A detection method, system, device and medium based on profile coordinates and specification postures of a laser cutting device

Abstract

The application provides a detection method, system, device and medium based on profile coordinate and specification posture of a laser cutting equipment, belongs to the technical field of laser cutting equipment, receives a drawing and user parameters, controls a 3D camera to collect web point cloud and processes to obtain web position and posture parameters, controls the 3D camera unit to move and rotate to four second groups of observation point positions and corresponding angles which are preset for collecting wing plate outer contour, shoots profile images, and obtains wing plate contour point cloud information; the wing plate contour point cloud information is processed to obtain profile wing plate position and specification posture parameters; the profile coordinate and specification posture are determined, and a profile three-dimensional model is constructed. Through phased point cloud collection and parameter extraction, the spatial position and specification posture of the web and the wing plate are positioned; multi-angle shooting and rotating positioning technology is used to improve the integrity of the point cloud data; finally, the profile actual form can be intuitively reflected by the three-dimensional model, and the production efficiency and cutting precision are improved.

Description

Technical Field

[0001] This invention belongs to the field of laser cutting equipment technology, specifically relating to a method, system, equipment, and medium for detecting profile coordinates and specifications on a laser cutting device. Background Technology

[0002] Laser cutting equipment is widely used in industries such as steel structures, rail transportation, construction machinery, shipbuilding, energy equipment, and building curtain walls. Among these, profile laser cutting equipment, due to its advantages of high efficiency, high flexibility, and low heat-affected zone, is applied to processes such as sawing, punching, and plasma cutting. To improve automation, it is often used in conjunction with 3D vision cameras. 3D vision-based online inspection technology is increasingly being introduced into laser cutting systems to acquire the spatial position and orientation of profiles in real time.

[0003] In related technologies, the problem of poor adaptability to the detection of profiles of different specifications is generally addressed by adjusting the camera position and detection parameters for profiles of different widths and heights. For example, the inner position of the flange of wide profiles differs greatly from that of narrow profiles. Fixed-point acquisition will lead to missed point cloud detections or excessive noise, making it unusable.

[0004] When laser cutting equipment is used in conjunction with a 3D camera, if point cloud data in the camera coordinate system is used directly to calculate profile parameters, systematic errors will be introduced due to inconsistent references, resulting in inaccurate calculation of key coordinates such as the web center and the edge of the flange.

[0005] Existing methods also detect the web or flange separately, ignoring the geometric constraints between the web center and the flange edge, resulting in a large deviation between the calculated profile rotation angle and the actual angle, and the 3D model cannot truly reflect the overall shape of the profile. Summary of the Invention

[0006] This invention provides a method for detecting the coordinates and specifications of profiles on a laser cutting machine. By using a 3D camera unit to detect the deviation of the profile placement position and angle, as well as the difference between the profile and the drawing, a three-dimensional model is established. The CNC system can adjust the cutting position according to the three-dimensional model to ensure the correct cutting position, thereby ensuring the safety of the processing.

[0007] The methods include: S101: Receive the drawing information of the profile to be cut and the interface parameters input by the user; S102: Based on the drawing information and interface parameters, control the 3D camera unit to move and rotate sequentially to the first set of observation points of six preset for collecting the inner contour of the web and wing plates, capture profile images, and obtain the web contour point cloud information of the profile. S103: Process the point cloud information of the web profile to obtain the web position and specification posture parameters of the profile. S104: Based on the web position and specification attitude parameters, control the 3D camera unit to move and rotate sequentially to four preset second set of observation points and corresponding angles for collecting the outer contour of the wing plate, capture profile images, and obtain wing plate contour point cloud information. S105: Process the point cloud information of the wing profile to obtain the position and specification attitude parameters of the profile wing; S106: Based on the web position and specification attitude parameters and the flange position and specification attitude parameters, determine the profile coordinates and specification attitude, and construct a three-dimensional model of the profile.

[0008] According to another embodiment of this application, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps of the detection method based on the profile coordinates and specification orientation on a laser cutting device.

[0009] According to another embodiment of this application, a storage medium is also provided, on which a computer program is stored, which, when executed by a processor, implements the steps of the detection method based on the profile coordinates and specification orientation on a laser cutting device.

[0010] As can be seen from the above technical solutions, the present invention has the following advantages: The present invention provides a method for detecting profile coordinates and specifications on a laser cutting device. This method uses a 3D camera unit to acquire point clouds from multiple points, combines this with a homogeneous transformation matrix to unify the coordinate system, filters edge noise and low-density noise, reduces position acquisition errors, and makes the calculation of the web center, flange edge, and rotation angle more accurate. Through segmented calculation of Yd, derivation of PA, and dynamic planning of flange points based on profile width Tw and height Th, the method adapts to profiles of different widths and heights, improving its versatility. The 3D model constructed by this invention contains 12 key point coordinates and three rotation angles, which can be directly used for dynamic adjustment of the laser cutting path, avoiding problems such as cutting misalignment and increased waste caused by profile placement deviations. Attached Figure Description

[0011] To more clearly illustrate the technical solution of the present invention, the accompanying drawings used in the description will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0012] Figure 1 This is a schematic diagram of a detection system based on the coordinates and specifications of profiles on a laser cutting machine. Figure 2This is a flowchart of a detection method based on the coordinates and specifications of profiles on a laser cutting machine. Figure 3 Example diagram of laser system coordinate system; Figure 4 Example diagram of 3D camera coordinate system; Figure 5 A schematic diagram showing the positions of the profile to be cut, the laser cutting equipment, and the 3D camera unit. Figure 6 This is a schematic diagram of a three-dimensional model of the profile; Figure 7 This is a schematic diagram of an electronic device. Detailed Implementation

[0013] Figure 1 This invention proposes a detection system based on the coordinates and specifications of profiles on a laser cutting device, wherein... Figure 1 The method includes a 3D camera unit 1 combined with a laser cutting device 2. The 3D camera unit is fixed to the laser cutting device and can be moved and rotated by the laser cutting system. The laser cutting system provides the drawing information of the profile to be cut to this method and controls the movement and rotation of the 3D camera unit to assist this method in acquiring image data. The 3D camera unit provides contour point cloud data for this method to identify the position and specification orientation of the profile. A support 3 is set at the bottom of the laser cutting device, and an I-beam 4 is mounted on the support 3.

[0014] The following describes in detail the detection method for profile coordinates and specification orientation on a laser cutting device, as per this application. Specific details, such as particular system structures and technologies, are presented for illustrative purposes and not for limitation, to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application can also be implemented in other embodiments without these specific details.

[0015] It should be understood that, when used in this specification, the term "comprising" indicates the presence of the described feature, integral, step, operation, element, and / or component, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components, and / or collections thereof. The terms "comprising," "including," "having," and variations thereof all mean "including but not limited to," unless otherwise specifically emphasized.

[0016] The terms "one embodiment" or "some embodiments" used in this application mean that one or more embodiments of this application include the specific features, structures, or characteristics described in that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this application do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized.

[0017] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0018] Please see Figure 2 The diagram shows a flowchart of a method for detecting profile coordinates and specifications on a laser cutting device, as described in a specific embodiment. The method includes: S101: Receive the drawing information of the profile to be cut and the interface parameters input by the user.

[0019] In some embodiments, the received drawing information includes profile width Tw, height Th, web thickness Tthick, and flange thickness Tlegthick; the interface parameters include estimated profile center coordinates (Cy, Cz), 3D camera movement distance Rd along the X-axis, distance from rotation center 5 to the cutting point (By, Bz), and camera calibration parameters (dx, dy, dz, rx, ry, rz). This information is input through the laser cutting system, the drawing information is stored in a local project file, and the interface parameters are transmitted through a configuration file.

[0020] Obtain the drawing information of the profile to be cut from the CNC system, including profile type, width Tw, height Th, web thickness Tthick, flange thickness Tlegthick, etc. For example... Figure 5 As shown, the profile type can be H-beams or I-beams.

[0021] Receive user-input interface parameters, including such as Figure 3 As shown, the estimated center coordinates of the profile (Cy, Cz) can be the coordinates in the machine coordinate system of the CNC system, such as... Figure 4The diagram shows the 3D camera coordinate system. During the measurement process, the distance Rd that the 3D camera unit moves along the X-axis is used for angle detection. Users can adjust this according to their needs. The diagram also shows the distance (By, Bz) from the rotation center 5 to the cutting point. The rotation center 5 is the center of the camera rotation, and By / Bz are its horizontal and vertical distances to the cutting point.

[0022] Specifically, S101 includes the following steps: S1011: Receive drawing information of the profile to be cut from the CNC system. The drawing information includes at least the profile width, profile height, profile web thickness, and profile flange thickness.

[0023] S1012: Receive interface parameters input by the user through the user interface. The interface parameters include at least the profile center coordinates estimated according to the drawing, the movement distance of the 3D camera unit along the X-axis set for measuring placement deviation, and the distance from the rotation center to the laser cutting point.

[0024] S1013: Call the pre-calibrated 3D camera unit parameters. The calibration parameters include at least the distance offset between the 3D camera unit and the laser cutting point in the X, Y, and Z directions, and the rotation angle offset of the camera coordinate system relative to the device coordinate system in the X, Y, and Z directions.

[0025] S1014: Based on the profile width in the profile drawing information, calculate the distance the 3D camera unit moves in the Y direction during image acquisition.

[0026] S1015: Temporarily store the drawing information, user-input interface parameters, calibration parameters, and calculated Y-direction movement distance.

[0027] In this embodiment, the drawing information provides the theoretical dimensional benchmark of the profile, and the interface parameters provide the initial position, motion parameters and equipment calibration data required for detection. Together, they serve as the basic input for subsequent camera positioning and point cloud processing, ensuring that the detection process matches the profile characteristics and equipment status.

[0028] S102: Based on the drawing information and interface parameters, control the 3D camera unit to move and rotate sequentially to the first set of six preset observation points for collecting the inner contour of the web and wing plates, capture profile images, and obtain the web contour point cloud information of the profile.

[0029] S102 specifically includes the following steps: S1021: Obtain the current X-axis mechanical coordinate CX of the 3D camera unit at the start of the inspection from the CNC system.

[0030] In some embodiments, at the start of the inspection, communication is established with the CNC system to query and record the absolute mechanical coordinates of the 3D camera unit on the X-axis. This establishes an absolute reference point for the entire inspection path in the X direction. This provides a precise starting reference point for all movements, ensuring consistency between the inspection path and the CNC system's mechanical coordinate system.

[0031] S1022: Based on the profile width Tw in the profile drawing information, calculate the moving distance Yd of the 3D camera unit in the Y-axis direction during image acquisition using the following formula (1).

[0032] In some embodiments, the distance moved in the Y direction during image acquisition is: Formula (1) It should be noted that S1014, based on the profile width in the profile drawing information, can calculate the movement distance of the 3D camera unit in the Y direction during image acquisition using formula (1). Furthermore, based on the physical width Tw of the profile, formula (1) dynamically determines the compensation distance the camera needs to move along the Y axis. This allows the detection system to automatically adapt to profiles of different specifications. For wide profiles, increasing the Y-axis movement ensures the camera can clearly observe the inner side of the flange; for narrow profiles, movement is reduced or eliminated to optimize detection efficiency.

[0033] S1023: Based on the profile drawing information, the calculated moving distance Yd, the interface parameters input by the user, and the distance from the rotation center to the cutting point, calculate the first specified rotation angle PA required to make the cutting point face the inner center of the wing plate according to formula (2). The rotation angle PA is: Formula (2) in, The distance traveled along the Y-axis during detection is the horizontal distance from the center of rotation to the inner side of the airfoil. Th is the profile height, Bz is the vertical distance from the cutting point to the rotation center, and the vertical distance from the rotation center to the inner center of the flange is... According to trigonometric functions, PA is the angle between the center of rotation, the inner center of the airfoil, and the Z-axis.

[0034] In some embodiments, using Yd calculated from the profile dimensions and the system mechanical parameters Bz, the theoretical rotation angle PA required for the camera laser plane to be perpendicularly aligned with the inner center surface of the wing plate is pre-calculated using formula (2). This ensures that in the collected point cloud data, the inner side of the wing plate is in the most easily processed and calculated position relative to the camera coordinate system, simplifying the subsequent data processing logic and improving the detection accuracy and noise resistance of feature edges.

[0035] S1024: Based on CX, the estimated profile center coordinates (CY, CZ) input by the user, the profile height Th in the profile drawing information, the calculated Yd and rotation angle PA, and the user-input distance of movement along the X-axis Rd, plan the spatial coordinates and rotation angle sequence of six first designated points for collecting web profile point cloud information.

[0036] In some embodiments, all coordinates (CX, CY, CZ), distances Yd, Rd, angles PA, and drawing parameters Th obtained in the preceding steps are combined and then combined with the image 1-6 point table to generate a complete sequence containing the spatial coordinates and rotation angles of the six points.

[0037] S1025: Control the 3D camera unit to move and rotate sequentially to each first designated point and angle according to the planned point sequence, trigger the 3D camera to take pictures of the profile at each point, and directly acquire and output the point cloud information of the profile web profile at that point.

[0038] In some embodiments, the CNC system drives the 3D camera unit to move and rotate point by point according to the path sequence generated in S1024. After each point is stable, the 3D line laser contour camera is triggered to take a single shot. The camera's internal processor directly converts the captured laser line image into three-dimensional contour point cloud data and outputs it, ensuring the consistency and repeatability of data acquisition. Using the 3D line laser contour camera to directly output the point cloud ensures the accuracy of the information.

[0039] As can be seen, after receiving the start command from the user, the laser cutting system transmits the command to this method, and then obtains the point cloud information of the profile web contour according to the following process: First, obtain the current X-axis mechanical coordinate CX of the 3D camera unit at the start of the detection from the CNC system. Next, based on the profile width Tw in the profile drawing information, calculate the moving distance Yd of the 3D camera unit in the Y-axis direction during image acquisition according to formula (1). Then, based on the profile drawing information, the calculated Yd, and the interface parameters input by the user (including the distance Bz from the rotation center to the cutting point, the flange thickness Tlegthick, etc.), calculate the first specified rotation angle PA required to make the cutting point face the inner center of the flange by combining geometric relationships. It is known that the Y and Z coordinates of the cutting head before rotation are CY+Yd and CZ+Th / 2+20, respectively, and the rotation angle is calculated by formula (2). Afterwards, based on CX, the estimated profile center coordinates (CY, CZ), the profile height Th, the calculated Yd and the rotation angle PA, and the moving distance Rd along the X-axis input by the user, plan the spatial coordinates and rotation angle sequence of the six first specified points for acquiring web profile point cloud information, which are the shooting points corresponding to images 1 to 6, as shown in Table 1 below: Table 1: Locations of images 1 to 6

[0040] Among them, Image 1 is used to identify the Z coordinate of the upper surface of the web; Images 2 and 6 are used to identify the distance from the inner side of the flange to the estimated profile center to determine the actual profile center position; Image 4 is used to identify the Z coordinate of the upper surface of the web after moving Rd, and calculate the profile placement angle deviation along the Y axis in combination with Image 1; Images 3 and 5 are used to identify the distance from the inner side of the flange to the estimated profile center after moving Rd, and calculate the profile placement angle deviation along the X and Z axes in combination with the data from Images 2 and 6.

[0041] Finally, the 3D camera unit is controlled to move and rotate sequentially to each designated first point and angle according to the planned point sequence. At each point, the 3D line laser profile camera is triggered to capture images of the profile. The camera directly outputs the profile web profile point cloud information for that point, ultimately obtaining six profile point clouds corresponding to the images. Precise point and angle control ensures that the point cloud data reflects the true shape of the key areas of the web. The collection of six point clouds provides multi-dimensional data support for subsequent calculations of the web center and rotation angle, reducing the limitations of single-angle acquisition.

[0042] S103: Process the point cloud information of the web profile to obtain the web position and specification posture parameters of the profile. S103 specifically includes the following steps: S1031: The point cloud data of the web contour at each point obtained in step S102 is transformed from the 3D camera coordinate system to the coordinate system centered on the laser device cutting point by using the homogeneous transformation matrix H composed of the pre-calibrated camera parameters and the rotation matrix R.

[0043] S1032: For the point cloud data of Image 1 and Image 4 after transformation to the cutting point coordinate system, sort them along the X-axis and extract the data points in the middle 90% range of the X coordinate. Then calculate the average value of the effective data point set in the Z coordinate direction.

[0044] S1033: Based on the average Z-coordinate of the effective data in Image 1, the Z-axis mechanical coordinate of the cutting point when Image 1 was acquired, and the web thickness in the profile drawing, calculate the Z-axis coordinate of the web center; and based on the Z-coordinate value of the web center calculated from Image 1 and Image 4 respectively, and the user-set moving distance Rd, calculate the rotation angle of the profile around the Y-axis.

[0045] S1034: For the point cloud data of images 2, 3, 5, and 6, the point cloud data is rotated in the opposite direction according to the rotation angle of the cutting point when it was acquired, so that the data of the inner surface of the wing plate in the point cloud is perpendicular to the Z-axis of the cutting point coordinate system. Then, the average value of the Z-coordinate of each image point cloud data after rotation is calculated to obtain the Y-direction distances YD2, YD3, YD5, and YD6 from the cutting point to the inner side of the wing plate at each shooting point.

[0046] S1035: Based on the Y-direction distance from each point to the inner side of the flange, the estimated Y-coordinate of the profile center CY input by the user, and the Y-direction movement distance Yd, calculate the Y-coordinate of the inner side of the left and right flanges and the Y-coordinate of the web center, and use the Y-direction distance values ​​measured before and after the movement distance Rd to calculate the rotation angle of the profile around the Z-axis.

[0047] In conjunction with the above S103, it should be noted that this embodiment requires the conversion of point cloud information, transforming the point cloud information corresponding to images 1 to 6 collected in step 102 from the camera coordinate system to a coordinate system centered on the laser device cutting point.

[0048] The specific conversion steps are as follows: Construct a rotation matrix R, where the rotation angles of R are rx, ry, and rz, which are the camera calibration parameters in S101.

[0049] If the rotation around the X-axis is by an angle rx, then Formula (3) If the rotation around the Y-axis is by an angle ry, then Formula (4) If the rotation around the Z-axis is by an angle rz, then Formula (5) The rotation matrix can be determined based on the rotation axis and rotation angle. The final rotation matrix R is: Formula (6) Construct the translation vector T as follows Formula (7) In this embodiment, dx, dy, and dz are camera calibration parameters in S101, and T is a constructed column vector.

[0050] Construct the homogeneous transformation matrix H as follows Formula (8) The coordinate transformation is performed, and each point in the point cloud information is transformed into coordinates in the coordinate system centered on the laser device cutting point through the homogeneous transformation matrix H.

[0051] Formula (9) in, , , The coordinates are from the original point cloud information. , , The coordinates are transformed into coordinates centered on the laser cutting point using a homogeneous transformation matrix.

[0052] The point cloud information in Image 1 is transformed as follows: Formula (10) Sort the data according to X in ascending order, and find the minimum value of X. and the maximum value of X Extract the data where the X-coordinate is in the middle 90%, that is: Formula (11) Extract and save point cloud information where the X coordinate is within the above range, and calculate the average value of the Z coordinate as avg_z. Given that the mechanical coordinates of the cutting point in the CNC system when image 1 is acquired are CZ+Th / 2+20, the mechanical coordinates of the upper surface of the web in the CNC system are CZ+Th / 2+20+avg_z. The Z coordinate of the web center is half the coordinate of the upper surface of the web minus the web thickness, i.e.: =CZ+Th / 2+20+avg_z-Tthick / 2 Formula (12) The web center of image 4 was extracted using the same steps as in image 1. The calculated web centers of images 1 and 4 are respectively... and According to trigonometric functions, the rotation angle of the profile around the Y-axis is: Formula (13) Images 2 and 3 were acquired with the cutting point directly facing the center of the inner side of the left wing. The rotation angle of the cutting point is -PA. Therefore, the angle between the left wing point cloud information and the Z-axis in the coordinate system of the cutting point is 90-PA. Rotating the point cloud information by PA degrees, the left wing point cloud information is now perpendicular to the Z-axis of the coordinate system of the cutting point. The Z-coordinate of the point cloud information is the horizontal distance from the cutting point to the left wing. The average Z-axis coordinate is calculated, and the absolute value of the average coordinate is the Y-direction distance from the cutting point to the inner edge of the wing. , .

[0053] Images 5 and 6 were acquired with the cutting point directly facing the center of the inner side of the left wing. The rotation angle of the cutting point is PA. Therefore, the angle between the left wing point cloud information and the Z-axis in the coordinate system of the cutting point is 90 + PA. Rotating the point cloud information by -PA degrees, the left wing point cloud information is now perpendicular to the Z-axis of the coordinate system of the cutting point. The Z-coordinate of the point cloud information is the horizontal distance from the cutting point to the left wing. Calculate the average Z-axis coordinate. The absolute value of the average coordinate is the Y-direction distance from the cutting point to the inner edge of the wing. , .

[0054] Based on the above data: The Y-coordinate of the inner side of the left wing is: Formula (14) The Y-coordinate of the inner side of the right wing is: Formula (15) The Y-coordinate of the web center is: Formula (16) The rotation angle of the profile around the Z-axis is: Formula (17) The coordinate transformation in this embodiment eliminates camera installation deviations and unifies the coordinate reference. Noise is reduced through point cloud filtering and averaging to extract the web center coordinates. The rotation angles of the profile around the Y and Z axes are calculated using the point cloud distance differences at different X positions, combined with trigonometric functions, reflecting the profile's placement posture. The comprehensive calculation of multiple YD values ​​makes the rotation angle more reliable, providing a precise web position reference for flange inspection.

[0055] S104: Based on the web position and specification attitude parameters, control the 3D camera unit to move and rotate sequentially to four preset second set of observation points and corresponding angles for collecting the outer contour of the wing plate, capture profile images, and obtain wing plate contour point cloud information.

[0056] S104 specifically includes the following steps: S1041: Obtain the Y-coordinate of the web center (CenterY) and the Z-coordinate of the web center (CenterZ) calculated in step S103, as well as the width (Tw), height (Th), and distance (By,Bz) from the rotation center to the cutting point of the profile drawing.

[0057] In some embodiments, the high-precision intermediate results output in step S103, the web center coordinates (CenterY, CenterZ), are combined with the original drawing parameters and system parameters and used as the direct input for this wing plate measurement path planning.

[0058] S1042: Based on the web center coordinates and profile drawing parameters, calculate the reference Y coordinates of the outer side of the right wing and the outer side of the left wing, namely CenterY+Tw / 2+100 and CenterY-Tw / 2-100; and calculate the reference Z coordinates of the upper 3 / 4 height and the lower 1 / 4 height of the wing, namely CenterZ+Th / 4 and CenterZ-Th / 4, based on the profile height.

[0059] In some embodiments, the spatial reference coordinates of the area to be measured on the outer side of the wingplate under ideal conditions are calculated based on the precisely located web center and profile dimensions. This clarifies the specific spatial objectives for data acquisition. By planning at a certain distance and two typical heights (3 / 4 and 1 / 4) on the outer side of the wingplate, it is ensured that the acquired point cloud can fully cover the upper and lower edge features of the wingplate.

[0060] S1043: Based on the reference coordinates of the outer side of the wing plate, the distance from the rotation center to the cutting point, and the preset 45-degree rotation angle, calculate the required Y and Z coordinates of the cutting point in the actual mechanical coordinate system when the camera rotates 45° and -45°, respectively, using trigonometric functions.

[0061] In some embodiments, considering that the cutting point will rotate around a fixed rotation center when the camera rotates, the actual mechanical coordinates that the camera needs to reach on the movement axis (Y,Z) in order to position the cutting point to the target measurement point determined in S1042 are calculated in advance using formula (18). Through accurate coordinate inverse solution, the nonlinear offset caused by the camera rotation is compensated, ensuring that the cutting point can accurately hover above the preset target observation point after the camera executes the rotation command, thereby ensuring the accuracy of the point cloud acquisition position.

[0062] S1044: Based on the acquired current X-axis mechanical coordinate CX and the calculated Y and Z mechanical coordinates and rotation angles of each point, plan the spatial coordinates and rotation angle sequence of four second designated points for collecting airfoil profile point cloud information.

[0063] In some embodiments, the calculated mechanical coordinates of all four points, with X represented as CX and the rotation angle integrated into an ordered sequence of instructions. This transforms a complex multi-point measurement task requiring spatial reasoning into a programmed sequence of actions that can be directly and stably executed by the CNC system.

[0064] S1045: Control the 3D camera unit to move and rotate to each specified point and angle according to the planned second point sequence, trigger the 3D camera to take pictures of the outer side of the profile airfoil at each point, and directly acquire and output the profile airfoil point cloud information at that point.

[0065] In some embodiments, the CNC system drives the 3D camera unit to precisely position itself and acquires point cloud information of the outer side of the wingplate at each point using a 3D line laser contour camera. This ultimately yields raw data for calculating the Y-coordinate of the outer side of the wingplate, the Z-coordinates of the upper and lower edges, and the rotation angle around the X-axis. The camera is then controlled to execute this precisely planned path, completing the high-quality point cloud acquisition of the outer side of the wingplate.

[0066] As can be seen, in this embodiment, based on the position and specifications of the web plate, the 3D camera unit is controlled to move to a designated point and rotate to a designated angle to start taking pictures of the profile image in order to obtain the profile flange contour point cloud information.

[0067] This embodiment captures a total of 4 images, which are then converted into contour point clouds, and are denoted as images 7 to 10. The specific capture points and angles of the images are shown in the table below: Define the constant t= Formula (18) Images 7 and 8 are for obtaining the Y-coordinate of the outer side of the right wing and the Z-coordinate of the upper and lower edges of the right wing. Images 9 and 10 are for obtaining the Y-coordinate of the outer side of the left wing and the Z-coordinate of the upper and lower edges of the left wing. Image 7 was captured 100mm to the right of the right wing at 3 / 4 of its height; Image 8 was captured 100mm to the right of the right wing at 1 / 4 of its height; Image 9 was captured 100mm to the left of the left wing at 3 / 4 of its height; and Image 10 was captured 100mm to the left of the left wing at 1 / 4 of its height.

[0068] The camera needs to be rotated 90 degrees at the cutting point to face the wingplate. To ensure efficiency, the cutting point is rotated 45 degrees for data acquisition, guaranteeing both measurement efficiency and accuracy. Based on the web centering results and drawing information, the Y-coordinate of 100mm to the right of the right wingplate is CenterY+Tw / 2+100. With a rotation angle of -45°, the coordinates of the rotation center are CenterY+Tw / 2+100+sin45°*Bz+cos45°*By. Substituting the constant t, we get CenterY+Tw / 2+100+t*(Bz+By). The Y-coordinate of the cutting point before rotation is CenterY+Tw / 2+100+t*(Bz+By)-By. The Y-coordinate of the left wing plate 100mm to the left is CenterY-Tw / 2-100. The rotation angle is 45°. At this time, the coordinate of the rotation center is CenterY+Tw / 2+100+sin45°*By-cos45°*Bz. Substituting the constant t, we get CenterY+Tw / 2+100+t*(By-Bz). The Y-coordinate of the cutting point before rotation is CenterY+Tw / 2+100+t*(By-Bz)-By.

[0069] The Z-coordinates at 3 / 4 of the height of the left and right wing plates are CenterZ+Th / 4, and the Z-coordinates at 1 / 4 of the height are CenterZ-Th / 4. The Z-coordinates before rotation are calculated based on the rotation angle and the distance from the rotation center to the cutting point, as shown in Table 2. Table 2: Z-coordinates before rotation calculated based on rotation angle and distance from rotation center to cutting point.

[0070] In this way, the point calculation is based on the actual position of the web, ensuring that the camera is aligned with the wing; the 45° rotation reduces the motion time while ensuring the quality of the point cloud; the four point clouds cover the upper and lower edges of the left and right wings respectively, providing data that meets the requirements for wing parameter extraction.

[0071] S105: Process the point cloud information of the wing profile to obtain the position and specification attitude parameters of the profile wing.

[0072] S105 specifically includes the following steps: S1051: The wing profile point cloud data of images 7 to 10 obtained in step S104 are transformed from the 3D camera coordinate system to the coordinate system centered on the laser device cutting point through the homogeneous transformation matrix H.

[0073] It should be noted that this embodiment uses the same coordinate transformation method as step S1031, and transforms it from the 3D camera coordinate system to the coordinate system centered on the laser device cutting point through the homogeneous transformation matrix H.

[0074] The homogeneous transformation matrix H is .

[0075] In some embodiments, the wing plate point cloud data is converted to a cutting point coordinate system that is consistent with the web point cloud and CNC machining instructions. This ensures that all measurement results are in the same coordinate system, allowing for direct data fusion and comparison.

[0076] S1052: Set the expected range of Z coordinates, and retain point clouds whose Z coordinates are within ±15mm of the predicted value as valid point clouds; apply radius filtering to the valid point clouds, and search for neighboring points within a given radius of each point through KD tree. If the number of neighboring points is less than the set threshold, the point is removed, thereby filtering out low-density noise points.

[0077] This embodiment combines known theoretical observation distances for range filtering, and then uses radius filtering based on the statistical density of neighboring points for noise reduction. Range filtering in this embodiment can remove a large number of obviously invalid background points, while radius filtering can precisely remove sparse noise points, while preserving the structurally complete point cloud of the wingplate. This improves the accuracy and stability of all subsequent calculation steps.

[0078] S1053: For the effective point clouds after filtering from images 7 to 10, calculate the average Z-coordinate of all points in each point cloud to obtain four measured distance values ​​(YD7, YD8, YD9, YD1). 10 Based on these distance values ​​and the profile height Th, the rotation angle of the profile around the X-axis is calculated, and combined with the profile width Tw, the Y coordinates of the outer sides of the left and right flanges are calculated.

[0079] In some embodiments, the torsion angle of the profile around the X-axis is calculated using trigonometric relationships by measuring the distance difference at different heights above and below the winglet. The actual coordinates of the outer side of the winglet are then calculated by combining the distance values ​​measured from both sides with the theoretical width. This achieves rotation of the profile around the X-axis. The dual-side, dual-height measurement scheme effectively eliminates the random errors that may exist in single-point measurements, making the calculation of the torsion angle more reliable.

[0080] S1054: Find the point with the smallest Y coordinate in the point cloud of image 7, and the point with the largest Y coordinate in the point cloud of image 9. Record their Y and Z coordinates respectively, and use them as the coordinates of the upper edge of the right wing plate and the upper edge of the left wing plate. Find the point with the largest Y coordinate in the point cloud of image 8, and the point with the smallest Y coordinate in the point cloud of image 10. Record their Y and Z coordinates respectively, and use them as the coordinates of the lower edge of the right wing plate and the lower edge of the left wing plate.

[0081] In some embodiments, the physical edge position of the airfoil is directly determined by searching for extreme points in the Y-coordinate within the filtered, high-purity airfoil point cloud. These extreme points are key feature points that best represent the true geometric boundary of the airfoil, providing the most direct and accurate data source for calculating the airfoil's height and center position.

[0082] S1055: Based on the obtained Z coordinates of the upper and lower edges of the wingplate, calculate the actual height of the left and right wingplates and the Z coordinates of the center of the left and right wingplates respectively.

[0083] As one implementation of this embodiment, the point cloud information is transformed by converting the point cloud information corresponding to images 7 to 10 acquired in step 104 from the camera coordinate system to a coordinate system centered on the laser device cutting point. The specific transformation steps are the same as in step 103, which involves transforming each point in the point cloud information into coordinates centered on the laser device cutting point through a homogeneous transformation matrix H.

[0084] As shown in Table 3, the coordinates of the cutting point after rotation are calculated based on the rotation angle and the distance from the rotation center to the cutting point.

[0085] Table 3: Coordinates of the cutting points after rotation

[0086] In this embodiment, based on the distance in the Z direction, the point cloud outside the filtering range is filtered out. The straight-line distance from the cutting point to the wing plate after rotation is: Formula (19) In the coordinate system of the cutting head, the z-coordinate corresponding to the y-coordinate should be: Formula (20) For each coordinate point in the point cloud information obtained from images 7 to 10, save the points whose Z coordinate is within ±15mm of the predicted value, and discard the rest. Keep the point cloud within ±15mm of the predicted value as the valid point cloud. Then use radius filtering to filter, that is, given a radius and a number, use KD tree to find points within the radius. If the number of points within the radius is less than the given number, remove the point; otherwise, keep it.

[0087] This embodiment can filter out low-density noise, resulting in a point cloud that only contains the wingplate contour point cloud. It should be noted that the contour point cloud is a series of three-dimensional coordinate points; traversing each point yields the x, y, and z coordinates. The vertical distance from the wingplate to the XZ plane where the cutting head is located is calculated as follows: Formula (21) in, The first in the point cloud information The z-coordinates of the points.

[0088] The distances calculated from image 7 to image 10 in this embodiment are as follows: , , , Given that the distance between the Z-coordinates of images 7 and 9 and those of images 8 and 10 is Th / 2, we can calculate... The angle of rotation of the profile about the x-axis is: Formula (22) The Y-coordinate of the outer side of the left wing is: Formula (23) The Y-coordinate of the outer side of the right wing is: Formula (24) Obtain the minimum Y-coordinate point of image 7 and the maximum Y-coordinate point of image 9, along with their corresponding Z-coordinates. These points are the coordinates of the upper edges of the left and right wings. Obtain the maximum Y-coordinate point of image 8 and the minimum Y-coordinate point of image 10, along with their corresponding Z-coordinates. These points are the coordinates of the lower edges of the left and right wings. The Z-coordinates of the upper and lower edges of the left and right wings are represented by LeftUpperZ, LeftLowerZ, RightUpperZ, and RightLowerZ, respectively. Therefore, the height of the left wing is: LeftUpperZ - LeftLowerZ; Formula (25) The height of the right wing is: RightUpperZ - RightLowerZ; Formula (26) The center of the left wing is: (LeftUpperZ+LeftLowerZ) / 2 Formula (27) The center of the right wing is: (RightUpperZ+RightLowerZ) / 2 (Formula 28) It can be seen that in this embodiment, the point cloud of image 7-10 is transformed to the coordinate system of the cutting point using formulas (3) to (9); points with Z coordinates within ±15mm are filtered according to formulas (19) to (20), and low-density noise points are removed by radius filtering. YD7-YD is calculated using formula (21). 10 Using formula (22) we get Formulas (23) to (24) yield LeftOutsideY and RightOutsideY; extract the extreme point Z coordinates of the cloud of points 7-10 in the image to obtain LeftUpperZ, LeftLowerZ, etc., and calculate the wing height and center through formulas (25) to (28).

[0089] Thus, this embodiment unifies all point clouds to a reference coordinate system suitable for precise measurement through coordinate transformation. Utilizing the known camera-target relative geometry during acquisition as a strong constraint, the original point cloud undergoes extensive data cleaning, eliminating noise and background interference that clearly does not conform to spatial positioning, thereby improving data quality. Based on the point cloud, the profile's rotation angle around the X-axis and the outer boundary and edge position of the airfoil are calculated using two complementary methods: statistical averaging and extreme value search. Finally, the actual dimensions and center position of the airfoil are calculated using key feature points, thereby obtaining the airfoil's specifications and attitude information. Filtering improves point cloud quality, and multi-parameter calculations ensure accurate airfoil position and angle, providing complete airfoil feature data for 3D modeling and reducing model deviations caused by data noise.

[0090] S106: Based on the web position and specification posture parameters and the wing plate position and specification posture parameters, determine the profile coordinates and specification posture, and construct a three-dimensional model of the profile.

[0091] S106 specifically includes the following steps: S1061: Integrate the web position and attitude parameters from step S103, the wing position and specification parameters from step S105, and the web thickness.

[0092] Optionally, the attitude parameters include the Y-coordinate of the web center (CenterY), the Z-coordinate of the web center (CenterZ), the Y-coordinates of the inner sides of the left / right wings (LeftInsideY / RightInsideY), and the rotation angles R_Y and R_Z around the Y and Z axes.

[0093] The specifications include the Y-coordinates of the outer edges of the left / right wing panels (LeftOutsideY / RightOutsideY), the Z-coordinates of the upper edges of the left / right wing panels (LeftUpperZ / RightUpperZ), and the Z-coordinates of the lower edges of the left / right wing panels (LeftLowerZ / RightLowerZ).

[0094] S1062: Based on all parameters integrated in S1061, calculate the Y and Z coordinates of 12 key feature points on the cross-section at the starting end of the profile in the CNC system's mechanical coordinate system. The 12 points include the upper and lower outer ends of the left and right flanges, the upper and lower inner ends of the flanges, and the corner points connecting to the web.

[0095] S1063: Obtain the profile length L, and rotate the profile around the Y-axis based on the measured angle. and rotation angle around the Z-axis Calculate the offset of the end position of the profile relative to the starting position in the Y and Z coordinates along the X-axis direction; Wherein, the Y-coordinate offset is -L*sin( ) or -L*cos( The Z-coordinate offset is -L*sin( ).

[0096] S1064: Combining the coordinates of the 12 points at the starting end of the profile, the profile length L, and the calculated end-point coordinate offset, a three-dimensional model of the profile is constructed; the three-dimensional model defines the spatial contour and posture of the profile along its entire length. S1065: Outputs the constructed 3D model data to the CNC system for path planning and control in subsequent laser cutting processes.

[0097] It should be noted that the 3D model of the constructed profile needs to be as follows: Figure 6The coordinates of the 12 points shown, along with their rotation angles around the X, Y, and Z axes, are used to calculate the mechanical coordinates of the 12 points in the CNC system based on the Y-coordinates of the inner left and right wing plates, the Y-coordinates of the web center, the Z-coordinates of the web center, the Y-coordinates of the outer left and right wing plates, the Z-coordinates of the upper left and right wing plates, the lower left and right wing plates, and the profile drawing information. As shown in Table 4, the starting position coordinates of the profile can be determined based on the data in step S106.

[0098] Table 4: Coordinates of the Starting Position of the Profile

[0099] Define the profile length as L, and combine the web parameters LeftInsideY, RightInsideY, etc., the flange parameters LeftOutsideY, LeftUpperZ, etc., and Tthick, calculate the coordinates of 12 points at the starting position of the profile, as shown in Table 4, and determine the rotation angle. , , Based on the profile length L, calculate the coordinates of 12 points at the endpoint. The coordinate offset of each point at the endpoint relative to the starting position is represented by the change in the Y-coordinate. Z-coordinate change Connect the starting and ending points to construct a three-dimensional mesh model.

[0100] As can be seen, this embodiment integrates and consolidates the web center, inner and outer sides of the flanges, upper and lower edges, and rotation angles around three axes calculated separately in all previous steps. Based on the measured feature points, the coordinates of all key contour points defining the cross-sectional shape of the profile are derived through geometric relationships, thereby drawing its two-dimensional cross-section at the starting end of the profile. This is achieved by combining the profile length dimension and the detected spatial attitude angles (…). , The two-dimensional cross-section is extended along a three-dimensional spatial vector that takes into account attitude offset, thereby constructing a three-dimensional solid model with torsional and bending attitudes that can realistically reflect the actual placement and orientation of the profile in space. Finally, the digital model is transmitted to the processing system, enabling the cutting path to accurately match the actual position of the profile, improving cutting accuracy and efficiency.

[0101] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0102] The following are embodiments of the detection system based on profile coordinates and specification orientation on a laser cutting device provided in this disclosure. This system and the detection methods based on profile coordinates and specification orientation on a laser cutting device in the above embodiments belong to the same inventive concept. For details not described in detail in the embodiments of the detection system based on profile coordinates and specification orientation on a laser cutting device, please refer to the embodiments of the detection methods based on profile coordinates and specification orientation on a laser cutting device described above.

[0103] The system includes: The information receiving module is used to receive the drawing information of the profile to be cut and the interface parameters input by the user; The web profile acquisition module, based on drawing information and interface parameters, controls the 3D camera unit to move and rotate sequentially to the first set of six preset observation points for acquiring the inner profile of the web and wing plates, captures profile images, and obtains profile web profile point cloud information. The web data processing module is used to process the web contour point cloud information to obtain the web position and specification posture parameters of the profile. The wing profile acquisition module, based on the web position and specification attitude parameters, controls the 3D camera unit to move and rotate sequentially to four preset second set of observation points and corresponding angles for acquiring the outer profile of the wing, captures profile images, and obtains wing profile point cloud information. The wing plate data processing module is used to process the wing plate contour point cloud information to obtain the wing plate position and specification attitude parameters. The model building module determines the profile coordinates and specifications based on the web position and specification attitude parameters and the wing plate position and specification attitude parameters, and builds a three-dimensional model of the profile.

[0104] like Figure 7 As shown, this application also provides an electronic device, including a display module 103, a memory 102, a processor 101, a communication module 104, and a computer program stored in the memory and executable on the processor 101. When the processor 101 executes the program, it implements the steps of a detection method based on the profile coordinates and specification orientation on a laser cutting device.

[0105] In embodiments of the present invention, electronic devices include, but are not limited to, laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. Electronic devices may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the embodiments described and / or claimed herein.

[0106] In this embodiment, processor 101 may be implemented using at least one of an application-specific integrated circuit, a programmable logic device, a field-programmable gate array, a processor, a controller, a microcontroller, a microprocessor, or an electronic unit designed to perform the functions described herein. In some cases, such an implementation may be implemented within a controller. For software implementation, implementations such as processes or functions may be implemented with separate software modules that allow the performance of at least one function or operation. Software code may be implemented by a software application (or program) written in any suitable programming language, and the software code may be stored in memory and executed by the controller.

[0107] The display module 103 is used to display information input by the user or information provided to the user. The display module 103 may include a display panel, which may be configured in the form of a liquid crystal display, an organic light-emitting diode, or the like.

[0108] The memory 102 can be used to store software programs and various data. The memory 102 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0109] The communication module 104 transmits radio signals to and / or receives radio signals from at least one of a base station, an external terminal, and a server. Such radio signals may include voice call signals, video call signals, or various types of data sent and / or received according to text and / or multimedia messages.

[0110] The present invention also provides a storage medium storing a computer program thereon, which, when executed by a processor, implements the steps of the detection method based on the profile coordinates and specification orientation on a laser cutting device.

[0111] The storage medium may be any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example,, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (a non-exhaustive list) of readable storage media include: electrical connections having one or more wires, portable disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0112] The storage medium stores a program product capable of implementing the methods described above in this specification. In some possible implementations, various aspects of this disclosure may also be implemented as a program product comprising program code that, when run on a terminal device, causes the terminal device to perform the steps described in the "Exemplary Methods" section of this specification according to various exemplary embodiments of this disclosure.

[0113] The above description of the disclosed embodiments enables those skilled in the art to make or use the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for detecting profile coordinates and specification orientation on a laser cutting machine, characterized in that, The methods include: S101: Receive the drawing information of the profile to be cut and the interface parameters input by the user; S102: Based on the drawing information and interface parameters, control the 3D camera unit to move and rotate sequentially to the first set of observation points of six preset for collecting the inner contour of the web and wing plates, capture profile images, and obtain the web contour point cloud information of the profile. S103: Process the point cloud information of the web profile to obtain the web position and specification posture parameters of the profile. S104: Based on the web position and specification attitude parameters, control the 3D camera unit to move and rotate sequentially to four preset second set of observation points and corresponding angles for collecting the outer contour of the wing plate, capture profile images, and obtain wing plate contour point cloud information. S105: Process the point cloud information of the wing profile to obtain the position and specification attitude parameters of the profile wing; S106: Based on the web position and specification attitude parameters and the flange position and specification attitude parameters, determine the profile coordinates and specification attitude, and construct a three-dimensional model of the profile.

2. The detection method based on profile coordinates and specification orientation on a laser cutting device according to claim 1, characterized in that, S101 specifically includes the following steps: Receive the drawing information of the profile to be cut from the CNC system; Receive user-inputted interface parameters through the user interface; The pre-calibrated 3D camera unit parameters are called, and the distance the 3D camera unit moves in the Y direction during image acquisition is calculated based on the profile width in the profile drawing information. The drawing information, user-input interface parameters, calibration parameters, and calculated Y-direction movement distance are temporarily stored.

3. The detection method based on profile coordinates and specification orientation on a laser cutting equipment according to claim 1, characterized in that, S102 specifically includes the following steps: Obtain the current X-axis mechanical coordinate CX of the 3D camera unit at the start of the inspection from the CNC system; Based on the profile width Tw in the profile drawing information, the following formula (1) is used to calculate the moving distance Yd of the 3D camera unit in the Y-axis direction during image acquisition; Official (1) Tw is the physical width of the profile; Based on the profile drawing information, the calculated moving distance Yd, the user-input interface parameters, and the distance from the rotation center to the cutting point, the first specified rotation angle PA required to make the cutting point face the inner center of the wing plate is calculated according to formula (2). The rotation angle PA is: Official (2) in, The distance traveled along the Y-axis during detection is the horizontal distance from the center of rotation to the inner side of the airfoil. Th is the profile height, Bz is the vertical distance from the cutting point to the rotation center, and the vertical distance from the rotation center to the inner center of the flange is... ; Based on CX, the estimated profile center coordinates (CY, CZ) input by the user, the profile height Th in the profile drawing information, the calculated Yd and rotation angle PA, and the user-input distance of movement along the X-axis Rd, a sequence of spatial coordinates and rotation angles for six first designated points used to collect web profile point cloud information is planned. The 3D camera unit is controlled to move and rotate sequentially to each first designated point and angle according to the planned point sequence. At each point, the 3D camera is triggered to take pictures of the profile, and the point cloud information of the profile web profile at that point is obtained and output.

4. The detection method based on profile coordinates and specification orientation on a laser cutting equipment according to claim 1, characterized in that, S103 specifically includes the following steps: The obtained web contour point cloud data is transformed from the 3D camera coordinate system to the coordinate system centered on the laser cutting point by using the homogeneous transformation matrix H composed of the pre-calibrated camera parameters and the rotation matrix R. For the point cloud data of Image 1 and Image 4 after transformation to the cutting point coordinate system, they are sorted along the X-axis and the data points in the middle 90% range of the X coordinate are extracted. Then the average value of the effective data point set in the Z coordinate direction is calculated. Based on the average Z-coordinate of the effective data in Image 1, the Z-axis mechanical coordinate of the cutting point when Image 1 was acquired, and the web thickness in the profile drawing, the Z-axis coordinate of the web center is calculated; and based on the Z-coordinate values ​​of the web center calculated from Images 1 and 4 respectively, and the user-defined moving distance Rd, the rotation angle of the profile around the Y-axis is calculated. For the point cloud data of images 2, 3, 5, and 6, the point cloud data is rotated in the opposite direction according to the rotation angle of the cutting point when it is collected, so that the data of the inner surface of the wing plate in the point cloud is perpendicular to the Z-axis of the cutting point coordinate system. Then, the average value of the Z-coordinate of each image point cloud data after rotation is calculated to obtain the Y-direction distances YD2, YD3, YD5, and YD6 from the cutting point to the inner side of the wing plate at each shooting point. Based on the Y-direction distance from each point to the inner side of the flange, the estimated Y-coordinate of the profile center (CY) input by the user, and the Y-direction movement distance (Yd), the Y-coordinates of the inner sides of the left and right flanges and the Y-coordinate of the web center are calculated. Using the Y-direction distance values ​​measured before and after the movement distance (Rd), the rotation angle of the profile around the Z-axis is calculated.

5. The detection method based on profile coordinates and specification orientation on a laser cutting equipment according to claim 1, characterized in that, S104 specifically includes the following steps: Obtain the Y-coordinate of the web center (CenterY) and the Z-coordinate of the web center (CenterZ) calculated in step S103, as well as the width (Tw), height (Th), and distance (By,Bz) from the rotation center to the cutting point of the profile drawing. Based on the web center coordinates and profile drawing parameters, the reference Y coordinates of the outer side of the right flange and the outer side of the left flange are calculated respectively. Based on the reference coordinates of the outer side of the wing plate, the distance from the rotation center to the cutting point, and the preset 45-degree rotation angle, the Y and Z coordinates required for the cutting point in the actual mechanical coordinate system when the camera rotates 45° and -45° are calculated using trigonometric functions. Based on the current X-axis mechanical coordinate CX obtained and the calculated Y and Z mechanical coordinates and rotation angles of each point; The 3D camera unit is controlled to move and rotate to each specified point and angle according to the planned second point sequence. At each point, the 3D camera is triggered to take pictures of the outer side of the profile airfoil, and the profile airfoil contour point cloud information of the point is acquired and output.

6. The detection method based on profile coordinates and specification orientation on a laser cutting equipment according to claim 1, characterized in that, S105 specifically includes the following steps: The wing profile point cloud data of images 7 to 10 obtained in step S104 are transformed from the 3D camera coordinate system to the coordinate system centered on the laser device cutting point through homogeneous transformation matrix H. Set the expected range of Z coordinates, and retain point clouds whose Z coordinates are within ±15mm of the predicted value as valid point clouds; apply radius filtering to the valid point clouds, and search for neighboring points within a given radius of each point using a KD tree. If the number of neighboring points is less than a set threshold, the point is removed, thereby filtering out low-density noise points. For the effective point clouds after filtering images 7 to 10, the average Z coordinate of all points in each point cloud is calculated to obtain four measured distance values. Based on these distance values ​​and the profile height Th, the rotation angle of the profile around the X-axis is calculated, and combined with the profile width Tw, the Y coordinates of the outer sides of the left and right flanges are calculated. Find the point with the smallest Y coordinate in the point cloud of image 7, and find the point with the largest Y coordinate in the point cloud of image 9. Record their Y and Z coordinates respectively, and use them as the coordinates of the upper edge of the right wing plate and the upper edge of the left wing plate. Find the point with the largest Y coordinate in the point cloud of image 8, and find the point with the smallest Y coordinate in the point cloud of image 10. Record their Y and Z coordinates respectively, and use them as the coordinates of the lower edge of the right wing plate and the lower edge of the left wing plate. Based on the obtained Z coordinates of the upper and lower edges of the wingplate, the actual heights of the left and right wingplates and the Z coordinates of the centers of the left and right wingplates are calculated respectively.

7. The detection method based on profile coordinates and specification orientation on a laser cutting equipment according to claim 1, characterized in that, S106 specifically includes the following steps: Receive web position and attitude parameters, wing plate position and specification parameters, and web thickness; Based on all parameters, calculate the Y and Z coordinates of 12 key feature points on the cross-section at the starting end of the profile in the CNC system's mechanical coordinate system. The 12 points include the upper and lower outer ends and the upper and lower inner ends of the left and right flanges, as well as the corner points connected to the web. Obtain the profile length L, and rotate the profile around the Y-axis based on the measured angle. and rotation angle around the Z-axis Calculate the offset of the end position of the profile relative to the starting position in the Y and Z coordinates along the X-axis direction; The Y-coordinate offset is -L. sin( ) or -L cos( The Z-coordinate offset is -L. sin( ); By combining the coordinates of 12 points at the beginning of the profile, the length L of the profile, and the calculated offset of the end point coordinates, a three-dimensional model of the profile is constructed. The constructed 3D model data is output to the CNC system for path planning and control in subsequent laser cutting processes.

8. A detection system based on profile coordinates and specification orientation on a laser cutting equipment, characterized in that, The system is used to implement the detection method based on the profile coordinates and specification orientation on a laser cutting device as described in any one of claims 1 to 7; The system includes: The information receiving module is used to receive the drawing information of the profile to be cut and the interface parameters input by the user; The web profile acquisition module, based on drawing information and interface parameters, controls the 3D camera unit to move and rotate sequentially to the first set of six preset observation points for acquiring the inner profile of the web and wing plates, captures profile images, and obtains profile web profile point cloud information. The web data processing module is used to process the web contour point cloud information to obtain the web position and specification posture parameters of the profile. The wing profile acquisition module, based on the web position and specification attitude parameters, controls the 3D camera unit to move and rotate sequentially to four preset second set of observation points and corresponding angles for acquiring the outer profile of the wing, captures profile images, and obtains wing profile point cloud information. The wing plate data processing module is used to process the wing plate contour point cloud information to obtain the wing plate position and specification attitude parameters. The model building module determines the profile coordinates and specifications based on the web position and specification attitude parameters and the wing plate position and specification attitude parameters, and builds a three-dimensional model of the profile.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the steps of the detection method based on the profile coordinates and specification orientation on a laser cutting device as described in any one of claims 1 to 7.

10. A storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the detection method based on the profile coordinates and specification orientation on a laser cutting device as described in any one of claims 1 to 7.

Images