Numerical control machining center and machining method for fasteners

Abstract

The application discloses a numerical control machining center and machining method for fasteners, comprising: a clamping module for clamping fasteners to a process plate based on machining specification requirements; a vision module for workpiece calibration processing on fasteners on the process plate through visual photography; a numerical control module for generating a machining control strategy based on machining parameters for fasteners after workpiece calibration processing; a multi-axis linkage module electrically connected with the numerical control module, containing at least three movement axes, each movement axis driving a cutter to move according to the machining control strategy. The application solves the problems of large clamping error, difficult workpiece calibration, inaccurate machining control strategy generation, and insufficient multi-axis linkage machining coordination and accuracy in traditional fastener numerical control machining, so as to improve the machining precision and production efficiency of fasteners and reduce the waste rate.

Description

Technical Field

[0001] This invention relates to the field of parts processing technology, and in particular to a CNC machining center and processing method for fasteners. Background Technology

[0002] Fasteners, as crucial components for connecting and fixing parts, directly impact the overall performance and reliability of mechanical equipment through their machining accuracy and quality. Traditional CNC machining of fasteners presents numerous technical challenges. Firstly, fastener clamping methods are often imprecise and inefficient, relying on manual labor or simple tooling. This makes it difficult to ensure the fastener's position on the process plate meets machining specifications, resulting in significant clamping errors and dimensional inaccuracies that fail to meet design standards. Secondly, workpiece calibration often lacks effective technical means, hindering rapid and accurate calibration of fasteners on the process plate, impacting subsequent machining accuracy and efficiency. Furthermore, existing technologies have limitations in generating machining control strategies and multi-axis linkage machining. They cannot flexibly generate precise machining control strategies based on the specific machining parameters of the fasteners, and the coordination and accuracy of multi-axis linkage movements are insufficient, making it difficult to accurately match the tool trajectory with machining requirements, leading to low machining efficiency and a high scrap rate. Summary of the Invention

[0003] This invention aims to at least partially solve one of the technical problems in the aforementioned technologies. Therefore, the purpose of this invention is to propose a CNC machining center and machining method for fasteners, addressing problems in traditional CNC machining of fasteners such as large clamping errors, difficulty in workpiece calibration, inaccurate generation of machining control strategies, and insufficient coordination and accuracy in multi-axis linkage machining, thereby improving the machining accuracy and production efficiency of fasteners and reducing the scrap rate.

[0004] To achieve the above objectives, embodiments of the present invention provide a CNC machining center for fasteners, comprising:

[0005] Clamping module, used to clamp fasteners onto the process plate according to machining specifications;

[0006] The vision module is used to perform workpiece calibration by visual photography on the fasteners on the process plate.

[0007] The CNC module is used to generate machining control strategies for fasteners after workpiece calibration based on machining parameters;

[0008] The multi-axis linkage module is electrically connected to the CNC module and contains at least three motion axes. Each motion axis drives the tool to move according to the machining control strategy.

[0009] According to some embodiments of the present invention, the vision module includes:

[0010] The acquisition module is used to acquire images of fasteners on the process board through visual photography.

[0011] The comparison module is used to compare the captured image with a preset database to obtain a matching image, and then perform workpiece calibration based on the matching image.

[0012] According to some embodiments of the present invention, the CNC module includes:

[0013] The cutting parameter acquisition module is used to determine the material properties and tool type of the fastener after workpiece calibration, input the material properties and tool type into a pre-built fuzzy rule base, and output the cutting parameters, which include cutting speed, feed rate and depth of cut.

[0014] The toolpath planning module is used to plan toolpaths.

[0015] The first generation module is used to determine the machining parameters based on the cutting parameters and tool path, and generate a machining control strategy based on the machining parameters.

[0016] According to some embodiments of the present invention, a path planning module includes:

[0017] The extraction module is used to generate a 3D model of the fastener after workpiece calibration, preprocess the 3D model, and extract machining features.

[0018] The second generation module is used to plan and generate the initial toolpath based on machining features and machining process requirements;

[0019] The optimization module is used to optimize the initial toolpath using a genetic algorithm to obtain the final toolpath.

[0020] According to some embodiments of the present invention, it further includes: a tool monitoring module, used to monitor the tool status and issue an alarm when it is determined that the tool status is abnormal;

[0021] The tool monitoring module includes:

[0022] The first identification module is used to acquire monitoring images of the cutting tool, identify the monitoring images, and obtain first monitoring information.

[0023] The second identification module is used to collect vibration and sound signals of the cutting tool during the cutting process, identify the vibration and sound signals, and obtain the second monitoring information.

[0024] The first determination module is used to determine the tool status based on the first monitoring information and the second monitoring information, and to issue an alarm when the tool status is determined to be abnormal.

[0025] According to some embodiments of the present invention, the first identification module includes:

[0026] The filtering module is used to filter the monitoring image to obtain a filtered image;

[0027] The second determining module is used for:

[0028] The filter image is extracted using a preset contour detection algorithm to obtain a contour image;

[0029] Key points are extracted from the contour image to obtain the target key points;

[0030] Extract key points from the preset contour images in the preset contour image library to obtain the preset key points corresponding to each preset contour image.

[0031] The lower left corner of the contour image is used as the origin of the coordinate system to obtain the target coordinates of the target key points. The target feature vector of the contour image is then determined based on the target coordinates.

[0032] The lower left corner of each preset contour image is taken as the origin of the coordinate system to obtain the coordinates of the preset key points corresponding to the preset contour image. Based on the coordinates of the preset key points, the preset feature vector corresponding to the preset contour image is determined.

[0033] Calculate the cosine distance between the target feature vector and each preset feature vector;

[0034] The cosine distance is compared with a preset distance threshold to obtain comparison information, and the first monitoring information is obtained based on the comparison information.

[0035] According to some embodiments of the present invention, the filtering module includes:

[0036] The third determining module is used for:

[0037] Identify any pixel in the monitored image as the target pixel, and determine the target region centered on the target pixel. The target region is an N×N pixel matrix, where N is an even number. Divide the target region into four square regions with side length N / 2, and select one of them as the square region to be processed. Obtain the pixel mean, pixel median, and pixel mode of all pixels in the square region to be processed. Obtain the sum of the pixel mean, pixel median, and pixel mode, and determine the first mean corresponding to the pixel mean, pixel median, and pixel mode based on the sum. Use the first mean as the first estimated value of the target pixel.

[0038] The above operation is performed on all the remaining square regions to obtain the second, third, and fourth estimates of the target pixel.

[0039] Replacement module, used for:

[0040] Obtain the target pixel value of the target pixel, calculate the absolute value of the difference between the target pixel value and the first estimate, the second estimate, the third estimate and the fourth estimate respectively, and take the estimate corresponding to the smallest absolute value as the first filtered pixel value of the target pixel;

[0041] The first weight corresponding to the first filtered pixel value is determined according to the first preset weight function;

[0042] Obtain the target gradient value of the target pixel, and determine the first coefficient based on the target gradient value;

[0043] Obtain the target pixel mean of all pixels in the target region;

[0044] Convert the image to a grayscale image, determine the target grayscale region corresponding to the target region in the grayscale image, and obtain the average grayscale pixel value of all pixels in the target grayscale region;

[0045] The second coefficient is determined based on the first coefficient, the average value of the target pixel, and the average value of the grayscale pixels;

[0046] Obtain the target pixel value of the target pixel, and determine the second filtered pixel value corresponding to the target pixel based on the target pixel value, the first coefficient, the second coefficient and the preset filtering formula;

[0047] The second weight corresponding to the second filtered pixel value is determined according to the second preset weight function;

[0048] Calculate the first product of the first filtered pixel value and the first weight, and the second product of the second filtered pixel value and the second weight. Use the sum of the first and second products as the filtered pixel value of the target pixel. Replace the target pixel value with the filtered pixel value to obtain the filtered pixel corresponding to the target pixel.

[0049] Perform the above operations on all pixels in the monitored image to obtain the filtered pixels corresponding to each pixel. All the filtered pixels form the filtered image.

[0050] According to some embodiments of the present invention, the multi-axis linkage module includes X-axis linear motion, Y-axis linear motion and Z-axis linear motion axes, and at least one rotary axis; the X-axis linear motion, Y-axis linear motion and Z-axis linear motion axes are used to realize the linear motion of the tool in three mutually perpendicular directions; the rotary axis is used to realize the rotational motion of the tool around a specific axis.

[0051] According to some embodiments of the present invention, it further includes: a processing quality inspection module, used for:

[0052] The processed fasteners are subjected to quality inspection, and the inspection results are obtained.

[0053] The processing quality of the fasteners is determined based on the test results. If it does not meet the requirements, the processing control strategy is optimized and adjusted, and the processing is repeated. If it meets the requirements, the processing task is completed.

[0054] According to some embodiments of the present invention, the machining method for fasteners using a CNC machining center as described above includes:

[0055] Fasteners are clamped onto the process plate according to the processing specifications;

[0056] The fasteners on the process plate are calibrated using visual photography.

[0057] A machining control strategy is generated based on machining parameters for fasteners after workpiece calibration.

[0058] The multi-axis linkage module includes motion axes that drive the tool to move according to the machining control strategy.

[0059] This invention proposes a CNC machining center and machining method for fasteners. The clamping module accurately clamps the fasteners onto the process plate according to machining specifications, effectively avoiding machining errors caused by improper clamping, ensuring the machining accuracy of fasteners from the source, reducing scrap caused by clamping problems, and improving the product qualification rate. The vision module performs workpiece calibration on the fasteners on the process plate through visual imaging, and can promptly detect and correct fastener positional deviations. The CNC module generates machining control strategies based on machining parameters, realizing intelligent and precise machining processes. It can flexibly adjust the machining control strategy for fasteners of different specifications and requirements, ensuring that the tool follows the optimal machining path, improving machining accuracy and production efficiency, and reducing reliance on operator experience. The multi-axis linkage module contains at least three motion axes, each of which drives the tool to move according to the machining control strategy, realizing complex machining trajectories and meeting the machining needs of various types of fasteners.

[0060] Other features and advantages of the invention will be set forth in the following description, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in the written description and the accompanying drawings.

[0061] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0062] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used in conjunction with embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings:

[0063] Figure 1 This is a block diagram of a CNC machining center for fasteners according to an embodiment of the present invention;

[0064] Figure 2 This is a block diagram of a vision module according to an embodiment of the present invention;

[0065] Figure 3 This is a block diagram of a numerical control module according to an embodiment of the present invention;

[0066] Figure 4 This is a block diagram of a path planning module according to an embodiment of the present invention;

[0067] Figure 5 This is a block diagram of a tool monitoring module according to an embodiment of the present invention;

[0068] Figure 6 This is a block diagram of a first identification module according to an embodiment of the present invention;

[0069] Figure 7 This is a block diagram of a filtering module according to an embodiment of the present invention;

[0070] Figure 8 This is a flowchart of a machining method for a CNC machining center for fasteners according to an embodiment of the present invention. Detailed Implementation

[0071] The preferred embodiments of the present invention will be described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are for illustration and explanation only and are not intended to limit the present invention.

[0072] like Figure 1 As shown in the figure, an embodiment of the present invention proposes a CNC machining center for fasteners, comprising:

[0073] Clamping module, used to clamp fasteners onto the process plate according to machining specifications;

[0074] The vision module is used to perform workpiece calibration by visual photography on the fasteners on the process plate.

[0075] The CNC module is used to generate machining control strategies for fasteners after workpiece calibration based on machining parameters;

[0076] The multi-axis linkage module is electrically connected to the CNC module and contains at least three motion axes. Each motion axis drives the tool to move according to the machining control strategy.

[0077] The working principle and beneficial effects of the above technical solution are as follows: The clamping module can accurately clamp fasteners onto the process plate according to the processing specifications, effectively avoiding processing errors caused by improper clamping, ensuring the processing accuracy of fasteners from the source, reducing scrap caused by clamping problems, and improving the product qualification rate. The vision module performs workpiece calibration on the fasteners on the process plate through visual comparison, and can promptly detect and correct fastener position deviations. The CNC module generates processing control strategies based on processing parameters, realizing intelligent and precise processing. It can flexibly adjust the processing control strategy for fasteners of different specifications and requirements, ensuring that the tool processes along the optimal path, improving processing accuracy and production efficiency, and reducing reliance on operator experience. The multi-axis linkage module contains at least three motion axes, each of which drives the tool to move according to the processing control strategy, realizing complex processing trajectories and meeting the processing needs of various types of fasteners. Through the collaborative work of the clamping module, vision module, CNC module, and multi-axis linkage module, the CNC machining center achieves high-precision and high-efficiency processing of fasteners.

[0078] like Figure 2 As shown, according to some embodiments of the present invention, the vision module includes:

[0079] The acquisition module is used to acquire images of fasteners on the process board through visual photography.

[0080] The comparison module is used to compare the captured image with a preset database to obtain a matching image, and then perform workpiece calibration based on the matching image.

[0081] The working principle of the above technical solution is as follows: The acquisition module is a high-resolution industrial camera with integrated autofocus, automatically adjusting the focus according to the fastener's position. The comparison module compares the captured image with a preset database to obtain a matching image, and performs workpiece calibration based on the matching image. The preset database contains standard images and parameters of various fasteners for comparison and calibration. Comparison processing is performed using methods such as template matching to obtain a matching image, which corresponds to the captured image. The comparison result is determined based on the matching image, the deviation between the actual and theoretical positions of the fastener is calculated, and calibration parameters are generated.

[0082] The beneficial effects of the above technical solution are as follows: The vision module, through the collaborative work of the acquisition and comparison modules, achieves high-precision image acquisition and calibration processing of fasteners on the process board. High-precision workpiece calibration is achieved through advanced image recognition algorithms and database comparison. This reduces manual intervention and improves production efficiency and consistency.

[0083] like Figure 3 As shown, according to some embodiments of the present invention, the CNC module includes:

[0084] The cutting parameter acquisition module is used to determine the material properties and tool type of the fastener after workpiece calibration, input the material properties and tool type into a pre-built fuzzy rule base, and output the cutting parameters, which include cutting speed, feed rate and depth of cut.

[0085] The toolpath planning module is used to plan toolpaths.

[0086] The first generation module is used to determine the machining parameters based on the cutting parameters and tool path, and generate a machining control strategy based on the machining parameters.

[0087] The working principle of the above technical solution is as follows: The cutting parameter acquisition module includes a detection sensor to acquire the material properties of the fastener, such as hardness, toughness, and thermal conductivity. The cutting parameter acquisition module also includes an identification module to determine the tool type, such as a milling cutter, drill bit, or tap. A fuzzy rule base containing the relationship between material properties, tool type, and cutting parameters is constructed, and the cutting parameters are output through fuzzy inference. A path planning module is used to plan the tool path. The first generation module combines the cutting parameters (cutting speed, feed rate, depth of cut) and the tool path to determine specific machining parameters. Based on the machining parameters, a motion control strategy for the tool is generated, including motion speed, acceleration, and direction.

[0088] The beneficial effects of the above technical solution are as follows: The CNC module, through the collaborative work of the cutting parameter acquisition module, path planning module, and first generation module, facilitates the accurate generation of machining control strategies. High-precision machining is achieved through precise cutting parameters and path planning. Intelligent control is realized through fuzzy logic, reducing manual intervention.

[0089] like Figure 4 As shown, according to some embodiments of the present invention, a path planning module includes:

[0090] The extraction module is used to generate a 3D model of the fastener after workpiece calibration, preprocess the 3D model, and extract machining features.

[0091] The second generation module is used to plan and generate the initial toolpath based on machining features and machining process requirements;

[0092] The optimization module is used to optimize the initial toolpath using a genetic algorithm to obtain the final toolpath.

[0093] The working principle of the above technical solution is as follows: Based on 3D scanning technology, a 3D model of the fastener is generated. Preprocessing operations such as denoising, smoothing, and simplification are performed on the 3D model to improve the accuracy of subsequent machining feature extraction. Features to be machined, such as holes, slots, and threads, are extracted from the 3D model, and their geometric parameters (such as size, position, and orientation) are determined. Machining process requirements, including milling, drilling, and tapping, are considered. Combining the extracted machining features and machining process requirements, the initial tool path is planned, including the tool's start point, end point, and trajectory. This initial tool path is used as the initial population for a genetic algorithm, and the tool path is optimized through selection, crossover, and mutation operations.

[0094] The beneficial effects of the above technical solution are as follows: The path planning module achieves high-precision and high-efficiency toolpath planning for fasteners through the collaborative work of the extraction module, the second generation module, and the optimization module. High-precision toolpath planning is achieved through 3D model generation and machining feature extraction. The use of a genetic algorithm to optimize the toolpath improves machining efficiency and tool life.

[0095] like Figure 5 As shown, according to some embodiments of the present invention, it further includes: a tool monitoring module, used to monitor the tool status and issue an alarm when it is determined that the tool status is abnormal;

[0096] The tool monitoring module includes:

[0097] The first identification module is used to acquire monitoring images of the cutting tool, identify the monitoring images, and obtain first monitoring information.

[0098] The second identification module is used to collect vibration and sound signals of the cutting tool during the cutting process, identify the vibration and sound signals, and obtain the second monitoring information.

[0099] The first determination module is used to determine the tool status based on the first monitoring information and the second monitoring information, and to issue an alarm when the tool status is determined to be abnormal.

[0100] The working principle of the above technical solution is as follows: The first identification module acquires a monitoring image of the cutting tool and identifies the image to obtain the first monitoring information. The second identification module uses vibration and sound sensors to collect vibration and sound signals of the cutting tool in real time during the cutting process. The collected signals are preprocessed, including filtering and amplification, to improve signal quality. Feature parameters (such as vibration frequency, amplitude, and sound intensity) are extracted from the signals using signal processing algorithms. Based on the extracted feature parameters, abnormal states of the cutting tool (such as excessive vibration or abnormal sound) are identified. The identification results are output as the second monitoring information, including the vibration and sound states of the cutting tool. The first determination module fuses the first and second monitoring information to comprehensively judge the state of the cutting tool. It identifies the tool state from multiple dimensions, including the tool's contour, vibration during operation, and sound, thus improving the accuracy of determining the tool state.

[0101] The beneficial effects of the above technical solution are as follows: The tool monitoring module, through the coordinated work of the first identification module, the second identification module, and the first determination module, monitors the tool status in real time, promptly detects abnormalities, and avoids machining accidents. Combining image recognition and signal recognition improves the accuracy of tool status judgment. Automatic alarm prompts reduce manual intervention and improve production efficiency.

[0102] like Figure 6 As shown, according to some embodiments of the present invention, the first identification module includes:

[0103] The filtering module is used to filter the monitoring image to obtain a filtered image;

[0104] The second determining module is used for:

[0105] The filter image is extracted using a preset contour detection algorithm to obtain a contour image;

[0106] Key points are extracted from the contour image to obtain the target key points;

[0107] Extract key points from the preset contour images in the preset contour image library to obtain the preset key points corresponding to each preset contour image.

[0108] The lower left corner of the contour image is used as the origin of the coordinate system to obtain the target coordinates of the target key points. The target feature vector of the contour image is then determined based on the target coordinates.

[0109] The lower left corner of each preset contour image is taken as the origin of the coordinate system to obtain the coordinates of the preset key points corresponding to the preset contour image. Based on the coordinates of the preset key points, the preset feature vector corresponding to the preset contour image is determined.

[0110] Calculate the cosine distance between the target feature vector and each preset feature vector;

[0111] The cosine distance is compared with a preset distance threshold to obtain comparison information, and the first monitoring information is obtained based on the comparison information.

[0112] The working principle of the above technical solution is as follows: The monitoring image is filtered using a filtering module to obtain a filtered image; a preset contour detection algorithm is used to extract the contour from the filtered image to obtain a contour image; the preset contour detection algorithm includes Canny edge detection and the Sobel operator. Key points are extracted from the contour image to obtain target key points; key points are extracted from preset contour images in a preset contour image library to obtain preset key points corresponding to each preset contour image; the preset contour image is a complete tool contour image. The lower left corner of the contour image is used as the origin to obtain the target coordinates of the target key points, and the target feature vector of the contour image is determined based on the target coordinates; the lower left corner of each preset contour image is used as the origin to obtain the coordinates of the preset key points corresponding to the preset contour image, and the preset feature vector corresponding to the preset contour image is determined based on the coordinates of the preset key points; the cosine distance between the target feature vector and each preset feature vector is calculated; the cosine distance is compared with a preset distance threshold to obtain comparison information, and key points whose cosine distance is less than the preset distance threshold are identified as wear points. The degree of wear is determined based on the difference between the two, and the first monitoring information is obtained based on the comparison information. The preset distance threshold is the wear threshold.

[0113] The beneficial effects of the above technical solution are as follows: The filtering module filters the monitoring image to obtain a filtered image; the second determination module extracts the contour of the filtered image to obtain a contour image; based on the calculated cosine distance between the corresponding key points of the contour image and the preset contour image, the cosine distance is compared with the preset distance threshold to obtain comparison information; and the first monitoring information is obtained based on the comparison information, which facilitates the accurate determination of the tool wear information and thus facilitates the determination of the tool status information.

[0114] like Figure 7 As shown, according to some embodiments of the present invention, the filtering module includes:

[0115] The third determining module is used for:

[0116] Identify any pixel in the monitored image as the target pixel, and determine the target region centered on the target pixel. The target region is an N×N pixel matrix, where N is an even number. Divide the target region into four square regions with side length N / 2, and select one of them as the square region to be processed. Obtain the pixel mean, pixel median, and pixel mode of all pixels in the square region to be processed. Obtain the sum of the pixel mean, pixel median, and pixel mode, and determine the first mean corresponding to the pixel mean, pixel median, and pixel mode based on the sum. Use the first mean as the first estimated value of the target pixel.

[0117] The above operation is performed on all the remaining square regions to obtain the second, third, and fourth estimates of the target pixel.

[0118] Replacement module, used for:

[0119] Obtain the target pixel value of the target pixel, calculate the absolute value of the difference between the target pixel value and the first estimate, the second estimate, the third estimate and the fourth estimate respectively, and take the estimate corresponding to the smallest absolute value as the first filtered pixel value of the target pixel;

[0120] The first weight corresponding to the first filtered pixel value is determined according to the first preset weight function;

[0121] Obtain the target gradient value of the target pixel, and determine the first coefficient based on the target gradient value;

[0122] Obtain the target pixel mean of all pixels in the target region;

[0123] Convert the image to a grayscale image, determine the target grayscale region corresponding to the target region in the grayscale image, and obtain the average grayscale pixel value of all pixels in the target grayscale region;

[0124] The second coefficient is determined based on the first coefficient, the average value of the target pixel, and the average value of the grayscale pixels;

[0125] Obtain the target pixel value of the target pixel, and determine the second filtered pixel value corresponding to the target pixel based on the target pixel value, the first coefficient, the second coefficient and the preset filtering formula;

[0126] The second weight corresponding to the second filtered pixel value is determined according to the second preset weight function;

[0127] Calculate the first product of the first filtered pixel value and the first weight, and the second product of the second filtered pixel value and the second weight. Use the sum of the first and second products as the filtered pixel value of the target pixel. Replace the target pixel value with the filtered pixel value to obtain the filtered pixel corresponding to the target pixel.

[0128] Perform the above operations on all pixels in the monitored image to obtain the filtered pixels corresponding to each pixel. All the filtered pixels form the filtered image.

[0129] The working principle of the above technical solution: In this embodiment, the specific implementation of determining the first weight corresponding to the first filtered pixel value according to the first preset weight function is as follows: The first preset weight function is determined as follows: Where W1 is the first weight, p1 is the target pixel mean of all pixels in the target region, and p2 is the pixel mean of all pixels in the square region corresponding to the first filtered pixel value.

[0130] In this embodiment, the specific implementation of obtaining the target gradient value of the target pixel and determining the first coefficient based on the target gradient value is as follows: If the target pixel is determined to be pixel j, then the target gradient value is... Where G(j) is the target gradient value of pixel j. This is the square of the pixel difference between pixel j and its neighboring pixels in the horizontal direction. Let be the square of the pixel difference between pixel j and its neighboring pixels in the vertical direction. Then the expression for the first coefficient is: Where a1 is the first coefficient.

[0131] In this embodiment, the specific implementation of determining the second coefficient based on the first coefficient, the target pixel mean, and the grayscale pixel mean is as follows: a2 = p1 - a1 × p3, where a2 is the second coefficient, p1 is the target pixel mean, and p3 is the grayscale pixel mean.

[0132] In this embodiment, the specific implementation of obtaining the target pixel value of the target pixel and determining the second filtered pixel value corresponding to the target pixel based on the target pixel value, the first coefficient, the second coefficient, and the preset filtering formula is as follows: The preset filtering formula is... Where E is the second filtered pixel value. The target pixel value.

[0133] In this embodiment, the specific implementation of determining the second weight corresponding to the second filtered pixel value according to the second preset weight function is as follows: the second preset weight function is W2 = 1 - W1, where W2 is the second weight.

[0134] An N×N neighborhood matrix is ​​constructed centered on the target pixel, dividing the neighborhood into four equally sized square sub-regions. For each sub-region, the following values ​​are calculated: pixel mean (reflecting overall brightness), pixel median (resisting impulse noise), and pixel mode (reflecting the main distribution). The arithmetic mean of these three values ​​is used to obtain the estimated value for each sub-region. The absolute difference between the target pixel value and the estimated values ​​of each sub-region is calculated, and the estimated value corresponding to the smallest difference is selected as the initial filtering result. Gradient information is introduced, and the gradient value of the target pixel is calculated. The gradient value determines the first coefficient, and the second filtered pixel value corresponding to the target pixel is determined based on the target pixel value, the first coefficient, the second coefficient, and the preset filtering formula; then, enhancement filtering is performed. The first product of the first filtered pixel value and the first weight, and the second product of the second filtered pixel value and the second weight are calculated. The sum of the first and second products is used as the filtered pixel value for the target pixel; the target pixel value is replaced with the filtered pixel value to obtain the filtered pixel value corresponding to the target pixel, thus achieving pixel filtering processing.

[0135] The beneficial effects of the above technical solution are: the filtering module achieves a balance between noise suppression and detail preservation through multi-level feature fusion, which facilitates the acquisition of accurate filtered images.

[0136] According to some embodiments of the present invention, the multi-axis linkage module includes X-axis linear motion, Y-axis linear motion and Z-axis linear motion axes, and at least one rotary axis; the X-axis linear motion, Y-axis linear motion and Z-axis linear motion axes are used to realize the linear motion of the tool in three mutually perpendicular directions; the rotary axis is used to realize the rotational motion of the tool around a specific axis.

[0137] The working principle and beneficial effects of the above technical solution are as follows: X-axis linear motion: controls the movement of the tool in the horizontal direction (the front-to-back direction of the machine tool). Y-axis linear motion: controls the movement of the tool in another horizontal direction (the left-to-right direction of the machine tool). Z-axis linear motion: controls the movement of the tool in the vertical direction (the up-to-down direction of the machine tool). High-precision linear guides and ball screws are used to achieve smooth and accurate linear motion. Servo motors and encoders are integrated to achieve closed-loop control of each axis, improving motion accuracy. Rotary axes enable the tool to rotate around specific axes, increasing the flexibility and complexity of machining. The rotary axis can be at least one of rotation around the X-axis, Y-axis, or Z-axis. By coordinating the control of the X-axis, Y-axis, Z-axis linear motion axes, and rotary axes, complex trajectory movements of the tool in three-dimensional space are achieved.

[0138] According to some embodiments of the present invention, it further includes: a processing quality inspection module, used for:

[0139] The processed fasteners are subjected to quality inspection, and the inspection results are obtained.

[0140] The processing quality of the fasteners is determined based on the test results. If it does not meet the requirements, the processing control strategy is optimized and adjusted, and the processing is repeated. If it meets the requirements, the processing task is completed.

[0141] The working principle of the above technical solution is as follows: Quality inspection is performed on the machined fasteners to obtain the inspection results. Inspection items include, but are not limited to, key quality indicators such as dimensional accuracy, shape accuracy, surface roughness, hardness, and material composition. Based on the fastener's design requirements and industry standards, a qualified quality standard range is set. The inspection results are compared with the set quality standards to determine whether the machining quality meets the requirements. The quality judgment result is output, including qualified, unqualified, and specific unqualified items. The reasons for unqualified machining quality are analyzed, such as tool wear, improper cutting parameters, and insufficient machine tool accuracy. Based on the cause analysis results, the machining control strategy is adjusted, such as replacing tools, optimizing cutting parameters, and calibrating the machine tool. The machining is then repeated according to the adjusted machining control strategy, and quality inspection is performed again.

[0142] The beneficial effects of the above technical solution are as follows: the processing quality inspection module integrates functions such as quality inspection, quality judgment, optimization and adjustment of processing control strategies, and completion of processing tasks, thereby realizing comprehensive monitoring and management of the quality of fasteners after processing.

[0143] like Figure 8 As shown, according to some embodiments of the present invention, the machining method for fasteners using a CNC machining center as described above includes steps S1-S4:

[0144] S1. Based on the processing specifications, clamp the fasteners onto the process plate;

[0145] S2. Perform workpiece calibration by visual photography on the fasteners on the process plate.

[0146] S3. Generate a machining control strategy for the fasteners after workpiece calibration based on machining parameters;

[0147] S4. The motion axes of the multi-axis linkage module drive the tool to move according to the machining control strategy.

[0148] The working principle and beneficial effects of the above technical solution are as follows: Based on processing specifications, fasteners are accurately clamped onto the process plate, effectively avoiding processing errors caused by improper clamping. This ensures the processing accuracy of fasteners from the source, reduces scrap caused by clamping problems, and improves the product qualification rate. Visual calibration of the fasteners on the process plate allows for timely detection and correction of fastener positional deviations. The generation of processing control strategies based on processing parameters achieves intelligent and precise processing. The processing control strategy can be flexibly adjusted for fasteners of different specifications and requirements, ensuring the tool follows the optimal path, improving processing accuracy and production efficiency, and reducing reliance on operator experience. The multi-axis linkage module contains at least three motion axes, each driving the tool according to the processing control strategy, realizing complex processing trajectories and meeting the processing needs of various types of fasteners.

[0149] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A CNC machining center for fasteners, characterized in that, include: Clamping module, used to clamp fasteners onto the process plate according to machining specifications; The vision module is used to perform workpiece calibration by visual photography on the fasteners on the process plate. The CNC module is used to generate machining control strategies for fasteners after workpiece calibration based on machining parameters; The multi-axis linkage module is electrically connected to the CNC module and contains at least three motion axes. Each motion axis drives the tool to move according to the machining control strategy. It also includes: a tool monitoring module, which monitors the tool status and issues an alarm when the tool status is found to be abnormal; The tool monitoring module includes: The first identification module is used to acquire monitoring images of the cutting tool, identify the monitoring images, and obtain first monitoring information. The second identification module is used to collect vibration and sound signals of the cutting tool during the cutting process, identify the vibration and sound signals, and obtain the second monitoring information. The first determination module is used to determine the tool status based on the first monitoring information and the second monitoring information, and to issue an alarm when the tool status is determined to be abnormal. The first identification module includes: The filtering module is used to filter the monitoring image to obtain a filtered image; The second determining module is used for: The filter image is extracted using a preset contour detection algorithm to obtain a contour image; Key points are extracted from the contour image to obtain the target key points; Extract key points from the preset contour images in the preset contour image library to obtain the preset key points corresponding to each preset contour image. The lower left corner of the contour image is used as the origin of the coordinate system to obtain the target coordinates of the target key points. The target feature vector of the contour image is then determined based on the target coordinates. The lower left corner of each preset contour image is taken as the origin of the coordinate system to obtain the coordinates of the preset key points corresponding to the preset contour image. Based on the coordinates of the preset key points, the preset feature vector corresponding to the preset contour image is determined. Calculate the cosine distance between the target feature vector and each preset feature vector; The cosine distance is compared with a preset distance threshold to obtain comparison information, and the first monitoring information is obtained based on the comparison information. The filtering module includes: The third determining module is used for: Identify any pixel in the monitored image as the target pixel, and determine the target region centered on the target pixel. The target region is an N×N pixel matrix, where N is an even number. Divide the target region into four square regions with side length N / 2, and select one of them as the square region to be processed. Obtain the pixel mean, pixel median, and pixel mode of all pixels in the square region to be processed. Obtain the sum of the pixel mean, pixel median, and pixel mode, and determine the first mean corresponding to the pixel mean, pixel median, and pixel mode based on the sum. Use the first mean as the first estimated value of the target pixel. The above operation is performed on all the remaining square regions to obtain the second, third, and fourth estimates of the target pixel. Replacement module, used for: Obtain the target pixel value of the target pixel, calculate the absolute value of the difference between the target pixel value and the first estimate, the second estimate, the third estimate and the fourth estimate respectively, and take the estimate corresponding to the smallest absolute value as the first filtered pixel value of the target pixel; The first weight corresponding to the first filtered pixel value is determined according to the first preset weight function; Obtain the target gradient value of the target pixel, and determine the first coefficient based on the target gradient value; Obtain the target pixel mean of all pixels in the target region; Convert the image to a grayscale image, determine the target grayscale region corresponding to the target region in the grayscale image, and obtain the average grayscale pixel value of all pixels in the target grayscale region; The second coefficient is determined based on the first coefficient, the average value of the target pixel, and the average value of the grayscale pixels; Obtain the target pixel value of the target pixel, and determine the second filtered pixel value corresponding to the target pixel based on the target pixel value, the first coefficient, the second coefficient and the preset filtering formula; The second weight corresponding to the second filtered pixel value is determined according to the second preset weight function; Calculate the first product of the first filtered pixel value and the first weight, and the second product of the second filtered pixel value and the second weight. Use the sum of the first and second products as the filtered pixel value of the target pixel. Replace the target pixel value with the filtered pixel value to obtain the filtered pixel corresponding to the target pixel. Perform the above operations on all pixels in the monitored image to obtain the filtered pixels corresponding to each pixel. All the filtered pixels form the filtered image.

2. The CNC machining center for fasteners as described in claim 1, characterized in that, The vision module includes: The acquisition module is used to acquire images of fasteners on the process board through visual photography. The comparison module is used to compare the captured image with a preset database to obtain a matching image, and then perform workpiece calibration based on the matching image.

3. The CNC machining center for fasteners as described in claim 1, characterized in that, The numerical control module includes: The cutting parameter acquisition module is used to determine the material properties and tool type of the fastener after workpiece calibration, input the material properties and tool type into a pre-built fuzzy rule base, and output the cutting parameters, which include cutting speed, feed rate and depth of cut. The toolpath planning module is used to plan toolpaths. The first generation module is used to determine the machining parameters based on the cutting parameters and tool path, and generate a machining control strategy based on the machining parameters.

4. The CNC machining center for fasteners as described in claim 3, characterized in that, The route planning module includes: The extraction module is used to generate a 3D model of the fastener after workpiece calibration, preprocess the 3D model, and extract machining features. The second generation module is used to plan and generate the initial toolpath based on machining features and machining process requirements; The optimization module is used to optimize the initial toolpath using a genetic algorithm to obtain the final toolpath.

5. The CNC machining center for fasteners as described in claim 1, characterized in that, The multi-axis linkage module includes X-axis linear motion, Y-axis linear motion, and Z-axis linear motion axes, as well as at least one rotary axis; the X-axis linear motion, Y-axis linear motion, and Z-axis linear motion axes are used to realize the linear motion of the tool in three mutually perpendicular directions; the rotary axis is used to realize the rotational motion of the tool around the axis.

6. The CNC machining center for fasteners as described in claim 1, characterized in that, Also includes: The processing quality inspection module is used for: The processed fasteners are subjected to quality inspection, and the inspection results are obtained. The processing quality of the fasteners is determined based on the test results. If it does not meet the requirements, the processing control strategy is optimized and adjusted, and the processing is repeated. If it meets the requirements, the processing task is completed.

7. The machining method for fasteners using a CNC machining center as described in any one of claims 1-6, characterized in that, include: Fasteners are clamped onto the process plate according to the processing specifications; The fasteners on the process plate are calibrated using visual photography. A machining control strategy is generated based on machining parameters for fasteners after workpiece calibration. The multi-axis linkage module includes motion axes that drive the tool to move according to the machining control strategy.

Images