A laser processing method and system

Abstract

The application discloses a laser processing method, which can effectively compensate for processing deviations caused by factors such as laser system axis calibration, axis setting, guide rail installation and tool flatness; the entire process does not need post-manual sampling and manual adjustment of parameters, realizes real-time detection of processing deviations and targeted adjustment of laser system parameters, greatly improves the precision and efficiency of target workpiece processing, and especially for large-size target workpieces, can avoid the problem of inaccurate deviation measurement caused by sparse measurement points and complex workpiece handling, and guarantees processing consistency.

Description

Technical Field

[0001] This application relates to the field of laser processing technology, and in particular to a laser processing method and system. Background Technology

[0002] In current laser processing, laser systems mostly execute processing according to a preset theoretical processing path. However, due to factors such as the laser system's own axis calibration error, axis adjustment error, guide rail and installation error, tooling flatness deviation and clamping deformation, and thermal drift, the actual processed graphics are prone to deviation from the graphic information in the theoretical processing path. Furthermore, the current processing flow lacks a mechanism to simultaneously collect the actual processed graphics and compare them with the theoretical graphic information during processing. It mostly relies on sampling the actual processed graphics after processing using measuring equipment, manually recording the deviation values, and writing the parameters back to the laser system for trial cutting and adjustment. This method is not only inefficient, but also makes it difficult to ensure the accuracy and consistency of deviation measurement for large-sized target workpieces due to sparse measurement points and complex workpiece handling. At the same time, it is impossible to correct subsequent processing deviations based on other graphic information in the theoretical processing path by adjusting the system parameters of the laser system in real time, resulting in the overall processing accuracy and efficiency failing to meet the requirements. Summary of the Invention

[0003] This application provides a laser processing method and system that can solve the problems of existing methods being not only inefficient, but also having sparse measurement points and complex workpiece handling for large-sized target workpieces, making it difficult to guarantee the accuracy and consistency of deviation measurement. Furthermore, it is impossible to correct subsequent processing deviations based on other primitive information in the theoretical processing path by adjusting the system parameters of the laser system in real time, resulting in the overall processing accuracy and efficiency failing to meet the requirements.

[0004] In a first aspect, this application provides a laser processing method, the method comprising: Based on the first primitive information in the preset theoretical processing path, the laser system is controlled to process the actual reference graphic corresponding to the first primitive information on the target workpiece. Acquire real-time images of the actual reference graphic; The real-time image is converted into a target type format image using a preset affine transformation matrix; Based on the deviation between the target type format image and the first primitive information, the system parameters of the laser system are adjusted so that the adjusted laser system can process the target workpiece according to the second primitive information in the preset theoretical processing path.

[0005] Secondly, this application provides a laser processing system, the system comprising: The first subsystem is used to control the laser system to process the actual reference graphic corresponding to the first primitive information on the target workpiece according to the first primitive information in the preset theoretical processing path. The second subsystem is used to acquire real-time images of the actual reference graphic; The third subsystem is used to convert the real-time image into a target type format image using a preset affine transformation matrix; The fourth subsystem is used to adjust the system parameters of the laser system according to the deviation value between the target type format image and the first primitive information, so as to use the adjusted laser system to process the target workpiece according to the second primitive information in the preset theoretical processing path.

[0006] Thirdly, this application provides a readable medium including executable instructions, which, when executed by a processor of an electronic device, cause the electronic device to perform any of the methods described in the first aspect.

[0007] Fourthly, this application provides an electronic device including a processor and a memory storing execution instructions, wherein when the processor executes the execution instructions stored in the memory, the processor performs the method as described in any of the first aspects.

[0008] As can be seen from the above technical solution, the method provided in this application can first control the laser system to process the actual reference graphic based on the first primitive information of the preset theoretical processing path, and then acquire the real-time image of the graphic and convert it into a target type format image through a preset affine transformation matrix. This allows the target type format image to be directly compared with the first primitive information to obtain the deviation value. Based on this deviation value, the system parameters of the laser system are adjusted. Subsequently, when the adjusted laser system processes the target workpiece based on the second primitive information of the theoretical processing path, it can effectively compensate for the processing deviation caused by factors such as laser system axis calibration, axis adjustment, guide rail installation, and tooling flatness. The entire process does not require manual sampling and manual parameter adjustment afterward, realizing real-time detection of processing deviation and targeted adjustment of laser system parameters, which greatly improves the accuracy and efficiency of target workpiece processing. Especially for large-sized target workpieces, it can avoid the problem of inaccurate deviation measurement caused by sparse measurement points and complex workpiece handling, ensuring processing consistency.

[0009] The further effects of the aforementioned non-conventional preferred method will be explained below in conjunction with specific embodiments. Attached Figure Description

[0010] To more clearly illustrate the embodiments of this application or the existing technical solutions, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0011] Figure 1 A schematic flowchart of a laser processing method provided in an embodiment of this application; Figure 2 This is a schematic diagram of coordinate transformation and overlay links provided in an embodiment of this application; Figure 3 A real-time processing flowchart provided for one embodiment of this application; Figure 4 A synchronization timing diagram provided for an embodiment of this application; Figure 5 This is a schematic diagram of the structure of a laser processing system provided in one embodiment of this application; Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0012] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0013] The various non-limiting embodiments of this application will now be described in detail with reference to the accompanying drawings.

[0014] The inventors discovered that in current laser processing, laser systems mostly execute processing based on preset theoretical processing paths. However, due to factors such as laser system own axis calibration errors, axis adjustment errors, guide rail and installation errors, tooling flatness deviations and clamping deformation, and thermal drift, the actual processed graphics are prone to deviation from the graphic information in the theoretical processing path. Furthermore, the current processing flow lacks a mechanism to simultaneously collect the actual processed graphics and compare them with the theoretical graphic information during processing. It mostly relies on sampling the actual processed graphics afterward using measuring equipment, manually recording the deviation values, and writing the parameters back to the laser system for trial cutting and adjustment. This method is not only inefficient, but also makes it difficult to guarantee the accuracy and consistency of deviation measurement for large-sized target workpieces due to sparse measurement points and complex workpiece handling. At the same time, it is impossible to correct subsequent processing deviations based on other graphic information in the theoretical processing path by adjusting the system parameters of the laser system in real time, resulting in the overall processing accuracy and efficiency failing to meet the requirements.

[0015] To address the aforementioned problems in the prior art, this application provides a laser processing method. This embodiment details a laser processing method primarily applied to the laser patterning of perovskite glass substrates (i.e., the "target workpiece"). High-precision processing is achieved through real-time image acquisition, coordinate transformation, deviation calculation, and parameter adjustment. The following first defines the coined terms and key terminology involved in the method, and then elaborates on the specific implementation details step-by-step according to the technical flow, ensuring smooth transitions and logical integrity among the steps.

[0016] Definitions and explanations of key terms: Theoretical processing path: refers to the pre-designed graphic trajectory used to guide the laser system processing. In this embodiment, the path is stored in DXF format file, which contains the geometric parameters of the primitives (such as the start / end coordinates of line segments, the center / radius of arcs, the position coordinates of corner points, etc.).

[0017] First primitive information: refers to primitive data selected from the theoretical processing path for processing the "actual reference graphic". It is a subset of the "primitive information set" and contains coordinate parameters of at least one geometric feature among line segments, arcs, and corner points (such as the endpoint coordinates of line segments, the center coordinates and radius of arcs, and the coordinates of corner points, etc.), which serve as the "theoretical reference" for subsequent deviation comparison.

[0018] Second primitive information: refers to other primitive data in the theoretical processing path besides the first primitive information. It is the core basis for the actual processing of the target workpiece after the laser system adjusts the parameters, and together with the first primitive information, it constitutes a complete theoretical processing path.

[0019] Actual reference pattern: refers to the pattern actually formed on the perovskite glass substrate by the laser system based on the first primitive information, which serves as the "actual sample" for subsequent acquisition of real-time images and calculation of deviations.

[0020] Real-time images: refer to image data that reflects the appearance of the actual reference graphic, which is acquired synchronously during the actual reference graphic processing process by an image acquisition device (such as an area scan camera or a line scan camera) that maintains a fixed relative position with the laser processing head.

[0021] Affine transformation matrix: refers to the mathematical matrix used to realize the coordinate transformation between the "image coordinate system" and the "target type format coordinate system" (i.e., the "preset affine transformation matrix", which is uniformly referred to as "affine transformation matrix" here to ensure consistency of terminology). It is derived from the intrinsic parameters, distortion parameters and plane homography matrix of the image acquisition device, and can map the pixel coordinates of the real-time image to the coordinates under the target type format coordinate system.

[0022] Target type format image: refers to the real-time image that has been preprocessed and affine transformed into an image that matches the target type format (in this embodiment, it can be a CAD file format). This image can be directly compared with the first primitive information (derived from a DXF format file, which is compatible with the CAD file format) for geometric feature comparison.

[0023] Target type format coordinate system: refers to the coordinate system corresponding to the CAD file format. Its unit is consistent with the design unit of the theoretical processing path (such as millimeters). It is used to unify the coordinate reference of the first primitive information and the target type format image to ensure the accuracy of deviation calculation.

[0024] Image coordinate system: refers to the coordinate system used to describe the position of pixels in a real-time image, specifically the camera pixel coordinate system of the image acquisition device (i.e., the "camera pixel coordinate system of the image acquisition device"), with the unit being "pixel". Its origin is usually set at the upper left corner of the image, the horizontal axis is the number of pixel columns, and the vertical axis is the number of pixel rows.

[0025] Deviation value: refers to the geometric difference between the actual reference graphic reflected by the target type format image and the theoretical graphic described by the first primitive information, including at least one of the following: translation deviation (ΔX, ΔY, i.e., positional offset in the X-axis and Y-axis directions), rotation deviation (Δθ, i.e., the rotation angle deviation of the actual graphic relative to the theoretical graphic), and scaling deviation (Δs, i.e., the size scaling ratio deviation of the actual graphic relative to the theoretical graphic).

[0026] Compensation parameters: These are parameters generated based on the deviation values ​​and used to correct the processing deviations of the laser system. Specifically, they are the correction amounts for the theoretical processing path (such as the coordinate correction values ​​for each processing point). The processing trajectory is adjusted by injecting these parameters into the motion controller of the laser system.

[0027] Compensation field model: refers to the mathematical model used to fit global and local deviations. In this embodiment, a thin plate spline model or radial basis function model is used to accurately fit the nonlinear deformation deviation of a large-size perovskite glass substrate (2.4 m × 1.2 m) and ensure the processing accuracy of the entire plate surface.

[0028] See Figure 1 This paper illustrates a laser processing method according to an embodiment of the present application. In this embodiment, the method may include, for example, the following steps: S101: Based on the first primitive information in the preset theoretical processing path, control the laser system to process the actual reference graphic corresponding to the first primitive information on the target workpiece.

[0029] In this embodiment, the preset theoretical processing path is a graphic path in a DXF format file, and the first primitive information includes coordinate parameters of at least one geometric feature among line segments, arcs, and corner points. In one implementation, the target workpiece can be a perovskite glass substrate.

[0030] In this embodiment, as Figure 2 The specific operation of controlling the laser system to process the actual reference graphic corresponding to the first primitive information on the target workpiece according to the first primitive information in the preset theoretical processing path can be as follows: In this embodiment, the laser system hardware can be prepared first. Specifically, the laser system used includes a picosecond laser (15W power, pulse frequency 20-100kHz, wavelength 355nm, suitable for high-precision scribing of perovskite glass substrates), an XY gantry motion platform (2600×1400mm travel, grating closed-loop control, repeatability ±5μm), a laser processing head (integrated focusing lens, focused spot diameter 50μm), and a motion controller (supporting G-code parsing and real-time parameter adjustment).

[0031] Then, the processing hyperparameters are set. Specifically, the processing parameters of the laser system can be preset according to the thickness (e.g., 2mm) and material characteristics of the perovskite glass substrate, including laser power (e.g., 8W), processing speed (e.g., 500mm / s), and pulse frequency (e.g., 50kHz) to ensure that the actual reference pattern processed is clear and free of edge burrs.

[0032] Next, actual reference graphic processing can be performed. Specifically, the motion controller can generate G code (such as G01 instruction for line segment processing and G02 instruction for arc processing) based on the first primitive information, drive the XY gantry motion platform to move the laser processing head, and control the laser to emit light, so as to process the actual reference graphic (such as 4 edge corner point marks and 2 center cross lines) on the perovskite glass substrate.

[0033] In one implementation, before the step of controlling the laser system to process the actual reference graphic corresponding to the first primitive information on the target workpiece according to the first primitive information in the preset theoretical processing path, the method further includes: The geometric parameters of the theoretical processing path are obtained by analyzing the preset theoretical processing path. Based on the geometric parameters of the theoretical processing path, a set of primitive information in the preset theoretical processing path is determined; wherein, the set of primitive information includes multiple primitive information.

[0034] As an example, before controlling the laser system to process the actual reference pattern, it is necessary to first analyze the preset theoretical processing path to obtain the first primitive information and the second primitive information. The specific process is described below.

[0035] First, load and parse the DXF format file. Specifically, import the DXF format file storing the theoretical processing path into the laser system's control software (this software integrates a DXF parsing module). The software extracts all geometric parameters of the theoretical processing path by reading the "ENTITIES" segment (the core data segment of the DXF file, which records the geometric information of the primitives), including the starting coordinates (X1, Y1) and ending coordinates (X2, Y2) of the line segment, the center coordinates (X0, Y0) and radius R of the arc, and the coordinates of the corner points (X1, Y2, Y2). n Y n )wait.

[0036] Then, the set of graphic element information and the first and second graphic element information are determined. Specifically, based on the extracted geometric parameters, a "set of graphic element information" (i.e., the "set of graphic element information") is generated. This set contains all graphic element information in the theoretical processing path (such as 100 line segment graphic elements, 50 arc graphic elements, and 30 corner point graphic elements). Subsequently, according to processing requirements, a portion of the graphic elements in the set of graphic element information is selected as the "first graphic element information"—usually, feature graphic elements distributed in the edge and central areas of the perovskite glass substrate (such as 4 edge corner points and 2 central cross segments) are selected to ensure that subsequent deviation calculations can cover the entire board surface; the remaining graphic elements are used as the "second graphic element information" for subsequent actual processing after parameter adjustments.

[0037] S102: Acquire a real-time image of the actual reference graphic.

[0038] As an example, this embodiment can acquire real-time images of the actual reference graphic using an image acquisition device that has a fixed relative position to the laser processing head.

[0039] Specifically, image acquisition equipment can be deployed and synchronized first. For example, a 5-megapixel CMOS area scan camera (3.45μm pixel size, 60fps frame rate) can be used as the image acquisition device, fixed to the side of the laser processing head, ensuring that the relative position of the camera and the laser processing head remains unchanged (e.g., the angle between the camera's optical axis and the processing axis of the laser processing head is 90°, and the height from the processing surface is 200mm), to ensure that the acquired image accurately reflects the processing area. Simultaneously, hardware triggers (such as encoder triggers) are used to synchronize camera acquisition with the movement of the motion platform. That is, when the motion platform moves to the processing area corresponding to the first primitive information, the trigger sends a signal to the camera, and the camera immediately takes a picture, ensuring that the acquired real-time image completely corresponds to the position of the actual reference graphic.

[0040] Then, real-time image acquisition can be performed. For example, such as... Figure 4 As shown, the camera can continuously acquire images of the actual benchmark graphic at a frame rate of 60fps. The acquired raw images are color images (resolution 2592×1944 pixels), and the image data is transmitted to an industrial computer for further processing.

[0041] S103: Using a preset affine transformation matrix, the real-time image is converted into a target type format image.

[0042] In this embodiment, before the step of converting the real-time image into a target type format image using a preset affine transformation matrix, the method further includes: The real-time image is preprocessed to obtain a processed real-time image; The preprocessing includes at least one of the following methods: grayscale processing, Gaussian filtering denoising processing, and adaptive threshold binarization processing.

[0043] Understandably, the image processing module in an industrial computer preprocesses the original image to eliminate noise and enhance the contrast between the actual reference graphic and the substrate background. Specific preprocessing methods include at least one of the following: Grayscale conversion: Convert the color image to a grayscale image. The grayscale value of each pixel is calculated using the formula "Gray = 0.299R + 0.587G + 0.114B" (where R, G, and B are the pixel values ​​of the red, green, and blue channels of the color image, respectively), which simplifies the computation of subsequent image processing.

[0044] Gaussian filtering for noise reduction: A 5×5 Gaussian filter (standard deviation σ=1.2) is used to filter the grayscale image. The filter kernel is calculated using the formula "G (x, y) = (1 / (2πσ²))×exp (-(x²+y²) / (2σ²))" to eliminate image noise caused by ambient light interference and camera noise, making the edges of the actual reference image smoother.

[0045] Adaptive threshold binarization: A local adaptive thresholding algorithm (such as the Otsu algorithm) is used to binarize the filtered grayscale image. The threshold for each local region (such as 128) is automatically calculated. Pixels with grayscale values ​​higher than the threshold are set to white (representing the lines of the actual reference graphic) and pixels with grayscale values ​​lower than the threshold are set to black (representing the background of the perovskite glass substrate), forming a black and white binary image, which further highlights the geometric features of the actual reference graphic.

[0046] Accordingly, the step of converting the real-time image into a target type format image using a preset affine transformation matrix includes: The process utilizes a preset affine transformation matrix to convert the processed real-time image into the target type format.

[0047] In this embodiment, the preset affine transformation matrix is ​​a transformation matrix between the image coordinate system and the target type format coordinate system. Specifically, converting the real-time image into a target type format image using the preset affine transformation matrix may include the following steps: Step 1: Determine the coordinates of the pixels in the real-time image in the image coordinate system. Specifically, the Hough transform isolinear feature extraction algorithm can be used to extract the geometric features of the actual reference graphic from the real-time image. The geometric features include endpoint coordinates, center point coordinates, and tilt angle; and the coordinates of the pixels in the geometric features in the image coordinate system are then determined.

[0048] Step 2: Using the preset affine transformation matrix, transform the coordinate values ​​of the pixels in the real-time image from the image coordinate system to the coordinate values ​​in the target type format coordinate system to obtain the target type format image. The target type format is a CAD file format.

[0049] It should be noted that the preset affine transformation matrix is ​​obtained in the following way: The camera pixel coordinate system of the image acquisition device used to acquire real-time images of the actual reference graphic is used as the image coordinate system; Establish a mapping relationship between the image coordinate system and the target type format coordinate system; the mapping relationship includes the intrinsic parameter matrix of the image acquisition device, distortion parameters, and plane homography matrix; Based on the mapping relationship and the alignment results of the design coordinate system and the workpiece coordinate system of the theoretical machining path, the affine transformation matrix is ​​generated.

[0050] Understandably, to convert the preprocessed real-time image (binary image) into a target-type format image that can be compared with the first primitive information, it is necessary to first obtain the affine transformation matrix and then perform coordinate transformation. The specific process is as follows: First, obtain the image acquisition device calibration and parameters: The camera is calibrated using Zhang Zhengyou's calibration method to obtain the camera's intrinsic parameter matrix K and distortion parameter d. The intrinsic parameter matrix K is in the form of: , where f x f y These are the focal lengths (in pixels) of the camera along the X and Y axes, respectively, calculated through calibration. x =2000 pixels, f y =2000 pixels; c x c y Given the principal point coordinates of the camera (i.e., the pixel coordinates of the image center), we can calculate c. x =1296 pixels, c y =972 pixels.

[0051] The distortion parameter d includes radial distortion coefficients (k1=-0.01, k2=0.005, k3=0) and tangential distortion coefficients (p1=0.001, p2=-0.0005), used to correct distortion errors in the camera lens. Simultaneously, the planar homography matrix H_ is calculated using a planar homography algorithm to determine the homography matrix H_ between the camera pixel coordinate system (image coordinate system) and the workpiece coordinate system (the actual coordinate system of the perovskite glass substrate, unit: millimeters). W←C This matrix reflects the mapping relationship between image pixel coordinates and actual substrate coordinates.

[0052] Affine transformation matrix generation: The target type format coordinate system is the coordinate system corresponding to the CAD file format, which is consistent with the design coordinate system of the theoretical machining path (i.e., the coordinate system of the DXF format file). Through datum alignment (e.g., aligning the positioning holes of the perovskite glass substrate with the origin of the design coordinate system), the affine transformation matrix T_ between the design coordinate system and the workpiece coordinate system is obtained. W←DXF Combined with the planar homography matrix H_ obtained from A W←C The affine transformation matrix T_ between the image coordinate system (camera pixel coordinate system) and the target type format coordinate system can be derived. CAD←C The derivation formula is as follows ;in for The inverse matrix, i.e., the transformation matrix from the workpiece coordinate system to the design coordinate system. This affine transformation matrix T_ CAD←C This is the "preset affine transformation matrix", which is used for coordinate transformation of subsequent real-time images.

[0053] Target type format image conversion: Pixel coordinate extraction: The Hough transform (line feature extraction algorithm) is used to extract the geometric features of the actual reference figure (such as the endpoints of line segments and the center of arcs) from the preprocessed binary image, and the coordinate values ​​of the corresponding pixels in the image coordinate system are determined (such as the coordinates of the endpoints of line segments being (500, 300) pixels and (1500, 800) pixels).

[0054] Coordinate transformation and image generation: Substitute the extracted pixel coordinates into the affine transformation matrix T_ CAD←C Through formula (where P) C P represents the pixel coordinates in the image coordinate system. CAD The pixel coordinates are converted to coordinates corresponding to the CAD file format (e.g., (10.5, 8.2) mm, (32.1, 18.5) mm) in the target type format coordinate system. Based on the converted coordinates, an image corresponding to the actual reference drawing is generated in the CAD software interface, i.e., the "target type format image".

[0055] In addition, this embodiment can also construct a nonlinear affine transformation model to map actual feature points to a theoretical feature point space, thereby achieving precise alignment between actual and theoretical features in the high-resolution image. Specifically, the real-time image can also be converted into a target type format image using an affine transformation matrix in the following way: First, local nonlinear compensation terms are generated by interpolating the real-time image. for: Where i and n represent the identifier and number of feature points in the real-time image, respectively. Indicates the weighting coefficient; Represents radial basis functions. It is the feature point (x,y) and its corresponding control point The Euclidean distance between points is used to measure the distance relationship between points and control points, and then to calculate the compensation amount. Thin plate spline interpolation is a function used for smooth interpolation, which can fit local nonlinear deformations well.

[0056] Then, a nonlinear affine transformation model is constructed using a pre-defined affine transformation matrix, mapping the actual feature points to the theoretical feature point space as follows: in, This represents the homogeneous coordinates of the transformed feature points, which should be consistent with the theoretical feature point coordinates. This represents the affine transformation matrix, which contains parameters for basic geometric transformations such as rotation, scaling, and translation. Represents the homogeneous coordinates of actual feature points in a real-time image. These represent local nonlinear compensation terms, used to compensate for local deviations between actual and theoretical feature points.

[0057] It should be noted that, in order to determine the weighting coefficients The parameters a, b, c, d, e, and f in the affine transformation matrix can be solved by solving a system of linear equations using the correspondence between actual and theoretical feature points. Specifically, by substituting the coordinates of the actual and corresponding theoretical feature points into the transformation model, a series of equations are obtained. These equations are then solved using numerical methods such as the least squares method to determine all the unknown parameters.

[0058] By constructing such a nonlinear affine transformation model and solving for its parameters, actual feature points can be effectively mapped to the theoretical feature point space. This compensates for deviations between actual and theoretical features caused by various factors during image acquisition, such as lens distortion and workpiece installation errors, achieving high-precision alignment. The local nonlinear compensation term introduced by thin-plate spline interpolation enables the model to adapt to complex local deformations, rather than just simple linear transformations, improving its adaptability to various real-world scenarios. Subsequently, the transformed image is converted to the target image type format to eliminate geometric distortions during image acquisition, achieving high-precision alignment between the theoretical and actual graphics.

[0059] S104: Adjust the system parameters of the laser system according to the deviation value between the target type format image and the first primitive information, so as to use the adjusted laser system to process the target workpiece according to the second primitive information in the preset theoretical processing path.

[0060] It should be emphasized that during the processing of the second primitive information, the processing accuracy of the laser system is controlled within the range of ±2-10μm by the adjusted system parameters.

[0061] In this embodiment, adjusting the system parameters of the laser system based on the deviation between the target type format image and the first primitive information may include the following steps: Step a: Display the target type format image as a semi-transparent layer overlaid on the first primitive information.

[0062] In this embodiment, image overlay can be performed first. In the CAD software interface, the target type format image is overlaid as a semi-transparent layer on top of the first primitive information (originating from a DXF format file). The overlay uses an Alpha blending algorithm, and the formula is: Among them, Color final Color is the color of the superimposed pixels. CAD Color is the color of the first primitive information. target The color of the target image type is α, which is a transparency parameter that can be 0.5 to ensure that the geometric features of the two images are clearly contrasted.

[0063] Step b: Based on the overlaid target type format image and the first primitive information, determine the deviation value between the target type format image and the first primitive information. The deviation value includes at least one of translation deviation, rotation deviation, and scaling deviation.

[0064] like Figure 3 The method described above can extract the geometric features of the actual reference graphic from the target type format image, and use a sub-pixel positioning algorithm to obtain the sub-pixel coordinates of the feature points of the geometric features; the sub-pixel coordinates of the feature points are matched and calculated with the theoretical coordinates in the first primitive information to obtain at least one deviation value among translation deviation, rotation deviation and scaling deviation.

[0065] To improve the accuracy of deviation calculation, a sub-pixel localization algorithm is used to accurately locate the pixels of geometric features in the target type format image. The calculation formula of the sub-pixel localization algorithm is: x_sub = x_int + (I (x-1,y) - I (x+1,y)) / (2 (I (x+1,y) - 2 The algorithm iterates through the coordinates: I(x,y) + I(x-1,y), where x_sub is the sub-pixel coordinate of the feature point (unit: pixel), x_int is the integer pixel coordinate of the feature point (e.g., 500 pixels), I is the pixel grayscale value of the feature point (e.g., 255), x is the x-coordinate of the integer pixel coordinates of the feature point, and y is the y-coordinate of the integer pixel coordinates of the feature point. This algorithm improves the coordinate precision from "pixel level" to "sub-pixel level" (e.g., 0.1 pixels), corresponding to an actual size precision of approximately 0.345 micrometers (3.45μm / pixel × 0.1 pixel).

[0066] Next, the deviation value can be calculated. For example, the sub-pixel coordinates can be converted to coordinates in the target type format coordinate system and then matched with the theoretical coordinates of the first primitive information (using the ICP iterative nearest point algorithm) to minimize the error function. (where p) i Let q be the theoretical coordinate point set of the first primitive information. i Given the actual coordinate point set of the target type format image, R is the rotation matrix, and t is the translation vector, solve for the translation deviation (e.g., ΔX=2μm, ΔY=-1.5μm), rotation deviation (e.g., Δθ=0.01°), and scaling deviation (e.g., Δs=0.001%).

[0067] Step c: Generate compensation parameters for the laser system based on the deviation between the target type format image and the first primitive information.

[0068] As an example, a compensation field model can be constructed based on the deviation value between the target type format image and the first primitive information. The compensation field model uses thin plate splines or radial basis functions to fit the global and local deviations. Then, the correction amount of the theoretical processing path is calculated using the compensation field model, and the correction amount is used as the compensation parameter of the laser system.

[0069] As an example, based on the calculated deviation value, a compensation field model can be constructed using a thin plate spline model. The formula for this thin plate spline model is: Where F(x,y) is the correction amount of the compensation field at coordinates (x,y), and a1, a2, and a3 are global linear parameters. Here are the weighting coefficients, and U(r) is the basis function of the thin plate spline. , r>0; U(r)=0, r=0), (x i ,y i The coordinates of the deviation sampling point are shown in the figure. By fitting the deviation distribution of the entire plate surface through this model, the correction amount (i.e., compensation parameter) of each processing point in the theoretical processing path is calculated. For example, the endpoint coordinates (50.000mm, 30.000mm) of a certain line segment in the second primitive information are corrected to (50.002mm, 29.9985mm).

[0070] Step d: Adjust the system parameters of the laser system using the compensation parameters.

[0071] In this embodiment, the compensation parameters can be injected into the motion controller of the laser system to adjust the machining trajectory parameters in the machine tool coordinate system corresponding to the laser system.

[0072] As an example, the generated compensation parameters can be injected into the motion controller of the laser system. The controller can adjust the system parameters of the laser system by updating the processing trajectory parameters (such as correcting the coordinate values ​​in the G-code). Specifically, it can adjust the motion trajectory of the XY gantry motion platform so that the actual movement path of the laser processing head is consistent with the corrected theoretical processing path, thus ensuring the accuracy of subsequent processing.

[0073] Next, an example will be used to illustrate how the adjusted laser system can process the target workpiece according to the second primitive information in the preset theoretical processing path.

[0074] For example, after the system parameters of the laser system are adjusted, the perovskite glass substrate is actually processed using the adjusted laser system based on the second primitive information. The specific process is as follows: Processing parameters confirmation: Reconfirm the processing parameters of the laser system (laser power, processing speed, pulse frequency), and check whether the compensation parameters in the motion controller have been correctly loaded.

[0075] Second-stage primitive information processing: The motion controller generates corrected G-code (incorporating compensation parameters) based on the second-stage primitive information (such as circuit patterns and cutting trajectories on the substrate), driving the XY gantry motion platform to work in conjunction with the laser processing head to process patterns that meet design requirements on the perovskite glass substrate. Since the compensation parameters have corrected the previous processing deviations, the processing accuracy of this step can be controlled within ±2-10μm, meeting the high-precision processing requirements of large-size perovskite glass substrates.

[0076] In one implementation, the method further includes: If the deviation between the target type format image and the first primitive information is greater than a preset threshold, an alarm will be triggered.

[0077] As an example, a deviation threshold is preset (e.g., ±10μm). If the calculated deviation value is greater than the threshold (e.g., ΔX=12μm), the alarm module of the industrial computer will immediately issue an audible and visual alarm and pause the laser system's processing flow. After the cause of the deviation (e.g., tooling positioning offset, camera calibration error) is manually checked and resolved, the above steps will be repeated until the deviation value meets the threshold requirement.

[0078] It should also be noted that, to verify the effectiveness of this method, a 2.4 m × 1.2 m perovskite glass substrate was selected as the target workpiece, and the above steps were followed for processing and verification. The first element information selects four corner points of the substrate (coordinates are (10mm, 10mm), (2390mm, 10mm), (2390mm, 1190mm), (10mm, 1190mm)) and two central cross lines (X-axis line segment: (1200mm, 600mm) - (1200mm, 600mm), Y-axis line segment: (1200mm, 600mm) - (1200mm, 600mm)).

[0079] After processing the actual reference graphic, the acquired real-time image undergoes preprocessing and affine transformation to generate a target type format image. Through sub-pixel localization and ICP algorithm calculations, the translational deviation ΔX = 3μm, ΔY = -2μm, and rotational deviation Δθ = 0.008° are obtained, all less than the preset threshold ±10μm. Specifically, the formula for the ICP (Iterative Closest Point) algorithm is: E = Σ ||R·p_i + t - q_i||², where p_i is the design point set (i.e., the first primitive information), q_i is the measured point set (i.e., the target type format image), R is the rotation matrix, t is the translation vector, and E is the deviation value between the target type format image and the first primitive information.

[0080] Based on the deviation value, a thin plate spline compensation field model is constructed to generate compensation parameters for the second primitive information. After adjusting the laser system parameters, the circuit pattern on the substrate is processed. After processing, the geometric error of the entire plate surface is measured by a laser interferometer, which is within the range of ±2-8μm, meeting the processing accuracy requirements of perovskite glass substrates.

[0081] In summary, this laser processing method achieves high-precision laser processing of perovskite glass substrates through theoretical path analysis, real-time image acquisition and conversion, deviation calculation and parameter adjustment. It solves the problems of large deviation and low efficiency in traditional processing and has significant practicality and engineering value.

[0082] As can be seen from the above technical solution, the method provided in this application can first control the laser system to process the actual reference graphic based on the first primitive information of the preset theoretical processing path, and then acquire the real-time image of the graphic and convert it into a target type format image through a preset affine transformation matrix. This allows the target type format image to be directly compared with the first primitive information to obtain the deviation value. Based on this deviation value, the system parameters of the laser system are adjusted. Subsequently, when the adjusted laser system processes the target workpiece based on the second primitive information of the theoretical processing path, it can effectively compensate for the processing deviation caused by factors such as laser system axis calibration, axis adjustment, guide rail installation, and tooling flatness. The entire process does not require manual sampling and manual parameter adjustment afterward, realizing real-time detection of processing deviation and targeted adjustment of laser system parameters, which greatly improves the accuracy and efficiency of target workpiece processing. Especially for large-sized target workpieces, it can avoid the problem of inaccurate deviation measurement caused by sparse measurement points and complex workpiece handling, ensuring processing consistency.

[0083] Thus, this embodiment, combined with a specific application scenario, implements the laser processing method. It should be noted that the above scenario is merely exemplary and does not constitute a limitation on the method provided in this application. The method provided in this application can be extended to other laser processing methods based on the same principle.

[0084] like Figure 5 The image shows a specific embodiment of the laser processing system described in this application. The system described in this embodiment is the physical system used to perform the method described in the above embodiments. Its technical solution is essentially the same as that of the above embodiments, and the corresponding descriptions in the above embodiments are also applicable to this embodiment. In this embodiment, the system includes: The first subsystem 501 is used to control the laser system to process the actual reference graphic corresponding to the first graphic element information on the target workpiece according to the first graphic element information in the preset theoretical processing path. The second subsystem 502 is used to acquire real-time images of the actual reference graphic; The third subsystem 503 is used to convert the real-time image into a target type format image using a preset affine transformation matrix; The fourth subsystem 504 is used to adjust the system parameters of the laser system according to the deviation value between the target type format image and the first primitive information, so as to use the adjusted laser system to process the target workpiece according to the second primitive information in the preset theoretical processing path.

[0085] Optionally, the preset theoretical processing path is a graphic path in a DXF format file, and the first primitive information includes coordinate parameters of at least one geometric feature among line segments, arcs, and corner points.

[0086] Optionally, before the step of controlling the laser system to process the actual reference graphic corresponding to the first primitive information on the target workpiece according to the first primitive information in the preset theoretical processing path, the method further includes: The geometric parameters of the theoretical processing path are obtained by analyzing the preset theoretical processing path. Based on the geometric parameters of the theoretical processing path, a set of primitive information in the preset theoretical processing path is determined; wherein, the set of primitive information includes multiple primitive information.

[0087] Optionally, acquiring real-time images of the actual reference graphic includes: Real-time images of the actual reference graphic are acquired using an image acquisition device that has a fixed relative position to the laser processing head.

[0088] Optionally, before the step of converting the real-time image into a target type format image using a preset affine transformation matrix, the method further includes: The real-time image is preprocessed to obtain a processed real-time image; The preprocessing includes at least one of the following methods: grayscale processing, Gaussian filtering denoising processing, and adaptive threshold binarization processing; Accordingly, the step of converting the real-time image into a target type format image using a preset affine transformation matrix includes: The process utilizes a preset affine transformation matrix to convert the processed real-time image into the target type format.

[0089] Optionally, the preset affine transformation matrix is ​​a transformation matrix between the image coordinate system and the target type format coordinate system; the step of converting the real-time image into a target type format image using the preset affine transformation matrix includes: Determine the coordinates of the pixels in the real-time image in the image coordinate system; Using the preset affine transformation matrix, the coordinate values ​​of the pixels in the real-time image are transformed from the image coordinate system to the coordinate values ​​in the target type format coordinate system to obtain the target type format image; The target type format is a CAD file format.

[0090] Optionally, determining the coordinates of a pixel in the real-time image within the image coordinate system includes: Using the Hough transform isolinear feature extraction algorithm, the geometric features of the actual reference figure are extracted from the real-time image. The geometric features include endpoint coordinates, center point coordinates, and tilt angle. Determine the coordinate values ​​of the pixels in the geometric features in the image coordinate system.

[0091] Optionally, the preset affine transformation matrix is ​​obtained in the following way: The camera pixel coordinate system of the image acquisition device used to acquire real-time images of the actual reference graphic is used as the image coordinate system; Establish a mapping relationship between the image coordinate system and the target type format coordinate system; the mapping relationship includes the intrinsic parameter matrix of the image acquisition device, distortion parameters, and plane homography matrix; Based on the mapping relationship and the alignment results of the design coordinate system and the workpiece coordinate system of the theoretical machining path, the affine transformation matrix is ​​generated.

[0092] Optionally, adjusting the system parameters of the laser system based on the deviation between the target type format image and the first primitive information includes: The target type format image is overlaid on the first primitive information as a semi-transparent layer; Based on the overlaid target type format image and the first primitive information, a deviation value between the target type format image and the first primitive information is determined; wherein, the deviation value includes at least one of translation deviation, rotation deviation, and scaling deviation; The compensation parameters for the laser system are generated based on the deviation between the target type format image and the first primitive information. The system parameters of the laser system are adjusted using the compensation parameters.

[0093] Optionally, determining the deviation value between the target type format image and the first primitive information based on the overlaid target type format image and the first primitive information includes: Geometric features of the actual reference graphic are extracted from the target type format image, and the sub-pixel coordinates of the feature points of the geometric features are obtained by using a sub-pixel positioning algorithm. The sub-pixel coordinates of the feature points are matched and calculated with the theoretical coordinates in the first primitive information to obtain at least one deviation value among translation deviation, rotation deviation and scaling deviation.

[0094] Optionally, the calculation formula for the sub-pixel localization algorithm is: x_sub = x_int + (I(x-1,y) - I(x+1,y)) / (2 (I (x+1,y) - 2 I (x,y) + I (x-1,y))); where x_sub is the subpixel coordinate of the feature point, x_int is the integer pixel coordinate of the feature point, I is the pixel gray value of the feature point, x is the x-coordinate of the integer pixel coordinate of the feature point, and y is the y-coordinate of the integer pixel coordinate of the feature point.

[0095] Optionally, generating compensation parameters for the laser system based on the deviation value between the target type format image and the first primitive information includes: A compensation field model is constructed based on the deviation value between the target type format image and the first primitive information. The compensation field model uses thin plate splines or radial basis functions to fit the global and local deviations. The correction amount of the theoretical processing path is calculated using the compensation field model, and the correction amount is used as the compensation parameter of the laser system.

[0096] Optionally, adjusting the system parameters of the laser system using the compensation parameters includes: The compensation parameters are injected into the motion controller of the laser system to adjust the machining trajectory parameters in the machine tool coordinate system corresponding to the laser system.

[0097] Optionally, the target workpiece is a perovskite glass substrate; during the processing corresponding to the second primitive information, the processing accuracy of the laser system is controlled within the range of ±2-10μm by the adjusted system parameters.

[0098] Optionally, the system also includes the following functions: If the deviation between the target type format image and the first primitive information is greater than a preset threshold, an alarm will be triggered.

[0099] Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. At the hardware level, the electronic device includes a processor, and optionally also includes an internal bus, a network interface, and a memory. The memory may include RAM, such as high-speed random-access memory (RAM), or non-volatile memory, such as at least one disk storage device. Of course, the electronic device may also include other hardware required for other services.

[0100] The processor, network interface, and memory can be interconnected via an internal bus, which can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus, etc. This bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 6 The symbol is represented by a single double-headed arrow, but this does not mean that there is only one bus or one type of bus.

[0101] Memory is used to store instructions for execution. Specifically, instructions for execution are computer programs that can be executed. Memory can include main memory and non-volatile memory, and it provides the processor with execution instructions and data.

[0102] In one possible implementation, the processor reads the corresponding execution instructions from non-volatile memory into main memory and then executes them. Alternatively, it may obtain the corresponding execution instructions from other devices to form a laser processing system at the logical level. The processor executes the execution instructions stored in the memory to implement the laser processing method provided in any embodiment of this application.

[0103] The above is as stated in this application. Figure 1 The laser processing system provided in the illustrated embodiment can be applied to or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method can be completed by integrated logic circuits in the processor's hardware or by instructions in software form. The processor can be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor can be a microprocessor or any conventional processor.

[0104] The steps of the method disclosed in the embodiments of this application can be directly manifested as being executed by a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software modules can reside in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. This storage medium is located in memory, and the processor reads information from the memory and, in conjunction with its hardware, completes the steps of the above method.

[0105] This application also proposes a readable medium that stores execution instructions. When the stored execution instructions are executed by the processor of an electronic device, the electronic device can execute the laser processing method provided in any embodiment of this application, and specifically be used to execute the method described above for data query.

[0106] The electronic devices described in the foregoing embodiments may be computers.

[0107] Those skilled in the art will understand that the embodiments of this application can be provided as methods or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or a combination of software and hardware.

[0108] The various embodiments in this application are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the system embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0109] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0110] The above description is merely an embodiment of this application and is not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A laser processing method, characterized in that, The method includes: Based on the first primitive information in the preset theoretical processing path, the laser system is controlled to process the actual reference graphic corresponding to the first primitive information on the target workpiece. Acquire real-time images of the actual reference graphic; The real-time image is converted into a target type format image using a preset affine transformation matrix; Based on the deviation between the target type format image and the first primitive information, the system parameters of the laser system are adjusted so that the adjusted laser system can process the target workpiece according to the second primitive information in the preset theoretical processing path.

2. The laser processing method according to claim 1, characterized in that, The preset theoretical processing path is a graphic path in a DXF format file, and the first primitive information includes the coordinate parameters of at least one geometric feature among line segments, arcs, and corner points.

3. The laser processing method according to claim 1, characterized in that, Before the step of controlling the laser system to process the actual reference graphic corresponding to the first primitive information on the target workpiece according to the first primitive information in the preset theoretical processing path, the method further includes: The geometric parameters of the theoretical processing path are obtained by analyzing the preset theoretical processing path. Based on the geometric parameters of the theoretical processing path, a set of primitive information in the preset theoretical processing path is determined; wherein, the set of primitive information includes multiple primitive information.

4. The laser processing method according to claim 1, characterized in that, The acquisition of real-time images of the actual reference graphic includes: Real-time images of the actual reference graphic are acquired using an image acquisition device that has a fixed relative position to the laser processing head.

5. The laser processing method according to claim 1, characterized in that, Before the step of converting the real-time image into a target type format image using a preset affine transformation matrix, the method further includes: The real-time image is preprocessed to obtain a processed real-time image; The preprocessing includes at least one of the following methods: grayscale processing, Gaussian filtering denoising processing, and adaptive threshold binarization processing; Accordingly, the step of converting the real-time image into a target type format image using a preset affine transformation matrix includes: The process utilizes a preset affine transformation matrix to convert the processed real-time image into the target type format.

6. The laser processing method according to claim 1, characterized in that, The preset affine transformation matrix is ​​the transformation matrix between the image coordinate system and the target type format coordinate system; Using a preset affine transformation matrix, the real-time image is converted into a target type format image, including: Determine the coordinates of the pixels in the real-time image in the image coordinate system; Using the preset affine transformation matrix, the coordinate values ​​of the pixels in the real-time image are transformed from the image coordinate system to the coordinate values ​​in the target type format coordinate system to obtain the target type format image; The target type format is a CAD file format.

7. The laser processing method according to claim 6, characterized in that, Determining the coordinates of pixels in the real-time image in the image coordinate system includes: Using the Hough transform line feature extraction algorithm, the geometric features of the actual reference figure are extracted from the real-time image. The geometric features include endpoint coordinates, center point coordinates, and tilt angle. Determine the coordinate values ​​of the pixels in the geometric features in the image coordinate system.

8. The laser processing method according to claim 1 or 6, characterized in that, The preset affine transformation matrix is ​​obtained in the following way: The camera pixel coordinate system of the image acquisition device used to acquire real-time images of the actual reference graphic is used as the image coordinate system; Establish the mapping relationship between the image coordinate system and the target type format coordinate system; The mapping relationship includes the intrinsic parameter matrix of the image acquisition device, distortion parameters, and plane homography matrix; Based on the mapping relationship, and combined with the alignment results of the design coordinate system and the workpiece coordinate system of the theoretical machining path, the affine transformation matrix is ​​generated.

9. The laser processing method according to claim 1, characterized in that, The step of adjusting the system parameters of the laser system based on the deviation value between the target type format image and the first primitive information includes: The target type format image is overlaid on the first primitive information as a semi-transparent layer; Based on the overlaid target type format image and the first primitive information, a deviation value between the target type format image and the first primitive information is determined; wherein, the deviation value includes at least one of translation deviation, rotation deviation, and scaling deviation; The compensation parameters for the laser system are generated based on the deviation between the target type format image and the first primitive information. The system parameters of the laser system are adjusted using the compensation parameters.

10. The laser processing method according to claim 9, characterized in that, The step of determining the deviation value between the target type format image and the first primitive information based on the superimposed target type format image and the first primitive information includes: Geometric features of the actual reference graphic are extracted from the target type format image, and the sub-pixel coordinates of the feature points of the geometric features are obtained by using a sub-pixel positioning algorithm. The sub-pixel coordinates of the feature points are matched and calculated with the theoretical coordinates in the first primitive information to obtain at least one deviation value among translation deviation, rotation deviation and scaling deviation.

11. The laser processing method according to claim 10, characterized in that, The calculation formula for the sub-pixel localization algorithm is: x_sub = x_int + (I (x-1,y) - I (x+1,y)) / (2 (I (x+1,y) - 2 I (x,y) + I(x-1,y))); where x_sub is the subpixel coordinate of the feature point, x_int is the integer pixel coordinate of the feature point, I is the pixel gray value of the feature point, x is the x-coordinate of the integer pixel coordinate of the feature point, and y is the y-coordinate of the integer pixel coordinate of the feature point.

12. The laser processing method according to claim 9, characterized in that, The step of generating compensation parameters for the laser system based on the deviation value between the target type format image and the first primitive information includes: A compensation field model is constructed based on the deviation value between the target type format image and the first primitive information. The compensation field model uses thin plate splines or radial basis functions to fit the global and local deviations. The correction amount of the theoretical processing path is calculated using the compensation field model, and the correction amount is used as the compensation parameter of the laser system.

13. The laser processing method according to claim 12, characterized in that, The adjustment of the system parameters of the laser system using the compensation parameters includes: The compensation parameters are injected into the motion controller of the laser system to adjust the machining trajectory parameters in the machine tool coordinate system corresponding to the laser system.

14. The laser processing method according to claim 1, characterized in that, The target workpiece is a perovskite glass substrate; during the processing corresponding to the second primitive information, the processing accuracy of the laser system is controlled within the range of ±2-10μm by the adjusted system parameters.

15. A laser processing system, characterized in that, The system includes: The first subsystem is used to control the laser system to process the actual reference graphic corresponding to the first primitive information on the target workpiece according to the first primitive information in the preset theoretical processing path. The second subsystem is used to acquire real-time images of the actual reference graphic; The third subsystem is used to convert the real-time image into a target type format image using a preset affine transformation matrix; The fourth subsystem is used to adjust the system parameters of the laser system according to the deviation value between the target type format image and the first primitive information, so as to use the adjusted laser system to process the target workpiece according to the second primitive information in the preset theoretical processing path.

Images