A control method based on visual recognition, automatic tool sharpening system

Abstract

The application discloses a control method based on visual identification, a cutter automatic sharpening system, and the control method based on visual identification comprises a compensation step: acquiring an image sequence of a disc-shaped grinding wheel, the image sequence comprising a plurality of first images. The plurality of first images of the image sequence are preprocessed to obtain a plurality of first binary images. The plurality of first binary images are synthesized into a synthesized contour image by using a preset algorithm. Based on the synthesized contour image and a standard contour image, the radius variation of the disc-shaped grinding wheel is identified. A compensation configuration matched with the radius variation is queried, and the sharpening mechanism is positionally compensated based on the compensation configuration. The mode based on visual identification and position compensation can adjust in real time and accurately according to the wear condition of the grinding wheel, effectively avoids the decrease of cutter polishing quality caused by the wear of the grinding wheel, and realizes stable and reliable continuous production.

Description

Technical Field

[0001] This invention relates to the field of computer data processing technology, and in particular to a control method based on vision recognition and an automatic tool sharpening system. Background Technology

[0002] With the development of industrialization, machining has been widely used in kitchen knife manufacturing. Various mechanical equipment, such as stamping presses and grinding machines, can effectively complete the forming and polishing processes of knives, meeting the demands of a large-scale market and representing one of the main methods of kitchen knife processing today.

[0003] The sharpening process of kitchen knives is a crucial step in the entire manufacturing process, directly affecting the knife's sharpness, durability, appearance quality, and performance. Chinese invention patent CN119772669A discloses a data processing method, a data processing system, and a fully automated intelligent knife production equipment. The data processing method is implemented based on a fully automated intelligent knife production equipment, which includes a camera assembly, a robotic arm, and a sharpening machine. This equipment is used for sharpening knives. The data processing method includes: instructing the robotic arm to grasp the knife to be sharpened; acquiring first image data from the camera assembly, the image content of which is the knife to be sharpened grasped by the robotic arm; identifying the knife type in the first image data; querying preset trajectory data matching the knife type, the preset trajectory data including a first trajectory and a second trajectory; instructing the sharpening machine to move to a target position along the first trajectory; and instructing the robotic arm to grasp the knife to be sharpened and move it to its initial position, then sharpening it on the sharpening machine along the second trajectory.

[0004] Existing technology uses commands to move the sharpening machine to accommodate the sharpening of different kitchen knives, reducing the control requirements of the robotic arm. However, the applicant found that in continuous operation, the sharpening quality of some kitchen knives cannot meet the required standards, making it difficult to guarantee the stability of kitchen knife product quality and reliable continuous mass production. Summary of the Invention

[0005] To address the technical problems existing in the prior art, the present invention aims to provide a control method based on vision recognition and an automatic tool sharpening system.

[0006] The objective of this invention is achieved through the following technical solution:

[0007] In a first aspect, the present invention provides a vision-based control method, which is implemented based on an automatic tool sharpening system. The automatic tool sharpening system includes a camera assembly, a robotic arm, a moving mechanism, and a sharpening mechanism, wherein the sharpening mechanism has a disc-shaped grinding wheel. The control method includes the following position compensation steps:

[0008] An image sequence of the disc-shaped grinding wheel is acquired, the image sequence including multiple first images, the multiple first images being obtained by the camera component rotating and sampling a local circumferential contour of the disc-shaped grinding wheel in the vertical direction;

[0009] The image sequence is preprocessed to obtain multiple first binary images;

[0010] A pre-defined algorithm is used to synthesize multiple first binary images to obtain a synthesized contour image.

[0011] Based on the synthesized contour image and the standard contour image, the radius change of the disc grinding wheel is identified;

[0012] Query the compensation configuration that matches the radius change, and perform position compensation on the grinding mechanism based on the compensation configuration.

[0013] In conjunction with the first aspect, the present invention provides a first specific implementation of the first aspect, specifically, employing a preset algorithm to synthesize multiple first binary images to obtain a synthesized contour image, specifically including:

[0014] Perform global thresholding segmentation on multiple first images;

[0015] Multiple first images are debinarized, and the pixel gray values ​​of the disc-shaped grinding wheel portion in the first image are set to 1, while the pixel gray values ​​of the non-disc-shaped grinding wheel portion are set to 0.

[0016] Opening morphological processing is performed on multiple first images;

[0017] Based on the contour frequency image generation algorithm, multiple first images are synthesized to obtain a contour image.

[0018] In conjunction with the first aspect, the present invention provides a second specific implementation of the first aspect, specifically, querying a compensation configuration that matches the radius change, specifically including:

[0019] When the radius change is less than or equal to a preset threshold S min At this time, no position compensation is required;

[0020] When the preset threshold S min <The radius change amount <Preset threshold S n At that time, the compensation configuration R is invoked. nn is an integer greater than or equal to 0;

[0021] When the preset threshold S n <The radius change amount <Preset threshold S n+1 At that time, the compensation configuration R is invoked. n+1 ;

[0022] When the preset threshold S max When the radius change is less than or equal to the specified amount, the disc grinding wheel is identified as being in a state of rapid wear, and an alarm message is generated indicating that the disc grinding wheel needs to be replaced or re-corrected.

[0023] In conjunction with the first aspect, the present invention provides a third specific embodiment of the first aspect, specifically, the control method further includes:

[0024] The number of tools that have completed the sharpening process by the sharpening mechanism is accumulated, and the sharpening value of the tools is output in real time.

[0025] When the sharpening value meets the preset sharpening value, the position compensation step is executed again.

[0026] In conjunction with the first aspect, the present invention provides a fourth specific embodiment of the first aspect. Specifically, when performing the position compensation step, the control method further includes the following steps:

[0027] A second image of the disc-shaped grinding wheel is obtained, which is a horizontal image of the end face of the disc-shaped grinding wheel captured by the camera assembly.

[0028] Identify the second image and output the outer circumference contour of the disc-shaped grinding wheel;

[0029] Calculate the actual cross-sectional area of ​​the disc-shaped grinding wheel based on its outer circular profile.

[0030] Based on the preset cross-sectional area and the actual cross-sectional area, the cross-sectional area loss of the disc grinding wheel is obtained;

[0031] When the cross-sectional area loss exceeds a preset threshold, the disc grinding wheel is identified as being in a state of rapid wear, and an alarm message is generated to replace or re-correct the disc grinding wheel.

[0032] In conjunction with the first aspect, the present invention provides a fifth specific embodiment of the first aspect, specifically, recognizing the second image and outputting the outer circumference contour of the disc-shaped grinding wheel, specifically including:

[0033] The second image is converted into a grayscale image, and the grayscale image is binarized to obtain a second binary image;

[0034] The second binary image is identified using a subpixel edge detection method to obtain multiple contour edge points of the disc grinding wheel;

[0035] Input multiple contour edge points into the MATLAB application to output the outer circle contour of the disc grinding wheel.

[0036] Secondly, the present invention also provides an automatic tool sharpening system, the automatic tool sharpening system comprising:

[0037] A frame is provided with a moving mechanism, a grinding mechanism, a camera assembly, a light source assembly, and a controller. The moving mechanism is fixedly connected to the frame and drives the grinding mechanism. The grinding mechanism has a disc-shaped grinding wheel. The camera assembly and the light source assembly are respectively located on the side of the grinding mechanism.

[0038] A robotic arm, located on the side of the frame, is used to grab the cutting tool to be sharpened from the feeding tool holder and move the cutting tool to the sharpening mechanism for sharpening.

[0039] The controller is configured to execute the following control method:

[0040] The image sequence acquired by the camera component is obtained, the image sequence including multiple first images, the multiple first images being obtained by the camera component rotating and sampling a local circumferential contour of the disc grinding wheel in the vertical direction;

[0041] The image sequence is preprocessed to obtain multiple first binary images;

[0042] A pre-defined algorithm is used to synthesize multiple first binary images to obtain a synthesized contour image.

[0043] Based on the synthesized contour image and the standard contour image, the radius change of the disc grinding wheel is identified;

[0044] The system queries a compensation configuration that matches the radius change and controls the moving mechanism to perform position compensation on the grinding mechanism based on the compensation configuration.

[0045] In conjunction with the second aspect, the present invention provides a first specific embodiment of the second aspect, specifically, the moving mechanism includes:

[0046] A transverse moving screw pair, which is fixedly connected to the frame;

[0047] A longitudinal moving lead screw pair is connected to the transverse moving lead screw pair, and the longitudinal moving lead screw pair is connected to the grinding mechanism;

[0048] The controller controls the longitudinal movement screw pair of the moving mechanism to perform position compensation on the grinding mechanism based on the compensation configuration, so as to adjust the distance between the grinding mechanism and the robot arm.

[0049] In conjunction with the second aspect, the present invention provides a second specific embodiment of the second aspect. Specifically, the frame is further provided with a white background plate, which is disposed on one side of the disc-shaped grinding wheel of the grinding mechanism, and the surface of the white background plate is parallel to the end face of the disc-shaped grinding wheel.

[0050] In conjunction with the second aspect, the present invention provides a third specific embodiment of the second aspect. Specifically, the grinding mechanism has a disc-shaped grinding wheel, the outer circumference of which is used for sharpening, the disc-shaped grinding wheel is horizontally arranged, the outer circumference of which faces the robot arm, and the outer circumference of which is used for sharpening.

[0051] Through in-depth research, the applicant discovered that existing technologies, by instructing the movement of the sharpening machine, can accommodate the sharpening of different kitchen knives, reducing the control requirements of the robotic arm. However, existing technologies neglect the wear and tear of the sharpening wheel after large-scale continuous sharpening, which directly affects the sharpening quality of the products, causing the technical problem that the sharpening quality of some kitchen knives cannot meet the required specifications.

[0052] Compared with the prior art, the present invention has at least the following beneficial effects:

[0053] This invention provides a vision-based control method implemented using an automatic tool sharpening system. The automatic tool sharpening system includes a camera assembly, a robotic arm, a moving mechanism, and a sharpening mechanism, the sharpening mechanism having a disc-shaped grinding wheel. The control method includes the following position compensation steps: acquiring an image sequence of the disc-shaped grinding wheel, the image sequence including multiple first images, which are obtained by the camera assembly rotating and sampling a local circumferential contour of the disc-shaped grinding wheel in a vertical direction. Preprocessing the multiple first images of the image sequence to obtain multiple first binary images. Using a preset algorithm, synthesizing the multiple first binary images to obtain a synthesized contour image. Based on the synthesized contour image and a standard contour image, identifying the radius change of the disc-shaped grinding wheel. Querying a compensation configuration matching the radius change, and performing position compensation on the sharpening mechanism based on the compensation configuration.

[0054] This invention acquires and processes image sequences of a disc-shaped grinding wheel to identify changes in the wheel radius, thereby compensating for the position of the grinding mechanism. This method, based on visual recognition and position compensation, can adjust the grinding mechanism in real time and accurately according to the wear of the grinding wheel, effectively preventing a decline in knife grinding quality caused by wheel wear. This significantly improves the stability of kitchen knife grinding quality, ensuring that each kitchen knife meets the expected quality indicators and achieving stable and reliable continuous mass production.

[0055] This invention utilizes a vision-based control method to achieve automated monitoring and compensation, avoiding the uncontrollable product quality issues caused by grinding mill errors in existing technologies. By automatically identifying and calculating changes in the grinding wheel radius through a preset algorithm, and automatically compensating for the position of the grinding mechanism according to the compensation configuration, the automation and intelligence levels of production are improved.

[0056] This invention also provides an automatic knife sharpening system, whose equipment composition and controller control method have achieved the same technical effects as those available in the market. Attached Figure Description

[0057] Figure 1 This is a system composition diagram of an automatic tool sharpening system according to the present invention;

[0058] Figure 2 This is a schematic diagram of the frame structure of an automatic tool sharpening system according to the present invention;

[0059] Figure 3 This is a schematic diagram of the moving mechanism and the sharpening mechanism of an automatic knife sharpening system according to the present invention;

[0060] Figure 4 This is a diagram showing the arrangement of the first camera in an automatic tool sharpening system according to the present invention.

[0061] Figure 5 This is a flowchart illustrating a visual recognition-based control method according to the present invention.

[0062] In the picture:

[0063] 100-robotic arm;

[0064] 200 - Sharpening mechanism; 210 - Disc grinding wheel;

[0065] 300 - Moving mechanism, 310 - Lateral moving screw pair, 320 - Longitudinal moving screw pair. Detailed Implementation

[0066] To facilitate understanding of the present invention, the technical solutions and advantages of the invention will be further described in detail below with reference to the accompanying drawings and embodiments. Any mechanisms or methods not elaborated in this invention can be referred to in the prior art. The specific structures and features of the present invention are illustrated below by way of example and should not be construed as limiting the present invention in any way. Furthermore, any of the technical features mentioned below (including implicit or disclosed features), as well as any technical features directly shown or implied in the figures, can be arbitrarily combined or deleted among these technical features to form more other embodiments that may not be directly or indirectly mentioned in this invention. The accompanying drawings show preferred embodiments of the present invention. However, the present invention can be implemented in many different forms and is not limited to the embodiments described herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of the disclosure of the present invention.

[0067] Currently, in the kitchen knife manufacturing industry, with the acceleration of industrialization, automated mass production has become the mainstream production mode. As mentioned in the background technology, in order to better adapt to the production needs of different kitchen knives, the industry has continuously optimized and improved kitchen knife production equipment. Existing technology uses commands to move the sharpening machine to accommodate the sharpening of different kitchen knives, reducing the control requirements of the robotic arm. However, the applicant found that in continuous operation, the sharpening quality of some kitchen knives cannot meet the required standards, making it difficult to guarantee the stability of kitchen knife product quality and reliable continuous mass production.

[0068] Through in-depth research, the applicant discovered that existing technologies, by instructing the movement of the sharpening machine, can accommodate the sharpening of different kitchen knives, reducing the control requirements of the robotic arm. However, existing technologies neglect the wear and tear of the sharpening wheel after large-scale continuous sharpening, which directly affects the sharpening quality of the products, causing the technical problem that the sharpening quality of some kitchen knives cannot meet the required specifications.

[0069] Therefore, refer to Figure 5 This invention provides a flowchart illustrating a vision-based control method. The main function of this invention is to acquire and process image sequences of a disc-shaped grinding wheel, identify changes in the wheel radius, and then compensate the position of the grinding mechanism. This vision-based recognition and position compensation method can adjust the grinding mechanism in real time and accurately according to the wear of the grinding wheel, effectively preventing a decline in knife grinding quality due to wheel wear. This significantly improves the stability of kitchen knife grinding quality, ensuring that each kitchen knife meets the expected quality indicators and achieving stable and reliable continuous mass production.

[0070] Example 1

[0071] like Figures 1-4 As shown, this invention presents a preferred structure of an automatic tool sharpening system.

[0072] In this invention, an automatic knife sharpening system is used for sharpening and edge-opening kitchen knives. The automatic knife sharpening system includes a frame and a robotic arm. The frame is equipped with a moving mechanism, a sharpening mechanism, a camera assembly, a light source assembly, and a controller. The moving mechanism is fixedly connected to the frame and drives the sharpening mechanism, which has a disc-shaped grinding wheel. The camera assembly and the light source assembly are respectively located beside the sharpening mechanism. The robotic arm is located beside the frame and is used to grasp the knife to be sharpened from the knife holder and move it to the sharpening mechanism for edge-opening. The controller is used to execute and implement the vision-based control method described below.

[0073] The automatic tool sharpening system of this invention achieves automated monitoring and compensation, avoiding the problem of uncontrollable product quality caused by grinding machine errors in existing technologies. It automatically identifies and calculates the change in grinding wheel radius through a preset algorithm, and automatically compensates the position of the sharpening mechanism according to the compensation configuration, thereby improving the automation and intelligence level of production.

[0074] In one specific implementation, the frame is a metal frame assembled from multiple square tubes and a metal shell. A workbench is installed above the frame to house the moving mechanism, grinding mechanism, camera assembly, and light source assembly. Electrical components, such as controllers, are housed within the electrical cabinet of the frame.

[0075] In some implementations, the moving mechanism is responsible for driving the grinding mechanism along a preset path to adapt to the grinding needs at different positions, and also for position compensation of the grinding mechanism. Specifically, the moving mechanism includes:

[0076] The lateral moving lead screw pair is fixedly connected to the machine frame.

[0077] The longitudinal moving screw pair is connected to the transverse moving screw pair, and the longitudinal moving screw pair is connected to the grinding mechanism.

[0078] The controller uses a longitudinal moving screw pair of the control mechanism based on compensation configuration to perform position compensation on the grinding mechanism, so as to adjust the distance between the grinding mechanism and the robot arm.

[0079] In automated tool sharpening systems, the design of the moving mechanism ensures that the sharpening mechanism can move precisely along a preset path to perform position compensation and guarantee sharpening accuracy. Therefore, a lead screw pair is a suitable choice. Lead screw pairs offer high-precision positioning capabilities and provide very precise control over minute movements, which is crucial for compensating for grinding wheel wear in the sharpening mechanism. This is because precise control of the sharpening mechanism's position is necessary to ensure sharpening quality, and lead screw pairs provide excellent positioning accuracy, stability, and repeatability.

[0080] Understandably, the lateral movement screw pair is responsible for driving the grinding mechanism's movement in the horizontal direction (X-axis). This screw pair is fixedly connected to the frame, providing a stable lateral movement platform for the grinding mechanism. The longitudinal movement screw pair is responsible for driving the grinding mechanism's movement in the longitudinal direction (Y-axis), which is perpendicular to the horizontal direction. The longitudinal movement screw pair is connected to the lateral movement screw pair, thereby achieving positional compensation relative to the manipulator. The controller controls the longitudinal movement screw pair of the moving mechanism based on the compensation configuration, performing positional compensation for the grinding mechanism.

[0081] In practice, both the transverse and longitudinal moving screw pairs are equipped with guide rail pairs, which provide guidance and stability through the guide rails and sliders.

[0082] In specific implementation, such as Figure 3 As shown, the sharpening mechanism has a disc-shaped grinding wheel. The outer circumference of the disc-shaped grinding wheel is used for sharpening the cutting edge. The disc-shaped grinding wheel is horizontally positioned, with its outer circumference facing the robot arm. The main function of the sharpening mechanism is to grind the cutting tool using a high-speed rotating grinding wheel, thus completing the sharpening process. In the automated system, the sharpening mechanism, in coordination with the robot arm and controller, ensures the accuracy and efficiency of tool sharpening.

[0083] The sharpening mechanism consists of a base, motor, transmission assembly, spindle, and disc grinding wheel. The base is connected to a transverse sliding screw pair. The outer circumference of the disc grinding wheel is the part that directly contacts the cutting edge of the tool, responsible for grinding and dressing the tool's cutting edge to achieve the desired sharpness and shape. The outer circumference of the grinding wheel faces the robotic arm; this arrangement ensures that when the robotic arm grasps the tool and moves it to the sharpening mechanism, the tool's cutting edge can directly contact the abrasive on the grinding wheel, facilitating the sharpening operation.

[0084] In one specific implementation, the sharpening mechanism of this invention is a movable design. Because each type of knife has different dimensions such as length, width, and thickness, the shape of the blade edge and the cutting angle also vary. By combining position compensation with high-precision adjustment of the sharpening mechanism, the contact position and angle between the disc grinding wheel and the knife can be ensured to be accurate, thereby achieving ideal sharpening quality. Different types of knives may require different sharpening processes. The automated sharpening mechanism, combined with disc grinding wheel wear detection for positional compensation, can flexibly address these differences. Furthermore, for knives of the same type with minor specification differences, the processing path of the robotic arm can be slightly adjusted without altering or modifying the existing path, thus meeting the processing needs of different knives. In addition, by combining vision recognition and position compensation, adjustments can be made in real time and accurately based on the wear condition of the disc grinding wheel, effectively preventing a decline in knife sharpening quality due to disc grinding wheel wear. This significantly improves the stability of kitchen knife sharpening quality, ensuring that each kitchen knife meets the expected quality indicators and achieving stable and reliable continuous mass production.

[0085] It is evident that only by automating the adjustment of the grinding mechanism's position, combined with position compensation for grinding wheel wear, can precise adjustments be made according to the specific shape, size, and angle of each tool, enabling high-quality, continuous mass production. Furthermore, the high-precision adjustable position design of the grinding mechanism is particularly effective for tools with small differences in shape and size, flexibly addressing the machining needs of various tools without requiring complex programming and path adjustments for robotic arms. In production, especially for small-batch tool production, this method offers greater flexibility and economy. This is because changing the position of the grinding mechanism is simpler and easier to implement. Moreover, for some tools, high-precision adjustment of the grinding mechanism's position may be faster than adjusting the robotic arm's path, allowing for quick adjustments without waiting for the design of complex robotic arm paths.

[0086] As shown in Figure 4, the imaging assembly includes a first industrial camera and a second industrial camera. The first industrial camera is mounted above the disc grinding wheel to capture a sequence of images of the grinding wheel, i.e., multiple first images. The second industrial camera is fixedly mounted on the base of the grinding mechanism via a bracket and moves synchronously with the grinding mechanism. The optical axis of the second industrial camera is coaxial with the axis of the disc grinding wheel and is at the same level. The second industrial camera is used to acquire second images.

[0087] In conjunction with the camera assembly, the light source assembly is positioned directly below the first camera, with the disc-shaped grinding wheel located between the first camera and the light source assembly. The light source assembly is fixed to the worktable and employs a telecentric parallel light source. In a preferred embodiment, blue LEDs with a wavelength of 460nm are used, which have lower reflectivity compared to white LEDs. This choice suppresses scattering and reflection from the circumferential surface of the grinding wheel, resulting in images with sharper contour edges, satisfying subsequent contour analysis.

[0088] In a preferred embodiment, the first industrial camera is equipped with dual telecentric lenses and uses a telecentric parallel light source to build an image acquisition system to acquire high-quality images of the grinding wheel contour. In another preferred embodiment, the first industrial camera is an MV-CH120-10TM monochrome grayscale industrial camera, using a SONY IMX253 CMOS chip with a pixel size of 3.45μm.

[0089] In a preferred embodiment, the front outer circumference of the disc grinding wheel faces the robot arm and is used for sharpening the cutting tool. The rear outer circumference of the disc grinding wheel faces the opposite side of the robot arm. Specifically, the first industrial camera and the light source assembly are both located on the rear side of the disc grinding wheel. This avoids contamination of the first industrial camera and the light source assembly by debris during processing, such as adhering to the optical components of the telecentric lens or the light-transmitting glass of the light source assembly, which would affect image acquisition.

[0090] In a preferred embodiment, the frame is further provided with a white background plate, which is positioned on one side of the disc-shaped grinding wheel of the grinding mechanism, with its surface parallel to the end face of the disc-shaped grinding wheel. The white background plate is positioned opposite to a second industrial camera, with the disc-shaped grinding wheel located between the white background plate and the second industrial camera. This aims to improve the accuracy of contour recognition of the disc-shaped grinding wheel in the second image. The white background plate provides a uniform and high-contrast background, making the contour edges sharper and enhancing the accuracy of image processing, facilitating subsequent image processing and analysis.

[0091] In one specific implementation, the robotic arm is set on the side of the frame, and the end effector of the robotic arm is equipped with a tool holder. The tool holder uses grippers to grasp the tool to be sharpened. Specifically, the robotic arm grasps the back of the tool to be sharpened, which is the position of the non-edge and non-handle.

[0092] Specifically, the robotic arm, through precisely controlled movement, moves the cutting tool to be sharpened from one position to another, such as from the loading tool holder to the sharpening mechanism, or moves a tool that has already been sharpened to a designated position, such as the quality inspection position or the unloading tool holder position. The controller generates control commands based on the data processing results and transmits them to the robotic arm. For example, based on the tool type and target trajectory, the controller instructs the robotic arm to grasp and position the tool, and instructs the moving mechanism to drive the sharpening mechanism to perform the sharpening operation along a preset trajectory. Specifically, the robotic arm is a commonly used device in this field and will not be elaborated upon further here.

[0093] For other technical implementations of the automatic tool sharpening system, please refer to the invention patent with announcement number CN119772669A.

[0094] In a preferred embodiment, the automatic tool sharpening system further includes a loading conveyor belt and a unloading conveyor belt, both of which are equipped with multiple tool holders. The loading conveyor belt transports multiple tools to be sharpened to the side of a robotic arm via the multiple holders, where the robotic arm picks up the tools to be sharpened from the holders on the loading conveyor belt. After sharpening, the robotic arm places the sharpened tools onto the holders on the unloading conveyor belt.

[0095] Example 2

[0096] refer to Figure 5Embodiment 2 of this invention provides a flowchart of a control method based on visual recognition. This invention provides a control technology for automated knife production equipment. The control method is based on the collaborative work of a camera assembly, a robotic arm, a moving mechanism, and a grinding mechanism. It is compatible with different types of knives and enables automated knife grinding operations with stable quality and continuous batch production. This control method acquires and processes image sequences of a disc grinding wheel to identify changes in the wheel radius, and then compensates for the position of the grinding mechanism. This method, based on visual recognition and position compensation, can adjust in real time and accurately according to the wear of the grinding wheel, effectively avoiding a decline in knife grinding quality caused by wheel wear. This significantly improves the stability of kitchen knife grinding quality, ensuring that each kitchen knife meets the expected quality indicators and achieving stable and reliable continuous batch production.

[0097] The control method of this invention can be executed by a control system, which can be implemented in hardware and / or software. This control system can be configured in the electronic equipment of the automatic tool sharpening system, such as a controller. The control method of this invention is based on an automatic tool sharpening system, specifically, the automatic tool sharpening system is completely identical to that described in Example 1. Figure 5 As shown, the visual recognition-based control method includes the following position compensation steps:

[0098] Step 501: Obtain an image sequence of the disc-shaped grinding wheel. The image sequence includes multiple first images, which are obtained by rotating and sampling a local circumferential contour of the disc-shaped grinding wheel in the vertical direction using a camera component.

[0099] In one possible implementation, the image sequence is acquired by the first industrial camera of the imaging component in Embodiment 1, combined with... Figure 4 As can be seen, for example, the controller starts the grinding mechanism, which controls the first camera to continuously and randomly acquire multiple photos, resulting in multiple first images of the disc grinding wheel in the circumferential direction, which are then combined into an image sequence.

[0100] Visual inspection based on a single cross-sectional profile cannot accurately reflect the actual wear profile of a disc grinding wheel. Therefore, in this application, an innovative method is used to detect the disc grinding wheel by synthesizing multiple cross-sectional profiles in the circumferential direction. The grinding wheel profile is rotated and sampled to obtain the full circumferential information of the disc grinding wheel profile. Based on the synthesized profile frequency image, the radius change is detected for position compensation.

[0101] Step 502: Preprocess the multiple first images of the image sequence to obtain multiple first binary images.

[0102] In one possible implementation, preprocessing includes image filtering and image enhancement. The implementation process of step S502 includes:

[0103] Step 5021: Apply guided filtering to the first image.

[0104] For example, guided filtering assumes the existence of local linear relationships within an image, considering the image as a non-analytical two-dimensional function, but locally expressible as an analytical linear function:

[0105]

[0106] In the formula q i I represents the filtered output image. i To guide the image (first image), Q k For a local window, a k and b k The coefficients are constants in the local window of k.

[0107] To reduce distortion, mean squared error is used for optimization:

[0108]

[0109] In the formula, ε is the compensation coefficient, p i This is the original image (first image).

[0110] Specifically, the least squares method can be used to calculate a. k and b k The value is . The guided filter works slightly better, removing a large amount of noise while preserving the outline edge details of the disc grinding wheel.

[0111] Step 5022: Perform grayscale transformation on the first image after filtering.

[0112] Gray-level transformation refers to mapping the pixel gray-level values ​​of an image according to a certain relationship, and can be divided into linear gray-level transformation and nonlinear gray-level transformation. In this application, piecewise linear transformation is used for image enhancement.

[0113] Step 5023: Convert the first image after grayscale transformation into a binary image, and divide the pixels in the image into foreground (grinding wheel outline) and background by setting a threshold. Commonly used binarization methods include global thresholding and adaptive thresholding.

[0114] Step 503: Use a preset algorithm to synthesize multiple first binary images to obtain a synthesized contour image.

[0115] In this application, the problem of poor detection accuracy due to the inability of a single cross-section to reflect the full contour information of the grinding wheel in traditional visual inspection is addressed. This invention synthesizes multi-section contour images of the disc-shaped grinding wheel for subsequent analysis. In one possible implementation, step 503 includes:

[0116] Step 5031: Perform global thresholding segmentation on multiple first images.

[0117] In step 5031, the disc-shaped grinding wheel portion in the first image is separated from the background, providing a basis for subsequent binarization processing. For example, a global threshold is selected to divide pixels in the image into foreground (disc-shaped grinding wheel portion) and background (non-disc-shaped grinding wheel portion). The global threshold can be automatically selected through histogram analysis, the Otsu method, etc., or it can be set manually. The grayscale value of each pixel in the first image is compared with the global threshold; pixels greater than the threshold are classified as foreground, and pixels less than or equal to the threshold are classified as background.

[0118] Understandably, the background and the grinding wheel contour in the preprocessed contour image have significant grayscale differences, so thresholding can be used to determine the contour edges. Thresholding is one of the most commonly used image segmentation methods. It divides pixels into different subsets based on their grayscale values, with each subset corresponding to different features.

[0119] Step 5032: Perform inverse binarization on multiple first images, setting the pixel grayscale value of the disc-shaped grinding wheel portion of the first image to 1, and setting the pixel grayscale value of the non-disc-shaped grinding wheel portion to 0.

[0120] In step 5032, the purpose is to generate a clear binary image that highlights the outline of the disc-shaped grinding wheel, facilitating subsequent morphological processing and contour extraction. For example, the segmented image is debinarized, meaning the pixel grayscale values ​​of the disc-shaped grinding wheel portion are set to 1, and the pixel grayscale values ​​of the non-disc-shaped grinding wheel portion are set to 0. This ensures that the disc-shaped grinding wheel is represented as white (pixel value 1) and the background as black (pixel value 0) in the binary image.

[0121] Step 5033: Perform opening operation morphological processing on multiple first images.

[0122] In this application, environmental factors (dust, etc.) in the production workshop can interfere with the subsequent testing process. Therefore, it is necessary to reduce interference noise in the contour image through image morphology operations.

[0123] In one possible implementation, the opening morphological operation can be used to remove discrete noise and edge burrs. Opening is an image processing operation based on mathematical morphology used to remove small objects, discrete noise, and edge burrs from an image while preserving the image's main structure. Opening consists of two basic operations: erosion and dilation. Specifically, opening first erodes the image, and then dilates the eroded image.

[0124] For example, erosion is a structuring element-based image processing method used to reduce the size of foreground objects in an image. The purpose of erosion is to remove small objects and edge burrs from an image.

[0125] h(x,y)=min (x′，y')：elem(x',y')≠0 g(x+x′,y+y′);

[0126] In the formula, elem represents a structuring element, (x, y) is the position of the anchor point of the structuring element, (x′, y′) is the position of the element with a value of 1 in the structuring element relative to its anchor point, h(x, y) is the output image, and g(x, y) is the input binary image.

[0127] For example, dilation is a structuring element-based image processing method used to increase the size of foreground objects in an image. The purpose of dilation is to fill in small holes and broken connections in the image.

[0128] h(x,y)=max (x′，y′)：elem(x',y′)≠0 g(x+x′,y+y′);

[0129] In the formula, elem represents a structuring element, (x, y) is the position of the anchor point of the structuring element, (x′, y′) is the position of the element with a value of 1 in the structuring element relative to its anchor point, h(x, y) is the output image, and g(x, y) is the input binary image.

[0130] Step 5034: Based on the contour frequency image generation algorithm, multiple first images are synthesized to obtain a contour image.

[0131] By using a contour frequency image generation algorithm, information from multiple images is combined to generate a complete and accurate synthetic contour image, providing high-quality contour data for subsequent radius change recognition. For example, for each pixel location, the frequency of that location being foreground (pixel value 1) in multiple first binary images is counted. The frequency values ​​can be normalized to the [0,1] interval, representing the probability that the location belongs to the contour of a disc grinding wheel.

[0132] In one possible implementation, a contour frequency image is generated based on contour frequency values, where regions with high frequency values ​​are more likely to represent the contour of a disc grinding wheel. Based on the contour frequency image, regions with frequency values ​​above a certain threshold (e.g., 0.5) are identified as part of a synthesized contour image. This allows for the integration of information from multiple first images, resulting in a more complete and accurate disc grinding wheel contour.

[0133] In one possible implementation, the contour frequency image generation algorithm sums the positions of identical pixels in the first image of the image sequence. The mathematical expression for the contour frequency image generation algorithm is:

[0134]

[0135] In the formula, N is the input image sequence after binarization and morphological processing, h(x,y) is the pixel value of the k-th image after binary inversion and morphological processing (x,y), and freq(x,y) is the value of the synthesized frequency image (x,y).

[0136] Step 504: Based on the synthesized contour image and the standard contour image, identify the radius change of the disc grinding wheel.

[0137] In one possible implementation, step 504 includes the following steps:

[0138] Step 5041: Extract the actual contour from the synthetic contour image.

[0139] For example, an edge detection algorithm (such as the Canny algorithm) is used to extract the contour line of a disc grinding wheel from a synthetic contour image. The Canny algorithm is able to effectively detect edges in the image and generate a clear contour line.

[0140] Step 5042: Identify the long side of the synthesized contour image.

[0141] For example, the long side can be identified from the extracted synthetic contour image. It can be understood that the synthetic contour image is actually a cross-sectional contour image of a disc-shaped grinding wheel, which resembles a rectangle. The four vertices of the contour can be determined by calculating a polygonal approximation (e.g., using OpenCV's cv2.approxPolyDP function), thereby identifying the long side.

[0142] Step 5043: Call the contour pixel data of the standard contour image.

[0143] For example, the standard contour image has been pre-associated with and stored with contour pixel data obtained through S5041 and S5042, i.e., the long side of the standard contour. In one possible implementation, the contour pixel data can be directly the number of pixels on the long side of the standard contour.

[0144] Step 5044: Calculate the pixel difference between the long side of the synthesized contour image and the long side of the standard contour image pixel by pixel.

[0145] For example, the contour pixel data of the standard contour image is the number of pixels on the long side of the standard contour. The number of pixels on the long side of the synthesized contour image is calculated pixel by pixel. The pixel difference is obtained by subtracting the number of pixels on the long side of the synthesized contour image from the number of pixels on the long side of the standard contour image. That is, pixel difference = number of pixels on the long side of the standard contour image - number of pixels on the long side of the synthesized contour image.

[0146] Step 5045: Output the change in radius.

[0147] Furthermore, in actual position compensation, the radius wear value of the disc grinding wheel can be derived from the radius change, i.e., radius change = pixel difference × pixel size, where pixel size is the actual physical size of each pixel in the image. Pixel size can be obtained through the camera calibration process or from the camera's parameter specifications.

[0148] For example, if the pixel difference is 10 pixels and the camera's pixel size is 0.05mm / pixel, then the radius change is calculated as follows: radius change = 10 pixels × 0.05mm / pixel = 0.5mm.

[0149] Step 505: Query the compensation configuration that matches the radius change, and perform position compensation on the grinding mechanism based on the compensation configuration.

[0150] In this application, the wear of the disc grinding wheel is the main reason why the grinding quality of the tool does not meet the requirements. Therefore, position compensation is performed on the grinding mechanism based on a compensation configuration. Specifically, a corresponding control signal is generated according to the compensation configuration and sent to the stepper motor of the longitudinal moving mechanism of the moving mechanism to execute the corresponding moving operation. For example, the stepper motor precisely moves the grinding mechanism to a specified position coordinate according to the number of pulses and the direction signal of the control signal. For instance, the feed rate of the longitudinal lead screw is set according to the radius change, directly changing the coordinate value that the grinding mechanism needs to compensate for to achieve the compensation purpose. The compensation principle is not complicated; the difficulty lies in how to identify the radius change.

[0151] One example involves querying a matching compensation configuration based on the identified radius change of the disc grinding wheel. The compensation configuration stores compensation measures to be taken for different radius changes, including parameters such as the direction and distance of movement.

[0152] In one possible implementation, step 505 involves querying a compensation configuration that matches the radius change, specifically including:

[0153] Step 505A: When the radius change is ≤ preset threshold S min At this time, no position compensation is required.

[0154] It is understandable that the change in radius ≤ S min This indicates that the wear of the grinding wheel is minor and no position compensation is required. For grinding wheels with slight wear, unnecessary compensation operations should be avoided. Additionally, this allows for some visual recognition error, thereby reducing system intervention and improving efficiency.

[0155] Step 505B: When the preset threshold S min<The radius change <Preset threshold S n At that time, the compensation configuration R is invoked. n , where n is an integer greater than or equal to 0.

[0156] In this application, when the radius change meets certain conditions, the compensation configuration Rn is invoked. The compensation configuration Rn is pre-set to handle wear conditions within this range. By invoking the corresponding compensation configuration, the position of the grinding mechanism is adjusted to ensure the accuracy of the machining process.

[0157] Step 505C: When the preset threshold S n <The radius change <Preset threshold S n+1 At that time, the compensation configuration R is invoked. n+1 .

[0158] Understandably, when the radius change meets certain conditions, the compensation configuration Rn is invoked. The compensation configuration Rn is pre-set to handle wear conditions within that range. By using multiple layers of different compensation configurations, it adapts to different wear levels, allowing for better adjustments and ensuring the accuracy of the machining process.

[0159] Step 505D: When the preset threshold S max When the radius change is less than or equal to the specified amount, the disc grinding wheel is identified as being in a state of rapid wear, and an alarm message is generated indicating that the disc grinding wheel needs to be replaced or re-corrected.

[0160] It is understandable that when the preset threshold S max When the radius change is less than or equal to the stated amount, it indicates that the disc grinding wheel has entered the third stage of wear, reaching a state of rapid wear. For severely worn grinding wheels, an alarm should be issued promptly to remind operators to replace or readjust the grinding wheel to avoid machining quality problems caused by grinding wheel wear.

[0161] The multi-layer compensation configuration is designed to adapt to grinding wheels at different wear stages, ensuring that the system maintains stable machining accuracy throughout the entire service life of the grinding wheel. Considering the wear pattern of the grinding wheel, this layered approach ensures accurate compensation, avoiding machining errors caused by under-compensation or over-compensation.

[0162] In some preferred embodiments, the control method further includes:

[0163] Step 506: Accumulate the number of tools that have completed the sharpening process by the sharpening mechanism and output the tool sharpening value in real time.

[0164] Understandably, the counter automatically increments by 1 each time the sharpening mechanism completes the sharpening process for a tool. For example, after the robotic arm picks up a tool to be sharpened and completes the sharpening process, the automatic tool sharpening system automatically starts counting.

[0165] Step 507: When the sharpening value meets the preset sharpening value, the position compensation step is executed again.

[0166] A preset sharpening value is set in the system, which can be determined based on the wear pattern of the sharpening mechanism and production requirements. For example, after processing a certain number of tools, the wear of the grinding wheel may reach a certain level, and the system automatically calls the position compensation step (steps 501-505) to perform new position compensation on the sharpening mechanism. This includes reacquiring the image sequence of the grinding wheel, performing image processing, calculating the radius change, and adjusting the position of the sharpening mechanism according to the new wear condition. By periodically re-executing the position compensation step, the system ensures that the sharpening mechanism maintains stable machining quality throughout long-term operation. This helps reduce machining errors caused by grinding wheel wear, improving product quality and production efficiency.

[0167] In metal grinding, the wear process of a disc grinding wheel can be divided into three stages: the initial wear stage (stage one), the wear and tear stage (stage two), and the rapid wear stage (stage three). In the third stage, as the dulling of the abrasive cutting edge exceeds a certain limit, the force acting on the abrasive grains increases dramatically, causing the abrasive grains to break into large pieces, the bonding agent to break, and the entire abrasive grain to fall off. Therefore, the wear of the grinding wheel increases dramatically, the curve rises very steeply, and the disc grinding wheel can no longer work properly, requiring dressing or replacement.

[0168] Therefore, this invention uses two methods to jointly determine the wear state of the disc grinding wheel. The first method, step 505D in step 505, determines whether the disc grinding wheel is in a stage of rapid wear by identifying the obtained radius change. The second method, when the controller performs the position compensation step, also includes the following steps:

[0169] Step 601: Obtain a second image of the disc-shaped grinding wheel. The second image is obtained by the camera assembly taking a picture of the end face of the disc-shaped grinding wheel from a horizontal direction.

[0170] In one possible implementation, the second image is acquired by the second industrial camera of the camera assembly in Embodiment 1. For example, the controller stops the grinding mechanism and controls the second camera to acquire the second image.

[0171] Step 602: Recognize the second image and output the outer circle contour of the disc grinding wheel.

[0172] In this invention, the outer circumference of the disc grinding wheel is extracted to provide contour data for subsequent cross-sectional area calculation.

[0173] In practical implementation, the second image needs to be preprocessed for image denoising. Since the outer circular contour image has high requirements for edge integrity, median filtering is used to process the noise in the second image. In one possible implementation, step 602, identifying the second image and outputting the outer circular contour of the disc-shaped grinding wheel, specifically includes:

[0174] Step 6021: Convert the second image into a grayscale image, and binarize the grayscale image to obtain a second binary image.

[0175] In this application, the image processing procedure is simplified to highlight the contour of the grinding wheel, providing a clear image foundation for subsequent edge detection. In one possible implementation, the color second image is converted to a grayscale image. Grayscale conversion can be achieved by using a weighted average method to convert an RGB image to grayscale.

[0176] For example, binarizing a grayscale image divides the pixels into foreground (grinding wheel portion) and background (non-grinding wheel portion). Common binarization methods include global thresholding (such as the Otsu method) and adaptive thresholding. Global thresholding determines a global threshold by calculating the image's histogram, while adaptive thresholding dynamically adjusts the threshold based on local regions of the image.

[0177] Step 6022: Use the subpixel edge detection method to identify the second binary image and obtain multiple contour edge points of the disc grinding wheel.

[0178] In one possible implementation, a sub-pixel edge detection method is used to process the binarized image. The sub-pixel edge detection method can improve the accuracy of edge detection and includes the following steps:

[0179] (1) Coarse edge detection: The edge detection algorithm (Canny algorithm) is used to initially extract the contour edges in the second image.

[0180] (2) Subpixel-level localization: Subpixel-level localization is performed on coarse edges to improve the accuracy of edge detection. Subpixel-level edge detection algorithms can be used, such as image interpolation-based methods or curve fitting-based methods. The contour edge points of the grinding wheel are extracted from the detected edges. These edge points will be used for subsequent contour fitting.

[0181] Step 6023: Input multiple contour edge points into the MATLAB application and output the outer circle contour of the disc grinding wheel.

[0182] In one possible implementation, the extracted contour edge points are imported into a MATLAB application. Specifically, the cftool curve fitting function in MATLAB is used. The extracted edge points are fitted using the cftool fitting tool. In the tool window, the x and y variables are selected respectively, and the fitting method is multinomial fitting.

[0183] Step 603: Calculate the actual cross-sectional area of ​​the disc grinding wheel based on its outer circumference.

[0184] In practice, the outer circumference of the disc grinding wheel is a curve obtained by polynomial fitting. The cross-sectional area is calculated based on the parameters of the fitted curve and the integration method. Specifically, the area is calculated using numerical integration.

[0185] Step 604: Based on the preset cross-sectional area and the actual cross-sectional area, obtain the cross-sectional area loss of the disc grinding wheel.

[0186] In one possible implementation, the difference between the preset cross-sectional area and the actual cross-sectional area is calculated to obtain the cross-sectional area loss. The calculation formula is: Cross-sectional area loss = Preset cross-sectional area - Actual cross-sectional area. By calculating the cross-sectional area loss, the wear degree of the grinding wheel can be quantified.

[0187] Step 605: When the cross-sectional area loss exceeds the preset threshold, the disc grinding wheel is identified as being in a state of rapid wear, and an alarm message is generated to replace or re-correct the disc grinding wheel.

[0188] In one possible implementation, a preset threshold for the amount of cross-sectional area loss is set based on the wear pattern of the disc grinding wheel to determine whether the disc grinding wheel has entered a state of rapid wear. For example, the preset threshold is determined by collecting cross-sectional area data of the disc grinding wheel at different stages of use and analyzing the wear pattern. When the cross-sectional area loss exceeds the preset threshold, the grinding wheel is identified as being in a state of rapid wear.

[0189] In the embodiments of this application, the terms "first," "second," and "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance. The term "at least one" refers to one or more, and the term "multiple" refers to two or more, unless otherwise expressly defined.

[0190] In this application, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this document generally indicates that the preceding and following related objects have an "or" relationship.

[0191] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the protection scope of the technical solutions of the embodiments of the present invention.

Claims

1. A control method based on visual recognition, characterized in that, The control method is based on an automatic tool sharpening system, which includes a camera assembly, a robotic arm, a moving mechanism, and a sharpening mechanism. The sharpening mechanism has a disc-shaped grinding wheel with its front outer circumference facing the robotic arm. The camera assembly includes a first industrial camera and a second industrial camera. The first industrial camera is positioned above the disc-shaped grinding wheel, and the second industrial camera is fixedly mounted on the base of the sharpening mechanism via a bracket. The optical axis of the second industrial camera is coaxial with the axis of the disc-shaped grinding wheel and is at the same level. The control method includes the following position compensation steps: An image sequence of the disc-shaped grinding wheel is acquired, the image sequence including multiple first images, the multiple first images being obtained by the camera component rotating and sampling a local circumferential contour of the disc-shaped grinding wheel in the vertical direction; The image sequence is preprocessed to obtain multiple first binary images; A pre-defined algorithm is used to synthesize multiple first binary images to obtain a synthesized contour image. Based on the synthesized contour image and the standard contour image, the radius change of the disc grinding wheel is identified, specifically including: The actual contour of the disc grinding wheel is extracted from the synthetic contour image using an edge detection algorithm; Identify the long side of the synthesized contour image from the actual contour; Call the contour pixel data of the standard contour image, wherein the contour pixel data is the number of pixels on the long side of the standard contour; The number of pixels on the long side of the synthesized contour image is calculated pixel by pixel, and the pixel difference is obtained by subtracting the number of pixels on the long side of the synthesized contour image from the number of pixels on the long side of the standard contour. The radius change is calculated based on the pixel difference. The process involves querying a compensation configuration that matches the radius change, and then performing position compensation on the grinding mechanism based on this configuration. Specifically, querying the compensation configuration that matches the radius change includes: when the radius change is ≤ a preset threshold S... min When the preset threshold S is reached, position compensation is not required; max When the radius change is less than or equal to the specified amount, the disc grinding wheel is identified as being in a state of rapid wear, and an alarm message is generated indicating that the disc grinding wheel needs to be replaced or re-corrected.

2. The control method based on visual recognition according to claim 1, characterized in that, A preset algorithm is used to synthesize multiple first binary images to obtain a synthesized contour image, specifically including: Perform global thresholding segmentation on multiple first images; Multiple first images are debinarized, and the pixel gray values ​​of the disc-shaped grinding wheel portion in the first image are set to 1, while the pixel gray values ​​of the non-disc-shaped grinding wheel portion are set to 0. Opening morphological processing is performed on multiple first images; Based on the contour frequency image generation algorithm, multiple first images are synthesized to obtain a contour image.

3. The control method based on visual recognition according to claim 1, characterized in that, Query the compensation configuration that matches the radius change, specifically including: When the preset threshold S min <The radius change amount <Preset threshold S n At that time, the compensation configuration R is invoked. n n is an integer greater than or equal to 0; When the preset threshold S n <The radius change amount <Preset threshold S n+1 At that time, the compensation configuration R is invoked. n+1 .

4. The control method based on visual recognition according to claim 1, characterized in that, The control method further includes: The number of tools that have completed the sharpening process by the sharpening mechanism is accumulated, and the sharpening value of the tools is output in real time. When the sharpening value meets the preset sharpening value, the position compensation step is executed again.

5. The control method based on visual recognition according to claim 1, characterized in that, The control method further includes the following steps when performing the position compensation step: A second image of the disc-shaped grinding wheel is obtained, which is a horizontal image of the end face of the disc-shaped grinding wheel captured by the camera assembly. Identify the second image and output the outer circumference contour of the disc-shaped grinding wheel; Calculate the actual cross-sectional area of ​​the disc-shaped grinding wheel based on its outer circular profile. Based on the preset cross-sectional area and the actual cross-sectional area, the cross-sectional area loss of the disc grinding wheel is obtained; When the cross-sectional area loss exceeds a preset threshold, the disc grinding wheel is identified as being in a state of rapid wear, and an alarm message is generated to replace or re-correct the disc grinding wheel.

6. The control method based on visual recognition according to claim 5, characterized in that, Recognizing the second image and outputting the outer circumference contour of the disc-shaped grinding wheel specifically includes: The second image is converted into a grayscale image, and the grayscale image is binarized to obtain a second binary image; The second binary image is identified using a subpixel edge detection method to obtain multiple contour edge points of the disc grinding wheel; Input multiple contour edge points into the MATLAB application to output the outer circle contour of the disc grinding wheel.

7. An automatic knife sharpening system, characterized in that, The automatic tool sharpening system includes: A frame is provided with a moving mechanism, a grinding mechanism, a camera assembly, a light source assembly, and a controller. The moving mechanism is fixedly connected to the frame and drives the grinding mechanism. The grinding mechanism has a disc-shaped grinding wheel with its front outer circumference facing the robot arm. The camera assembly and the light source assembly are respectively located on the sides of the grinding mechanism. The camera assembly includes a first industrial camera located above the disc-shaped grinding wheel, with the disc-shaped grinding wheel located between the first industrial camera and the light source assembly. A robotic arm, located on the side of the frame, is used to grab the cutting tool to be sharpened from the feeding tool holder and move the cutting tool to the sharpening mechanism for sharpening. The controller is configured to execute the following control method: The image sequence acquired by the camera component is obtained, the image sequence including multiple first images, the multiple first images being obtained by the camera component rotating and sampling a local circumferential contour of the disc grinding wheel in the vertical direction; The image sequence is preprocessed to obtain multiple first binary images; A pre-defined algorithm is used to synthesize multiple first binary images to obtain a synthesized contour image. Based on the synthesized contour image and the standard contour image, the radius change of the disc grinding wheel is identified, specifically including: The actual contour of the disc grinding wheel is extracted from the synthetic contour image using an edge detection algorithm; Identify the long side of the synthesized contour image from the actual contour; Call the contour pixel data of the standard contour image, wherein the contour pixel data is the number of pixels on the long side of the standard contour; The number of pixels on the long side of the synthesized contour image is calculated pixel by pixel, and the pixel difference is obtained by subtracting the number of pixels on the long side of the synthesized contour image from the number of pixels on the long side of the standard contour. The radius change is calculated based on the pixel difference. The system queries a compensation configuration that matches the radius change, and controls the moving mechanism to perform position compensation on the grinding mechanism based on the compensation configuration. Specifically, querying the compensation configuration that matches the radius change includes: when the radius change is ≤ a preset threshold S... min When the preset threshold S is reached, position compensation is not required; max When the radius change is less than or equal to the specified amount, the disc grinding wheel is identified as being in a state of rapid wear, and an alarm message is generated indicating that the disc grinding wheel needs to be replaced or re-corrected.

8. The automatic tool sharpening system according to claim 7, characterized in that, The moving mechanism includes: A transverse moving screw pair, which is fixedly connected to the frame; A longitudinal moving lead screw pair is connected to the transverse moving lead screw pair, and the longitudinal moving lead screw pair is connected to the grinding mechanism; The controller controls the longitudinal movement screw pair of the moving mechanism to perform position compensation on the grinding mechanism based on the compensation configuration, so as to adjust the distance between the grinding mechanism and the robot arm.

9. The automatic tool sharpening system according to claim 7, characterized in that: The frame is also provided with a white background plate, which is located on one side of the disc grinding wheel of the grinding mechanism. The surface of the white background plate is parallel to the end face of the disc grinding wheel.

10. An automatic tool sharpening system according to claim 7, characterized in that: The grinding mechanism has a disc-shaped grinding wheel, the outer circumference of which is used for sharpening. The disc-shaped grinding wheel is horizontally arranged, and the outer circumference of which faces the robot arm is used for sharpening.

Images