Production and processing control method and system for circular knife mold

Abstract

The invention discloses a production processing control method and system for a circular knife mold, and the method comprises the steps: determining a first coordinate of a first actual cutting track and a second coordinate of a first planned cutting track, comparing the first coordinate with the second coordinate, and extracting key feature points of cutting, an error between the first actual cutting track and the first planned cutting track is analyzed, and an error source is determined; weighting different error sources to construct a cutting track correction model, calculating a second planned cutting track to feed back and adjust operation parameters of production and processing of the circular knife mold, generating a compensated second actual cutting track, and judging whether the error between the second actual cutting track and the second planned cutting track meets a preset condition or not; and if not, iteratively updating the weight of the error source until a preset condition is met, and generating a target cutting track to complete production and processing of the circular knife mold. According to the invention, through dynamic error source weight distribution and an iterative optimization mechanism, more accurate, more flexible and more efficient production and processing control of the circular knife mold is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of mold processing, and in particular to a production and processing control method and system for a circular knife mold. Background Art

[0002] In the field of circular die manufacturing, traditional cutting trajectory control methods rely primarily on pre-set fixed parameters and empirical formulas. These methods are typically based on idealized models for planning. In actual production, due to factors such as equipment vibration, tool wear, and uneven material properties, the actual cutting trajectory often deviates from the planned trajectory.

[0003] To mitigate this deviation, some existing technologies employ simple feedback mechanisms, comparing selected feature points of the actual cutting trajectory with the planned trajectory and then adjusting parameters accordingly. Other technologies utilize machine learning algorithms to classify and predict errors, such as using support vector machine (SVM) classifiers to identify error sources. However, these methods are not ideal when dealing with complex and variable error scenarios. Therefore, the production and processing of circular die molds still suffers from numerous shortcomings: 1) Traditional methods typically focus only on a few key feature points, failing to fully capture the error information between the actual cutting trajectory and the planned trajectory, resulting in inaccurate error analysis. 2) When addressing multiple error sources, existing technologies often use fixed weights that cannot be dynamically adjusted based on actual conditions, making them difficult to adapt to complex and changing production environments. 3) When the trajectory after initial adjustment still does not meet requirements, some existing technologies resort to simple trial-and-error iterative optimization, which is inefficient and consumes a significant amount of time and resources. Summary of the Invention

[0004] In order to solve at least one of the above-mentioned technical problems, the present invention provides a production and processing control method and system for a circular knife mold.

[0005] In a first aspect, the present invention provides a production and processing control method for a circular knife mold, the method comprising:

[0006] Collecting an image of the actual cutting path during the production and processing of a circular knife mold, and identifying the first coordinate of the first actual cutting path in the image through an edge detection algorithm;

[0007] Obtain the second coordinate of the first planned cutting trajectory during circular knife mold production and processing, compare the first coordinate with the second coordinate, extract the key feature points of the cutting, and analyze the error data between the first actual cutting trajectory and the first planned cutting trajectory based on the key feature points;

[0008] A feature vector is constructed based on the error data and input into the SVM classifier to obtain the error source. A simulated annealing algorithm is used to assign weights to different error sources, and a cutting trajectory correction model is constructed based on the error sources and corresponding weights to calculate the compensated second planned cutting trajectory.

[0009] The second planned cutting trajectory is used to feedback and adjust the operating parameters of the circular knife mold production and processing, and a compensated second actual cutting trajectory is generated. It is judged whether the error between the second actual cutting trajectory and the second planned cutting trajectory meets the preset conditions; if not, the weight of the error source is iteratively updated through the simulated annealing algorithm until the error between the second actual cutting trajectory and the second planned cutting trajectory meets the preset conditions, and the target cutting trajectory is generated to complete the production and processing process of the circular knife mold.

[0010] Preferably, identifying the first coordinate of the first actual cutting trajectory in the image by an edge detection algorithm includes:

[0011] Collect dynamic processing image sequences of the contact area between the tool and the workpiece during the production of circular knife molds, and dynamically adjust the optical filtering parameters according to the material reflection characteristics through an adaptive edge enhancement model;

[0012] An improved Canny operator detection algorithm is used to extract the sub-pixel machining trajectory contour, and the extracted machining trajectory contour is verified by physical constraints.

[0013] According to the verification result, first coordinates of a first actual cutting trajectory with a confidence rating are generated.

[0014] Preferably, the physical constraint verification of the extracted machining trajectory profile includes:

[0015] Establish tool kinematic constraint model, including:

[0016] ;

[0017] Tool tip arc radius;

[0018] Calculate the continuity coefficient between adjacent edge points and eliminate abnormal edge segments that do not conform to the tool kinematic equation;

[0019] For the remaining trajectory profiles, the image thermal distribution is compared with the theoretical cutting thermal model to correct the edge position deviation caused by thermal deformation.

[0020] Preferably, the error sources include one or more of material thermal deformation, laser power fluctuation, ambient temperature change and external vibration.

[0021] Preferably, constructing a cutting trajectory correction model according to error sources and corresponding weights includes:

[0022] ;

[0023] Where, represents the revised second planned cutting trajectory, represents the initial length of the material, 、 、 、 are the weights of the four error sources: material thermal deformation, ambient temperature change, external vibration, and laser power fluctuation; is the linear expansion coefficient of the material; is the material temperature change; is the linear expansion coefficient of the machine tool, 、 is the actual ambient temperature and the target ambient temperature; 、 are the acceleration and frequency of the external vibration, is the vibration compensation coefficient, and its value range is ; 、 is the target power and actual power of the laser, is the power fluctuation compensation coefficient, and its value range is .

[0024] Preferably, extracting key feature points of cutting and analyzing error data between the first actual cutting trajectory and the first planned cutting trajectory according to the key feature points includes:

[0025] Extract key feature points, including the starting point, end point, intersection point and inflection point of the cutting; the inflection point is determined according to the magnitude of the curvature;

[0026] According to the coordinates of the key feature points in the first actual cutting trajectory and the coordinates in the first planned cutting trajectory, the position error, angle error and shape error of the cutting are analyzed.

[0027] In a second aspect, the present invention further provides a production and processing control system for circular knife molds, the system comprising:

[0028] A data acquisition unit is used to acquire an image of an actual cutting trajectory during the production and processing of a circular knife mold, and identify a first coordinate of a first actual cutting trajectory in the image through an edge detection algorithm;

[0029] An error analysis unit is used to obtain the second coordinate of the first planned cutting trajectory during the production and processing of the circular knife mold, compare the first coordinate with the second coordinate, extract the key feature points of the cutting, and analyze the error data between the first actual cutting trajectory and the first planned cutting trajectory based on the key feature points;

[0030] The trajectory correction unit is used to construct a feature vector based on the error data and input the feature vector into the SVM classifier to obtain the error source; the simulated annealing algorithm is used to assign weights to different error sources, and a cutting trajectory correction model is constructed based on the error sources and corresponding weights to calculate the compensated second planned cutting trajectory;

[0031] The target generation unit is used to use the second planned cutting trajectory feedback to adjust the operating parameters of the circular knife mold production and processing, generate a compensated second actual cutting trajectory, and judge whether the error between the second actual cutting trajectory and the second planned cutting trajectory meets the preset conditions; when it does not meet the conditions, the weight of the error source is iteratively updated through the simulated annealing algorithm until the error between the second actual cutting trajectory and the second planned cutting trajectory meets the preset conditions, and generate a target cutting trajectory to complete the production and processing process of the circular knife mold.

[0032] In a third aspect, the present invention also provides an electronic device comprising a processor and a memory, wherein the memory is used to store computer program code, and the computer program code comprises computer instructions. When the processor executes the computer instructions, the electronic device executes the method as described in the first aspect above and any possible implementation thereof.

[0033] In a fourth aspect, the present invention also provides a computer-readable storage medium, in which a computer program is stored. The computer program includes program instructions, and when the program instructions are executed by a processor of an electronic device, the processor executes the method as described in the first aspect above and any possible implementation method thereof.

[0034] Compared with the prior art, the present invention has the following beneficial effects:

[0035] 1) This method captures images of the actual cutting path during circular die production and processing, uses an edge detection algorithm to identify the first coordinate of the actual cutting path, and then compares it in detail with the second coordinate of the planned cutting path. This method comprehensively extracts key cutting feature points, enabling more accurate analysis of the error data between the actual and planned cutting paths. Compared to traditional methods that focus only on a subset of feature points, this method captures more error details, providing a more reliable basis for subsequent error correction.

[0036] 2) This invention incorporates a simulated annealing algorithm to assign weights to different error sources. This algorithm dynamically adjusts the weights based on the actual error situation. As the production environment changes, the simulated annealing algorithm automatically finds the optimal weight combination, making the cutting trajectory correction model more adaptable to actual production needs. Compared with traditional fixed-weight methods, this invention more accurately reflects the impact of different error sources on the cutting trajectory, improving the accuracy of error correction.

[0037] 3) When the present invention determines that the error between the second actual cutting trajectory and the second planned cutting trajectory does not meet the preset conditions, the weight of the error source is iteratively updated through a simulated annealing algorithm. The simulated annealing algorithm has a strong global search capability and can quickly find the optimal solution, avoiding the blindness and inefficiency of the traditional trial and error method. This efficient iterative optimization mechanism greatly shortens the production debugging time, improves production efficiency, and reduces production costs. In summary, the present invention solves the problems of incomplete error analysis, fixed weights, and low iteration efficiency in the prior art through comprehensive error analysis, dynamic error source weight allocation, and an efficient iterative optimization mechanism, thereby achieving more accurate, flexible, and efficient circular knife mold production and processing control.

[0038] It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the background technology, the drawings required for use in the embodiments of the present invention or the background technology will be described below.

[0040] The accompanying drawings herein are incorporated into and constitute a part of the specification. These drawings illustrate embodiments consistent with the present disclosure and, together with the specification, are used to explain the technical solutions of the present disclosure.

[0041] Figure 1 A schematic flow chart of a production and processing control method for a circular knife mold provided by an embodiment of the present invention;

[0042] Figure 2 for Figure 1 Schematic diagram of the flow of sub-steps of step S10;

[0043] Figure 3 for Figure 1 Schematic diagram of the flow of sub-steps of step S20;

[0044] Figure 4 A schematic structural diagram of a production and processing control system for a circular knife mold provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0045] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0046] References herein to "embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present invention. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute a separate or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0047] See also Figure 1 , Figure 1 The following is a flow chart of a production and processing control method of a circular knife mold provided by an embodiment of the present invention. Figure 1 As shown, the method includes:

[0048] S10, collecting an actual cutting track image during the production and processing of a circular knife mold, and identifying a first coordinate of a first actual cutting track in the image through an edge detection algorithm;

[0049] When capturing images, a high-resolution, high-speed industrial camera should be selected to ensure that the details of the cutting path can be clearly captured. The camera should be installed in a suitable position to cover the entire cutting area and minimize external light interference. When setting the camera parameters, it is necessary to adjust the exposure time and gain to ensure that the image brightness is moderate and avoid overexposure or underexposure. Then calibrate the camera to ensure that the geometric distortion of the image is minimized. Finally, set a suitable trigger mechanism to ensure that the image is captured at the right time during the cutting process. The laser tube cutting machine's control system can be used to send a trigger signal, or an external sensor such as a photoelectric switch can be used to detect the start and end points of the cutting.

[0050] After acquiring an image, image preprocessing is typically performed to improve trajectory recognition accuracy. This includes grayscaling, denoising, and contrast enhancement. Grayscaling converts color images to grayscale, reducing data dimensionality and simplifying subsequent processing. Denoising methods such as median filtering or Gaussian filtering are preferred to remove image noise and improve edge detection accuracy. Finally, histogram equalization or adaptive histogram equalization is used to enhance image contrast and make the cutting trajectory more distinct.

[0051] See also Figure 2 In one embodiment, identifying the first coordinate of the first actual cutting trajectory in the image by an edge detection algorithm includes:

[0052] S201, collecting a dynamic processing image sequence of the contact area between the tool and the workpiece during the production and processing of the circular knife mold, and dynamically adjusting the optical filtering parameters according to the material reflection characteristics through an adaptive edge enhancement model;

[0053] A high-speed industrial camera array is used to capture the contact area between the tool and the workpiece during circular die production and processing from multiple angles, generating a dynamic sequence of processing images. The camera frame rate needs to be dynamically adjusted according to the processing speed to ensure that the critical moment of contact between the tool and the workpiece is captured. A database of the reflective properties of common mold materials is pre-established, including parameters such as the reflectivity and polarization properties of different materials under different lighting conditions. During image acquisition, the reflective properties of the current processing material are analyzed in real time. Based on the analyzed material reflective properties, the optical filter parameters are dynamically adjusted. For example, for high-reflectivity materials, the filter intensity is increased to reduce reflection interference; for low-reflectivity materials, the contrast is enhanced to highlight edge features. Specifically, a deep learning-based image enhancement model can be used. This model takes the material reflective property parameters as input and outputs the optimal combination of optical filter parameters.

[0054] Multi-angle shooting and dynamic frame rate adjustment ensure the capture of complete and clear processing image sequences, providing a high-quality data foundation for subsequent edge detection. Dynamic adjustment of optical filter parameters effectively suppresses interference caused by the reflective properties of different materials, improving the clarity and recognizability of the cutting track edges in the image, thereby enhancing the accuracy of edge detection.

[0055] S202, using an improved Canny operator detection algorithm to extract a sub-pixel processing trajectory contour, and performing physical constraint verification on the extracted processing trajectory contour;

[0056] Improved Canny operator detection algorithm:

[0057] Multi-scale Gaussian filtering: This method uses Gaussian filters of different scales to process the image, capturing edge features of varying thickness. An adaptive threshold selection method is used to determine the optimal threshold at each scale.

[0058] Gradient direction refinement: When calculating the gradient direction, the quadratic interpolation method is used to refine the gradient direction to the sub-pixel level to improve the accuracy of edge positioning.

[0059] Dual-threshold hysteresis processing: A dynamic dual-threshold mechanism is introduced to automatically adjust the high and low thresholds based on the statistical characteristics of the local area of the image to ensure that faint but important edges can be detected.

[0060] Based on the edges detected by the Canny operator, the grayscale moment method or surface fitting method is used for sub-pixel positioning, and the edge position is accurately determined to the sub-pixel level.

[0061] Physical constraint verification includes:

[0062] Kinematic constraints: Based on the kinematic model of the circular die, verify whether the extracted contour conforms to the tool's motion trajectory. For example, parameters such as the tool's rotation angle and feed rate should be consistent with the machining process parameters.

[0063] Geometric constraints: Check whether the extracted contour meets the geometric characteristics of the circular knife mold, such as the radius of the tool, the angle of the blade, etc.

[0064] Material removal constraints: Based on the material removal principle, verify whether the contour conforms to the physical laws of material removal, such as the shape and size of the chips.

[0065] An improved Canny operator detection algorithm, combined with sub-pixel positioning technology, improves the positioning accuracy of cutting path contours from the traditional pixel level to the sub-pixel level (typically up to 0.1-0.01 pixels), significantly improving the measurement accuracy of trajectory coordinates. A physical constraint verification mechanism effectively eliminates erroneous detection results caused by interference factors such as image noise and false edges, improving the reliability and accuracy of contour extraction.

[0066] S203: Generate first coordinates of a first actual cutting trajectory with a confidence rating according to the verification result.

[0067] Confidence Assessment Model: A confidence assessment model based on multi-feature fusion is established to evaluate the confidence of each coordinate point by comprehensively considering the following factors:

[0068] Edge strength: The larger the gradient magnitude of the edge pixel, the higher the confidence level.

[0069] Continuity: The better the continuity between a coordinate point and its adjacent points, the higher the confidence level. Continuity can be assessed by calculating the distance and angle difference between adjacent points.

[0070] Physical Constraint Compliance: The higher the degree to which a coordinate point complies with physical constraints, the higher the confidence level. This can be evaluated by quantifying the degree to which kinematic constraints, geometric constraints, and material removal constraints are satisfied.

[0071] Repeated measurement consistency: For multiple measurements of the same location, the higher the consistency, the higher the confidence.

[0072] Confidence rating: Confidence is divided into multiple levels, such as high, medium, and low. Coordinate points with confidence levels below the set threshold are marked or re-detected.

[0073] Coordinate generation: Based on the confidence level obtained by the evaluation, the extracted sub-pixel coordinates are weighted to generate the first coordinate of the final first actual cutting trajectory with a confidence rating.

[0074] The confidence rating mechanism provides a reliability indicator for each coordinate point, allowing subsequent error analysis and trajectory correction to focus more on high-confidence coordinate points, improving the stability and reliability of the entire control system. For low-confidence coordinate points, targeted measures can be taken, such as increasing the number of measurements and adjusting detection parameters, to further improve measurement accuracy.

[0075] Therefore, this embodiment achieves high-precision and reliable measurement of the actual cutting trajectory of the circular knife mold through technical means such as dynamic adjustment of optical filtering parameters, sub-pixel level contour extraction and physical constraint verification, and confidence rating, providing a solid foundation for subsequent error analysis and trajectory correction.

[0076] Preferably, the physical constraint verification of the extracted machining trajectory profile includes:

[0077] Establish tool kinematic constraint model, including:

[0078] ;

[0079] Tool tip arc radius;

[0080] Calculate the continuity coefficient between adjacent edge points and eliminate abnormal edge segments that do not conform to the tool kinematic equation;

[0081] For the remaining trajectory profiles, the image thermal distribution is compared with the theoretical cutting thermal model to correct the edge position deviation caused by thermal deformation.

[0082] During circular die machining, the tool's motion follows specific physical laws, and the heat generated during machining causes thermal deformation of both the material and the tool. The core principle of physical constraint verification is to utilize these known physical laws and characteristics to filter and modify the extracted machining trajectory profile to improve the accuracy of the trajectory coordinates.

[0083] Tool kinematic constraints: Tool motion during machining is limited by parameters such as spindle speed and tool radius. For example, the cutting speed cannot exceed the tool's maximum linear velocity, and the radius of curvature of the tool path cannot be less than the arc radius of the tool tip. By establishing these constraint models, anomalous edge segments that do not conform to physical laws can be eliminated.

[0084] Continuity constraint: The actual machining trajectory should be continuous and smooth, with a certain continuity relationship between adjacent edge points. By calculating the continuity coefficient, discontinuous abnormal points can be identified and their interference with the trajectory can be eliminated.

[0085] Thermal Deformation Correction: Heat generated during machining causes thermal deformation of the material and tool, affecting the cutting path. By comparing the image thermal distribution with the theoretical cutting thermal model, the amount of thermal deformation can be estimated and the trajectory can be corrected.

[0086] 1. Establish tool kinematic constraint model:

[0087] Determine the spindle speed and tool radius based on the machining process parameters.

[0088] Calculate the maximum cutting speed: .

[0089] For each point on the extracted machining trajectory contour, its cutting speed and curvature radius are calculated.

[0090] Eliminate cutting speed exceeding Or the point where the radius of curvature is less than the radius of the arc at the tool tip.

[0091] 2. Calculate the continuity coefficient and remove abnormal edge segments:

[0092] For adjacent edge points on the trajectory contour and , calculate the distance between them and direction angle ;

[0093] Continuity coefficient ,in and are the average values of the distance and direction angle of all adjacent points, Is the weight coefficient. Set the continuity threshold. When the continuity coefficient When the value is greater than the continuity threshold, the point is considered an outlier and the point and the edge segment where it is located are removed.

[0094] 3. Compare the thermal distribution of the image with the theoretical cutting thermal model and correct the thermal deformation:

[0095] Acquire thermal distribution images: Use an infrared thermal imager to capture thermal distribution images during the processing process and extract the temperature distribution near the trajectory contour.

[0096] Establish a theoretical cutting thermal model: Based on the processing parameters (such as cutting speed, feed rate, cutting depth, etc.), a theoretical cutting thermal model is established to calculate the temperature distribution during the processing.

[0097] Comparison and correction: Compare the thermal distribution of the image with the theoretical cutting thermal model, calculate the temperature difference, calculate the thermal deformation based on the thermal expansion coefficient and material properties, and perform position correction on each point on the trajectory profile based on the thermal deformation at its location.

[0098] Therefore, by eliminating outliers and edge segments that do not conform to the tool's kinematic constraints, false edge interference is reduced and trajectory coordinate accuracy is improved. The calculation of the continuity coefficient and the elimination of outliers enable the system to better cope with interference factors such as image noise and illumination variations, enhancing system robustness. Thermal deformation correction ensures accurate acquisition of the actual cutting trajectory even under high-temperature machining conditions. Accurate trajectory coordinates provide a reliable basis for subsequent error analysis and trajectory correction, helping to optimize machining parameters and improve machining quality and efficiency.

[0099] S20, obtaining the second coordinate of the first planned cutting trajectory during the production and processing of the circular knife mold, comparing the first coordinate with the second coordinate, extracting key feature points of the cutting, and analyzing error data between the first actual cutting trajectory and the first planned cutting trajectory based on the key feature points;

[0100] The first planned cutting path is typically generated by CAD software and consists of a series of coordinate points, known as second coordinates. These points define the desired cutting path. Typically, this first planned cutting path needs to be imported into the control system in advance to match the operating parameters of the pipe cutter, thereby controlling the pipe cutter to cut along the desired cutting path. Therefore, to obtain the second coordinate data for the first planned cutting path, simply export the coordinate data for the designed cutting path from the system and convert it into the required format, such as a CSV file, DXF file, or JSON format.

[0101] See also Figure 3 In one embodiment, extracting key feature points of cutting and analyzing error data between the first actual cutting trajectory and the first planned cutting trajectory according to the key feature points includes:

[0102] S201, extracting key feature points, including the starting point, end point, intersection point and inflection point of the cutting; the inflection point is determined according to the magnitude of the curvature;

[0103] S202: Analyze the position error, angle error, and shape error of the cutting according to the coordinates of the key feature points in the first actual cutting trajectory and the coordinates of the key feature points in the first planned cutting trajectory, including:

[0104] ;

[0105] ;

[0106] ;

[0107] Where, Indicates the Key feature points, a total of indivual; Indicates the actual cutting trajectory The coordinates of the key feature points, Indicates the first planned cutting trajectory corresponding to the first actual cutting trajectory The coordinates of key feature points; 、 represents the average position error and average angle error, represents the shape error, represents the structural similarity index between the first actual cutting trajectory and the first planned cutting trajectory, is the maximum structural similarity index.

[0108] In this step, the first point and the last point are extracted from the coordinate data of the first planned cutting trajectory and the first actual cutting trajectory as the starting point and the end point, respectively. For the identification of intersections, geometric algorithms or image processing methods can be used for detection. For example, Hough transform can be used to detect the intersection of straight lines. As for the inflection point, the curvature of the trajectory can be calculated, and the inflection point can be determined according to the magnitude of the curvature. For example, a certain curvature threshold is set, and then a point with a curvature greater than the curvature threshold is identified, and the point is used as the inflection point. It can be understood that the starting point, end point and inflection point can be one or more. When the cutting trajectory is long, the cutting trajectory can be segmented to determine the starting point, end point and inflection point of each segment, and finally the error of the entire cutting trajectory is integrated and analyzed.

[0109] This step considers three errors when calculating errors: position error, angle error, and shape error. Position error is calculated by calculating the Euclidean distance between the actual coordinates and the planned coordinates of each key feature point and then averaging it. Angle error is calculated by calculating the angle difference between the two points before and after each key feature point and then averaging it. Shape error uses the Structural Similarity Index (SSIM) to measure the shape similarity between the first actual cutting trajectory and the first planned cutting trajectory.

[0110] Therefore, by extracting key feature points and calculating positional, angular, and shape errors, this embodiment can comprehensively and accurately analyze the error between the actual cutting trajectory and the designed trajectory based on a limited number of representative feature points, providing detailed data support for subsequent error compensation. By calculating the average positional, angular, and shape errors, the cutting quality can be quantitatively assessed, providing a scientific basis for optimizing the operating parameters of circular knife grinding tool processing. Furthermore, the entire error analysis process can be automated, reducing manual intervention and improving work efficiency and accuracy.

[0111] S30, constructing a feature vector based on the error data, inputting the feature vector into the SVM classifier to obtain the error source; assigning weights to different error sources through a simulated annealing algorithm, constructing a cutting trajectory correction model based on the error source and the corresponding weight, and calculating the compensated second planned cutting trajectory;

[0112] In order to identify the error source, that is, the influencing factors that cause the error, this embodiment will train a support vector machine model in advance, so that the error source can be identified quickly and accurately based on the error data.

[0113] Specifically, training the support vector machine model includes the following steps:

[0114] 1) Error Data Preparation: A large amount of cutting trajectory data is extracted from historical cutting processes. Key feature points are then extracted from this data. Error data, including positional error, angular error, and shape error, is then calculated relative to the corresponding design trajectory to construct a feature vector. When constructing the feature vector, the error data for each key feature point is combined into a single feature vector. This feature vector can contain positional error, angular error, shape error, and the type of key feature point (starting point, end point, intersection point, inflection point).

[0115] 2) Data preprocessing: Normalize the feature vectors to ensure that the scales of different features are consistent and improve the training effect of the model.

[0116] 3) Kernel Function Selection: A support vector machine (SVM) model is trained using known error source data and corresponding eigenvectors. Kernel functions can be polynomial or RBF to handle nonlinear data. Known error sources include, but are not limited to, material thermal deformation, laser power fluctuations, ambient temperature changes, and external vibrations. Before training, each data sample must be labeled with its corresponding error source to obtain labeled data corresponding to the error data.

[0117] 4) Model training: Set the hyperparameters of the SVM model, such as the penalty parameter and kernel function parameters; train the SVM model using the training set data, which includes error data and labeled data.

[0118] 5) Model Evaluation: K-fold cross-validation is performed to assess the model's generalization ability. Evaluation metrics are set, including accuracy, confusion matrix, and F1 score. Accuracy calculates the model's accuracy on the test set. The confusion matrix provides information about the predictions for each category. The F1 score provides a comprehensive analysis of precision and recall. Grid search or random search can then be used to automatically find the optimal hyperparameter combination.

[0119] Finally, the final trained support vector machine model is used to predict the error source type. Simply obtain the feature vector constructed based on the error data and input it into the support vector machine model to quickly and accurately output the error source type.

[0120] Preferably, the error sources identified are material thermal deformation, ambient temperature change, external vibration, and laser power fluctuation. Furthermore, in order to reasonably construct the correction model, it is necessary to assign weights to these four error sources. Specifically, the weighting process is as follows:

[0121] 1) Define the objective function: Define an objective function to evaluate the performance of different weighted combinations of error sources. The objective function can be the sum of the errors, the average error, or other relevant indicators.

[0122] 2) Initialization parameters: Initialize the weights of the error sources, usually randomly. Set parameters such as initial temperature, cooling rate, and termination temperature.

[0123] 3) Simulated Annealing: At each iteration, a new weight combination is generated and its objective function value is calculated. The Metropolis criterion is used to decide whether to accept the new solution. The temperature is gradually lowered until the termination temperature is reached.

[0124] 4) Evaluate and update weights: After each iteration, evaluate the performance of the current weight combination and record the best weight combination.

[0125] This embodiment utilizes a simulated annealing algorithm to perform a global search within the solution space, avoiding local optimal solutions and improving optimization results. By gradually decreasing the temperature, the simulated annealing algorithm adaptively adjusts the search strategy, ensuring that better solutions are found at different stages. By optimizing the error source weights through the simulated annealing algorithm, the robustness of the system can be improved, adapting to different error sources, thereby enhancing the accuracy of the correction model.

[0126] After the first weighting is completed, a cutting trajectory correction model needs to be constructed based on the error source and the corresponding weight. Preferably, the cutting trajectory correction model is constructed based on the error source and the corresponding weight, and the second planned cutting trajectory after compensation is calculated, including:

[0127] ;

[0128] Where, Indicates the corrected cutting trajectory, represents the initial length of the material, 、 、 、 are the weights of the four error sources: material thermal deformation, ambient temperature change, external vibration, and laser power fluctuation; is the linear expansion coefficient of the material; is the material temperature change; is the linear expansion coefficient of the machine tool, 、 is the actual ambient temperature and the target ambient temperature; 、 are the acceleration and frequency of the external vibration, is the vibration compensation coefficient, and its value range is ; 、 are the target power and actual power of the laser, is the power fluctuation compensation coefficient, and its value range is .

[0129] In the above formula, It is the thermal deformation compensation item, the material changes due to temperature Thermal expansion and contraction occur, linear expansion coefficient Describes the rate of change of length caused by unit temperature rise. Adjust the impact intensity. This item is used to compensate for the dimensional deviation of the material itself due to temperature changes. It is the compensation item for ambient temperature changes. The machine tool is affected by ambient temperature fluctuations. Influence, linear expansion coefficient Reflects the deformation ratio of the machine tool structure. Weight Controls the correction ratio, which is used to offset the mechanical deformation of the machine tool caused by the deviation of the ambient temperature from the target value.

[0130] is the vibration compensation term, vibration acceleration Converted into displacement through integration, compensation coefficient Reduce the sensitivity of high frequency vibration, weight Adjust the overall contribution. The vibration compensation term is used to dynamically offset the instantaneous displacement error of the cutting head caused by vibration. is the power fluctuation compensation term, the actual power With target power The ratio reflects the energy input deviation, and the exponential term is expressed by Adjust compensation strength, weight Control its impact on the trajectory. Power fluctuation compensation is used to extend the cutting path or adjust the speed when power is insufficient to ensure consistent cutting depth.

[0131] By comprehensively considering the influence of multiple error sources, this embodiment uses a correction model to more accurately predict and compensate for the error between the second planned cutting trajectory and the first planned cutting trajectory, significantly improving cutting accuracy. Once the correction model is generated, the compensated cutting path is prioritized for correction and integrated into the CNC system. Feedback control enables real-time compensation of the cutting trajectory, reducing scrap rates due to errors and lowering production costs.

[0132] S40. Use the second planned cutting trajectory feedback to adjust the operating parameters of the circular knife mold production and processing, generate a compensated second actual cutting trajectory, and judge whether the error between the second actual cutting trajectory and the second planned cutting trajectory meets the preset conditions; if not, iteratively update the weight of the error source through the simulated annealing algorithm until the error between the second actual cutting trajectory and the second planned cutting trajectory meets the preset conditions, and generate the target cutting trajectory to complete the production and processing process of the circular knife mold.

[0133] After the feedback is fed back to adjust the operating parameters of the circular knife mold production and processing, the cutting process is controlled according to the parameters, and the second actual cutting trajectory after compensation is further obtained. At this time, the error between the second actual cutting trajectory and the second planned cutting trajectory can be analyzed according to the process of the aforementioned steps S10-S20. If the error between the two cannot meet the preset conditions, for example, it is higher than the set error threshold, then it means that the correction model at this time needs to be optimized, that is, the model is optimized by adjusting the initial assignment weights. It is specifically achieved through the process of step S30, that is, the weight of the error source is iteratively updated through the simulated annealing algorithm, and the cutting path compensation and cutting are re-performed until the error meets the preset conditions, and the final operating parameters and final cutting trajectory of the circular knife mold production and processing are obtained. This trajectory is used as the target cutting trajectory to complete the production and processing process of the circular knife mold.

[0134] Therefore, the above embodiment can gradually reduce the error between the actual cutting trajectory and the planned cutting trajectory by iteratively optimizing the weights of the error sources, thereby improving cutting accuracy. The entire process can be automated, reducing manual intervention and improving work efficiency and accuracy. Optimizing the error source weights through a simulated annealing algorithm improves the robustness of the system and can adapt to different types of error sources. By continuously iteratively updating the error source weights, the cutting path can be continuously optimized to ensure that the final cutting trajectory meets the preset conditions.

[0135] In summary, the method provided by the present invention can at least achieve the following beneficial effects:

[0136] 1) This method captures images of the actual cutting path during circular die production and processing, uses an edge detection algorithm to identify the first coordinate of the actual cutting path, and then compares it in detail with the second coordinate of the planned cutting path. This method comprehensively extracts key cutting feature points, enabling more accurate analysis of the error data between the actual and planned cutting paths. Compared to traditional methods that focus only on a subset of feature points, this method captures more error details, providing a more reliable basis for subsequent error correction.

[0137] 2) This invention incorporates a simulated annealing algorithm to assign weights to different error sources. This algorithm dynamically adjusts the weights based on the actual error situation. As the production environment changes, the simulated annealing algorithm automatically finds the optimal weight combination, making the cutting trajectory correction model more adaptable to actual production needs. Compared with traditional fixed-weight methods, this invention more accurately reflects the impact of different error sources on the cutting trajectory, improving the accuracy of error correction.

[0138] 3) When the present invention determines that the error between the second actual cutting trajectory and the second planned cutting trajectory does not meet the preset conditions, the weight of the error source is iteratively updated through a simulated annealing algorithm. The simulated annealing algorithm has a strong global search capability and can quickly find the optimal solution, avoiding the blindness and inefficiency of the traditional trial and error method. This efficient iterative optimization mechanism greatly shortens the production debugging time, improves production efficiency, and reduces production costs. In summary, the present invention solves the problems of incomplete error analysis, fixed weights, and low iteration efficiency in the prior art through comprehensive error analysis, dynamic error source weight allocation, and an efficient iterative optimization mechanism, thereby achieving more accurate, flexible, and efficient circular knife mold production and processing control.

[0139] See also Figure 4 In one embodiment, the present invention further provides a production and processing control system for a circular knife mold, the system comprising:

[0140] The data acquisition unit 100 is used to collect an image of an actual cutting trajectory during the production and processing of a circular knife mold, and identify a first coordinate of a first actual cutting trajectory in the image through an edge detection algorithm;

[0141] The error analysis unit 200 is used to obtain the second coordinate of the first planned cutting trajectory during the production and processing of the circular knife mold, compare the first coordinate with the second coordinate, extract the key feature points of the cutting, and analyze the error data between the first actual cutting trajectory and the first planned cutting trajectory based on the key feature points;

[0142] The trajectory correction unit 300 is used to construct a feature vector based on the error data, input the feature vector into the SVM classifier to obtain the error source; assign weights to different error sources through the simulated annealing algorithm, construct a cutting trajectory correction model based on the error sources and corresponding weights, and calculate the compensated second planned cutting trajectory;

[0143] The target generation unit 400 is used to use the second planned cutting trajectory feedback to adjust the operating parameters of the circular knife mold production and processing, generate a compensated second actual cutting trajectory, and judge whether the error between the second actual cutting trajectory and the second planned cutting trajectory meets the preset conditions; when it does not meet the conditions, the weight of the error source is iteratively updated through the simulated annealing algorithm until the error between the second actual cutting trajectory and the second planned cutting trajectory meets the preset conditions, and generate a target cutting trajectory to complete the production and processing process of the circular knife mold.

[0144] It can be understood that the functions or modules included in the system provided in this embodiment can be used to execute the method described in the above method embodiment. Its specific implementation can refer to the description of the above method embodiment. For the sake of brevity, it will not be repeated here.

[0145] The present invention also provides an electronic device, including a processor and a memory, wherein the memory is used to store computer program code, and the computer program code includes computer instructions. When the processor executes the computer instructions, the electronic device executes a method as described in any one of the possible implementation modes.

[0146] The present invention also provides a computer-readable storage medium, in which a computer program is stored. The computer program includes program instructions. When the program instructions are executed by a processor of an electronic device, the processor executes a method as described in any one of the possible implementation methods described above.

[0147] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present invention.

Claims

1. A production and processing control method for a circular knife mold, characterized in that: The method comprises: Collecting an image of the actual cutting path during the production and processing of a circular knife mold, and identifying the first coordinate of the first actual cutting path in the image through an edge detection algorithm; Obtain the second coordinate of the first planned cutting trajectory during circular knife mold production and processing, compare the first coordinate with the second coordinate, extract the key feature points of the cutting, and analyze the error data between the first actual cutting trajectory and the first planned cutting trajectory based on the key feature points; A feature vector is constructed based on the error data and input into the SVM classifier to obtain the error source. A simulated annealing algorithm is used to assign weights to different error sources, and a cutting trajectory correction model is constructed based on the error sources and corresponding weights to calculate the compensated second planned cutting trajectory. The second planned cutting trajectory is used to feedback and adjust the operating parameters of the circular knife mold production and processing, and a compensated second actual cutting trajectory is generated. It is judged whether the error between the second actual cutting trajectory and the second planned cutting trajectory meets the preset conditions; if not, the weight of the error source is iteratively updated through the simulated annealing algorithm until the error between the second actual cutting trajectory and the second planned cutting trajectory meets the preset conditions, and the target cutting trajectory is generated to complete the production and processing process of the circular knife mold.

2. The production and processing control method of the circular knife mold according to claim 1 is characterized in that: The identifying the first coordinate of the first actual cutting trajectory in the image by using an edge detection algorithm includes: Collect dynamic processing image sequences of the contact area between the tool and the workpiece during the production of circular knife molds, and dynamically adjust the optical filtering parameters according to the material reflection characteristics through an adaptive edge enhancement model; An improved Canny operator detection algorithm is used to extract sub-pixel machining trajectory contours, and physical constraint verification is performed on the extracted machining trajectory contours. According to the verification result, first coordinates of a first actual cutting trajectory with a confidence rating are generated.

3. The production and processing control method of the circular knife mold according to claim 2 is characterized in that: The physical constraint verification of the extracted machining trajectory contour includes: Establish tool kinematic constraint model, including: ； Tool tip arc radius; Calculate the continuity coefficient between adjacent edge points and eliminate abnormal edge segments that do not conform to the tool kinematic equation; For the remaining trajectory profiles, the image thermal distribution is compared with the theoretical cutting thermal model to correct the edge position deviation caused by thermal deformation.

4. The production and processing control method of the circular knife mold according to claim 1 is characterized in that: The error sources include one or more of material thermal deformation, laser power fluctuation, ambient temperature change and external vibration.

5. The production and processing control method of the circular knife mold according to claim 4 is characterized in that: The cutting trajectory correction model is constructed according to the error sources and corresponding weights, including: ； Where, represents the revised second planned cutting trajectory, represents the initial length of the material, 、 、 、 are the weights of the four error sources: material thermal deformation, ambient temperature change, external vibration, and laser power fluctuation; is the linear expansion coefficient of the material; is the material temperature change; is the linear expansion coefficient of the machine tool, 、 is the actual ambient temperature and the target ambient temperature; 、 are the acceleration and frequency of the external vibration, is the vibration compensation coefficient, and its value range is ; 、 are the target power and actual power of the laser, is the power fluctuation compensation coefficient, and its value range is .

6. The production and processing control method of the circular knife mold according to claim 5, characterized in that: The extracting key feature points of the cutting and analyzing error data between the first actual cutting trajectory and the first planned cutting trajectory according to the key feature points includes: Extract key feature points, including the starting point, end point, intersection point and inflection point of the cutting; the inflection point is determined according to the magnitude of the curvature; According to the coordinates of the key feature points in the first actual cutting trajectory and the coordinates in the first planned cutting trajectory, the position error, angle error and shape error of the cutting are analyzed.

7. A production and processing control system for circular knife molds, characterized in that: The system comprises: A data acquisition unit is used to acquire an image of an actual cutting trajectory during the production and processing of a circular knife mold, and identify a first coordinate of a first actual cutting trajectory in the image through an edge detection algorithm; An error analysis unit is used to obtain the second coordinate of the first planned cutting trajectory during the production and processing of the circular knife mold, compare the first coordinate with the second coordinate, extract the key feature points of the cutting, and analyze the error data between the first actual cutting trajectory and the first planned cutting trajectory based on the key feature points; The trajectory correction unit is used to construct a feature vector based on the error data and input the feature vector into the SVM classifier to obtain the error source; the simulated annealing algorithm is used to assign weights to different error sources, and a cutting trajectory correction model is constructed based on the error sources and corresponding weights to calculate the compensated second planned cutting trajectory; The target generation unit is used to use the second planned cutting trajectory feedback to adjust the operating parameters of the circular knife mold production and processing, generate a compensated second actual cutting trajectory, and judge whether the error between the second actual cutting trajectory and the second planned cutting trajectory meets the preset conditions; when it does not meet the conditions, the weight of the error source is iteratively updated through the simulated annealing algorithm until the error between the second actual cutting trajectory and the second planned cutting trajectory meets the preset conditions, and generate a target cutting trajectory to complete the production and processing process of the circular knife mold.

8. An electronic device, characterized in that: include: A processor and a memory, wherein the memory is used to store computer program code, and the computer program code includes computer instructions. When the processor executes the computer instructions, the electronic device executes the production and processing control method of the circular knife mold as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, which includes program instructions. When the program instructions are executed by a processor of an electronic device, the processor executes the production and processing control method of the circular knife mold according to any one of claims 1 to 6.

Images