A machining standard positioning method and system for high-precision CNC machine tools

Abstract

The present invention relates to the field of machine tool processing positioning, and more specifically, the present invention relates to a processing standard positioning method and system for high-precision CNC machine tools. The method comprises: performing edge detection and connected domain extraction on the HSV map of the machine tool surface to obtain multiple regions, screening the regions using the calculated abnormality degree, and obtaining a fuzzy processing region; obtaining a central region, connecting the central point and edge point of the central region; constructing a positioning window, respectively constructing the brightness co-occurrence matrix of the central region and the positioning window, and calculating the brightness consistency of the central region and the positioning window; traversing the fuzzy positioning points in the direction from the edge point to the central point, obtaining a brightness consistency sequence, performing a first-order difference on the brightness consistency sequence, and taking the largest difference point as the actual processing point of the fuzzy processing region in a preset direction to complete the processing positioning of the machine tool. Through the technical solution of the present invention, the positioning accuracy of CNC machine tool processing can be improved.

Description

Technical Field

[0001] The present invention relates to the field of machine tool processing positioning, and more specifically, to a processing standard positioning method and system for a high-precision numerical control machine tool. Background Art

[0002] As the core equipment of modern manufacturing industry, CNC machine tools play a vital role in the field of high-end manufacturing due to their high precision and flexibility. In the aviation field, CNC machine tools can process key aircraft structures; in automobile manufacturing, they are used to produce high-precision engine components and body parts; and in the mold manufacturing industry, CNC machine tools can produce molds with complex shapes and extremely high precision. In order to ensure the accuracy and quality of each processing, operators must perform strict processing standard positioning, which usually involves the precise setting of tool position, workpiece clamping and machine tool coordinate system. By adopting advanced positioning technology and real-time monitoring systems, CNC machine tools can achieve fine control of the processing process, thereby ensuring product consistency.

[0003] The existing Chinese patent application document with publication number CN115936962A discloses a machine tool processing positioning method based on image analysis. The method collects images of the processing area and the workpiece in the processing area, and then combines image recognition technology to establish a regional three-dimensional model of the processing area containing the workpiece; the workpiece is positioned in the regional three-dimensional model, and then the detailed position of the workpiece is obtained by corresponding conversion.

[0004] However, the above application documents did not take into account that image recognition technology may be affected by factors such as lighting conditions, workpiece surface reflections, image noise, etc., resulting in inaccurate processing positioning. Summary of the invention

[0005] In order to solve the problem of inaccurate machining positioning, the present invention proposes a machining standard positioning method and system for a high-precision CNC machine tool.

[0006] In a first aspect, the present invention discloses a processing standard positioning method for a high-precision CNC machine tool, comprising: collecting a preprocessed HSV map of the machine tool surface, performing edge detection and connected domain extraction on the machine tool surface HSV map to obtain multiple areas, screening the areas using the calculated abnormality degree, and obtaining a fuzzy processing area; obtaining the central area of ​​the fuzzy processing area, connecting the central point and the edge point of the central area, wherein the edge point is in a preset direction of the central point and on the edge of the fuzzy processing area, and taking the pixel point on the line connecting the central point and the edge point as a fuzzy positioning point; constructing a positioning window with the fuzzy positioning point as the center, constructing the brightness co-occurrence matrix of the central area and the positioning window respectively, and calculating the brightness consistency of the central area and the positioning window; traversing the fuzzy positioning points in the direction from the edge point to the central point to obtain a brightness consistency sequence, performing a first-order difference on the brightness consistency sequence, and taking the largest difference point as the actual processing point of the fuzzy processing area in the preset direction to complete the processing positioning of the machine tool.

[0007] By extracting the connected domain of the detected edges, multiple possible processing areas can be identified. The abnormality degree is calculated to preliminarily screen these areas and eliminate those that do not belong to the processing area, which helps to reduce misidentification and improve the accuracy of processing positioning. By obtaining the central area of ​​the fuzzy processing area and connecting the center point and edge point of the central area, the fuzzy positioning point is constructed, providing an accurate processing position for the CNC machine tool.

[0008] Preferably, the method of screening the region by using the calculated abnormality degree includes: taking the number of pixels contained in the region as the area of ​​the region; taking any region as the target region and taking the region other than the target region as the reference region; and the abnormality degree satisfies the relationship: , Indicates area The degree of abnormality, Indicates area area The target area, Indicates the reference area The area of Represents the total number of reference areas; traverse to obtain the abnormality degree of each area, and normalize the abnormality degrees of all areas, eliminate the areas with abnormality degrees greater than or equal to the preset abnormality threshold, and use the remaining areas as fuzzy processing areas.

[0009] By taking the number of pixels contained in the region as the area of ​​the region, the size of each region can be quantified. The difference in area values ​​and the degree of abnormality calculated by the normalization function can effectively distinguish those areas that do not belong to processing.

[0010] Preferably, the abnormality degree also includes: performing corner point detection on the area to obtain the number of corner points corresponding to each area; using the normalized number of corner points as the abnormality degree, eliminating areas with abnormality degrees greater than or equal to a preset abnormality threshold, and using the remaining areas as fuzzy processing areas.

[0011] Preferably, obtaining the central area of ​​the blurred processing area includes: performing distance transformation on the blurred processing area, taking the highlight point after the distance transformation as the central point of the central area, and taking the area formed by connecting all pixel points in the blurred processing area that are greater than a preset threshold as the central area.

[0012] Through distance transformation, the pixel points that best represent the characteristics of the fuzzy processing area can be obtained, thus providing an accurate reference for processing positioning.

[0013] Preferably, the step of obtaining the central region of the fuzzy processed region further comprises: taking the centroid of the fuzzy processed region as the central point of the central region, and obtaining the central region by region growing.

[0014] Preferably, the brightness consistency includes: obtaining a minimum bounding rectangle of the central area, decomposing the minimum bounding rectangle into a plurality of sub-areas of the same size, wherein the size of the sub-areas is consistent with the size of the positioning window; and calculating the brightness consistency of the sub-areas and the central area, wherein the brightness consistency satisfies the relationship:

[0015] , Indicates brightness consistency, represents the length of the brightness co-occurrence matrix, represents the width of the brightness co-occurrence matrix, represents the brightness co-occurrence matrix of the positioning window, represents the transpose of the brightness co-occurrence matrix of the sub-region, represents the modulus of the brightness co-occurrence matrix of the positioning window, Represents the module of the brightness co-occurrence matrix of the sub-region; traverse to obtain the brightness consistency of each sub-region and the positioning window, and take the mean of all brightness consistencies as the brightness consistency of the central region and the positioning window.

[0016] It is possible to evaluate the degree of brightness matching between each sub-region and the central region. By traversing each sub-region and locating the window, calculating their brightness consistency, and taking their average as the final brightness consistency evaluation result, it not only improves the evaluation accuracy of brightness consistency, but also helps to identify and correct those areas that may affect the processing quality.

[0017] Preferably, the brightness consistency further includes: constructing a central window with the central point as the center, wherein the size of the central window is consistent with the size of the positioning window; calculating the brightness consistency of the central window and the positioning window, and the brightness consistency satisfies the relationship:

[0018] ,in, Indicates brightness consistency, represents the brightness feature vector of the positioning window, represents the transpose of the brightness feature vector of the center window, represents the modulus of the brightness feature vector of the positioning window, Represents the modulus of the brightness feature vector of the center window; the brightness consistency of the center window and the positioning window is the brightness consistency of the center area and the positioning window.

[0019] By calculating the brightness consistency of the modulus of the brightness feature vector, the consistency and changes of the positioning window and the center window content can be effectively detected and analyzed, thereby improving the accuracy and reliability of the analysis.

[0020] In a second aspect, the present invention discloses a processing standard positioning system for a high-precision CNC machine tool, comprising: a processor; and a memory, wherein the memory stores computer instructions. When the computer instructions are executed by the processor, the system executes the above-mentioned processing standard positioning method for a high-precision CNC machine tool.

[0021] Beneficial effects of the present invention:

[0022] 1. Screen these areas by calculating the degree of abnormality to eliminate non-processing areas and ensure the accuracy of processing positioning.

[0023] 2. By constructing a brightness co-occurrence matrix and calculating brightness consistency to optimize the positioning process, not only the brightness similarity between the center area and the positioning window is considered, but also the actual processing point is accurately determined through the first-order difference technology, thereby improving the processing accuracy and efficiency. In this way, it is possible to effectively deal with various complex situations that may arise during machine tool processing, such as surface reflections, coolant interference, etc., ensuring the consistency of processing quality and the processing accuracy of the product, and improving the accuracy of processing positioning. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] By reading the following detailed description with reference to the accompanying drawings, the above and other objects, features and advantages of the exemplary embodiments of the present invention will become readily understood. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-limiting manner, and the same or corresponding reference numerals represent the same or corresponding parts, wherein:

[0025] Figure 1 The present invention is a flowchart of a method for machining standard positioning of a high-precision CNC machine tool according to an embodiment of the present invention. DETAILED DESCRIPTION

[0026] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0027] It should be understood that when the terms "first", "second", etc. are used in the claims, descriptions, and drawings of the present invention, they are only used to distinguish different objects, rather than to describe a specific order. The terms "include" and "comprise" used in the description and claims of the present invention indicate the presence of the described features, wholes, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their collections.

[0028] The present invention provides a method for standard positioning of high-precision CNC machine tools. Figure 1 As shown, a processing standard positioning method for a high-precision CNC machine tool includes steps S1 to S4, which are described in detail below.

[0029] S1, collect the pre-processed HSV map of the machine tool surface, perform edge detection and connected domain extraction on the HSV map of the machine tool surface to obtain multiple regions, use the calculated abnormality degree to screen the regions, and obtain the fuzzy processing region.

[0030] It should be noted that in the processing of CNC machine tools, it is crucial to ensure the high accuracy of the processing standard positioning. However, since the parts will be affected by factors such as iron filings, reflections and coolant during the processing, these influencing factors may be the residues that have not been cleaned up after the previous batch of parts were processed. These interference factors may cause the positions that do not need to be processed to be mistakenly identified as the positions that need to be processed. This situation not only reduces the positioning accuracy of CNC machine tool processing, but also may reduce the quality of the processed parts, thereby affecting the processing efficiency of CNC machine tools.

[0031] In one embodiment, an industrial camera is used to capture an RGB (Red Green Blue) image of the machine tool surface, and the RGB image of the machine tool surface is converted into an HSV (Hue Saturation Value) image of the machine tool surface using a color space.

[0032] Edge detection and connected domain extraction are performed on the HSV image to obtain multiple regions. The edge detection algorithm can be Canny, Sobel, Roberts, Prewitt, etc. Edge detection and connected domain extraction are well-known techniques for those skilled in the art and will not be described in detail here.

[0033] Calculating the abnormality degree of each region includes: taking the number of pixels contained in the region as the area of ​​the region; taking any region as a target region, and taking the region other than the target region as a reference region.

[0034] The degree of abnormality satisfies the relationship:

[0035] , Indicates area The degree of abnormality, Indicates area area The target area, Indicates the reference area The area of Indicates the total number of reference areas.

[0036] The abnormality degree of each area is obtained by traversing, and the abnormality degrees of all areas are normalized, and the areas with abnormality degrees greater than or equal to the preset abnormality threshold are eliminated, and the remaining areas are used as fuzzy processing areas.

[0037] It should be noted that, by calculating the degree of abnormality, all areas can be preliminarily screened and areas that do not belong to processing can be eliminated first, such as a separate portion of coolant or other foreign matter on a machine tool.

[0038] In another embodiment, the degree of abnormality also includes: performing corner point detection on the area to obtain the number of corner points corresponding to each area; using the normalized number of corner points as the degree of abnormality, eliminating areas with an abnormality degree greater than or equal to a preset abnormality threshold, and using the remaining areas as fuzzy processing areas.

[0039] It should be noted that the residual coolant or other foreign matter generally changes the gradient direction of the edge more times than the gradient direction of the workpiece edge, so the more corner points there are, the more likely it is that the area is not a workpiece.

[0040] S2, obtaining the central area of ​​the fuzzy processing area, connecting the central point and the edge point of the central area, and using the pixel points on the line connecting the central point and the edge point as fuzzy positioning points.

[0041] In one embodiment, distance transformation is performed on the blurred area, and the highlight point after distance transformation is used as the center point of the central area, and the area formed by connecting all pixel points in the blurred area with a value greater than a preset threshold is used as the central area.

[0042] It should be noted that distance transformation is a commonly used technique in image processing, which calculates the distance from each pixel in the image to the nearest feature. The brightness can be distance transformed, and the highlight point is the pixel with the largest brightness value in the fuzzy processing area. The RGB image of the machine tool surface obtained in step S1 can also be converted into a grayscale image of the machine tool surface, and the grayscale value in the fuzzy processing area can be distance transformed.

[0043] Connect the center point and edge point of the central area, where the edge point is in the preset direction of the center point and on the edge of the fuzzy processing area, and use the pixel points on the line connecting the center point and the edge point as fuzzy positioning points.

[0044] Exemplarily, the preset direction may be 0 degrees, 45 degrees, 90 degrees, 135 degrees, 180 degrees, 270 degrees, etc., and the preferred preset directions of the present invention are 0 degrees, 90 degrees, 180 degrees, and 270 degrees.

[0045] In another embodiment, obtaining the central region of the fuzzy processed region further includes: taking the centroid of the fuzzy processed region as the central point of the central region, and obtaining the central region by region growing.

[0046] It should be noted that the centroid, also known as the geometric center, is the average position of all points in an object, and it represents the equilibrium point of the object. In a plane figure, the centroid can be determined by calculating the average value of the coordinates of all vertices of the figure. For a complex plane figure, the figure can be divided into multiple simple figures (such as triangles), and then the centroid of each figure is calculated separately, and finally the position of the overall centroid is determined by weighted average of area or volume.

[0047] S3, construct a positioning window with the blurred positioning point as the center, construct the brightness co-occurrence matrix of the central area and the positioning window respectively, and calculate the brightness consistency of the central area and the positioning window.

[0048] In one embodiment, a positioning window is constructed with the fuzzy positioning point as the center. Exemplarily, the size of the positioning window is set to 3 times 3.

[0049] The brightness co-occurrence matrix of the central area and the positioning window is constructed respectively. It should be noted that the brightness co-occurrence matrix describes the brightness characteristics of the image by quantifying the spatial relationship of the pixel brightness values ​​in the image. The construction method of the brightness co-occurrence matrix is ​​the same as that of the grayscale co-occurrence matrix.

[0050] There are two methods for constructing the brightness co-occurrence matrix. The first is the frequency method: This method counts the number of times a pair of brightness values ​​co-occur at a given direction and distance. By counting the frequency of occurrence of all possible brightness pairs in the entire image, a matrix can be constructed, in which each element of the matrix represents the frequency of occurrence of a specific brightness pair. The second frequency method: Similar to the frequency method, the frequency method is also based on counting the number of occurrences of brightness pairs, but it focuses more on recording the specific number of occurrences of each brightness pair rather than calculating their frequency ratio.

[0051] Whether it is the central area or the positioning window, the key to constructing the brightness co-occurrence matrix is ​​to determine the direction and distance of the analysis. Usually, multiple directions (such as 0 degrees, 45 degrees, 90 degrees, and 135 degrees) and different distances (such as 1 pixel, 2 pixels, etc.) are considered to fully capture the brightness information of the image.

[0052] Calculating the brightness consistency of the central area and the positioning window includes: obtaining a minimum bounding rectangle of the central area, and decomposing the minimum bounding rectangle into a plurality of sub-areas of the same size, wherein the size of the sub-areas is consistent with the size of the positioning window.

[0053] Calculate the brightness consistency of the sub-area and the central area. The brightness consistency satisfies the relationship:

[0054] , Indicates brightness consistency, represents the length of the brightness co-occurrence matrix, represents the width of the brightness co-occurrence matrix, represents the brightness co-occurrence matrix of the positioning window, represents the transpose of the brightness co-occurrence matrix of the sub-region, represents the modulus of the brightness co-occurrence matrix of the positioning window, Represents the magnitude of the brightness co-occurrence matrix of the sub-region.

[0055] The brightness consistency of each sub-region and positioning window is obtained by traversal, and the mean of all brightness consistency is taken as the brightness consistency of the central region and the positioning window.

[0056] In another embodiment, calculating the brightness consistency further includes: constructing a central window with the central point as the center, wherein the size of the central window is consistent with the size of the positioning window.

[0057] Calculate the brightness consistency of the center window and the positioning window. The brightness consistency satisfies the relationship:

[0058] ,in, Indicates brightness consistency, represents the brightness feature vector of the positioning window, represents the transpose of the brightness feature vector of the center window, represents the modulus of the brightness feature vector of the positioning window, Represents the magnitude of the brightness feature vector of the center window.

[0059] The brightness consistency between the center window and the positioning window is the brightness consistency between the center area and the positioning window.

[0060] S4, traverse the fuzzy positioning points from the edge point to the center point to obtain a brightness consistency sequence, perform first-order difference on the brightness consistency sequence, and use the largest difference point as the actual processing point of the fuzzy processing area in the preset direction to complete the processing positioning of the machine tool.

[0061] In one embodiment, the fuzzy positioning points are traversed from the edge points to the center point.

[0062] Exemplarily, in a preset direction, from the center point to the edge point is represented as: ,in represents the center point, represents the edge point, represents the first fuzzy positioning point, Indicates The last fuzzy positioning point. Start calculating with The brightness consistency between the positioning window constructed with the fuzzy positioning point as the center and the central window is then Calculate the The brightness consistency between the positioning window constructed with the first fuzzy positioning point as the center and the central window is calculated until the brightness consistency between the positioning window constructed with the first fuzzy positioning point as the center and the central window is calculated to obtain a brightness consistency sequence.

[0063] The first-order difference of the brightness consistency sequence is performed, and the maximum difference point is taken as the actual processing point of the fuzzy processing area in the preset direction. Similarly, the actual processing point corresponding to each preset direction is obtained, and the fuzzy processing area is corroded to obtain the actual processing area, completing the processing positioning of the machine tool.

[0064] An embodiment of the present invention further discloses a processing standard positioning system for a high-precision CNC machine tool, comprising a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, a processing standard positioning method for a high-precision CNC machine tool according to the present invention is implemented.

[0065] The above system also includes other components well known to those skilled in the art, such as a communication bus and a communication interface, and their configuration and functions are known in the art, so they will not be described in detail here.

[0066] In the present invention, the aforementioned memory may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, apparatus or device. For example, a computer-readable storage medium may be any appropriate magnetic storage medium or magneto-optical storage medium, such as a resistive random access memory RRAM (Resistive Random Access Memory), a dynamic random access memory DRAM (Dynamic Random Access Memory), a static random access memory SRAM (Static Random-Access Memory), an enhanced dynamic random access memory EDRAM (Enhanced Dynamic Random Access Memory), a high-bandwidth memory HBM (High-Bandwidth Memory), a hybrid memory cube HMC (Hybrid Memory Cube), etc., or any other medium that can be used to store the required information and can be accessed by an application, a module or both. Any such computer storage medium may be part of a device or accessible or connectable to a device.

[0067] Although this specification has shown and described a number of embodiments of the present invention, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Those skilled in the art will conceive of many modifications, changes and alternatives without departing from the ideas and spirit of the present invention. It should be understood that in the practice of the present invention, various alternatives to the embodiments of the present invention described herein may be employed.

[0068] The above are all preferred embodiments of the present invention, and are not intended to limit the protection scope of the present invention. Therefore, any equivalent changes made based on the structure, shape, and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A processing standard positioning method for a high-precision CNC machine tool, characterized in that: include: Collect the pre-processed HSV map of the machine tool surface, perform edge detection and connected domain extraction on the HSV map of the machine tool surface to obtain multiple regions, and use the calculated abnormality degree to screen the regions to obtain the fuzzy processing region; Obtaining the central area of ​​the fuzzy processing area, connecting the central point and the edge point of the central area, wherein the edge point is in a preset direction of the central point and on the edge of the fuzzy processing area, and using the pixel points on the line connecting the central point and the edge point as fuzzy positioning points; A positioning window is constructed with the fuzzy positioning point as the center, the brightness co-occurrence matrix of the central area and the positioning window is constructed respectively, and the brightness consistency of the central area and the positioning window is calculated; The fuzzy positioning points are traversed from the edge point to the center point to obtain a brightness consistency sequence, and the brightness consistency sequence is first-order differentiated. The maximum differential point is used as the actual processing point of the fuzzy processing area in the preset direction to complete the processing positioning of the machine tool.

2. A processing standard positioning method for a high-precision CNC machine tool according to claim 1, characterized in that: The method of screening the region by using the calculated abnormality degree includes: The number of pixels contained in the region is taken as the area of ​​the region; Any area is taken as the target area, and the area other than the target area is taken as the reference area; The degree of abnormality satisfies the relationship: , Indicates area The degree of abnormality, Indicates area area The target area, Indicates the reference area The area of Indicates the total number of reference areas; The abnormality degree of each area is obtained by traversing, and the abnormality degrees of all areas are normalized, and the areas with abnormality degrees greater than or equal to the preset abnormality threshold are eliminated, and the remaining areas are used as fuzzy processing areas.

3. A method for machining standard positioning of a high-precision CNC machine tool according to claim 2, characterized in that: The degree of abnormality also includes: Perform corner point detection on the region to obtain the number of corner points corresponding to each region; The normalized number of corner points is used as the abnormality degree, and the areas with abnormality greater than or equal to the preset abnormality threshold are eliminated, and the remaining areas are used as fuzzy processing areas.

4. The method for machining standard positioning of a high-precision CNC machine tool according to claim 1, characterized in that: The central area of ​​the fuzzy processing area is obtained as follows: The fuzzy processing area is subjected to distance transformation, and the highlight point after the distance transformation is used as the center point of the central area, and the area formed by connecting all the pixel points in the fuzzy processing area that are greater than a preset threshold is used as the central area.

5. The method for machining standard positioning of a high-precision CNC machine tool according to claim 1, characterized in that: The obtaining of the central area of ​​the fuzzy processing area also includes: The centroid of the fuzzy processed area is taken as the center point of the central area, and the central area is obtained by region growing.

6. The method for machining standard positioning of a high-precision CNC machine tool according to claim 1, characterized in that: The brightness consistency includes: Obtain the minimum bounding rectangle of the central area, and decompose the minimum bounding rectangle into multiple sub-areas of the same size, where the size of the sub-areas is consistent with the size of the positioning window; Calculate the brightness consistency of the sub-area and the central area. The brightness consistency satisfies the relationship: , Indicates brightness consistency, represents the length of the brightness co-occurrence matrix, represents the width of the brightness co-occurrence matrix, represents the brightness co-occurrence matrix of the positioning window, represents the transpose of the brightness co-occurrence matrix of the sub-region, represents the modulus of the brightness co-occurrence matrix of the positioning window, represents the magnitude of the brightness co-occurrence matrix of the sub-region; The brightness consistency of each sub-region and positioning window is obtained by traversal, and the mean of all brightness consistency is taken as the brightness consistency of the central region and the positioning window.

7. The method for machining standard positioning of a high-precision CNC machine tool according to claim 1, characterized in that: The brightness consistency also includes: A center window is constructed with the center point as the center, wherein the size of the center window is consistent with the size of the positioning window; Calculate the brightness consistency of the center window and the positioning window. The brightness consistency satisfies the relationship: ,in, Indicates brightness consistency, represents the brightness feature vector of the positioning window, represents the transpose of the brightness feature vector of the center window, represents the modulus of the brightness feature vector of the positioning window, represents the magnitude of the brightness feature vector of the center window; The brightness consistency between the center window and the positioning window is the brightness consistency between the center area and the positioning window.

8. A processing standard positioning system for high-precision CNC machine tools, characterized in that: include: Processor; and A memory storing computer instructions, wherein when the computer instructions are executed by a processor, the system executes a processing standard positioning method for a high-precision CNC machine tool according to any one of claims 1 to 7.

Images