachable space of the arc welding gun end effector in Cartesian space is determined based on the set of effective end attitudes.

5. The method as described in claim 1, characterized in that, Based on a pre-set welding heat transfer model, the predicted heat-affected zones at various process control points under thermal conditions specifically include: The preset welding heat transfer model is invoked, and heat conduction simulation calculations are performed for each process control point to generate the temperature gradient distribution corresponding to each process control point. For each process control point, the heat-affected zone of the process control point is determined based on the temperature gradient distribution of the process control point.

6. The method as described in claim 1, characterized in that, The surface morphology data of the welding area is obtained by dynamically scanning the welding area of ​​the liquefied natural gas ship pipe fittings using a laser scanner.

7. An automated welding system for manufacturing liquefied natural gas (LNG) ship pipe fittings, comprising a heat-guiding unit, wherein the system uses the method described in any one of claims 1 to 6 for heat energy guidance, characterized in that... The thermal energy guiding unit includes: The scanning module is used to dynamically scan the welding area of ​​liquefied natural gas ship pipe fittings to obtain surface morphology data of the welding area; The processing module is used to divide the welding area into multiple welding sub-regions with different surface morphologies based on the surface topography data, and extract the weld geometric features of the pipe fitting weld in each welding sub-region. The processing module is further configured to determine the attitude reachable space of the arc welding torch end effector in Cartesian space, and then, based on the feature correlation between various weld geometric features and the attitude reachable space, calibrate multiple process control points of the ship fitting welding area. Specifically, calibrating multiple process control points of the ship fitting welding area based on the feature correlation between various weld geometric features and the attitude reachable space includes: determining the feature correlation between various weld geometric features; constructing constraint identification parameters for welding constraints on the ship fitting welding area based on all feature correlations; obtaining the initial weld curve corresponding to each welding sub-region in the ship fitting welding area; for each welding sub-region, calculating the curvature deviation at different sampling points in the initial weld curve corresponding to each welding sub-region; extracting multiple candidate process control points from all sampling points based on all curvature deviations and the constraint identification parameters; selecting multiple process control points of the ship fitting welding area from all candidate process control points based on the attitude reachable space; and predicting the heat-affected zone of each process control point under thermal conditions based on a preset welding heat transfer model. The processing module is also used to determine the preheating control parameters when welding the welding area of ​​the ship pipe fittings by means of the interaction relationship between the heat-affected zones of adjacent process control points. The execution module is used to guide the heat energy of the welding area according to the preheating control parameters, and then the arc welding gun completes the weld fusion operation of the welding area after the heat energy is guided.

8. A computer device, characterized in that, The computer device includes a memory and a processor, the memory storing code, and the processor being configured to retrieve the code and execute the heat-directing method for welding liquefied natural gas ship pipe fittings as described in any one of claims 1 to 6.

9. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the heat energy guiding method for welding liquefied natural gas ship pipe fittings as described in any one of claims 1 to 6.

Images