Image Analysis-Based Method, Equipment, and Storage Medium for Ceramic Cutter Dimensioning and Grinding

Abstract

This application provides a method, apparatus, and storage medium for grinding ceramic chopping tools based on image analysis. The method includes: acquiring a surface image of the ceramic chopping tool to be ground; analyzing the surface image using an image processing model to obtain the outer contour information of the ceramic chopping tool, the outer contour information including the chopping corner point, the head length, the side length, and the side angle; obtaining the grinding wheel corner point information of the grinding wheel for grinding the ceramic chopping tool; generating grinding path information for grinding the ceramic chopping tool based on the outer contour information and the grinding wheel corner point information, the grinding path information including grinding direction, grinding force, and grinding angle; and controlling the grinding wheel to grind the ceramic chopping tool according to the grinding path information. This method improves the accuracy and efficiency of grinding ceramic chopping tools.

Description

Technical Field

[0001] This application relates to the field of machining technology, and in particular to a method, equipment and storage medium for grinding the dimensions of ceramic chopping tools based on image analysis. Background Technology

[0002] During use, ceramic chopping knives may change in size and shape due to wear and other factors, requiring periodic sharpening to restore their precision. Traditional sharpening methods often rely on the worker's experience and intuition, resulting in uneven sharpening and inaccurate dimensions.

[0003] Therefore, improving the precision and efficiency of grinding ceramic chopping tools is an urgent problem to be solved. Summary of the Invention

[0004] This application provides a method, device, and storage medium for grinding ceramic chopping tools based on image analysis, in order to solve the problem of low precision and efficiency in grinding ceramic chopping tools.

[0005] In a first aspect, this application provides a method for grinding the dimensions of ceramic chopping tools based on image analysis, including: Acquire surface images of the ceramic chopping tool to be polished; The surface image is analyzed using an image processing model to obtain the outer contour information of the ceramic chopping knife. The outer contour information includes the corner point of the ceramic chopping knife, the head length of the ceramic chopping knife, the side length of the ceramic chopping knife, and the side angle of the ceramic chopping knife. Obtain the grinding wheel bend point information of the grinding wheel tool used to grind the ceramic chopping tool; Based on the outer contour information and the grinding wheel bend point information, grinding path information for grinding the ceramic wedge is generated, and the grinding path information includes grinding direction, grinding force, and grinding angle. The grinding wheel is controlled to grind the ceramic chopping tool according to the grinding path information.

[0006] Optionally, the step of analyzing the surface image using an image processing model to obtain the outer contour information of the ceramic chopping tool includes: Obtain the color parameters and preset color weights of the surface image; The surface image is converted into a grayscale image based on the color parameters and the preset color weights. The grayscale image is normalized and denoised to generate the processed first image; The first image is input into the pre-trained image processing model, and the image processing model extracts the shape features of the ceramic chopping knife from the first image. The image processing model includes an input layer, a convolutional layer, a pooling layer, a fully connected layer, and an output layer. The convolutional layer is used to extract local features in the first image, including edge features and corner features. The pooling layer is used to reduce the dimensionality of the local features through downsampling. Based on the extracted shape features of the ceramic chopping knife, the head length, side length, and side angle of the ceramic chopping knife are calculated and generated. The outer contour information is generated based on the head length, side length, and side angle of the ceramic chopping blade; The step of calculating and generating the head length, side length, and side angle of the ceramic chopping knife based on the extracted shape features includes: The contour point set of the ceramic chopping knife is extracted based on its shape features, and the contour point set represents the outer boundary of the ceramic chopping knife; The contour point set and the ceramic chopping knife feature region template are matched by a shape matching algorithm to obtain the similarity between the contour point set and the ceramic chopping knife feature region template. The ceramic chopping knife feature region template is a template pre-drawn according to the ceramic chopping knife type and model. The ceramic chopping knife feature region template includes a head region and a side region. Based on the similarity, a first subset of contour points corresponding to the head region of the ceramic chopping knife and a second subset of contour points corresponding to the side region of the ceramic chopping knife are determined. The length of the head of the ceramic chopping knife is obtained by calculating the length of the contour line segment within the head region using the first subset of contour points. The length of the contour line segment in the side region is calculated by using the second subset of contour points to obtain the side length of the ceramic chopping knife; The included angle between adjacent side line segments of the ceramic chopping blade is calculated using the first subset of contour points and the second subset of contour points to obtain the side angle of the ceramic chopping blade.

[0007] Optionally, generating grinding path information for grinding the ceramic wedge based on the outer contour information and the grinding wheel bend point information includes: The data formats of the outer contour information and the grinding wheel corner point information are unified, and the outer contour information and the grinding wheel corner point information are transformed to the target reference coordinate system through coordinate system transformation; The relative position information of the grinding wheel tool and the ceramic chopping tool is determined based on the grinding wheel bend point information and the outer contour information; Based on the outer contour information and the relative position information of the ceramic chopping knife, the grinding starting point and the initial grinding direction of grinding the ceramic chopping knife are determined, and the initial grinding direction is related to the outer contour tangent direction in the outer contour information. Based on the size and shape of the ceramic chopping knife, the wear condition of the grinding wheel, and the expected grinding effect, calculate the force and depth parameters for grinding the ceramic chopping knife. Based on the grinding start point, the initial grinding direction, the force parameter, and the depth parameter, a grinding path is planned to grind the outer contour of the ceramic chopping knife, and the grinding path information for grinding the ceramic chopping knife is generated.

[0008] Optionally, the step of planning a grinding path for grinding the outer contour of the ceramic chopping knife based on the grinding starting point, the initial grinding direction, the force parameter, and the depth parameter, and generating the grinding path information for grinding the ceramic chopping knife, includes: Determine the polishing step length based on the expected polishing effect; Starting from the grinding start point, along the initial grinding direction, a set of path points covering the area to be ground on the outer contour of the ceramic chopping tool is generated with the grinding step length; Based on the set of path points, the grinding path information for grinding the ceramic chopping knife is generated.

[0009] Optionally, the method further includes: During the polishing process of the ceramic chopping tool, polishing images of the ceramic chopping tool are captured to monitor changes in the outer contour of the ceramic chopping tool; By comparing the current grinding path point with the outer contour information, the changes in the outer contour after grinding are determined, including curve changes and angle changes. If a change in the outer contour is detected, a new tangent direction on the outer contour is determined based on the change information, and the grinding direction of the ceramic wedge is dynamically adjusted based on the new tangent direction so that the grinding wheel tool closely fits the outer contour of the ceramic wedge for grinding. Adjust the grinding path after the current grinding path point according to the adjusted grinding direction; Continue polishing the ceramic chopping tool according to the adjusted polishing path.

[0010] Optionally, the method further includes: The expected polishing effect is input into the target machine learning model to obtain the target polishing parameters. The target machine learning model is used to output the target polishing parameters based on the expected polishing effect of the ceramic chopping knife. During the polishing process of the ceramic chopping tool, polishing images of the ceramic chopping tool are captured to monitor changes in the outer contour of the ceramic chopping tool; The actual polishing effect is determined based on the polishing image; If the difference between the actual polishing effect and the expected polishing effect is greater than or equal to a preset difference threshold, the polishing path information for polishing the ceramic chopping knife is adjusted according to the target polishing parameters. Continue polishing the ceramic chopping tool according to the adjusted polishing path.

[0011] Optionally, the method further includes: Collect parameter information of the sample ceramic chopping tool corresponding to the grinding wheel tool, and grinding history data of the sample ceramic chopping tool. The parameter information includes the shape and size of the sample ceramic chopping tool, and the grinding history data includes the grinding parameters and grinding effect of the sample ceramic chopping tool. The grinding parameters include grinding direction, grinding force, and grinding angle. Extract a set of polishing effect features related to the polishing effect from the parameter information of the sample ceramic chopping knife and the polishing history data of the sample ceramic chopping knife; An initial machine learning model is trained using the set of polishing effect features to generate a target machine learning model. The target machine learning model is used to output the target polishing parameters based on the expected polishing effect of the ceramic chopping knife.

[0012] Secondly, this application provides an electronic device, including: a processor, a communication interface, and a memory, wherein the processor is communicatively connected to the communication interface and the memory respectively; The memory stores computer-executed instructions; The communication interface communicates and interacts with external devices. The processor executes computer execution instructions stored in the memory to implement the method as described in any one of the first aspects.

[0013] Thirdly, this application provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of the first aspects.

[0014] Fourthly, this application provides a computer program product, including a computer program that, when executed by a processor, implements the method described in any one of the first aspects.

[0015] This application provides a method, device, and storage medium for grinding ceramic wedges based on image analysis. It acquires a surface image of the ceramic wedge to be ground, analyzes the image using an image processing model to obtain the outer contour information of the wedge, and obtains the grinding wheel bend point information of the grinding wheel. Based on the outer contour information and the grinding wheel bend point information, grinding path information is generated, including grinding direction, grinding force, and grinding angle. The grinding wheel is then controlled to grind the ceramic wedge according to the grinding path information. This improves the accuracy and efficiency of grinding ceramic wedges. Attached Figure Description

[0016] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0017] Figure 1 A schematic flowchart illustrating a method for grinding the dimensions of a ceramic chopping tool based on image analysis, provided in an embodiment of this application; Figure 2 A schematic flowchart illustrating another image analysis-based method for grinding the dimensions of ceramic chopping tools, provided in an embodiment of this application; Figure 3 A schematic flowchart illustrating another image analysis-based method for grinding the dimensions of ceramic chopping tools provided in this application embodiment; Figure 4 A schematic flowchart illustrating another image analysis-based method for grinding the dimensions of ceramic chopping tools provided in this application embodiment; Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application.

[0018] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0019] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0020] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems will be described in detail below with reference to specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will be described below with reference to the accompanying drawings.

[0021] Figure 1 This is a schematic flowchart illustrating a method for grinding the dimensions of a ceramic chopping tool based on image analysis, provided as an embodiment of this application. Figure 1 As shown, the method may include: S101. Collect a surface image of the ceramic chopping tool to be polished.

[0022] Before grinding the ceramic wedge, the server controls a high-precision industrial camera to acquire images of the ceramic wedge to be ground. This process is typically carried out under stable lighting conditions to ensure the stability and consistency of image quality. The industrial camera is mounted in an appropriate position to ensure that it can capture a complete surface image of the ceramic wedge. The acquired images are then transmitted to the server for subsequent image processing and analysis.

[0023] For example, on an automated ceramic cleaver production line, each cleaver passes through an inspection station equipped with an industrial camera before entering the grinding process. When the cleaver arrives at the inspection station, the camera automatically triggers, capturing a clear image of the cleaver's surface. These images are then uploaded to a server for further image analysis.

[0024] Because ceramic chopping tools require extremely high dimensional precision, such as a tolerance of 1μm, the resolution requirements for industrial cameras are also extremely high. Assuming the technical requirement for ceramic chopping tools is at the 0.1μm level, and the dimensions of the ceramic chopping tool are 11200μm * 1700μm, with a required grinding dimension of 1700μm * 900μm, then the required number of industrial camera pixels would be 17000 * 9000 = 153,000,000, or 150 million pixels.

[0025] S102. Analyze the surface image using an image processing model to obtain the outer contour information of the ceramic chopping knife.

[0026] The outer contour information includes the bend point of the ceramic chopping blade, the head length of the ceramic chopping blade, the side length of the ceramic chopping blade, and the side angle of the ceramic chopping blade.

[0027] After receiving the surface image of the ceramic chopping knife, the server can analyze the image using a pre-trained image processing model. This model might be a deep learning model, such as a convolutional neural network (CNN), trained to recognize the shape features of the ceramic chopping knife. The model first extracts the color parameters of the image and converts it into a grayscale image according to preset color weights. Next, the grayscale image undergoes normalization and denoising to improve image quality. The processed image is then input into the image processing model, which extracts the shape features of the ceramic chopping knife, including edges and corners. Based on these features, the model can calculate the head length, side length, and side angle of the ceramic chopping knife, thereby generating complete outer contour information.

[0028] S103. Obtain the grinding wheel corner point information of the grinding wheel tool for grinding the ceramic chopping knife.

[0029] Before grinding, the server needs to obtain the grinding wheel bend point information of the grinding wheel tool. This is typically achieved through direct measurement or by using sensors. The grinding wheel bend point is an important reference point on the grinding wheel tool, determining the position and angle at which the grinding wheel contacts the ceramic wedge. This information is crucial for generating an accurate grinding path.

[0030] For example, each grinding wheel is equipped with sensors to monitor its status and position in real time. When grinding ceramic wedges, the server automatically uses these sensors to obtain information about the wheel's bend point. This ensures that the server ensures the grinding wheel contacts the ceramic wedge at the correct angle and position.

[0031] S104. Based on the outer contour information and the grinding wheel bend point information, generate grinding path information for grinding the ceramic chopping tool.

[0032] The polishing path information includes polishing direction, polishing force, and polishing angle.

[0033] After acquiring the outer contour information of the ceramic wedge and the grinding wheel's bend point information, the server uses this information to generate a grinding path. First, the server standardizes the data format of these two pieces of information and converts them to a common target reference coordinate system. Then, based on the grinding wheel bend point information and the outer contour information of the ceramic wedge, the server determines the relative position of the grinding wheel and the ceramic wedge. Next, the server determines the starting point and initial direction of grinding based on the outer contour information and relative position information of the ceramic wedge. Finally, combining the size and shape of the ceramic wedge, the wear condition of the grinding wheel, and the expected grinding effect, the server calculates the grinding force and depth parameters, thereby planning a complete grinding path.

[0034] S105. Control the grinding wheel tool to grind the ceramic chopping tool according to the grinding path information.

[0035] After generating the grinding path information, the server can send this information to the robot or automated equipment controlling the grinding wheel. These devices will precisely control the movement trajectory, speed, and force of the grinding wheel according to the received instructions to ensure that the ceramic wedge is ground along the predetermined path. Throughout the grinding process, the server will also monitor the grinding status and effect in real time to adjust the grinding parameters or path as needed.

[0036] The method provided in this application involves acquiring a surface image of a ceramic chopping tool to be ground, analyzing the surface image using an image processing model to obtain the outer contour information of the ceramic chopping tool, and obtaining the grinding wheel bend point information of the grinding wheel for grinding the ceramic chopping tool. Based on the outer contour information and the grinding wheel bend point information, grinding path information for grinding the ceramic chopping tool is generated, including grinding direction, grinding force, and grinding angle. The grinding wheel is then controlled to grind the ceramic chopping tool according to the grinding path information. This improves the accuracy and efficiency of grinding ceramic chopping tools.

[0037] In one possible implementation, step S102 may include: S1021. Obtain the color parameters and preset color weights of the surface image.

[0038] When processing the surface image of a ceramic chopping knife, the server first needs to obtain the image's color parameters. These color parameters include the red, green, and blue (RGB) values ​​for each pixel, representing the color information in the image. Simultaneously, the server loads preset color weights, which are set based on the color characteristics of the ceramic chopping knife and the difference between the image's background color. The purpose of these preset color weights is to enhance the contrast between the ceramic chopping knife and the background in subsequent image processing, facilitating more accurate extraction of the ceramic chopping knife's shape.

[0039] For example, in a ceramic chopping knife image analysis scenario, the server reads RGB color parameters from images captured by an industrial camera. Simultaneously, based on previous experience analyzing similar ceramic chopping knife images, a set of color weights is set. These weights may amplify the difference between the ceramic chopping knife's unique colors (such as white or light gray) and other colors in the image (such as background or shadow colors), preparing for subsequent image conversion and analysis.

[0040] S1022. Convert the surface image into a grayscale image of the surface image according to the color parameters and the preset color weight.

[0041] The server converts the original color image into a grayscale image based on the acquired color parameters and preset color weights. During this process, the server uses color weights to adjust the RGB values ​​of each pixel, making the ceramic cleaver part stand out more in the grayscale image. The converted grayscale image removes color information, retaining only luminance information, simplifying subsequent image processing steps.

[0042] For example, taking a color photograph of a ceramic chopping knife, the server enhances the contrast between the ceramic chopping knife and its surroundings when converting it to a grayscale image by using preset color weights. This makes the outline of the ceramic chopping knife clearer in the grayscale image, facilitating subsequent shape feature extraction.

[0043] S1023. Normalize and denoise the grayscale image to generate the processed first image.

[0044] The server normalizes the grayscale image, adjusting its brightness values ​​to a standard range, such as between 0 and 1. This eliminates brightness differences caused by varying lighting conditions, improving the stability of image processing. Next, the server performs denoising, using filters or image processing algorithms to reduce noise in the image, further highlighting the contours and details of the ceramic chopping knife.

[0045] S1024. Input the first image into the pre-trained image processing model, and extract the shape features of the ceramic chopping knife from the first image through the image processing model.

[0046] The image processing model includes an input layer, a convolutional layer, a pooling layer, a fully connected layer, and an output layer. The convolutional layer is used to extract local features from the first image, including edge features and corner features. The pooling layer is used to reduce the dimensionality of the local features through downsampling.

[0047] The server inputs the pre-processed first image into a pre-trained image processing model. This model might be a deep learning network, such as a convolutional neural network (CNN), which contains an input layer, convolutional layers, pooling layers, fully connected layers, and an output layer. The convolutional layers are responsible for extracting local features from the image, such as edges and corners, while the pooling layers reduce the dimensionality of the features through downsampling, thus reducing computational cost. After training, the model can automatically recognize and extract the shape features of a ceramic chopping knife from the image.

[0048] On the ceramic chopping knife production line, the server feeds the processed first image into a pre-trained CNN model. This model has already learned how to recognize the shape features of the ceramic chopping knife during the previous training phase. As the image passes through the model's convolutional and pooling layers, the model automatically extracts key shape information such as the edges and corners of the ceramic chopping knife, providing a data foundation for the next step of size calculation and outer contour generation.

[0049] S1025. Based on the extracted shape features of the ceramic chopping knife, calculate and generate the head length, side length, and side angle of the ceramic chopping knife.

[0050] Based on the shape features extracted from the image processing model, the server further calculates the specific dimensional parameters of the ceramic chopping knife. By analyzing and measuring the distances between feature points, such as the length of the edges and the position of the corners, the server can calculate the head length and side length of the ceramic chopping knife. Simultaneously, based on the relative positions of the corners and the direction of the edges, the server can also determine the side angle of the ceramic chopping knife.

[0051] Specifically, this step can be achieved through the following sub-steps: S1. Extract the contour point set of the ceramic chopping knife based on its shape features. The contour point set represents the outer boundary of the ceramic chopping knife.

[0052] After extracting the shape features of the ceramic chopping knife, the server further processes these features to extract the contour point set of the ceramic chopping knife. This contour point set is a collection of coordinate points that precisely describe the outer boundary of the ceramic chopping knife. The server may use edge detection algorithms, such as Canny edge detection, to identify and extract these contour points. These points are organized into an ordered set according to their order of appearance in the image for subsequent analysis and processing.

[0053] S2. The contour point set and the ceramic chopping knife feature region template are matched using a shape matching algorithm to obtain the similarity between the contour point set and the ceramic chopping knife feature region template.

[0054] The ceramic chopping knife feature area template is a template pre-drawn according to the type and model of the ceramic chopping knife, and the ceramic chopping knife feature area template includes a head area and a side area.

[0055] The server employs a shape matching algorithm to compare the extracted contour point set with pre-drawn feature region templates for ceramic chopping knives. These templates are pre-created based on different types and models of ceramic chopping knives and contain key feature regions such as the head and side regions. The shape matching algorithm calculates the similarity between the contour point set and the templates to determine which points belong to the head region and which belong to the side region.

[0056] The server has a feature region template for a specific model of ceramic chopping knife. After extracting the contour point set of the ceramic chopping knife, the server uses a shape matching algorithm to compare these points with the template. This comparison process calculates a similarity score, representing the degree of matching between the contour point set and the template. This similarity score will be used to subsequently determine which points in the contour point set belong to the head region of the ceramic chopping knife and which belong to the side region.

[0057] S3. Based on the similarity, determine the first subset of contour points corresponding to the head region of the ceramic chopping knife and the second subset of contour points corresponding to the side region of the ceramic chopping knife.

[0058] Based on the similarity calculated using a shape matching algorithm, the server divides the contour point set into two subsets: a first subset (corresponding to the head region of the ceramic chopping knife) and a second subset (corresponding to the side region of the ceramic chopping knife). This segmentation process is performed based on a similarity threshold and the region boundaries defined in the template. The server ensures that the points within each subset highly match their corresponding feature regions.

[0059] S4. Calculate the length of the contour line segment in the head region using the first subset of contour points to obtain the head length of the ceramic chopping knife.

[0060] The server uses a subset of the first contour points to calculate the length of the ceramic chopping tool's head region. This typically involves sorting the points in the set and calculating the sum of the distances between adjacent points to obtain the overall length of the head region. This process may involve some geometric calculations to ensure the accuracy of the length.

[0061] S5. Calculate the length of the contour line segment in the side region using the second contour point subset to obtain the side length of the ceramic chopping knife.

[0062] Similar to calculating the head length, the server uses a second subset of contour points to calculate the length of the side region of the ceramic chopping tool. This includes points from the sorted point set and sums the distances between adjacent points to arrive at the overall length of the side region. This calculation process ensures accurate measurement of the side length of the ceramic chopping tool.

[0063] S6. Calculate the included angle between adjacent side line segments of the ceramic chopping blade using the first subset of contour points and the second subset of contour points to obtain the side angle of the ceramic chopping blade.

[0064] To calculate the side angles of a ceramic chopping knife, the server uses points from a first subset of contour points and a second subset of contour points to determine the angle between adjacent side line segments. This typically involves calculating the angle between two line segments formed by points from the contour point subsets. The server uses a geometric algorithm to accurately calculate this angle.

[0065] S1026. Generate the outer contour information based on the head length, side length, and side angle of the ceramic chopping knife.

[0066] After completing all necessary calculations and measurements, the server generates a report or data structure containing information about the ceramic chopping tool's outer contour. This information includes not only the precise lengths of the head and sides of the tool but also a detailed description of the side angles. With this accurate contour information, the server can develop an efficient grinding plan, ensuring the ceramic chopping tool is precisely ground to the desired shape and size.

[0067] In one possible implementation, step S104 may include: S1041. Unify the data format of the outer contour information and the grinding wheel corner point information, and transform the outer contour information and the grinding wheel corner point information to the target reference coordinate system through coordinate system transformation.

[0068] Before performing the grinding operation, the server needs to ensure that the outer contour information of the ceramic chopping tool and the grinding wheel corner point information are consistent in data format and coordinate system. First, the server standardizes the data format of these two types of information. For example, if the outer contour information is stored as a series of point coordinates, while the grinding wheel corner point information is represented by specific angle values, the server will convert this information into the same representation, such as converting them both into a set of coordinate points. Next, the server performs coordinate system transformation. Since the outer contour information and the grinding wheel corner point information may be obtained in different coordinate systems, they need to be transformed to the same target reference coordinate system. For example, linear transformation operations such as translation and rotation can be used to ensure that the two correspond correctly in spatial position.

[0069] For example, suppose the server receives the outer contour information based on a local coordinate system with the center of the ceramic chopping tool as the origin, while the grinding wheel corner point information is based on the global coordinate system of the grinding equipment. The server first identifies the difference between these two coordinate systems, and then uses a transformation matrix to convert the outer contour information in the local coordinate system to the global coordinate system, placing it in the same reference system as the grinding wheel corner point information. In this way, the server can accurately assess the relative position and orientation of the grinding wheel and the ceramic chopping tool.

[0070] S1042. Determine the relative position information of the grinding wheel tool and the ceramic chopping tool based on the grinding wheel bend point information and the outer contour information.

[0071] After standardizing the data format and coordinate system, the server uses the corner information of the grinding wheel and the outer contour information of the ceramic wedge to determine their relative positions. The server calculates the distance and direction from the corner point of the grinding wheel to the nearest point on the outer contour of the ceramic wedge, thus determining the relative positional relationship between the grinding wheel and the ceramic wedge.

[0072] For example, the server can calculate that the bend point of the grinding wheel corresponds precisely to the midpoint of one side of the ceramic wedge. By measuring the straight-line distance and angle from this midpoint to the bend point of the grinding wheel, the server can accurately determine the position and orientation of the grinding wheel to ensure that it correctly contacts the side of the ceramic wedge during grinding.

[0073] S1043. Based on the outer contour information of the ceramic chopping tool and the relative position information, determine the grinding starting point and the initial grinding direction for grinding the ceramic chopping tool.

[0074] The initial grinding direction is related to the outer contour tangent direction in the outer contour information.

[0075] After determining the relative positions of the grinding wheel and the ceramic wedge, the server needs to further determine the starting point and initial direction of grinding. The starting point is usually the point where the grinding wheel first contacts the outer contour of the ceramic wedge, and this point can be found by analyzing the outer contour information and relative position information. The initial grinding direction is usually consistent with the tangent direction of the outer contour at that point to ensure that the grinding wheel can smoothly grind along the outer contour of the ceramic wedge.

[0076] S1044. Based on the size and shape of the ceramic chopping knife, the wear condition of the grinding wheel, and the expected grinding effect, calculate the force and depth parameters for producing and grinding the ceramic chopping knife.

[0077] When calculating the grinding force and depth parameters, the server can consider multiple factors. The size and shape of the ceramic wedge determine the required grinding force and depth. For example, a larger ceramic wedge may require a greater grinding force to ensure the desired grinding effect. The wear condition of the grinding wheel is also an important factor. If the grinding wheel is already worn to a certain extent, the grinding depth may need to be increased to compensate for this wear. Finally, the desired grinding effect will also influence the choice of force and depth. If a finer grinding effect is desired, the grinding force and depth may need to be reduced.

[0078] S1045. Based on the grinding starting point, the grinding initial direction, the force parameter, and the depth parameter, plan a grinding path for grinding on the outer contour of the ceramic chopping knife, and generate the grinding path information for grinding the ceramic chopping knife.

[0079] After collecting all the necessary information, the server can begin planning the grinding path. This path specifies in detail the movement trajectory of the grinding wheel on the outer contour of the ceramic wedge, including the starting point, direction, force, and depth. The server can use path planning algorithms, such as interpolation or spline curve fitting, to generate a smooth and efficient grinding path. This path must not only ensure the uniformity and quality of grinding but also consider grinding efficiency and the durability of the grinding wheel.

[0080] The following section details how, in step S1045, a grinding path is planned to grind the outer contour of the ceramic chopping knife based on the grinding starting point, the initial grinding direction, the force parameter, and the depth parameter, thereby generating the grinding path information for grinding the ceramic chopping knife.

[0081] Figure 2 This is a schematic flowchart illustrating another image analysis-based method for grinding the dimensions of ceramic chopping tools, provided as an embodiment of this application. Figure 2 As shown, the method may include: S201. Determine the polishing step length based on the expected polishing effect.

[0082] When determining the grinding step size, the server can comprehensively consider the expected grinding effect. The grinding step size refers to the distance covered by the grinding wheel in each movement along the outer contour of the ceramic wedge. Setting this parameter is crucial for both grinding precision and efficiency. If a rough grinding effect is expected, a larger grinding step size can be selected to increase grinding speed. Conversely, if a fine effect is expected, a smaller grinding step size should be selected to ensure that each part is meticulously ground. The server will automatically calculate the appropriate grinding step size based on the user-inputted expected grinding effect parameters, or based on historical data and empirical rules.

[0083] For example, suppose a user wants to finely grind a ceramic wedge to achieve a smoother surface. Upon receiving this instruction, the server will automatically set a small grinding step, such as 0.1 mm, based on historical data and empirical rules. This way, as the grinding wheel moves along the outer contour of the ceramic wedge, only a small portion of material is removed each time, ensuring the final grinding effect meets the user's precision requirements.

[0084] S202. Starting from the grinding start point, along the initial grinding direction, generate a set of path points on the outer contour of the ceramic chopping tool that cover the area to be ground on the outer contour of the ceramic chopping tool with the grinding step size.

[0085] After determining the grinding step size, the server can generate path points gradually along the outer contour of the ceramic wedge, starting from the grinding start point and moving along the initial grinding direction. These path points are the positions the grinding wheel needs to pass through sequentially during the grinding process, and the spacing between them is the previously determined grinding step size. The server can use the outer contour information of the ceramic wedge, the grinding start point, and the initial grinding direction to precisely determine the position of each path point through mathematical calculations. This process needs to ensure that the path points uniformly and accurately cover the entire area to be ground.

[0086] S203. Based on the set of path points, generate the grinding path information for grinding the ceramic chopping knife.

[0087] After generating a set of path points covering the entire area to be polished, the server can generate polishing path information based on these path points. This information includes parameters such as the coordinates, polishing direction, force, and depth of each path point the grinding wheel needs to pass through in sequence. The server integrates this information into a complete polishing path instruction set, which is then sent to the polishing equipment to guide it in performing the polishing operation according to the predetermined path and parameters.

[0088] For example, suppose the server has generated a series of path points and calculated the corresponding grinding direction, pressure, and depth based on these path points. Next, the server can integrate this information into a grinding path instruction set and send it to the grinding device via the network. Upon receiving the instruction set, the grinding device will move sequentially to each path point according to the instructions and perform the grinding operation according to the specified grinding direction, pressure, and depth. In this way, the server can achieve precise control over the grinding process, thereby ensuring that the final grinding effect meets the user's requirements.

[0089] In one possible implementation, the method may also include the following. Figure 3 This is a schematic flowchart illustrating another image analysis-based method for grinding the dimensions of ceramic chopping tools, provided in an embodiment of this application. Figure 3 As shown, the method may further include: S301. During the polishing process of the ceramic chopping tool, a polishing image of the ceramic chopping tool is acquired to monitor the change in the outer contour of the ceramic chopping tool.

[0090] During the polishing process of the ceramic chopping tool, the server controls image acquisition devices (such as cameras or sensors) to capture polishing images of the tool in real time. These images are acquired at a certain frequency to ensure that subtle changes in the outer contour of the ceramic chopping tool are captured. The acquired images are then transmitted to the server for further processing and analysis. In this way, the server can monitor the changes in the outer contour of the ceramic chopping tool in real time during the polishing process.

[0091] For example, the server is equipped with a high-definition camera mounted next to the grinding equipment, aimed at the ceramic chopping tool being ground at a fixed angle and distance. Whenever grinding is in progress, the camera captures images of the ceramic chopping tool at 50 frames per second and transmits this image data to the server in real time. Upon receiving these images, the server performs subsequent processing and analysis.

[0092] S302. By comparing the current grinding path point with the outer contour information, determine the change information of the outer contour after grinding. The change information includes curve change information and angle change information.

[0093] The server compares the real-time captured polishing images with the original outer contour information. Using image processing techniques such as edge detection and contour extraction, the server can identify the current outer contour of the ceramic chopping tool and compare it with preset outer contour information. By calculating the differences, the server can determine the changes in the outer contour of the ceramic chopping tool after polishing, including the degree of curvature and the size of the angles.

[0094] During the polishing process, the server continuously compares the captured images with the original outline information. For example, the server might notice that a certain side of the ceramic chopping tool becomes smoother after polishing, or that the angle of a certain bend has decreased. This change information is recorded by the server and used for subsequent polishing direction adjustments.

[0095] S303. If a change in the outer contour is detected, a new tangent direction on the outer contour is determined based on the change information, and the grinding direction of the ceramic chopping tool is dynamically adjusted based on the new tangent direction so that the grinding wheel tool closely fits the outer contour of the ceramic chopping tool for grinding.

[0096] Once a change in the outer contour of the ceramic wedge is detected, the server calculates a new tangent direction based on this information. This new tangent direction is derived from the outer contour shape of the current grinding point, reflecting the surface orientation of the ceramic wedge at that point. The server adjusts the grinding direction of the grinding wheel in real time to align it with the new tangent direction, ensuring that the grinding wheel closely conforms to the outer contour of the ceramic wedge during grinding.

[0097] Suppose that during the grinding process, the server detects a significant curve change on one side of the ceramic chopping tool. Based on this change, the server recalculates the tangent direction of that side and immediately adjusts the grinding wheel's direction to align with the new tangent direction. This allows the grinding wheel to grind more precisely along the outer contour of the ceramic chopping tool, thereby improving grinding quality and efficiency.

[0098] S304. Adjust the grinding path after the current grinding path point according to the adjusted grinding direction.

[0099] After adjusting the polishing direction, the server also needs to adjust the subsequent polishing path accordingly. This is because a change in polishing direction may render the original polishing path inapplicable. Therefore, the server will replan the subsequent polishing path based on the new polishing direction and the current position of the polishing point.

[0100] Suppose that during the grinding process, the server adjusts the grinding direction due to changes in the outer contour of the ceramic chopping tool. Then, based on this new grinding direction and the current grinding point's position, the server uses a path planning algorithm to regenerate the subsequent grinding path. In this way, the grinding wheel tool can continue the grinding operation according to the new path.

[0101] S305. Continue grinding the ceramic chopping tool according to the adjusted grinding path.

[0102] After adjusting the polishing path, the server controls the polishing equipment to continue polishing along the new path. During this process, the server continuously monitors changes in the outer contour of the ceramic chopping blade and adjusts the polishing direction and path in real time as needed. In this way, the server ensures that the polishing operation always closely follows the outer contour of the ceramic chopping blade, achieving the best polishing results.

[0103] In one possible implementation, the method may also include the following. Figure 4 This is a schematic flowchart illustrating another image analysis-based method for grinding the dimensions of ceramic chopping tools, provided in an embodiment of this application. Figure 4 As shown, the method may further include: S401. Input the expected polishing effect into the target machine learning model to obtain the target polishing parameters.

[0104] The target machine learning model is used to output the target polishing parameters based on the expected polishing effect of the ceramic chopping knife.

[0105] The server can receive parameters for the expected polishing effect from the user interface or system settings. These parameters typically include specific requirements for the surface quality of the ceramic chopping tool after polishing, such as surface roughness, gloss, and smoothness. The server organizes these parameters into a format that a machine learning model can understand and prepares them for input into a pre-trained target machine learning model.

[0106] The target machine learning model is a complex system built on big data and deep learning algorithms. During the model training phase, a large amount of historical data and experiential knowledge related to ceramic chopping knife polishing has been used. By learning the mapping relationship between polishing parameters and polishing effects, the model can output the optimal combination of polishing parameters for a specific expected polishing effect.

[0107] When the server inputs the desired polishing effect parameters into the model, the model first parses and preprocesses these parameters to ensure they meet the model's input requirements. Then, the neural network structure inside the model extracts features and learns patterns step by step based on the input parameters through multi-layer convolution, pooling, and fully connected operations, ultimately outputting a set of optimal polishing parameters for the current ceramic chopping knife and the desired polishing effect. These parameters include, but are not limited to, polishing force, polishing angle, polishing speed, and possible grinding wheel types and grit sizes.

[0108] For example, if the server receives a request for high-precision grinding of a certain model of ceramic chopping knife, the production department sets the expected grinding effect parameters, including surface roughness Ra≤0.05μm and gloss ≥90%. The server formats these parameters into the input format required by the model and sends them to the target machine learning model. The model internally uses a complex deep learning algorithm to parse and learn the input parameters, ultimately outputting a detailed set of target grinding parameters, including grinding force of 4.8 to 5.2N, grinding angle of 43° to 47°, and grinding speed of 45 to 50 mm / s. These parameters are verified and optimized, recorded by the server, and prepared for subsequent grinding path adjustments and grinding execution.

[0109] S402. During the polishing process of the ceramic chopping tool, a polishing image of the ceramic chopping tool is acquired to monitor the change in the outer contour of the ceramic chopping tool.

[0110] During the actual grinding process of ceramic cleavers, the server can control image acquisition devices (such as high-definition cameras or industrial cameras) to capture images of the grinding site in real time. These image acquisition devices are usually installed near the grinding workbench to ensure that every detailed change of the ceramic cleaver during the grinding process can be clearly captured.

[0111] The server receives continuous image streams or image frame sequences from image acquisition devices and analyzes and processes these images using image processing techniques. First, the server preprocesses the images, including noise reduction, contrast enhancement, and brightness adjustment, to improve image quality and clarity. Then, the server uses edge detection and contour extraction algorithms to identify and locate the ceramic chopping knife in the image and extract its outer contour information.

[0112] After extracting the outer contour information of the ceramic chopping tool, the server further analyzes the changes in these contours. By comparing contour images at different time points, the server can calculate key indicators such as edge smoothness, angle changes, and shape fine-tuning during the polishing process. This information is crucial for evaluating the polishing effect and adjusting the polishing path.

[0113] S403. Determine the actual polishing effect based on the polishing image.

[0114] After acquiring and analyzing the polishing images of the ceramic chopping tool and its outer contour changes, the server needs to further determine the actual polishing effect based on these images. The server can use image processing and analysis software to perform detailed surface quality inspection on the polished images. First, the server performs preprocessing operations such as grayscale conversion and filtering on the images to reduce the impact of noise and interference factors on the evaluation results. Then, the server applies surface roughness measurement algorithms to evaluate the roughness of the ceramic chopping tool surface in the images. These algorithms estimate the surface's micro-geometry and roughness parameters by analyzing the changes in pixel grayscale values ​​in the image.

[0115] In addition to roughness assessment, the server can also utilize other image processing techniques to evaluate surface quality indicators of ceramic wedges, such as gloss and flatness. For example, gloss can be assessed by calculating the intensity distribution of reflected light on the surface of the ceramic wedge in an image; flatness can be assessed by comparing the uniformity of brightness in different areas of the image.

[0116] Finally, the server will generate a detailed report on the actual polishing effect based on the evaluation results, including numerical values ​​and charts for key indicators such as surface roughness, gloss, and smoothness. This report will be used for comparison and analysis with the expected polishing effect.

[0117] S404. If the difference between the actual polishing effect and the expected polishing effect is greater than or equal to a preset difference threshold, the polishing path information for polishing the ceramic chopping knife is adjusted according to the target polishing parameters.

[0118] After determining the actual polishing effect and comparing it with the expected effect, the server needs to evaluate the degree of difference between the two. If the difference between the actual polishing effect and the expected effect is greater than or equal to the preset difference threshold, it indicates that the current polishing path and parameter settings may not meet the expected polishing quality requirements and need to be adjusted and optimized.

[0119] At this point, the server dynamically adjusts the current grinding path information based on the target grinding parameters previously obtained from the target machine learning model, combined with the current actual grinding effect feedback. This adjustment may involve multiple aspects, including fine-tuning of key parameters such as grinding force, grinding angle, and grinding speed; it may also involve replanning the grinding path to ensure that the grinding wheel can grind the ceramic chopping tool along a more reasonable and effective path.

[0120] When adjusting the grinding path information, the server comprehensively considers multiple factors, such as the shape, size, and material properties of the ceramic cleaver; the type, grit size, and wear condition of the grinding wheel; and economic factors such as production efficiency and cost. By weighing the pros and cons of these factors, the server can formulate the optimal grinding path adjustment scheme and implement and verify it in the actual grinding process.

[0121] S405. Continue grinding the ceramic chopping tool according to the adjusted grinding path.

[0122] After adjusting the grinding path, the server controls the grinding equipment to continue grinding the ceramic wedge according to the new grinding path parameters. During the grinding process, the server continuously monitors the grinding image and actual effect to ensure that the grinding operation is performed according to the predetermined path and parameters. If the server finds that the actual grinding effect is still significantly different from the expected effect or that new problems have occurred (such as excessive wear of the grinding wheel, breakage of the ceramic wedge, etc.), it will immediately stop the grinding operation and conduct further inspection and analysis. After confirming the cause of the problem, the server will readjust the grinding path and parameter settings and restart the grinding operation until the expected effect is achieved.

[0123] Furthermore, during the polishing process, the server also needs to consider economic factors such as production efficiency and cost. By optimizing the polishing path and parameter settings, the server can maximize production efficiency and minimize production costs while ensuring polishing quality. For example, polishing time can be shortened by reducing unnecessary polishing paths and repetitive operations; wear rate and replacement frequency can be reduced by selecting appropriate grinding wheel types and grit sizes.

[0124] exist Figure 4 Under this implementation method, the training process of the target machine learning model is as follows: Collect parameter information of the sample ceramic chopping tool corresponding to the grinding wheel tool, and grinding history data of the sample ceramic chopping tool. The parameter information includes the shape and size of the sample ceramic chopping tool, and the grinding history data includes the grinding parameters and grinding effect of the sample ceramic chopping tool. The grinding parameters include grinding direction, grinding force, and grinding angle.

[0125] To train a machine learning model capable of accurately predicting and outputting target grinding parameters, the server first needs to collect a large amount of sample data. This data includes detailed parameter information and grinding history data of sample ceramic wedges corresponding to specific grinding wheels. The parameter information covers the physical characteristics of the sample ceramic wedges, such as shape and size, which are crucial for understanding the structure of the ceramic wedges and grinding requirements. The grinding history data records the specific parameters and final results of grinding the sample ceramic wedges using the same or similar grinding wheels in the past. These parameters include, but are not limited to, grinding direction, grinding force, and grinding angle, while the grinding effect is an evaluation of the surface quality of the ceramic wedge after grinding, such as surface roughness and gloss.

[0126] The server retrieves sample data in batches from production record systems, quality inspection systems, or other relevant data sources through data interfaces or database queries. During the collection process, the server ensures the integrity, accuracy, and consistency of the data, performing necessary cleaning and preprocessing on missing or abnormal data to ensure the effectiveness and reliability of subsequent model training.

[0127] Extract a set of polishing effect features related to the polishing effect from the parameter information of the sample ceramic chopping knife and the polishing history data of the sample ceramic chopping knife.

[0128] After collecting sufficient sample data, the server needs to extract a set of features closely related to the polishing effect. These features should comprehensively and accurately reflect the physical properties of the ceramic chopping knife, key parameters during the polishing process, and the final polishing effect. The server will utilize feature engineering techniques, employing methods such as statistical analysis, correlation analysis, and principal component analysis, to screen out the feature variables that have the greatest impact on the polishing effect. These features may include the specific size proportions of the ceramic chopping knife, the combination of polishing parameters, and their interaction with the polishing effect.

[0129] During the feature extraction process, the server also needs to consider the interpretability of the features and the generalization ability of the model. Features with strong interpretability help to understand the working principle and decision-making basis of the model; while models with strong generalization ability can maintain high prediction accuracy when faced with new samples. Therefore, the server will weigh these two factors when selecting features, striving to improve the practical application value while maintaining the model's prediction accuracy.

[0130] An initial machine learning model is trained using the set of polishing effect features to generate a target machine learning model. The target machine learning model is used to output the target polishing parameters based on the expected polishing effect of the ceramic chopping knife.

[0131] After extracting the feature set relevant to the polishing effect, the server uses these features to train an initial machine learning model. The training process typically includes steps such as data partitioning, model selection, parameter tuning, and performance evaluation. First, the server divides the sample data into a training set and a test set. The training set is used to train the model parameters, and the test set is used to evaluate the model's performance. Then, the server selects an appropriate machine learning algorithm to build the initial model based on the nature of the problem and the characteristics of the data. During model training, the server continuously adjusts the model's parameters to optimize its performance on the training set. Finally, the server uses the test set to evaluate the generalization ability of the trained model and, based on the evaluation results, further tunes the model or retrains it using a different algorithm.

[0132] During training, the server also utilizes techniques such as cross-validation to improve the model's stability and reliability. Cross-validation evaluates model performance by further dividing the training set into multiple subsets and using them alternately as the validation set, thereby avoiding overfitting. After multiple iterations of training and parameter tuning, the server ultimately generates a high-performance target machine learning model for practical applications.

[0133] Figure 5 This is a schematic diagram of an electronic device provided in an embodiment of this application. The electronic device is used to perform the aforementioned image analysis-based ceramic chopping tool size grinding method, and may be, for example, the aforementioned server. Figure 5 As shown, the electronic device 500 may include at least one processor 501, a memory 502, and a communication interface 503.

[0134] The memory 502 is used to store programs. Specifically, the program may include program code, which includes computer operation instructions.

[0135] Memory 502 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.

[0136] The processor 501 is used to execute computer execution instructions stored in the memory 502 to implement the method described in the foregoing method embodiments. The processor 501 may be a CPU, an Application Specific Integrated Circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application.

[0137] Processor 501 can communicate and interact with external devices through communication interface 503. In specific implementations, if communication interface 503, memory 502, and processor 501 are implemented independently, they can be interconnected via a bus to complete communication. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc., but this does not imply that there is only one bus or one type of bus.

[0138] Optionally, in a specific implementation, if the communication interface 503, memory 502, and processor 501 are integrated on a single chip, then the communication interface 503, memory 502, and processor 501 can communicate through an internal interface.

[0139] This application also provides a computer-readable storage medium, which may include various media capable of storing program code, such as a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk. Specifically, the computer-readable storage medium stores program instructions, which are used in the methods described in the above embodiments.

[0140] This application also provides a program product including executable instructions stored in a readable storage medium. At least one processor of a computing device can read the executable instructions from the readable storage medium, and the at least one processor executes the executable instructions to cause the computing device to perform the methods described above.

[0141] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application 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 or all of the technical features therein. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application.

Claims

1. A method for grinding the dimensions of ceramic chopping tools based on image analysis, characterized in that, The method includes: Acquire surface images of the ceramic chopping tool to be polished; The surface image is analyzed using an image processing model to obtain the outer contour information of the ceramic chopping knife. The outer contour information includes the corner point of the ceramic chopping knife, the head length of the ceramic chopping knife, the side length of the ceramic chopping knife, and the side angle of the ceramic chopping knife. Obtain the grinding wheel bend point information of the grinding wheel tool used to grind the ceramic chopping tool; Based on the outer contour information and the grinding wheel bend point information, grinding path information for grinding the ceramic wedge is generated, and the grinding path information includes grinding direction, grinding force, and grinding angle. The grinding wheel and cutting tool are controlled to grind the ceramic chopping tool according to the grinding path information; The step of analyzing the surface image using an image processing model to obtain the outer contour information of the ceramic chopping tool includes: Obtain the color parameters and preset color weights of the surface image; The surface image is converted into a grayscale image based on the color parameters and the preset color weights. The grayscale image is normalized and denoised to generate the processed first image; The first image is input into the pre-trained image processing model, and the image processing model extracts the shape features of the ceramic chopping knife from the first image. The image processing model includes an input layer, a convolutional layer, a pooling layer, a fully connected layer, and an output layer. The convolutional layer is used to extract local features in the first image, including edge features and corner features. The pooling layer is used to reduce the dimensionality of the local features through downsampling. Based on the extracted shape features of the ceramic chopping knife, the head length, side length, and side angle of the ceramic chopping knife are calculated and generated. The outer contour information is generated based on the head length, side length, and side angle of the ceramic chopping blade; The step of calculating and generating the head length, side length, and side angle of the ceramic chopping knife based on the extracted shape features includes: The contour point set of the ceramic chopping knife is extracted based on its shape features, and the contour point set represents the outer boundary of the ceramic chopping knife; The contour point set and the ceramic chopping knife feature region template are matched by a shape matching algorithm to obtain the similarity between the contour point set and the ceramic chopping knife feature region template. The ceramic chopping knife feature region template is a template pre-drawn according to the ceramic chopping knife type and model. The ceramic chopping knife feature region template includes a head region and a side region. Based on the similarity, a first subset of contour points corresponding to the head region of the ceramic chopping knife and a second subset of contour points corresponding to the side region of the ceramic chopping knife are determined. The length of the head of the ceramic chopping knife is obtained by calculating the length of the contour line segment within the head region using the first subset of contour points. The length of the contour line segment in the side region is calculated by using the second subset of contour points to obtain the side length of the ceramic chopping knife; The included angle between adjacent side line segments of the ceramic chopping blade is calculated using the first subset of contour points and the second subset of contour points to obtain the side angle of the ceramic chopping blade. The step of generating grinding path information for grinding the ceramic wedge based on the outer contour information and the grinding wheel bend point information includes: The data formats of the outer contour information and the grinding wheel corner point information are unified, and the outer contour information and the grinding wheel corner point information are transformed to the target reference coordinate system through coordinate system transformation; The relative position information of the grinding wheel tool and the ceramic chopping tool is determined based on the grinding wheel bend point information and the outer contour information; Based on the outer contour information and the relative position information of the ceramic chopping knife, the grinding starting point and the initial grinding direction of grinding the ceramic chopping knife are determined, and the initial grinding direction is related to the outer contour tangent direction in the outer contour information. Based on the size and shape of the ceramic chopping knife, the wear condition of the grinding wheel, and the expected grinding effect, calculate the force and depth parameters for grinding the ceramic chopping knife. Based on the grinding start point, the grinding initial direction, the force parameter, and the depth parameter, a grinding path is planned to grind the outer contour of the ceramic chopping knife, and the grinding path information for grinding the ceramic chopping knife is generated. The step of planning a grinding path for grinding the outer contour of the ceramic chopping knife based on the grinding start point, the initial grinding direction, the force parameter, and the depth parameter, and generating the grinding path information for grinding the ceramic chopping knife, includes: Determine the polishing step length based on the expected polishing effect; Starting from the grinding start point, along the initial grinding direction, a set of path points covering the area to be ground on the outer contour of the ceramic chopping tool is generated with the grinding step length; Based on the set of path points, the grinding path information for grinding the ceramic chopping knife is generated.

2. The method for grinding the dimensions of ceramic chopping tools based on image analysis according to claim 1, characterized in that, The method further includes: During the polishing process of the ceramic chopping tool, polishing images of the ceramic chopping tool are captured to monitor changes in the outer contour of the ceramic chopping tool; By comparing the current grinding path point with the outer contour information, the changes in the outer contour after grinding are determined, including curve changes and angle changes. If a change in the outer contour is detected, a new tangent direction on the outer contour is determined based on the change information, and the grinding direction of the ceramic wedge is dynamically adjusted based on the new tangent direction so that the grinding wheel tool closely fits the outer contour of the ceramic wedge for grinding. Adjust the grinding path after the current grinding path point according to the adjusted grinding direction; Continue polishing the ceramic chopping tool according to the adjusted polishing path.

3. The method for grinding the dimensions of ceramic chopping tools based on image analysis according to claim 1 or 2, characterized in that, The method further includes: The expected polishing effect is input into the target machine learning model to obtain the target polishing parameters. The target machine learning model is used to output the target polishing parameters based on the expected polishing effect of the ceramic chopping knife. During the polishing process of the ceramic chopping tool, polishing images of the ceramic chopping tool are captured to monitor changes in the outer contour of the ceramic chopping tool; The actual polishing effect is determined based on the polishing image; If the difference between the actual polishing effect and the expected polishing effect is greater than or equal to a preset difference threshold, the polishing path information for polishing the ceramic chopping knife is adjusted according to the target polishing parameters. Continue polishing the ceramic chopping tool according to the adjusted polishing path.

4. The method for grinding the dimensions of ceramic chopping tools based on image analysis according to claim 3, characterized in that, The method further includes: Collect parameter information of the sample ceramic chopping tool corresponding to the grinding wheel tool, and grinding history data of the sample ceramic chopping tool. The parameter information includes the shape and size of the sample ceramic chopping tool, and the grinding history data includes the grinding parameters and grinding effect of the sample ceramic chopping tool. The grinding parameters include grinding direction, grinding force, and grinding angle. Extract a set of polishing effect features related to the polishing effect from the parameter information of the sample ceramic chopping knife and the polishing history data of the sample ceramic chopping knife; An initial machine learning model is trained using the set of polishing effect features to generate a target machine learning model. The target machine learning model is used to output the target polishing parameters based on the expected polishing effect of the ceramic chopping knife.

5. An electronic device, characterized in that, include: The processor includes a communication interface and a memory, wherein the processor is communicatively connected to the communication interface and the memory, respectively. The memory stores computer-executed instructions; The communication interface communicates and interacts with external devices. The processor executes the computer execution instructions stored in the memory to implement the image analysis-based ceramic chopping tool size grinding method as described in any one of claims 1-4.

6. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the image analysis-based ceramic chopping tool size grinding method as described in any one of claims 1 to 4.

7. A computer program product, characterized in that, The invention includes a computer program that, when executed by a processor, implements the image analysis-based ceramic chopping tool size grinding method according to any one of claims 1-4.

Images