Hard and brittle material processing edge breakage detection and volume calculation method based on three-dimensional point cloud
Through the three-dimensional point cloud-based method, the processing edge collapse of hard brittle materials is quickly and accurately detected, which solves the problem of the inability to accurately quantify edge collapse damage in the existing technology, and provides more accurate three-dimensional information and efficient detection methods.
Patent Information
- Application Number
- CN202510381216.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-03-28
- Publication Date
- 2025-07-29
AI Technical Summary
The prior art is difficult to fully reflect the three-dimensional spatial characteristics of hard brittle materials processing edge collapse. Especially in the case of complex shapes or irregular surfaces, the two-dimensional measurement accuracy is insufficient, and the actual damage degree of edge collapse cannot be accurately quantified.
Using a three-dimensional point cloud-based method, the original point cloud data of the machining edge morphology of hard brittle material workpieces is obtained, the point cloud is constructed, the rotation reference plane is aligned with the coordinate system, threshold segmentation and triangulation are performed, and the measured volume of the collapsed area is calculated by combining the tetrahedral volume method, and the ideal geometric enclosure box parameters are obtained to calculate the actual collapsed volume.
It realizes rapid and accurate detection of edge damage, provides more accurate three-dimensional information, simple process and low computational complexity, is suitable for scientific research and actual production, and improves the applicability and accuracy of detection.
Smart Images
Figure CN120387984A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of defect detection, and particularly to a method for detecting chipping and calculating volume of hard and brittle materials based on three-dimensional point cloud during processing. Background Art
[0002] Chipping is one of the processing damages easily generated during the processing of hard and brittle materials. The generation of chipping will lead to a significant decrease in the processing accuracy of products, affecting the service life and comprehensive performance of products. At the same time, chipping may also lead to an increase in the rejection rate, thereby increasing production costs and affecting production efficiency. In order to suppress the generation of chipping in subsequent processing, it is necessary to detect and quantitatively characterize the chipping situation after processing, so as to optimize the processing technology and reduce the generation of chipping damage.
[0003] Currently, the detection and quantification of chipping mainly rely on two-dimensional image processing technology, and usually quantitative analysis is carried out by measuring two-dimensional parameters such as the length, width, and depth of chipping. However, this method is difficult to comprehensively reflect the three-dimensional spatial characteristics of chipping. Especially in the case of complex shapes or irregular surfaces, the two-dimensional measurement accuracy is insufficient, and the actual damage degree of chipping cannot be accurately quantified.
[0004] Therefore, the existing detection and quantification methods have great limitations, and it is necessary to provide a method for detecting chipping and calculating volume of hard and brittle materials based on three-dimensional point cloud to solve the above problems. Summary of the Invention
[0005] The present invention provides a method for detecting chipping and calculating volume of hard and brittle materials based on three-dimensional point cloud to solve the problem that the existing methods are difficult to comprehensively reflect the three-dimensional spatial characteristics of chipping. Especially in the case of complex shapes or irregular surfaces, the two-dimensional measurement accuracy is insufficient, and the actual damage degree of chipping cannot be accurately quantified.
[0006] The method for detecting chipping and calculating volume of hard and brittle materials based on three-dimensional point cloud of the present invention adopts the following technical solutions, including: Obtain the original point cloud data of the processed edge morphology of the hard and brittle material workpiece, and construct a point cloud based on the original point cloud data; Fit the processed surface of the hard and brittle material workpiece based on the point cloud, and use the fitted processed surface as the reference plane; Obtain the normal vector of the reference plane, construct a first rotation matrix based on the normal vector of the reference plane, rotate the point cloud based on the first rotation matrix so that the reference plane is aligned with the Z-axis of the coordinate system where the point cloud is located, and obtain the first point cloud; Fit a straight line with a preset number of points with the smallest Z-axis values in the first point cloud, construct a second rotation matrix based on the direction vector of the straight line, rotate the first point cloud based on the second rotation matrix so that the straight line is aligned with the Y-axis of the coordinate system where the point cloud is located, and obtain the target point cloud; Perform threshold segmentation on the machined surface of the hard and brittle material workpiece based on the target point cloud to obtain the chipping area; triangulate the point cloud in the chipping area in three-dimensional space, and obtain the measured volume of the chipping area through the tetrahedron integration method; Obtain the parameters of the ideal geometric body bounding box of the edge of the hard and brittle material workpiece, and use the bounding box volume as the theoretical volume of the chipping area; According to the theoretical volume and the measured volume corresponding to the chipping area, obtain the actual chipping volume of the hard and brittle material workpiece.
[0007] Preferably, the step of obtaining the original point cloud data of the machined edge morphology of the hard and brittle material is: using a three-dimensional measurement device to scan the machined edge morphology of the hard and brittle material to obtain the original point cloud data.
[0008] Preferably, based on the point cloud, the random sample consensus algorithm is used to fit the machined surface of the hard and brittle material workpiece.
[0009] Preferably, the steps of constructing the first rotation matrix based on the normal vector of the reference plane are: Normalize the normal vector of the reference plane to obtain the target normal vector; Obtain the first rotation angle according to the target normal vector and the unit vector of the Z-axis of the coordinate system where the point cloud is located; Based on the rotation angle and using the Rodriguez formula to construct the first rotation matrix.
[0010] Preferably, the steps of fitting a straight line with a preset number of points with the smallest Z-axis value in the first point cloud are: Traverse all data points in the first point cloud and find a preset number of points with the smallest Z-axis value in the first point cloud; Merge a preset number of points with the smallest Z-axis value into a new point cloud, and perform principal component analysis on the new point cloud to determine the principal component direction; Determine the straight line based on the principal component direction and a preset number of points with the smallest Z-axis value.
[0011] Preferably, the steps of constructing the second rotation matrix based on the direction vector of the straight line are: Normalize the direction vector of the straight line to obtain the target direction vector; Obtain the second rotation angle according to the target direction vector and the unit vector of the Y-axis of the coordinate system where the point cloud is located; Based on the second rotation angle and using the Rodriguez formula to construct the second rotation matrix.
[0012] Preferably, the steps of performing threshold segmentation on the machined surface of the hard and brittle material workpiece based on the target point cloud to obtain the chipping area are: Generate a density distribution histogram of the target point cloud along the X-axis direction of the original point cloud; Based on the density distribution histogram of the target point cloud, and use the Otsu algorithm to determine the optimal segmentation threshold; Based on the optimal segmentation threshold, perform threshold segmentation on the machined surface of the hard and brittle material workpiece to obtain the chipping area and the normal machined surface.
[0013] Preferably, the steps of triangulating the point cloud in the chipping area in three-dimensional space and obtaining the measured volume of the chipping area by the tetrahedron integration method are as follows: Project the data points of the point cloud in the chipping area onto the XOY plane of the coordinate system where the original point cloud is located, and generate a triangular mesh; Construct a three-dimensional pyramid corresponding to each triangular area in the triangular mesh, and obtain the volume of the three-dimensional pyramid; Take the sum of the volumes of all three-dimensional pyramids as the measured volume of the chipping area.
[0014] Preferably, take the sum of the volumes of all three-dimensional pyramids as the measured volume of the chipping area.
[0015] Preferably, the steps of obtaining the parameters of the bounding box of the ideal geometric body at the edge of the hard and brittle material workpiece are as follows: The bounding box parameters include: the length, width, and height of the bounding box; Obtain the maximum length value and the minimum length value corresponding to the X, Y, and Z directions of the chipping area in the coordinate system where the original point cloud is located; Take the difference between the maximum length value and the minimum length value corresponding to the X direction as the length of the bounding box; Take the difference between the maximum length value and the minimum length value corresponding to the Y direction as the width of the bounding box; Take the difference between the maximum length value and the minimum length value corresponding to the Z direction as the height of the bounding box.
[0016] The beneficial effects of the present invention are: The present invention can quickly and accurately detect whether there is chipping damage according to the three-dimensional topography at the edge of the hard and brittle material flat workpiece, calculate the actual chipping volume, and clarify the damage degree through the actual chipping volume. The implementation process of this method is simple, does not adopt complex graphics methods, only uses simple mathematical methods for operation, and has a low computational complexity; as a general method, it does not need to set exclusive parameters for operation according to different material properties, thereby improving the applicability of this method; compared with traditional two-dimensional metrological characterization, it provides more accurate and rich three-dimensional information, so it is more suitable for scientific research and actual production sites. Description of the Drawings
[0017] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.
[0018] Figure 1 It is a flowchart of a method for detecting chipping and calculating volume in the processing of hard and brittle materials based on 3D point cloud according to the present invention; Figure 2 It is a 3D point cloud map of the edge of a hard and brittle material workpiece and the fitted normal processing surface in an embodiment of the present invention; Figure 3 It is a schematic diagram of chipping at the edge and the bounding box for this edge in an embodiment of the present invention. Specific embodiments
[0019] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention.
[0020] An embodiment of a method for detecting chipping and calculating volume in the processing of hard and brittle materials based on 3D point cloud according to the present invention. This embodiment is for program development in a Python 3.7 development environment running on a Windows 11 system. The program runs on a laptop computer, as Figure 1 shown. Specifically, this embodiment includes: S1. Obtain the original point cloud data and construct the point cloud; Specifically, obtain the original point cloud data of the machining edge morphology of the hard and brittle material workpiece, and construct the point cloud based on the original point cloud data.
[0021] Exemplarily, in a specific embodiment, the step of obtaining the original point cloud data of the machining edge morphology of the hard and brittle material workpiece is: use a 3D measurement device (light field camera) to scan the machining edge morphology of the hard and brittle material to obtain the original point cloud data, and save the original point cloud data in ply format.
[0022] Exemplarily, in a specific embodiment, the step of constructing the point cloud based on the original point cloud data is: read the file of the original point cloud data, call the open3d and numpy toolkits in python, reconstruct the point cloud in the program, and store the point cloud coordinate point data in the program to obtain the constructed point cloud.
[0023] S2. Determine the reference plane and obtain the rotated target point cloud; Specifically, in step 21, the machined surface of the hard and brittle material workpiece is fitted based on the point cloud, and the fitted machined surface is used as the reference plane; in step 22, the normal vector of the reference plane is obtained, the first rotation matrix is constructed based on the normal vector of the reference plane, the point cloud is rotated based on the first rotation matrix to align the reference plane with the Z-axis of the coordinate system where the point cloud is located, and the first point cloud is obtained; in step 23, a preset number of points with the smallest Z-axis values in the first point cloud are fitted into a straight line, the second rotation matrix is constructed based on the direction vector of the straight line, and the first point cloud is rotated based on the second rotation matrix to align the straight line with the Y-axis of the coordinate system where the point cloud is located, and the target point cloud is obtained.
[0024] Exemplarily, in a specific embodiment, step 21, the step of fitting the machined surface of the hard and brittle material workpiece based on the point cloud and using the fitted machined surface as the reference plane is: fitting the machined surface of the hard and brittle material workpiece based on the point cloud and using the random sample consensus algorithm, where, as Figure 2 shown, the expression of the plane equation is:
[0025] In the formula, is the x coordinate component of the normal vector of the plane to be fitted; is the y coordinate component of the normal vector of the plane to be fitted; is the z coordinate component of the normal vector of the plane to be fitted; is the constant term describing the position of the plane to be fitted.
[0026] Step 22, the step of obtaining the normal vector of the reference plane, constructing the first rotation matrix based on the normal vector of the reference plane, rotating the point cloud based on the first rotation matrix to align the reference plane with the Z-axis of the coordinate system where the point cloud is located, and obtaining the first point cloud is: Exemplarily, in a specific embodiment, the step of obtaining the normal vector of the reference plane is: based on the parameters , , and , obtain the normal vector of the reference plane.
[0027] Exemplarily, in a specific embodiment, the step of constructing the first rotation matrix based on the normal vector of the reference plane is: normalizing the normal vector of the reference plane to obtain the target normal vector; obtaining the first rotation angle according to the target normal vector and the unit vector of the Z-axis of the coordinate system where the point cloud is located; constructing the first rotation matrix based on the rotation angle and using the Rodriguez formula; the target normal vector is expressed as:
[0028] In the formula, is the x - coordinate component of the normal vector of the plane to be fitted; is the y - coordinate component of the normal vector of the plane to be fitted; is the z - coordinate component of the normal vector of the plane to be fitted; is the constant term describing the position of the plane to be fitted, is the normal vector of the reference plane.
[0029] Among them, the first rotation angle has the following expression:
[0030] In the formula, represents the unit vector of the Z - axis of the coordinate system where the point cloud is located; Among them, the first rotation matrix has the following expression:
[0031] In the formula, is the cross - product matrix of the normal vector of the reference plane; is the identity matrix; is the rotation angle.
[0032] Step 23: The steps of fitting a preset number of points with the minimum Z - axis values in the first point cloud into a straight line, constructing a second rotation matrix based on the direction vector of the straight line, rotating the first point cloud based on the second rotation matrix so that the straight line is aligned with the Y - axis of the coordinate system where the point cloud is located, and obtaining the target point cloud are as follows: Exemplarily, in a specific embodiment, the steps of fitting a preset number of points with the minimum Z - axis values in the first point cloud into a straight line are as follows: Traverse all data points in the first point cloud, find a preset number of points with the minimum Z - axis values in the first point cloud. In this embodiment, the preset number is 6, that is, find 6 points with the minimum Z - axis values; Combine the 6 points with the minimum Z - axis values into a new point cloud, perform principal component analysis on the new point cloud using the principal component analysis method (PCA) to determine the principal component direction; Find the starting point and ending point of the straight line from the 6 points with the minimum Z - axis values according to the principal component direction, and determine the straight line.
[0033] Exemplarily, in a specific embodiment, the steps of constructing a second rotation matrix based on the direction vector of the straight line are as follows: Normalize the direction vector of the straight line to obtain the target direction vector; Obtain the second rotation angle according to the target direction vector and the unit vector of the Y - axis of the coordinate system where the point cloud is located; Construct the second rotation matrix based on the second rotation angle and using Rodrigues' formula, that is, the second rotation angle is the product of the unit vector of the Y - axis of the coordinate system where the point cloud is located and the target direction vector. Among them, the second rotation matrix The expression of
[0034] In the formula, is the cross - product matrix of the direction vector of the straight line; is the identity matrix; is the second rotation angle; is the first rotation matrix.
[0035] Thus, the rotated target point cloud can be obtained.
[0036] S3. Obtain the measured volume of the chipping area; Specifically, perform threshold segmentation on the target point cloud to obtain the chipping area; triangulate the point cloud of the chipping area in three - dimensional space, and obtain the measured volume of the chipping area through tetrahedron integration method.
[0037] Exemplarily, in a specific embodiment, the steps of performing threshold segmentation on the machining surface of the hard - brittle material workpiece based on the target point cloud to obtain the chipping area point cloud are as follows: call the histogram function in numpy to generate a point cloud density distribution histogram along the X - axis direction of the original point cloud in the target point cloud; based on the density distribution histogram of the target point cloud, and use the Otsu algorithm to determine the optimal segmentation threshold; perform threshold segmentation on the machining surface of the hard - brittle material workpiece based on the optimal segmentation threshold to obtain the chipping area and the normal machining surface.
[0038] Among them, the threshold for dividing the chipping area and the normal machining surface in the X - direction has the following calculation formula:
[0039] Among them, is the maximum value of the target point cloud in the X - direction; is the optimal segmentation threshold determined by the Otsu algorithm:
[0040] Among them, is the between - class variance, which is calculated by traversing the gray levels of the histogram.
[0041] It should be noted that in this embodiment, the size of the three - dimensional point cloud obtained by the sample used is 8 mm in length (Y - direction), 6 mm in width (X - direction), and 1 mm in height (Z - direction). The relative position of the boundary between the chipping area and the normal machining surface relative to the outermost edge of the chipping is 0.814 mm. Thus, the chipping area and the normal machining surface are segmented. At the same time, perform voxel filtering on the point cloud of the segmented chipping area to eliminate isolated noise points, and obtain the chipping area point cloud for calculating the measured volume.
[0042] Exemplarily, in a specific embodiment, the steps of triangulating the point cloud of the chipping edge region in three-dimensional space and obtaining the measured volume of the chipping edge region by the tetrahedron integration method are as follows: project the data points of the point cloud of the chipping edge region onto the XOY plane of the coordinate system where the original point cloud is located, and generate a triangular mesh (i.e., perform two-dimensional Delaunay triangulation on the point cloud of the chipping edge region in the XOY plane and generate a triangular mesh by projection in the XOY plane); construct a three-dimensional pyramid corresponding to each triangular region in the triangular mesh, and obtain the volume of the three-dimensional pyramid; take the sum of the volumes of all the three-dimensional pyramids as the measured volume of the chipping edge region. Among them, the measured volume of the chipping edge region calculated in this example is 2.16685 mm 3 。
[0043] Among them, the three-dimensional pyramid The volume calculation formula is:
[0044] Among them, is the area of the triangle at the bottom of the three-dimensional pyramid, 、 、 are the height differences from the vertex to the projection plane; The measured volume is:
[0045] In the formula, is the number of triangular regions in the triangular mesh.
[0046] S4. Obtain the theoretical volume of the chipping edge region; Specifically, obtain the parameters of the bounding box of the ideal geometric body at the edge of the hard and brittle material workpiece, and take the volume of the bounding box as the theoretical volume of the chipping edge region.
[0047] Exemplarily, in a specific embodiment, the steps of obtaining the parameters of the bounding box of the ideal geometric body at the edge of the hard and brittle material workpiece are as follows: the bounding box parameters include: the length, width, and height of the bounding box; obtain the maximum length value and the minimum length value corresponding to the X, Y, and Z directions of the chipping edge region in the coordinate system where the original point cloud is located; take the difference between the maximum length value and the minimum length value corresponding to the X direction as the length of the bounding box; take the difference between the maximum length value and the minimum length value corresponding to the Y direction as the width of the bounding box; take the difference between the maximum length value and the minimum length value corresponding to the Z direction as the height of the bounding box.
[0048] Among them, the maximum length value and the minimum length value corresponding to the X, Y, and Z directions of the chipping edge region in the coordinate system of the point cloud are respectively 、 、 、 , , , and construct a bounding box accordingly, as Figure 3 shown, and calculate the length , width , and height of:
[0049]
[0050]
[0051] Exemplarily, in a specific embodiment, the volume of the bounding box (the theoretical volume of the chipping area ) is: , and the theoretical volume of the chipping area calculated in this example is 3.23951 mm 3 .
[0052] S5. Obtain the actual chipping volume of the hard brittle material workpiece; Specifically, according to the theoretical volume and the measured volume corresponding to the chipping area, obtain the actual chipping volume of the hard brittle material workpiece, that is, subtract the measured volume from the theoretical volume of the chipping area to obtain the actual chipping volume of the hard brittle material workpiece .
[0053] Exemplarily, in a specific embodiment, the expression of the actual chipping volume is: ; the actual chipping volume of the hard brittle material workpiece calculated in this example is 1.07266 mm 3 .
[0054] The above are only the preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present invention shall be included in the protection scope of the present invention.
Claims
1. A method for detecting chipping and calculating volume in the machining of hard and brittle materials based on 3D point clouds, characterized in that, Including: Obtain the original point cloud data of the machined edge morphology of the hard and brittle material workpiece, and construct a point cloud based on the original point cloud data; Fit the machined surface of the hard and brittle material workpiece based on the point cloud, and use the fitted machined surface as the reference plane; Obtain the normal vector of the reference plane, construct a first rotation matrix based on the normal vector of the reference plane, rotate the point cloud based on the first rotation matrix to align the reference plane with the Z-axis of the coordinate system where the point cloud is located, and obtain the first point cloud; In the first point cloud, fit a preset number of points with the smallest Z-axis values into a straight line, construct a second rotation matrix based on the direction vector of the straight line, rotate the first point cloud based on the second rotation matrix to align the straight line with the Y-axis of the coordinate system where the point cloud is located, and obtain the target point cloud; Perform threshold segmentation on the machined surface of the hard and brittle material workpiece based on the target point cloud to obtain the chipping area; Triangulate the point cloud in the chipping area in three-dimensional space, and obtain the measured volume of the chipping area through the tetrahedron volume integration method; Obtain the parameters of the bounding box of the ideal geometric body of the edge of the hard and brittle material workpiece, and use the volume of the bounding box as the theoretical volume of the chipping area; According to the theoretical volume and the measured volume corresponding to the chipping area, obtain the actual chipping volume of the hard and brittle material workpiece.
2. The method for detecting chipping and calculating volume in the machining of hard and brittle materials based on 3D point cloud according to claim 1, characterized in that The step of obtaining the original point cloud data of the machined edge morphology of the hard and brittle material is: use a three-dimensional measurement device to scan the machined edge morphology of the hard and brittle material to obtain the original point cloud data.
3. A method for detecting chipping and calculating volume in the machining of hard and brittle materials based on 3D point clouds according to claim 1, characterized in that, Fit the machined surface of the hard and brittle material workpiece based on the point cloud and using the Random Sample Consensus algorithm.
4. A method for detecting chipping and calculating volume in the machining of hard and brittle materials based on three-dimensional point clouds according to claim 1, characterized in that, The step of constructing the first rotation matrix based on the normal vector of the reference plane is: Normalize the normal vector of the reference plane to obtain the target normal vector; Obtain the first rotation angle according to the target normal vector and the unit vector of the Z-axis of the coordinate system where the point cloud is located; Construct the first rotation matrix based on the rotation angle and using the Rodriguez formula.
5. A method for detecting chipping and calculating volume in the machining of hard and brittle materials based on three-dimensional point clouds according to claim 1, characterized in that, The step of fitting a preset number of points with the smallest Z-axis values into a straight line in the first point cloud is: Traverse all data points in the first point cloud and find a preset number of points with the smallest Z-axis values in the first point cloud; Merge a preset number of points with the smallest Z-axis values into a new point cloud, perform principal component analysis on the new point cloud to determine the principal component direction; Determine the straight line based on the principal component direction and a preset number of points with the smallest Z-axis values.
6. The method for detecting chipping and calculating volume in the machining of hard and brittle materials based on 3D point cloud according to claim 1, characterized in that, The step of constructing the second rotation matrix based on the direction vector of the straight line is: Normalize the direction vector of the straight line to obtain the target direction vector; Obtain the second rotation angle according to the target direction vector and the unit vector of the Y-axis of the coordinate system where the point cloud is located; Construct the second rotation matrix based on the second rotation angle and using the Rodriguez formula.
7. A method for detecting chipping and calculating volume in the machining of hard and brittle materials based on 3D point clouds according to claim 1, characterized in that, The step of performing threshold segmentation on the machined surface of the hard and brittle material workpiece based on the target point cloud to obtain the chipping area is: Generate a density distribution histogram of the target point cloud along the X-axis direction of the original point cloud; Based on the density distribution histogram of the target point cloud, and use the Otsu algorithm to determine the optimal segmentation threshold; Perform threshold segmentation on the machined surface of the hard and brittle material workpiece based on the optimal segmentation threshold to obtain the chipping area and the normal machined surface.
8. A method for detecting chipping and calculating volume in the machining of hard and brittle materials based on three-dimensional point clouds according to claim 1, characterized in that, The step of triangulating the point cloud in the chipping area in three-dimensional space and obtaining the measured volume of the chipping area through the tetrahedron volume integration method is: Project the data points of the point cloud in the chipping area onto the XOY plane of the coordinate system where the original point cloud is located, and generate a triangular mesh; Construct a three-dimensional pyramid corresponding to each triangular area in the triangular mesh, and obtain the volume of the three-dimensional pyramid; Take the sum of the volumes of all the three-dimensional pyramids as the measured volume of the chipping area.
9. A method for detecting chipping and calculating volume in the machining of hard and brittle materials based on 3D point clouds according to claim 8, characterized in that, Take the sum of the volumes of all the three-dimensional pyramids as the measured volume of the chipping area.
10. A method for detecting chipping and calculating volume in the machining of hard and brittle materials based on three-dimensional point clouds according to claim 1, characterized in that, The steps to obtain the parameters of the bounding box of the ideal geometric body at the edge of the hard and brittle material workpiece are as follows: The bounding box parameters include: the length, width, and height of the bounding box; Obtain the maximum length value and the minimum length value corresponding to the X, Y, and Z directions of the chipping area in the coordinate system where the original point cloud is located; Take the difference between the maximum length value and the minimum length value corresponding to the X direction as the length of the bounding box; Take the difference between the maximum length value and the minimum length value corresponding to the Y direction as the width of the bounding box; Take the difference between the maximum length value and the minimum length value corresponding to the Z direction as the height of the bounding box.