Pipeline all-position submerged arc welding optimization method, device and equipment based on temperature field monitoring and welding seam tracking and storage medium

Abstract

The invention discloses a pipeline all-position submerged arc welding optimization method, device and equipment based on temperature field monitoring and welding seam tracking and a storage medium, and relates to the technical field of submerged arc welding, the method comprises the steps that a three-dimensional pipeline model is obtained, and width, depth and curvature information of a target welding seam area in the three-dimensional pipeline model is extracted; a welding gun path is planned according to the width, depth and curvature information, and a welding gun is controlled to move along the welding gun path; under the condition that the welding gun moves, the temperature field of the target welding seam area is monitored, and the target welding current, the target welding voltage and the offset of the welding gun position are calculated according to the temperature field; and the welding current, the welding voltage and the position of the welding gun are adjusted based on the target welding current, the target welding voltage and the offset, and welding optimization is completed. According to the method, the welding quality and the heat input uniformity of all-position submerged arc welding of the pipeline are improved by accurately tracking the welding seam position and monitoring the temperature field change in real time, and the stability and the high efficiency of the welding process are ensured.

Description

Technical Field

[0001] The present application relates to the technical field of submerged arc welding, and in particular to a pipeline full-position submerged arc welding optimization method, device, equipment and storage medium based on temperature field monitoring and weld tracking. Background Art

[0002] In modern industrial manufacturing, all-position submerged arc welding (SAW) technology for pipelines is widely used in energy pipelines, chemical equipment, and other fields. Stable weld quality and uniform heat input are key factors in ensuring the safety and reliability of welded structures. The welding process becomes significantly more complex, especially when the pipeline cannot rotate. The welding gun must be precisely aligned with the weld center at various positions (such as vertical welding, overhead welding, and at elbows) while ensuring uniform heat input distribution. This high-precision welding requirement is particularly important in modern industrial manufacturing.

[0003] Currently, full-position submerged arc welding (SAW) of pipelines typically utilizes a flux scooping device to stabilize flux delivery, while visual or laser sensors are used for weld tracking. Furthermore, temperature field monitoring technology is also used during the welding process, primarily using infrared temperature sensors or thermal imaging cameras to capture temperature data in the weld area.

[0004] However, the existing practices still have many shortcomings. First, the fluidity problem of the flux leads to uneven temperature distribution in the welding area, which in turn affects the stability of the heat input. Even if a flux pocket device is used, the fluidity of the flux in the pocket device is still difficult to fully control, resulting in unstable molten pool morphology and easy welding defects. Secondly, the existing weld tracking technology has low accuracy in complex welding positions (such as pipe elbows, vertical welding and overhead welding, etc.), and it is difficult to ensure that the welding gun is always aligned with the center of the weld. In addition, although the existing temperature field monitoring technology can obtain temperature data, it cannot realize real-time dynamic adjustment of welding parameters (such as current, voltage and welding speed), and it is difficult to effectively deal with the temperature unevenness during the welding process. Therefore, how to improve the welding quality and heat input uniformity of pipeline full-position submerged arc welding by accurately tracking the weld position and real-time monitoring of temperature field changes has become an urgent problem to be solved.

[0005] The above content is only used to assist in understanding the technical solution of this application and does not constitute an admission that the above content is prior art. Summary of the Invention

[0006] The purpose of this application is to provide a pipeline full-position submerged arc welding optimization method, device, equipment and storage medium based on temperature field monitoring and weld tracking, aiming to solve the technical problem of how to improve the welding quality and heat input uniformity of pipeline full-position submerged arc welding by accurately tracking the weld position and real-time monitoring of temperature field changes.

[0007] To achieve the above objectives, the present application proposes a pipeline all-position submerged arc welding optimization method based on temperature field monitoring and weld tracking, the method comprising:

[0008] Acquire a three-dimensional pipeline model, and extract width, depth, and curvature information of a target weld area in the three-dimensional pipeline model;

[0009] planning a welding gun path according to the width, the depth, and the curvature information, and controlling the welding gun to move along the welding gun path;

[0010] When the welding gun is moving, monitoring the temperature field of the target weld area, and calculating the target welding current, target welding voltage and the offset of the welding gun position according to the temperature field;

[0011] The welding current, the welding voltage and the position of the welding gun are adjusted based on the target welding current, the target welding voltage and the offset to complete welding optimization.

[0012] In one embodiment, the steps of obtaining a three-dimensional pipeline model and extracting width, depth, and curvature information of a target weld area in the three-dimensional pipeline model include: performing multi-angle scanning on the pipeline weld area to obtain three-dimensional point cloud data; performing denoising and registration processing on the three-dimensional point cloud data to obtain a three-dimensional pipeline model; segmenting the target weld area from the three-dimensional pipeline model based on a region growing algorithm; and extracting width, depth, and curvature information of the target weld area.

[0013] In one embodiment, the step of segmenting the target weld area from the three-dimensional pipeline model based on the region growing algorithm includes: selecting at least one seed point on the weld surface of the three-dimensional pipeline model and calculating the normal direction of the seed point; searching for the neighborhood points of the seed point, and calculating the normal angle and curvature difference between the neighborhood point and the seed point according to the normal direction; when the normal angle is less than a preset angle threshold and the curvature difference is less than a preset curvature threshold, adding the neighborhood point to the initial weld area; returning to the step of searching for the neighborhood points of the seed point, and calculating the normal angle and curvature difference between the neighborhood point and the seed point according to the normal direction, until the radius of the initial weld area is greater than the preset expansion threshold or the number of points in the initial weld area reaches a preset point number threshold, thereby obtaining the target weld area.

[0014] In one embodiment, the step of extracting the width, depth and curvature information of the target weld area includes: fitting the edge points on both sides of the target weld area by the least squares method; taking the maximum width of the edge points on both sides as the width of the target weld area; calculating the depth based on the normal distance between the point cloud of the target weld area and the inner wall of the three-dimensional pipeline model; and extracting the curvature information of the surface of the target weld area by the principal component analysis method.

[0015] In one embodiment, the step of denoising and registering the three-dimensional point cloud data to obtain a three-dimensional pipeline model includes: performing neighborhood distance calculation on each point in the three-dimensional point cloud data to obtain a distance distribution between each point and its neighboring points; removing outliers exceeding a preset noise threshold based on the mean and standard deviation of the distance distribution to obtain denoised point cloud data; using the denoised point cloud data scanned from a first angle as a reference point cloud and the rest of the denoised point cloud data as an initial point cloud; matching each point in the initial point cloud with the nearest point of the reference point cloud to obtain a matching point pair; calculating a rotation matrix and a translation vector based on the matching point pair by a least squares method; transforming the initial point cloud according to the rotation matrix and the translation vector, and returning to the step of matching each point in the initial point cloud with the nearest point of the reference point cloud to obtain a matching point pair, until the alignment error between the initial point cloud and the reference point cloud is less than a preset convergence threshold or the number of iterations reaches a preset iteration threshold, thereby obtaining a target point cloud; and merging the target point cloud with the reference point cloud to obtain a three-dimensional pipeline model.

[0016] In one embodiment, the step of planning a welding gun path according to the width, the depth, and the curvature information, and controlling the welding gun to move along the welding gun path includes: calculating an initial motion trajectory of the welding gun along the centerline of the weld based on the width and the curvature information; smoothing the initial motion trajectory using a B-spline curve algorithm and a Bezier algorithm to obtain a target welding gun path; calculating a target inclination angle of the welding gun according to the curvature information, the normal direction of the welding gun, and the normal direction of the weld centerline; calculating motion parameters of each joint of the welding gun using an inverse kinematics algorithm according to the target welding gun path and the target inclination angle, and generating a welding gun control instruction according to the motion parameters; and sending the welding gun control instruction to a welding gun drive device so that the welding gun drive device controls the welding gun to maintain the target inclination angle and move along the target welding gun path.

[0017] In one embodiment, the steps of monitoring the temperature field of the target weld area when the welding gun moves, and calculating the target welding current, target welding voltage and offset of the welding gun position based on the temperature field include: monitoring the temperature field of the target weld area when the welding gun moves, wherein the temperature field is obtained by continuously scanning the target weld area with an infrared thermal imaging camera; extracting the left temperature value and the right temperature value of the welding gun from the temperature field, and calculating the absolute value of the temperature difference between the left temperature value and the right temperature value; calculating the target welding current and target welding voltage based on the absolute value of the temperature difference, a preset current adjustment coefficient, a preset voltage adjustment coefficient, an initial welding current and an initial welding voltage; when the absolute value of the temperature difference exceeds a preset temperature difference threshold, determining the welding gun offset direction based on the size relationship between the left temperature value and the right temperature value; and calculating the offset of the welding gun position based on a preset path correction coefficient based on the welding gun offset direction and the absolute value of the temperature difference.

[0018] In addition, to achieve the above objectives, the present application also proposes a pipeline all-position submerged arc welding optimization device based on temperature field monitoring and weld tracking, the device comprising:

[0019] A model acquisition module is used to acquire a three-dimensional pipeline model and extract width, depth and curvature information of a target weld area in the three-dimensional pipeline model;

[0020] a path planning module, configured to plan a welding gun path according to the width, the depth, and the curvature information, and control the welding gun to move along the welding gun path;

[0021] a temperature monitoring module, configured to monitor the temperature field of the target weld area while the welding gun is moving, and calculate the target welding current, target welding voltage, and an offset of the welding gun position based on the temperature field;

[0022] The dynamic adjustment module is used to adjust the welding current, welding voltage and the position of the welding gun based on the target welding current, the target welding voltage and the offset to achieve welding optimization.

[0023] In addition, to achieve the above-mentioned purpose, the present application also proposes a pipeline full-position submerged arc welding optimization device based on temperature field monitoring and weld tracking, the device comprising: a memory, a processor, and a computer program stored on the memory and executable on the processor, the computer program being configured to implement the steps of the pipeline full-position submerged arc welding optimization method based on temperature field monitoring and weld tracking as described above.

[0024] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by the processor, the steps of the pipeline full-position submerged arc welding optimization method based on temperature field monitoring and weld tracking as described above are implemented.

[0025] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, it implements the steps of the pipeline full-position submerged arc welding optimization method based on temperature field monitoring and weld tracking as described above.

[0026] One or more technical solutions proposed in this application have at least the following technical effects:

[0027] First, the welding control system acquires 3D point cloud data and generates a 3D pipeline model. It then extracts the width, depth, and curvature of the target weld area. This process provides precise geometric data for torch path planning, ensuring precise alignment of the torch with the weld and minimizing welding deviation. Next, the welding control system plans the torch path based on the extracted weld geometry and controls the torch movement along this path. This precise path planning allows the torch to dynamically adjust according to the actual shape and size of the weld, ensuring uniformity and consistency during the welding process. During torch movement, the temperature field of the target weld area is monitored in real time. Based on this temperature field data, the target welding current, target welding voltage, and torch position offset are calculated. This real-time temperature monitoring allows the system to promptly detect uneven heat input and dynamically adjust welding parameters and torch position accordingly, ensuring welding stability and uniform heat input. Finally, the welding control system adjusts the welding current, welding voltage, and torch position based on the calculated target welding current, target welding voltage, and offset, completing welding optimization. By accurately tracking the weld position and real-time monitoring of temperature field changes, the welding quality and heat input uniformity of pipeline submerged arc welding in all positions are improved, ensuring the stability and efficiency of the welding process. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0029] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0030] Figure 1A flow chart of the first embodiment of the pipeline all-position submerged arc welding optimization method based on temperature field monitoring and weld tracking is provided in this application;

[0031] Figure 2 A schematic structural diagram of a pipeline all-position submerged arc welding system provided in Example 1 of the present application for an optimization method for pipeline all-position submerged arc welding based on temperature field monitoring and weld tracking;

[0032] Figure 3 A flow chart of the second embodiment of the pipeline all-position submerged arc welding optimization method based on temperature field monitoring and weld tracking is provided in this application;

[0033] Figure 4 This is a schematic diagram of the module structure of a pipeline all-position submerged arc welding optimization device based on temperature field monitoring and weld tracking according to an embodiment of the present application;

[0034] Figure 5 This is a schematic diagram of the equipment structure of the hardware operating environment involved in the pipeline all-position submerged arc welding optimization method based on temperature field monitoring and weld tracking in the embodiment of the present application.

[0035] Description of Figure Numbers:

[0036] 1. Pipeline; 2. Flux box moving device; 3. Line laser profile sensor; 4. Infrared thermal imaging camera; 5. Welding gun; 6. Welding gun adjustment mechanism; 7. Welding carriage; 8. Welding wire reel; 9. Ring rail; 10. Cover plate drive motor; 11. Flux box; 12. Feed pipe.

[0037] The purpose, features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0038] It should be understood that the specific embodiments described herein are merely used to explain the technical solutions of the present application and are not intended to limit the present application.

[0039] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0040] In modern industry, full-position submerged arc welding of pipelines is widely used in fields such as energy and chemical engineering. Weld quality and heat input uniformity are critical to ensuring structural safety. However, despite the use of flux scooping devices, visual or laser sensors for weld tracking, and infrared sensors for temperature field monitoring, existing practices still present numerous challenges: flux fluidity leads to uneven temperature distribution, weld tracking accuracy is low, and it is impossible to adjust welding parameters in real time to address temperature variations.

[0041] The main solution of this embodiment is to first acquire 3D point cloud data to generate a pipeline model, extract the weld width, depth, and curvature information, and provide accurate data for torch path planning, ensuring precise alignment of the torch to the weld. Next, based on this geometric information, the torch path is planned and its movement is controlled, dynamically adjusting according to the weld shape to ensure weld uniformity. During the welding process, the temperature field is monitored in real time, and the target welding parameters and torch offset are calculated. The welding current, voltage, and torch position are dynamically adjusted, ultimately completing welding optimization and improving weld quality and heat input uniformity.

[0042] It should be noted that the execution subject of the embodiments of the present application may be a computing service device with data processing, network communication, and program execution functions, such as a tablet computer, personal computer, mobile phone, etc., or an electronic device capable of implementing the above functions, such as a welding control system. The following describes this embodiment and the following embodiments using a welding control system as an example.

[0043] Based on this, the embodiment of the present application provides a pipeline full-position submerged arc welding optimization method based on temperature field monitoring and weld tracking, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the pipeline all-position submerged arc welding optimization method based on temperature field monitoring and weld tracking in this application.

[0044] In this embodiment, the pipeline all-position submerged arc welding optimization method based on temperature field monitoring and weld tracking includes steps S10 to S40:

[0045] Step S10: obtaining a three-dimensional pipeline model, and extracting width, depth, and curvature information of a target weld area in the three-dimensional pipeline model.

[0046] Please note that, please refer to Figure 2 , Figure 2This figure provides a schematic diagram of the structure of a pipeline all-position submerged arc welding system, including several key components, for the first embodiment of the present application's method for optimizing pipeline all-position submerged arc welding based on temperature field monitoring and weld tracking. The figure shows a schematic diagram of the structure of a pipeline all-position submerged arc welding system. The pipeline 1, the object to be welded, is placed at the center of the welding system. The flux box moving device 2 controls the movement of the flux box 11 along the pipeline, ensuring uniform flux coverage of the weld area. A line laser profile sensor 3 and an infrared thermal imaging camera 4 are mounted on the welding gun 5 to monitor the geometry and temperature field of the weld area in real time. The welding gun adjustment mechanism 6 precisely adjusts the position and angle of the welding gun to accommodate different welding positions. The welding carriage 7 carries the welding gun and associated sensors and moves along a circular track 9, ensuring precise positioning of the welding gun. The wire reel 8 provides the required welding wire, which is delivered to the welding gun via a feed pipe 12. The cover plate drive motor 10 controls the movement of the cover plate, which protects or supports the pipeline. The entire system coordinates the actions of various components to achieve precise welding of the pipeline weld area, ensuring welding quality and efficiency.

[0047] A 3D pipeline model is a 3D geometric model of the pipeline reconstructed from 3D point cloud data. It accurately reflects the pipeline's shape, dimensions, and the spatial location of welds, providing a foundation for subsequent weld geometry extraction and welding path planning. The target weld area is the area within the 3D pipeline model where the weld is located, segmented from the entire point cloud data. This area requires special attention and processing during the welding process, and contains information about the weld's geometric characteristics, such as width, depth, and curvature.

[0048] Width refers to the transverse dimension of the weld area along the weld direction in the 3D pipe model. It is a key parameter in weld geometry, directly influencing the welding torch path and welding parameter settings, and is crucial for ensuring weld quality and heat input uniformity. Depth refers to the vertical distance from the pipe surface to the weld bottom in the 3D pipe model. Depth information is crucial for controlling heat input and adjusting the welding torch angle during welding, helping the welding system better adapt to different groove shapes. Curvature information refers to the degree of curvature of the weld surface in the 3D pipe model, including Gaussian curvature and mean curvature. It reflects the shape variation of the weld surface, particularly in pipe welding, where weld morphology can be affected by pipe curvature or groove angle. Accurate curvature information is crucial for the welding control system to perform precise path planning and welding torch angle adjustment, ensuring that the welding torch maintains an optimal contact angle with the weld surface throughout the welding process, thereby improving weld quality and stability.

[0049] As you can understand, the welding control system first acquires the pipeline's 3D point cloud data and performs 3D modeling based on this data, forming a complete 3D pipeline model. Secondly, the system segments the target weld area from the 3D pipeline model, ensuring that the extracted area accurately reflects the weld's actual position and shape. Finally, based on the segmented weld area point cloud data, the system calculates the weld's width, depth, Gaussian curvature, and mean curvature using a fitting algorithm, providing precise geometric data support for subsequent welding path planning and parameter optimization.

[0050] Step S20 , planning a welding gun path according to the width, the depth, and the curvature information, and controlling the welding gun to move along the welding gun path.

[0051] It's important to note that the torch path refers to the trajectory of the torch during welding, calculated and planned by the welding control system based on the weld's geometric characteristics (including width, depth, and curvature). This path ensures the torch is precisely aligned with the weld's centerline and dynamically adjusts to the weld's actual shape and size. By accurately planning the torch path, the welding control system ensures stable tracking of the torch even in complex weld geometries, ensuring uniformity and high quality during the welding process.

[0052] As an example, the steps of planning a welding gun path according to the width, the depth and the curvature information, and controlling the welding gun to move along the welding gun path include: calculating an initial motion trajectory of the welding gun along the center line of the weld based on the width and the curvature information; smoothing the initial motion trajectory using a B-spline curve algorithm and a Bezier algorithm to obtain a target welding gun path; calculating a target inclination angle of the welding gun according to the curvature information, the normal direction of the welding gun and the normal direction of the center line of the weld; calculating motion parameters of each joint of the welding gun through an inverse kinematics algorithm according to the target welding gun path and the target inclination angle, and generating a welding gun control instruction according to the motion parameters; and sending the welding gun control instruction to a welding gun drive device so that the welding gun drive device controls the welding gun to maintain the target inclination angle and move along the target welding gun path.

[0053] The weld centerline refers to the geometric centerline of the target weld area in the 3D pipeline model. It is the central axis in the weld width direction and is used to define the path that the welding gun needs to accurately track during the welding process.

[0054] The B-spline curve algorithm is a mathematical method used to generate smooth curves, which is used to smooth the initial motion trajectory of the welding gun. By defining a set of control points and corresponding weights, the B-spline curve can generate a continuous and smooth curve, avoiding sudden changes or discontinuities in the path. This helps optimize the welding gun's motion trajectory, allowing it to smoothly follow the weld during the welding process and reduce welding defects.

[0055] The Bezier algorithm, a control-point-based parametric curve generation method, is used to further optimize the welding gun's trajectory and ensure smoothness. Defined by control points and parametric equations, the Bezier curve generates a smooth curve from the starting point to the end point. Combined with the B-spline algorithm, it further optimizes the welding gun path, making it more suitable for complex weld shapes and welding requirements.

[0056] The initial motion trajectory refers to the preliminary motion path of the welding gun, calculated based on the weld centerline and weld width. It is the first step in welding gun path planning and reflects the ideal movement direction and position of the welding gun. The initial motion trajectory is usually a simple geometric path that may contain some uneven points or segments. It is subsequently smoothed using the B-spline curve algorithm and the Bezier algorithm to generate the final target welding gun path. The target welding gun path refers to the final optimized and smoothed welding gun trajectory. It is obtained by processing the initial motion trajectory through the B-spline curve algorithm and the Bezier algorithm, ensuring smooth and continuous movement of the welding gun during the welding process.

[0057] The normal direction of the welding gun refers to the direction in which the end of the welding gun nozzle is perpendicular to the weld surface during the welding process. It is used to describe the welding gun's posture relative to the weld surface. By adjusting the normal direction of the welding gun, the welding gun can maintain an optimal contact angle with the weld surface, thereby optimizing welding heat input and molten pool stability, and improving welding quality. The normal direction of the weld centerline refers to the direction perpendicular to the weld centerline at a certain point on the weld centerline. It reflects the degree of curvature and direction of the weld centerline at that point. It helps the welding system dynamically adjust the movement trajectory and tilt angle of the welding gun according to the actual shape of the weld, ensuring that the welding gun always welds along the weld centerline and maintains the optimal contact angle with the weld surface.

[0058] The target tilt angle refers to the optimal tilt angle the welding gun should maintain during welding. It ensures the gun can dynamically adjust to the actual shape and curvature of the weld, thereby ensuring welding stability and uniform heat input. The inverse kinematics algorithm is a mathematical method used to calculate the kinematic parameters of the robot's joints. It calculates the kinematic parameters of each gun joint based on the target gun path and target tilt angle. The inverse kinematics algorithm determines the joint angles and positions of the gun at each moment, generating precise gun control instructions to ensure the gun adheres to the planned path and angle. Kinematic parameters describe the kinematic state of each gun joint, including joint angles, velocities, and accelerations. They define the specific motion of the gun during welding. These parameters determine the gun's trajectory, velocity changes, and posture adjustments, and serve as the basis for gun control instructions. Gun control instructions are generated by the welding control system to control the gun's motion. They contain kinematic information about each gun joint, such as joint angles, velocities, and accelerations. Gun control instructions are transmitted to the gun via the gun driver to ensure the gun adheres to the planned path and angle.

[0059] The welding gun drive device refers to the hardware device used to control the movement of the welding gun, which usually includes a motor, a driver and other mechanical components. The welding gun drive device drives the movement of each joint of the welding gun according to the welding gun control instructions, thereby achieving precise control of the welding gun.

[0060] First, the welding control system converts the point cloud data P of the target weld area into local = (x, y, z) is converted from the local coordinate system of the line laser profile sensor to the global coordinate system P of the welding gun control system global =(X, Y, Z), coordinate transformation is performed through the known rotation matrix R and translation vector T to ensure that the point cloud data and the welding gun control system are in the same coordinate frame, thus providing an accurate reference for subsequent path planning. The conversion formula is:

[0061] P global =R·P local +T

[0062] Among them, P local is the point cloud data in the local coordinate system of the line laser profile sensor, P global is the point cloud data in the global coordinate system, R is the rotation matrix, and T is the translation vector.

[0063] Next, based on the width and curvature of the weld, the system calculates a preliminary motion trajectory along the weld centerline. This trajectory is formed by extracting key points on the weld centerline and connecting these points, providing a basic path for the movement of the welding gun. The initial motion trajectory is then smoothed using the B-spline curve algorithm. By defining control points and weights, a continuous and smooth curve is generated to eliminate sudden changes and discontinuities in the path. At the same time, the Bezier algorithm is used to further optimize this curve to ensure the smoothness of the welding gun path, ultimately obtaining the target welding gun path. The B-spline curve formula is:

[0064]

[0065] Among them, P smooth is the smoothed path, N i (t) is the B-spline basis function, P i is the control point, n is the number of control points, and t is the path parameter.

[0066] Bezier curve formula:

[0067] P smooth (t) = (1-t) 3 P0+3(1-t) 2 tP1+3(1-t)t 2 P2+t 3 P3

[0068] Among them, P0, P1, P2, P3 are control points, and t is the path parameter.

[0069] Then, based on the curvature information of the weld and the normal direction of the welding gun and the weld centerline, the system calculates the target tilt angle of the welding gun at different positions. By comparing the normal direction of the welding gun at its current position with the normal direction of the weld centerline, the welding gun angle is adjusted to maintain the optimal contact angle with the weld surface. The target tilt angle calculation formula is:

[0070]

[0071] Among them, N i is the normal direction of the current position of the welding gun, N weld is the normal direction of the weld centerline, θ gun is the tilt angle of the welding gun.

[0072] Next, using the inverse kinematics algorithm, the motion parameters of each joint of the welding gun, including joint angle, velocity, and acceleration, are calculated based on the target welding gun path and target tilt angle. These parameters are derived through mathematical models and algorithms to ensure that the welding gun can move according to the planned path and angle. The ideal position calculation formula for the welding gun is:

[0073] Pgun (x,y,z)=f(C weld ,N weld ,θ gun )

[0074] Among them, P gun (x, y, z) is the welding gun position, C weld is the coordinate of the weld centerline, N weld is the normal direction of the weld, θ gun is the welding gun angle.

[0075] Finally, welding gun control instructions are generated based on the calculated motion parameters and sent to the welding gun drive device. The drive device controls the welding gun to maintain the target tilt angle and move along the target welding gun path according to the instructions, thereby achieving precise welding operations.

[0076] Step S30 , when the welding gun is moving, monitoring the temperature field of the target weld area, and calculating the target welding current, target welding voltage and the offset of the welding gun position according to the temperature field.

[0077] It should be noted that the temperature field refers to the temperature distribution within the target weld area during welding. The temperature field is monitored in real time by an infrared thermal imaging camera mounted on the welding torch, reflecting temperature changes in the weld area and surrounding areas. Temperature field data, presented as temperature values, is used to analyze whether heat input is uniform during welding and whether there are localized temperature anomalies caused by torch offset or flux fluidity. The target welding current is the welding current value dynamically adjusted based on the real-time temperature field data. If the temperature field indicates that certain areas are too high or too low, the system calculates the required welding current value based on a preset adjustment strategy to optimize heat input and ensure weld quality. The target welding voltage is the welding voltage value dynamically adjusted based on the real-time temperature field data. If the temperature field indicates that certain areas are too high or too low, the system calculates the required welding voltage value based on a preset adjustment strategy to optimize heat input and ensure weld quality. The welding torch position offset refers to the deviation between the actual welding torch position and the planned path during welding.

[0078] As an example, the steps of monitoring the temperature field of the target weld area when the welding gun moves, and calculating the target welding current, target welding voltage and offset of the welding gun position based on the temperature field include: monitoring the temperature field of the target weld area when the welding gun moves, wherein the temperature field is obtained by continuously scanning the target weld area with an infrared thermal imaging camera; extracting the left temperature value and the right temperature value of the welding gun from the temperature field, and calculating the absolute value of the temperature difference between the left temperature value and the right temperature value; calculating the target welding current and target welding voltage based on the absolute value of the temperature difference, a preset current adjustment coefficient, a preset voltage adjustment coefficient, an initial welding current and an initial welding voltage; when the absolute value of the temperature difference exceeds a preset temperature difference threshold, determining the welding gun offset direction based on the size relationship between the left temperature value and the right temperature value; and calculating the offset of the welding gun position based on a preset path correction coefficient based on the welding gun offset direction and the absolute value of the temperature difference.

[0079] The absolute value of the temperature difference refers to the absolute value of the difference between the temperature values on the left and right sides of the welding gun. It is used to determine whether the welding gun deviates from the center line of the weld and the degree of deviation. It is an important basis for dynamically adjusting the welding current, voltage and welding gun position.

[0080] The preset current adjustment coefficient is a fixed parameter used to calculate the target welding current. It is calibrated based on the actual welding process and experience. This coefficient is used to convert the absolute value of the temperature difference into the adjustment amount of the welding current to optimize the heat input and ensure the uniformity of the welding process. It reflects the influence of the temperature difference on the welding current adjustment and is one of the key parameters used in the welding control system to dynamically adjust the welding parameters.

[0081] The preset voltage adjustment coefficient is a fixed parameter used to calculate the target welding voltage. It is also calibrated based on the actual welding process and experience. This coefficient is used to convert the absolute value of the temperature difference into an adjustment amount for the welding voltage to optimize heat input and ensure the uniformity of the welding process. It reflects the degree of influence of the temperature difference on the welding voltage adjustment and is one of the key parameters used in the welding control system to dynamically adjust the welding parameters.

[0082] The initial welding current refers to the welding current value set at the beginning of the welding process. It is pre-set according to the welding process requirements and the characteristics of the pipeline material. It is the benchmark value for the welding control system to dynamically adjust the welding current. The subsequent target welding current is adjusted based on the initial welding current and the absolute value of the temperature difference.

[0083] The initial welding voltage refers to the welding voltage value set at the beginning of the welding process. It is pre-set according to the welding process requirements and the characteristics of the pipeline material. It is the reference value for the welding control system to dynamically adjust the welding voltage. The subsequent target welding voltage is adjusted based on the initial welding voltage and the absolute value of the temperature difference.

[0084] The target welding current refers to the welding current value calculated based on the absolute value of the temperature difference and the preset current adjustment coefficient. It is a dynamically adjusted welding current used to compensate for uneven heat input caused by welding gun offset or uneven temperature field. The target welding voltage refers to the welding voltage value calculated based on the absolute value of the temperature difference and the preset voltage adjustment coefficient. It is a dynamically adjusted welding voltage used to compensate for uneven heat input caused by welding gun offset or uneven temperature field. The preset temperature difference threshold is a pre-set temperature difference value used to determine whether the welding gun has deviated from the center line of the weld. When the absolute value of the temperature difference exceeds the preset temperature difference threshold, it indicates that the welding gun position has significantly deviated and path correction is required.

[0085] Gun offset refers to the direction the gun deviates from the weld centerline during welding. By comparing the temperature values on the left and right sides of the gun, we can determine whether the gun is deviating to the left or right. If the left temperature is higher than the right temperature, the gun is deviating to the right; conversely, if the right temperature is higher than the left temperature, the gun is deviating to the left. The preset path correction factor is a fixed parameter used to calculate the gun position offset. Calibrated based on actual welding processes and experience, this factor converts the absolute value of the temperature difference into a correction for the gun position, adjusting the gun's position to realign it with the weld centerline.

[0086] First, the welding control system continuously scans the target weld area using an infrared thermal imaging camera mounted on the welding gun, acquiring real-time temperature field data for the weld area. This data includes temperature information on both sides of the welding gun for subsequent analysis and adjustment. Second, the system extracts the temperature values on the left and right sides of the welding gun from the temperature field data and calculates the absolute value of the temperature difference between the two temperature values. By comparing the temperature difference between the left and right sides, the system determines whether the welding gun has deviated from the weld centerline and the degree of deviation. The temperature difference value ΔT is calculated using the following formula:

[0087] ΔT=|T left -T right |

[0088] Where T left and T right These are the temperature values on the left and right side of the welding gun respectively.

[0089] Next, the system calculates the target welding current and target welding voltage based on the absolute value of the temperature difference, the preset current adjustment coefficient, the voltage adjustment coefficient, and the initially set welding current and voltage. It dynamically adjusts the welding parameters to optimize heat input and ensure uniformity during the welding process. The target welding current and target welding voltage calculation formula is:

[0090] I adjusted =I initial +k I ΔT

[0091] U adjusted =U initial +k U ΔT

[0092] Among them, I adjusted and U adjusted is the target welding current and target welding voltage; I initial and U initial is the initial set welding current and voltage; k I and k U are the current and voltage adjustment coefficients (calibrated by the actual welding process).

[0093] When the absolute value of the temperature difference exceeds the preset temperature difference threshold, the system determines the offset direction of the welding gun based on the size relationship between the left and right temperature values, that is, determines whether the welding gun is biased to the left or right. Finally, based on the offset direction of the welding gun and the absolute value of the temperature difference, the preset path correction coefficient is used to calculate the offset of the welding gun position, and the position of the welding gun is adjusted accordingly to realign it with the center line of the weld, thereby ensuring the stability and quality of the welding process. The offset calculation formula of the welding gun position is:

[0094] ΔP gun =k path ΔT

[0095] Where ΔP gun k is the path correction of the welding gun, which indicates the distance the welding gun should move. path The path correction coefficient is calibrated based on actual welding process parameters (such as welding speed, pipe curvature, etc.).

[0096] Step S40 , adjusting the welding current, welding voltage, and position of the welding gun based on the target welding current, the target welding voltage, and the offset to complete welding optimization.

[0097] As you can understand, first, the welding control system dynamically adjusts the output parameters of the welding power supply based on the calculated target welding current and target welding voltage, ensuring a smooth transition from the initial or current values to the target values. This optimizes welding heat input and ensures uniformity during the welding process. Next, based on the calculated gun position offset, the system uses the gun drive to adjust the lateral position of the gun, realigning it with the weld centerline and correcting gun offset caused by temperature differences.

[0098] Finally, the welding control system synchronizes the adjusted welding current, welding voltage and welding gun position into the welding process, ensuring that the welding gun welds along the optimized path and parameters in subsequent welding, thereby completing welding optimization and improving welding quality and stability. Position adjustment formula:

[0099]

[0100] in is the welding gun position after adjustment, P gun is the current position of the welding gun, ΔP gun is the corrected path deviation.

[0101] This embodiment provides a pipeline full-position submerged arc welding optimization method based on temperature field monitoring and weld tracking. First, the welding control system acquires three-dimensional point cloud data, generates a three-dimensional pipeline model, and then extracts the width, depth, and curvature information of the target weld area. This process provides accurate geometric data for welding gun path planning, ensuring that the welding gun can accurately align with the weld and reduce welding deviation. Next, the welding control system plans the welding gun path based on the extracted weld geometry information and controls the welding gun movement along this path. Through accurate path planning, the welding gun can dynamically adjust according to the actual shape and size of the weld, ensuring uniformity and consistency of the welding process. During the movement of the welding gun, the temperature field of the target weld area is monitored in real time. Based on the temperature field data, the target welding current, target welding voltage, and offset of the welding gun position are calculated. By monitoring the temperature field in real time, the system can promptly detect uneven heat input and dynamically adjust welding parameters and welding gun position accordingly to ensure stability of the welding process and uniformity of heat input. Finally, the welding control system adjusts the welding current, welding voltage, and welding gun position based on the calculated target welding current, target welding voltage, and offset, completing the welding optimization. By accurately tracking the weld position and real-time monitoring of temperature field changes, the welding quality and heat input uniformity of pipeline submerged arc welding in all positions are improved, ensuring the stability and efficiency of the welding process.

[0102] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above embodiment 1 can be referred to the above introduction and will not be described in detail later. Figure 3 , Figure 3 This is a flow chart of a second embodiment of a pipeline all-position submerged arc welding optimization method based on temperature field monitoring and weld tracking of this application. Step S10 of the pipeline all-position submerged arc welding optimization method based on temperature field monitoring and weld tracking includes steps S11 to S14:

[0103] Step S11: Scan the pipeline weld area at multiple angles to obtain three-dimensional point cloud data.

[0104] It should be noted that 3D point cloud data refers to a set of points with three-dimensional spatial coordinates obtained by scanning the pipeline weld area from multiple angles using a line laser profiler. Each point represents a specific location on the weld surface and includes the X, Y, and Z coordinates of that location, as well as possible reflection intensity or other properties.

[0105] As you can see, first, the welding control system controls the circular track drive, causing the line laser profiler to perform multi-angle rotational scanning around the pipe weld area, ensuring comprehensive coverage of the weld area. Second, the sensor collects point cloud data of the weld surface at each preset angle. This data reflects the three-dimensional geometric characteristics of the weld area. Finally, the welding control system integrates and processes this multi-angle point cloud data to generate a complete three-dimensional point cloud model, providing accurate data support for subsequent weld inspection and welding path planning.

[0106] Step S12: performing denoising and registration processing on the three-dimensional point cloud data to obtain a three-dimensional pipeline model.

[0107] It should be noted that registration processing refers to the process of aligning three-dimensional point cloud data obtained from different angles or positions to the same coordinate system. Since the point cloud data obtained from each scan when the line laser profile sensor scans the pipeline weld area at multiple angles may have position and direction deviations, these scattered point cloud data need to be aligned through registration processing to form a complete and accurate three-dimensional model.

[0108] As an example, the step of denoising and aligning the three-dimensional point cloud data to obtain a three-dimensional pipeline model includes: performing neighborhood distance calculation on each point in the three-dimensional point cloud data to obtain a distance distribution between each point and the neighboring points; based on the mean and standard deviation of the distance distribution, eliminating outliers that exceed a preset noise threshold to obtain denoised point cloud data; using the denoised point cloud data scanned from a first angle as a reference point cloud, and the other denoised point cloud data as an initial point cloud; matching each point in the initial point cloud with the nearest point between the reference point cloud to obtain a matching point pair; calculating a rotation matrix and a translation vector by the least squares method based on the matching point pair; transforming the initial point cloud according to the rotation matrix and the translation vector, and returning to the step of matching each point in the initial point cloud with the nearest point between the reference point cloud to obtain a matching point pair, until the alignment error between the initial point cloud and the reference point cloud is less than a preset convergence threshold or the number of iterations reaches a preset iteration threshold, to obtain a target point cloud; merging the target point cloud with the reference point cloud to obtain a three-dimensional pipeline model.

[0109] Neighborhood points are points that are spatially close to a specific point in 3D point cloud data. In denoising, by calculating the distance between a point and its neighboring points, we can analyze whether the point is an outlier.

[0110] Distance distribution refers to the statistical properties of the distance between a point and its neighboring points, including the mean and standard deviation of the distance. By calculating these statistics, we can identify points whose distances from surrounding points significantly deviate from the normal range.

[0111] The preset noise threshold is a set value used to determine whether a point is a noise point. If the distance between a point and its neighboring points exceeds this threshold, the point will be identified as a noise point and removed.

[0112] Outliers are points in point cloud data whose distance from surrounding points significantly deviates from the normal range. These points may be caused by scanning errors, reflection interference, or other abnormal conditions.

[0113] Denoised point cloud data refers to point cloud data that has been processed to remove outliers. This data is cleaner and can more accurately reflect the true geometric characteristics of the weld area.

[0114] The first angle refers to the angular position at which the line laser profiler first captures data during the scanning process. The point cloud data scanned from this angle is used as the reference point cloud.

[0115] The reference point cloud refers to the denoised point cloud data obtained from the first angle scan. It remains unchanged during the point cloud registration process and serves as the benchmark for aligning other point cloud data.

[0116] The initial point cloud refers to the denoised point cloud data obtained by scanning from other angles. These point cloud data need to be aligned with the reference point cloud.

[0117] Matching point pairs are the closest point pairs found in the initial point cloud to those in the reference point cloud. By calculating the distance between these point pairs, the optimal alignment between the initial point cloud and the reference point cloud can be determined.

[0118] A rotation matrix is a mathematical tool used to describe the rotation relationship between the initial point cloud and the reference point cloud. The rotation matrix is calculated using the least squares method and can be used to rotate the initial point cloud to align with the reference point cloud.

[0119] The translation vector is a mathematical tool used to describe the translation relationship of the initial point cloud relative to the reference point cloud. The translation vector is calculated using the least squares method and can be used to translate the initial point cloud to a position aligned with the reference point cloud.

[0120] The alignment error is the difference in distance between the initial point cloud and the reference point cloud during the point cloud registration process. Through iterative optimization, the alignment error is gradually reduced until the preset convergence condition is met.

[0121] The preset convergence threshold is a set value used to determine whether the point cloud registration process is accurate enough. When the alignment error is less than this threshold, the registration process can be stopped.

[0122] The preset iteration threshold is a set value that limits the maximum number of iterations in the point cloud registration process. If the convergence condition is not met after reaching this number of iterations, the registration process will stop.

[0123] The target point cloud refers to the point cloud data that is aligned with the reference point cloud after multiple iterative registrations.

[0124] First, the welding control system calculates the distance between each point in the point cloud data and its surrounding neighborhood points one by one. The calculation formula is as follows:

[0125]

[0126] Among them, P i and P j is a neighborhood point, d(P i ,P j ) is the distance between two points.

[0127] By counting these distance values, we can get the distance distribution of each point, including the mean μ and standard deviation σ of the distance, so as to identify which points have significantly deviated from the normal range from the surrounding points. These points may be noise points. The calculation formula is as follows:

[0128]

[0129] Where n is the number of points in the neighborhood, μ is the mean distance, and σ is the standard deviation of the distance.

[0130] Secondly, the system removes outliers whose distance from the mean exceeds the threshold according to the preset noise threshold α (d(P i ,P j )>μ+α·σ), and obtain the denoised point cloud data. This process effectively reduces the impact of scanning errors and environmental interference on the data, providing a more accurate point cloud foundation for subsequent processing. Next, the system uses the denoised point cloud data obtained from the first angle scan as the reference point cloud, and the denoised point cloud data obtained from other angles scanned as the initial point cloud, providing a benchmark and a data set to be aligned for point cloud registration. Then, for each point in the initial point cloud, the system calculates its Euclidean distance to all points in the reference point cloud, finds the nearest matching point, and forms a matching point pair. This process ensures that each point in the initial point cloud can find the closest corresponding point in the reference point cloud.

[0131] Subsequently, based on these matching point pairs, the optimal rotation matrix and translation vector are calculated by the least squares method. These two matrices describe the precise spatial transformation relationship of the initial point cloud relative to the reference point cloud, providing a mathematical basis for point cloud alignment. The calculation formula is as follows:

[0132]

[0133] in, and are the i-th matching point of the target point cloud and the reference point cloud respectively, R is the rotation matrix, and T is the translation vector.

[0134] Next, the system uses the calculated rotation matrix and translation vector to transform the initial point cloud, that is, to adjust each point in the initial point cloud to a position aligned with the reference point cloud according to the rotation and translation relationship. This transformation process is achieved through matrix operations to ensure the precise alignment of the point cloud data in space. Then, the system again matches each point in the transformed initial point cloud with the reference point cloud at the closest point, and calculates the new alignment error, that is, the distance difference between the reference point cloud and the transformed initial point cloud. This process is used to evaluate the alignment effect of the current transformation. Finally, the system determines whether the alignment error is less than the preset convergence threshold, or whether the number of iterations reaches the preset iteration threshold. If the conditions are met, the final aligned initial point cloud is merged with the reference point cloud to form a complete three-dimensional pipeline model, completing the point cloud data registration and model construction; if the conditions are not met, it returns to the nearest point matching step and continues iterative optimization until the conditions are met.

[0135] Step S13: segmenting the target weld region from the three-dimensional pipeline model based on a region growing algorithm.

[0136] It should be noted that the region growing algorithm is a segmentation method based on the geometric features of point clouds, which is used to extract specific regions from three-dimensional pipeline models. It starts with one or more seed points and gradually aggregates neighborhood points with similar features (such as normal direction, curvature, etc.) to the seed points into the same region. The algorithm determines whether the neighborhood points belong to the target region by setting similarity criteria (such as the angle threshold of the normal direction, curvature similarity, etc.), and continues to expand until the stopping condition is met (such as reaching the set neighborhood radius or the number of points in the area reaches the upper limit). This method can effectively identify and separate regions with similar geometric features and is suitable for weld segmentation with complex shapes.

[0137] As an example, the step of segmenting the target weld area from the three-dimensional pipeline model based on the region growing algorithm includes: selecting at least one seed point on the weld surface of the three-dimensional pipeline model and calculating the normal direction of the seed point; searching for the neighborhood points of the seed point, and calculating the normal angle and curvature difference between the neighborhood point and the seed point according to the normal direction; when the normal angle is less than a preset angle threshold and the curvature difference is less than a preset curvature threshold, adding the neighborhood point to the initial weld area; returning to the step of searching for the neighborhood points of the seed point, and calculating the normal angle and curvature difference between the neighborhood point and the seed point according to the normal direction, until the radius of the initial weld area is greater than the preset expansion threshold or the number of points in the initial weld area reaches a preset point number threshold, thereby obtaining the target weld area.

[0138] The weld surface refers to the actual physical surface of the weld in a 3D pipeline model, specifically the area where welding operations are performed. It represents the weld's geometric characteristics, including its shape, width, and depth. It serves as the starting point and foundation for weld segmentation using the region growing algorithm.

[0139] Seed points are one or more starting points selected on the weld surface to initiate the region growing algorithm. These points are typically located at the center of the weld and have representative geometric features, such as normal direction and curvature. The choice of seed points directly affects the starting direction and range of region growing.

[0140] The normal direction of a seed point is the direction perpendicular to the weld surface in three-dimensional space. It is calculated by calculating the geometric characteristics of points in the seed point's neighborhood and reflects the local orientation of the weld surface at that point. The normal direction is one of the key criteria used in the region growing algorithm to determine whether a neighboring point belongs to the weld region.

[0141] The normal angle refers to the angle between the normal direction of the neighboring point and the normal direction of the seed point. By calculating this angle, the similarity of the geometric features of the neighboring point and the seed point can be judged. If the angle is small, it means that the normal directions of the neighboring point and the seed point are close, and they are more likely to belong to the same weld area.

[0142] Curvature difference refers to the difference between the curvature of a neighboring point and the curvature of the seed point. Curvature reflects the degree of curvature of the weld surface at a given point. By calculating the curvature difference, we can determine the similarity of the curvature characteristics of the neighboring point and the seed point. If the curvature difference is small, it means that the neighboring point and the seed point have similar curvature and are more likely to belong to the same weld area.

[0143] Preset angle threshold θ thresholdThis is a set value used to determine whether the angle between the normal direction of the neighboring point and the normal direction of the seed point is small enough. If the normal angle is less than this threshold, the neighboring point is considered to be geometrically similar to the seed point and can be added to the weld area.

[0144] The preset curvature threshold is a set value used to determine whether the difference between the curvature of the neighboring point and the curvature of the seed point is small enough. If the curvature difference is less than this threshold, the neighboring point is considered to have similar curvature characteristics to the seed point and can be included in the weld area.

[0145] The initial weld region refers to the initial part of the weld region that is gradually expanded from the seed point through the region growing algorithm. It includes the seed point and the neighborhood points that meet the similarity criterion.

[0146] The preset expansion threshold is a set value used to limit the expansion range of the initial weld area. It is usually expressed in the form of a radius. When the radius of the initial weld area is greater than this threshold, the region growing algorithm will stop expanding.

[0147] The number of points refers to the number of points included in the initial weld area or the target weld area.

[0148] The preset point threshold is a set value that limits the maximum number of points included in the initial weld area. It is used to control the size of the weld area and prevent overgrowth.

[0149] First, the welding control system selects at least one seed point on the weld surface of the 3D pipeline model and determines the normal direction of the seed point by calculating the geometric features of the points in the seed point neighborhood, providing a directional reference for subsequent regional growth. Secondly, the system searches for neighboring points within a preset radius with the seed point as the center, and calculates the normal angle and curvature difference between these neighboring points and the seed point, and compares whether the normal angle is less than the preset angle threshold θ. threshold , whether the curvature difference is less than the preset curvature threshold, and whether the neighborhood points have similar geometric features to the seed points. If the conditions are met, these neighborhood points are added to the initial weld area and the weld area range is gradually expanded. The normal angle calculation formula is:

[0150]

[0151] Among them, N i and N j is the normal vector of the seed point and the neighboring point in the point cloud, θ is the angle between them, if θ≤θ threshold , then the neighborhood points are considered to belong to the weld area.

[0152] Finally, the system repeats the steps of searching for neighborhood points and calculating feature differences, and continuously incorporates qualified neighborhood points into the initial weld area until the radius of the initial weld area exceeds the preset expansion threshold r threshold , or when the number of points in the area reaches the preset point threshold (such as 5000 points), the area growth stops and the target weld area is finally obtained, thereby accurately segmenting the weld area and providing accurate positioning and range for subsequent welding operations. Condition judgment formula:

[0153]

[0154] Among them, d(P i ,P seed ) is the distance between each point and the seed point, N max is the maximum number of points set.

[0155] Step S14: extracting the width, depth and curvature information of the target weld area.

[0156] As an example, the step of extracting the width, depth and curvature information of the target weld area includes: fitting the edge points on both sides of the target weld area by the least squares method; taking the maximum width of the edge points on both sides as the width of the target weld area; calculating the depth based on the normal distance between the point cloud of the target weld area and the inner wall of the three-dimensional pipeline model; and extracting the curvature information of the surface of the target weld area by the principal component analysis method.

[0157] The two side edge points refer to the points on the two boundaries of the target weld area in the width direction. These points are obtained by least squares fitting and are used to define the two side boundaries of the weld.

[0158] The maximum width refers to the maximum distance between the edge points on both sides of the target weld area. The width of the weld can be obtained by calculating the distance between the edge points on both sides and taking the maximum value.

[0159] The normal distance to the inner wall of a 3D pipe model is the vertical distance from a point in the target weld area to the inner wall of the 3D pipe model. This distance is determined by calculating the distance in the normal direction between the point and the inner wall. The normal direction is the direction from the weld surface to the inner wall of the pipe, perpendicular to the weld surface.

[0160] First, the welding control system processes the point cloud data of the target weld area and fits the edge points on both sides of the weld using the least squares method. Specifically, the system substitutes the coordinate data of the edge points into the mathematical model of the least squares method and obtains two best-fit straight lines by solving the optimization problem of minimizing the sum of squared errors. These two straight lines represent the boundaries of the weld on both sides. Then, the system calculates the distance between each point on the two fitted straight lines and selects the maximum value as the width of the target weld area. This width value is used for subsequent welding gun path planning and welding parameter adjustment to ensure that the welding gun can be accurately aligned with the center of the weld. The width calculation formula is as follows:

[0161] W=max(d(P left ,P right ))

[0162] Among them, P left and P right are the left and right edge points of the weld area, d(P left ,P right ) is the Euclidean distance between the two points, and W is the width of the target weld area.

[0163] Next, the system calculates the normal distance from each point in the point cloud data of the target weld area to the inner wall of the three-dimensional pipe model. Specifically, for each point, calculate the vector between it and the reference point of the inner wall of the pipe, and find the projection length of the vector in the normal direction of the inner wall of the pipe. The maximum value of these projection lengths is the depth of the weld, and the depth information is used to optimize the settings of welding current and voltage to meet different weld depth requirements. The depth is mainly affected by the groove shape of the pipe (such as a deep V-shaped groove). The V-shaped groove of the area to be welded is fitted by point cloud, and its groove angle α is calculated. If the groove of the welded pipe is a standard deep V-shaped groove, the angle α can be determined by fitting the points on the inner and outer surfaces of the pipe. Groove angle calculation formula:

[0164] α=atan2(y2-y1,x2-x1)

[0165] Among them, (x1, y1) and (x2, y2) are the points on both sides of the weld groove, and α is the groove angle.

[0166] Depth calculation formula:

[0167]

[0168] Among them, (x i ,y i ,z i ) is a point in the point cloud, (x w ,y w ,z w ) is the reference point of the inner wall of the pipe, N iIt's point P i The normal vector, D i is the depth of the point.

[0169] Finally, the curvature information of the target weld area surface is extracted by principal component analysis. The system first calculates the covariance matrix of the neighborhood points of each point, and then solves the eigenvalue and eigenvector of the matrix. The size of the eigenvalue reflects the distribution of the neighborhood points in different directions, while the eigenvector indicates the direction of the principal component. i =(x i ,y i ,z i ), calculate the normal direction of the point by PCA method:

[0170] N i =(N x ,N y ,N z )

[0171] N i =PCA(P neighborhood (i))

[0172] Among them, P neighborhood (i) represents point P i The PCA method is used to calculate the normal vector N i .

[0173] By analyzing these eigenvalues and eigenvectors, the system can calculate the Gaussian curvature and average curvature of each point. This curvature information is used to optimize the posture adjustment of the welding gun, ensuring that the welding gun maintains the best contact angle with the weld surface during welding, thereby improving welding quality and stability. Gaussian curvature calculation formula:

[0174] Mean curvature calculation formula:

[0175] Among them, L, M, and N are the parameters of the second-order derivative matrix, and E, F, and G are the coefficients of the first fundamental form, which represent the degree of curvature of the surface in different directions.

[0176] This embodiment first uses a line laser profiler to perform multi-angle scanning of the pipeline weld area to obtain three-dimensional point cloud data of the weld area. This process can fully cover the weld area and ensure the integrity and accuracy of the data. Next, the acquired three-dimensional point cloud data is denoised and registered to remove outliers and integrate multi-angle data to generate a complete three-dimensional pipeline model. The denoising process improves data quality, while the registration process ensures the accuracy of the model. Then, based on the region growing algorithm, the target weld area is segmented from the three-dimensional pipeline model. By selecting seed points and gradually expanding them, the weld area is accurately identified, providing clear positioning for subsequent welding operations. Finally, the width, depth, and curvature information of the target weld area are extracted. The extraction of these geometric features provides key data support for the optimization of welding parameters and the planning of welding gun paths, thereby improving welding quality and efficiency.

[0177] This application also provides a pipeline full-position submerged arc welding optimization device based on temperature field monitoring and weld tracking, please refer to Figure 4 The pipeline full-position submerged arc welding optimization device based on temperature field monitoring and weld tracking includes:

[0178] The model acquisition module 10 is used to acquire a three-dimensional pipeline model and extract the width, depth and curvature information of the target weld area in the three-dimensional pipeline model;

[0179] a path planning module 20, configured to plan a welding gun path according to the width, the depth, and the curvature information, and control the welding gun to move along the welding gun path;

[0180] a temperature monitoring module 30 for monitoring the temperature field of the target weld area while the welding gun is moving, and calculating a target welding current, a target welding voltage, and an offset of the welding gun position based on the temperature field;

[0181] The dynamic adjustment module 40 is used to adjust the welding current, the welding voltage and the position of the welding gun based on the target welding current, the target welding voltage and the offset to achieve welding optimization.

[0182] The present application provides a device for optimizing pipeline submerged arc welding in all positions based on temperature field monitoring and weld tracking. This device employs the method for optimizing pipeline submerged arc welding in all positions based on temperature field monitoring and weld tracking described in the aforementioned embodiments. This device can address the technical problem of improving the welding quality and heat input uniformity of pipeline submerged arc welding in all positions by accurately tracking weld positions and monitoring temperature field changes in real time. Compared to the prior art, the present application provides the same beneficial effects as the method for optimizing pipeline submerged arc welding in all positions based on temperature field monitoring and weld tracking described in the aforementioned embodiments. Furthermore, the other technical features of the device for optimizing pipeline submerged arc welding in all positions based on temperature field monitoring and weld tracking are the same as those disclosed in the aforementioned embodiments and are not further elaborated upon here.

[0183] The present application provides a pipeline all-position submerged arc welding optimization device based on temperature field monitoring and weld tracking. The pipeline all-position submerged arc welding optimization device based on temperature field monitoring and weld tracking includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the pipeline all-position submerged arc welding optimization method based on temperature field monitoring and weld tracking in the above-mentioned embodiment 1.

[0184] Reference below Figure 5 , which shows a schematic structural diagram of a pipeline all-position submerged arc welding optimization device based on temperature field monitoring and weld tracking suitable for implementing an embodiment of the present application. The pipeline all-position submerged arc welding optimization device based on temperature field monitoring and weld tracking in the embodiment of the present application may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (e.g., vehicle-mounted navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 5 The pipeline all-position submerged arc welding optimization equipment based on temperature field monitoring and weld tracking shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0185] like Figure 5As shown, the pipeline full-position submerged arc welding optimization device based on temperature field monitoring and weld tracking may include a processing device 1001 (such as a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to the program stored in ROM (Read Only Memory, read-only memory) 1002 or the program loaded from the storage device 1003 into RAM (Random Access Memory, random access memory) 1004. In RAM1004, various programs and data required for the operation of the pipeline full-position submerged arc welding optimization device based on temperature field monitoring and weld tracking are also stored. The processing device 1001, ROM1002 and RAM1004 are connected to each other via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; an output device 1008 including, for example, an LCD (Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the pipeline full-position submerged arc welding optimization device based on temperature field monitoring and weld tracking to communicate wirelessly or wired with other devices to exchange data. Although the figure shows the pipeline full-position submerged arc welding optimization device based on temperature field monitoring and weld tracking with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be implemented or have instead.

[0186] In particular, according to the embodiments disclosed in the present application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, the embodiments disclosed in the present application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program comprising program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0187] The pipeline full-position submerged arc welding optimization device based on temperature field monitoring and weld tracking provided in this application, which utilizes the pipeline full-position submerged arc welding optimization method based on temperature field monitoring and weld tracking described in the above-mentioned embodiment, can solve the technical problem of how to improve the welding quality and heat input uniformity of pipeline full-position submerged arc welding by accurately tracking weld positions and real-time monitoring of temperature field changes. Compared with the prior art, the beneficial effects of the pipeline full-position submerged arc welding optimization device based on temperature field monitoring and weld tracking provided in this application are the same as the beneficial effects of the pipeline full-position submerged arc welding optimization method based on temperature field monitoring and weld tracking provided in the above-mentioned embodiment. The other technical features of the pipeline full-position submerged arc welding optimization device based on temperature field monitoring and weld tracking are the same as those disclosed in the method of the above-mentioned embodiment and are not further described here.

[0188] The present application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, and the computer-readable program instructions are used to execute the pipeline full-position submerged arc welding optimization method based on temperature field monitoring and weld tracking in the above-mentioned embodiment.

[0189] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, RAM (Random Access Memory), ROM (Read Only Memory), EPROM (Erasable Programmable Read Only Memory or Flash memory), optical fiber, CD-ROM (CD-Read Only Memory, portable compact disk read-only memory), optical storage device, magnetic storage device, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0190] The above-mentioned computer-readable storage medium can be included in the pipeline full-position submerged arc welding optimization equipment based on temperature field monitoring and weld tracking; or it can exist independently and not be assembled into the pipeline full-position submerged arc welding optimization equipment based on temperature field monitoring and weld tracking.

[0191] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by the pipeline all-position submerged arc welding optimization device based on temperature field monitoring and weld tracking, the pipeline all-position submerged arc welding optimization device based on temperature field monitoring and weld tracking: obtains a three-dimensional pipeline model and extracts the width, depth and curvature information of the target weld area in the three-dimensional pipeline model; plans a welding gun path according to the width, depth and curvature information, and controls the welding gun to move along the welding gun path; when the welding gun moves, monitors the temperature field of the target weld area, and calculates the target welding current, target welding voltage and offset of the welding gun position according to the temperature field; adjusts the welding current, welding voltage and position of the welding gun based on the target welding current, the target welding voltage and the offset to complete welding optimization.

[0192] The computer program code for performing the operations of the present application can be written in one or more programming languages or a combination thereof, including object-oriented programming languages such as Java, Smalltalk, C++, and conventional procedural programming languages such as "C" or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer can be connected to the user's computer through any type of network, including a LAN (Local Area Network) or a WAN (Wide Area Network), or can be connected to an external computer (e.g., using an Internet service provider to connect via the Internet).

[0193] The flow charts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a module, program segment or a part of code, and the module, program segment or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented by a dedicated hardware-based system that performs the specified function or operation, or can be implemented by a combination of dedicated hardware and computer instructions.

[0194] The computer-readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the aforementioned method for optimizing all-position submerged arc welding of pipelines based on temperature field monitoring and weld tracking. This method solves the technical problem of improving the welding quality and heat input uniformity of all-position submerged arc welding of pipelines by accurately tracking weld positions and monitoring temperature field changes in real time. Compared to the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the method for optimizing all-position submerged arc welding of pipelines based on temperature field monitoring and weld tracking provided in the aforementioned embodiments, and are not further elaborated here.

[0195] The present application also provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of the above-mentioned pipeline full-position submerged arc welding optimization method based on temperature field monitoring and weld tracking.

[0196] The computer program product provided in this application solves the technical problem of improving the welding quality and heat input uniformity of all-position submerged arc welding of pipelines by accurately tracking weld seam locations and monitoring temperature field changes in real time. Compared to the prior art, the computer program product provided in this application offers the same beneficial effects as the method for optimizing all-position submerged arc welding of pipelines based on temperature field monitoring and weld seam tracking provided in the aforementioned embodiments, and will not be further elaborated here.

[0197] The above description is only part of the embodiments of the present application and does not limit the patent scope of the present application. All equivalent structural transformations made by using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect application in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A pipeline full-position submerged arc welding optimization method based on temperature field monitoring and weld tracking, characterized in that: The method comprises: Acquire a three-dimensional pipeline model, and extract width, depth, and curvature information of a target weld area in the three-dimensional pipeline model; planning a welding gun path according to the width, the depth, and the curvature information, and controlling the welding gun to move along the welding gun path; When the welding gun is moving, monitoring the temperature field of the target weld area, and calculating the target welding current, target welding voltage and the offset of the welding gun position according to the temperature field; The welding current, the welding voltage and the position of the welding gun are adjusted based on the target welding current, the target welding voltage and the offset to complete welding optimization.

2. The method according to claim 1, wherein The step of obtaining a three-dimensional pipeline model and extracting width, depth, and curvature information of a target weld area in the three-dimensional pipeline model includes: Scan the pipeline weld area at multiple angles to obtain three-dimensional point cloud data; Performing denoising and registration processing on the three-dimensional point cloud data to obtain a three-dimensional pipeline model; Segmenting a target weld region from the three-dimensional pipeline model based on a region growing algorithm; The width, depth and curvature information of the target weld area are extracted.

3. The method according to claim 2, wherein The step of segmenting the target weld region from the three-dimensional pipeline model based on the region growing algorithm includes: Selecting at least one seed point on the weld surface of the three-dimensional pipeline model and calculating the normal direction of the seed point; Searching for a neighboring point of the seed point, and calculating a normal angle and a curvature difference between the neighboring point and the seed point according to the normal direction; When the normal angle is less than a preset angle threshold and the curvature difference is less than a preset curvature threshold, adding the neighborhood point to the initial weld area; Return to the step of searching for the neighborhood points of the seed point, and calculating the normal angle and curvature difference between the neighborhood points and the seed point according to the normal direction, until the radius of the initial weld area is greater than a preset expansion threshold or the number of points in the initial weld area reaches a preset point number threshold, to obtain a target weld area.

4. The method according to claim 2, wherein The step of extracting the width, depth and curvature information of the target weld area includes: Fitting the edge points on both sides of the target weld area by the least square method; The maximum width of the edge points on both sides is used as the width of the target weld area; Calculating the depth based on the normal distance between the point cloud of the target weld area and the inner wall of the three-dimensional pipeline model; The curvature information of the target weld area surface is extracted by principal component analysis.

5. The method according to claim 2, wherein The step of performing denoising and registration processing on the three-dimensional point cloud data to obtain a three-dimensional pipeline model comprises: Performing neighborhood distance calculation on each point in the three-dimensional point cloud data to obtain a distance distribution between each point and its neighboring points; Based on the mean and standard deviation of the distance distribution, outliers exceeding a preset noise threshold are removed to obtain denoised point cloud data; The denoised point cloud data scanned from the first angle is used as a reference point cloud, and the other denoised point cloud data is used as an initial point cloud; Matching each point in the initial point cloud with the closest point between the reference point cloud to obtain a matching point pair; Calculating a rotation matrix and a translation vector by a least squares method according to the matching point pairs; transforming the initial point cloud according to the rotation matrix and the translation vector, and returning to the step of matching each point in the initial point cloud with the nearest point between the reference point cloud to obtain a matching point pair, until the alignment error between the initial point cloud and the reference point cloud is less than a preset convergence threshold or the number of iterations reaches a preset iteration threshold, thereby obtaining a target point cloud; The target point cloud and the reference point cloud are merged to obtain a three-dimensional pipeline model.

6. The method according to claim 1, wherein The step of planning a welding gun path according to the width, the depth and the curvature information and controlling the welding gun to move along the welding gun path includes: Calculating an initial motion trajectory of the welding gun along a centerline of the weld based on the width and the curvature information; The initial motion trajectory is smoothed using a B-spline curve algorithm and a Bezier algorithm to obtain a target welding gun path; Calculating a target tilt angle of the welding gun according to the curvature information, the normal direction of the welding gun, and the normal direction of the weld centerline; According to the target welding gun path and the target tilt angle, motion parameters of each joint of the welding gun are calculated by an inverse kinematics algorithm, and welding gun control instructions are generated according to the motion parameters; The welding gun control instruction is sent to a welding gun driving device, so that the welding gun driving device controls the welding gun to maintain the target tilt angle and move along the target welding gun path.

7. The method according to any one of claims 1 to 6, characterized in that The step of monitoring the temperature field of the target weld area and calculating the target welding current, target welding voltage and the offset of the welding gun position according to the temperature field when the welding gun is moving includes: When the welding gun moves, monitoring the temperature field of the target weld area, wherein the temperature field is obtained by continuously scanning the target weld area with an infrared thermal imaging camera; Extracting a left side temperature value and a right side temperature value of the welding gun from the temperature field, and calculating an absolute value of a temperature difference between the left side temperature value and the right side temperature value; Calculating a target welding current and a target welding voltage according to the absolute value of the temperature difference, a preset current adjustment coefficient, a preset voltage adjustment coefficient, an initial welding current, and an initial welding voltage; When the absolute value of the temperature difference exceeds a preset temperature difference threshold, determining the welding gun offset direction according to the magnitude relationship between the left temperature value and the right temperature value; Based on the welding gun offset direction and the absolute value of the temperature difference, the offset of the welding gun position is calculated using a preset path correction coefficient.

8. A pipeline full-position submerged arc welding optimization device based on temperature field monitoring and weld tracking, characterized in that: The device comprises: A model acquisition module is used to acquire a three-dimensional pipeline model and extract width, depth and curvature information of a target weld area in the three-dimensional pipeline model; a path planning module, configured to plan a welding gun path according to the width, the depth, and the curvature information, and control the welding gun to move along the welding gun path; a temperature monitoring module, configured to monitor the temperature field of the target weld area while the welding gun is moving, and calculate the target welding current, target welding voltage, and an offset of the welding gun position based on the temperature field; The dynamic adjustment module is used to adjust the welding current, welding voltage and the position of the welding gun based on the target welding current, the target welding voltage and the offset to achieve welding optimization.

9. A pipeline full-position submerged arc welding optimization device based on temperature field monitoring and weld tracking, characterized in that: The device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the pipeline all-position submerged arc welding optimization method based on temperature field monitoring and weld tracking as described in any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by the processor, the steps of the pipeline all-position submerged arc welding optimization method based on temperature field monitoring and weld tracking are implemented as described in any one of claims 1 to 7.

Images