Efficient cutting system for trimming edges of plastic molds

Abstract

The invention discloses an efficient cutting system for plastic mold edge trimming. The efficient cutting system comprises a visualization module, a motion control module, a cutting execution module, a parameter monitoring module and a data analysis and feedback module. The data analysis and feedback module is connected with the visualization module, the motion control module and the parameter monitoring module and used for receiving and deeply analyzing data in real time, evaluating the cutting quality and outputting a feedback instruction to the motion control module and the visualization module. The visual module is used for acquiring the edge image information of the plastic mold, analyzing and processing the edge image information and determining a cutting path; through cooperation of the visualization module, the motion control module, the cutting execution module, the parameter monitoring module and the data analysis and feedback module, key cutting parameters can be monitored in real time, problems occurring in the cutting process can be found and solved in time, and therefore the cutting quality of plastic mold edge trimming is effectively improved.

Description

Technical Field

[0001] The invention belongs to the technical field of plastic mold processing, and in particular relates to a high-efficiency cutting system for trimming the edges of plastic molds. Background Art

[0002] Plastic mold edge trimming is to improve the quality of the mold edge so that it meets the requirements of precision, appearance and performance of plastic products. Among them, plastic mold trimming includes eliminating edge burrs, flash, and removing surface roughness. Currently, plastic mold trimming usually adopts laser cutting, which uses a high-energy laser beam to cut the mold edge or clad a layer of anti-friction material on the mold edge surface to improve the quality of the plastic mold.

[0003] For example, Chinese patent application number 202410961018.1 discloses a cutting device for producing plastic molds with an edge trimming structure, comprising a bracket, wherein the bracket is fixedly connected to two symmetrically distributed connecting frames, one of the symmetrically distributed connecting frames being rotatably connected to a lead screw, the connecting frame being slidably connected to a slider, the symmetrically distributed sliders being rotatably connected to lead screws, the connecting frame being rotatably connected to lead screws, the connecting frame being rotatably connected to lead screws, the lead screw being mounted on the connecting frame being rotatably connected to a driven wheel, the output shaft of the motor being fixedly connected to a driving wheel, the symmetrically distributed slider being mounted on the motor, the output shaft of the motor being fixedly connected to a driving wheel, the lead screw being splined to the driven wheel. This invention changes the moving speed of the laser cutting head by bringing connecting rods 1 and 2 closer to each other, thereby changing the transmission ratio between driven wheel 1 and driving wheel 1 and between driven wheel 2 and driving wheel 2.

[0004] However, since most current cutting devices lack the function of comprehensive monitoring of the cutting process, it is not convenient to obtain detailed information on key parameters such as cutting quality, cutting speed, laser power, etc. in real time, which affects the cutting quality. For example, during the cutting process, if the laser power fluctuates, it may not be detected in time, and problems arising in the cutting process cannot be discovered and solved in time, resulting in unstable cutting quality. Therefore, we need to propose an efficient cutting system for plastic mold edge trimming to solve the above-mentioned problems, so that it can monitor the information of key cutting parameters in real time, discover and solve problems arising in the cutting process in time, and improve cutting quality. Summary of the Invention

[0005] The purpose of the present invention is to provide an efficient cutting system for trimming the edges of plastic molds, which can monitor the information of key cutting parameters in real time, promptly discover and solve problems that arise during the cutting process, improve cutting quality, and solve the problems raised in the above-mentioned background technology.

[0006] To achieve the above object, the present invention adopts the following technical solutions:

[0007] An efficient cutting system for plastic mold edge trimming, including a visualization module, a motion control module, a cutting execution module, a parameter monitoring module, and a data analysis and feedback module;

[0008] The data analysis and feedback module is connected to the visualization module, motion control module, and parameter monitoring module respectively, and is used to receive and deeply analyze data in real time, evaluate cutting quality, and output feedback instructions to the motion control module and visualization module;

[0009] The visualization module obtains and analyzes the edge image information of the plastic mold to determine the cutting path;

[0010] The motion control module generates control instructions according to the cutting path determined by the visualization module;

[0011] The cutting execution module performs a cutting operation on the edge of the plastic mold according to the control instruction generated by the motion control module;

[0012] The parameter monitoring module collects key parameters in the cutting process in real time, converts and processes the collected parameter data, and transmits them to the data analysis and feedback module in the form of digital signals.

[0013] Preferably, the data analysis and feedback module analyzes and processes the data and evaluates the cutting quality in real time. Once an abnormal parameter is found, the data analysis and feedback module immediately generates a feedback instruction and sends it to the motion control module. The motion control module adjusts the cutting parameters according to the instruction and feeds back the adjustment information to the visualization module. The visualization module updates the display content in real time.

[0014] Preferably, the process of the data analysis and feedback module for performing cutting quality assessment is as follows:

[0015] S1. Set the window size and use the sliding average algorithm to smooth the received data;

[0016] S2. Use the collected data as feature vectors and perform normalization on the data;

[0017] S3. Use radial basis function to build support vector machine model. The formula of support vector machine model is:

[0018] K(y i ,y)=exp(-γ‖y i -y‖ 2 ), where γ is a hyperparameter, ‖y i -y|| 2 is the sample y i The square of the Euclidean distance to sample y, K(y i ,y) is the output value of radial basis function;

[0019] S4. Collect data containing qualified product labels to train the support vector machine model:

[0020] S5. Input the normalized real-time data into the trained support vector machine model for prediction, and determine the cutting quality based on the prediction results.

[0021] Preferably, the visualization module includes an image acquisition unit, an image preprocessing unit and a display unit connected in sequence, the image acquisition unit captures image information of the edge of the plastic mold through a camera, and the camera uses a high-definition camera; the image processing unit analyzes and processes the collected image and determines the cutting path; the display unit is used to display the processed image and determine the display of the cutting path.

[0022] Preferably, the image processing unit performs image analysis and processing as follows:

[0023] A1. Convert the collected image to grayscale using a weighted average algorithm, and then filter the converted image using a median filter algorithm to remove interference noise.

[0024] A2. Use the Canny edge detection algorithm to detect edges on the filtered image, retaining the true edges and removing the false edges;

[0025] A3. Extract key features of the edge of the plastic mold based on the image after edge detection processing, and determine the cutting path based on the extracted features.

[0026] Preferably, the key feature extraction process is as follows:

[0027] A31. Calculate the gradient of each pixel in the image in the x-direction and the y-direction, and calculate the autocorrelation matrix based on the calculated gradient values. The autocorrelation matrix calculation formula is:

[0028] Among them, M(x,y) is the autocorrelation matrix of pixel point (x,y), I x is the gradient of the pixel (x, y) in the x direction, I y is the gradient of the pixel point (x, y) in the y direction;

[0029] A32. Calculate the corner point response function value based on the autocorrelation matrix. The corner point response function value calculation formula is:

[0030] R=det(M)-k[trace(M)] 2, where R is the corner point response function value, det(M) is the determinant of the matrix M, k is an empirical constant ranging from 0.04 to 0.06, and trace(M) is the trace of the matrix M. The larger the R value, the more likely the point is a corner point.

[0031] A33. Set a corner threshold and determine the pixel points whose corner response function values ​​are greater than the corner threshold as feature points, thereby extracting the key features of the edge of the plastic mold.

[0032] Preferably, the motion control module uses a PID control algorithm to generate control instructions. The PID control algorithm calculates the proportional term, integral term and differential term based on the deviation value between the motor set speed and the actual speed in the cutting execution module, and then adds the proportional term, integral term and differential term to obtain the control quantity of the motor speed regulation.

[0033] Preferably, the cutting path determination process is as follows:

[0034] B1. Divide the processed mold edge image into multiple sub-regions using a uniform grid;

[0035] B2. Select one starting point and one target point in each sub-area as the cutting start point and cutting end point;

[0036] B3. Calculate the Euclidean distance from the cutting start point to the cutting end point based on the coordinates of the cutting start point and the cutting end point;

[0037] B4. Plan multiple feasible movement paths from the cutting start point to the cutting end point. Count the number of segments where two adjacent nodes are horizontal or vertical, and the number of segments where two adjacent nodes are diagonal, on each path. Calculate the movement cost from the cutting start point to the cutting end point.

[0038] B5. Calculate the total cost from the starting point to the end point of the cutting. The total cost calculation formula is:

[0039] f(n)=g(n)+h(n), where f(n) is the total cost from the starting point to the end point, g(n) is the moving cost from the starting point to the end point, and h(n) is the Euclidean distance from the starting point to the end point.

[0040] B6. Select the moving path with the minimum total cost in each sub-area for expansion and splicing. The spliced ​​path is the cutting path.

[0041] Preferably, the parameter monitoring module includes a sensor module and a signal processing unit. The sensor module collects physical parameters during the cutting process, and the signal processing unit converts the collected physical parameters into analog-to-digital values ​​and transmits them to the data analysis and feedback module. The sensor module includes a laser power sensor, a speed sensor, a temperature sensor and a displacement sensor.

[0042] Preferably, it also includes a fixture positioning module, which is connected to the motion control module and is used to accurately fix and position the plastic module, and cooperate with the visualization module and the motion control module to accurately position the plastic mold in the cutting area.

[0043] The present invention proposes an efficient cutting system for trimming the edges of plastic molds, which has the following advantages over the prior art:

[0044] 1. The present invention cooperates with the visualization module, motion control module, cutting execution module, fixture positioning module, parameter monitoring module and data analysis and feedback module. The parameter monitoring module collects key parameters such as laser power and cutting speed in real time, and transmits the data to the data analysis and feedback module. The data analysis and feedback module analyzes and processes the data and evaluates the cutting quality in real time. Once an abnormal parameter is found, the data analysis and feedback module immediately generates a feedback instruction and sends it to the motion control module. The motion control module adjusts the cutting parameters according to the instruction and feeds back the adjustment information to the visualization module. The visualization module updates the display content in real time, so that the system can monitor the key cutting parameters in real time, promptly discover and solve problems that arise during the cutting process, thereby effectively improving the cutting quality of plastic mold edge trimming.

[0045] 2. The present invention uses the setting of the clamp positioning mold to accurately fix and position the plastic module, and cooperates with the visualization module and the motion control module to accurately position the plastic mold in the cutting area, providing a reliable basic guarantee for high-quality cutting. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 Shows a block diagram of a cutting system according to an embodiment of the present invention;

[0047] Figure 2 A flowchart of cutting quality evaluation performed by a data analysis and feedback module according to an embodiment of the present invention is shown;

[0048] Figure 3 A flow chart of cutting path determination according to an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0049] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. The specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0050] The present invention provides Figure 1-3 The illustrated system is an efficient cutting system for trimming plastic mold edges, comprising a visualization module, a motion control module, a cutting execution module, a fixture positioning module, a parameter monitoring module, and a data analysis and feedback module. The data analysis and feedback module is connected to the visualization module, the motion control module, and the parameter monitoring module, respectively, and is used to receive and analyze data in real time, evaluate cutting quality, and output feedback instructions to the motion control module and the visualization module.

[0051] like Figure 2 As shown in the figure, the process of cutting quality evaluation in the data analysis and feedback module is as follows:

[0052] S1. Set the window size and use the sliding average algorithm to smooth the received data. The calculation formula of the sliding average algorithm is:

[0053] Among them, y p is the value of the pth data after processing, N is the window size, x h is the hth original data;

[0054] S2. Use the collected data as feature vectors and perform normalization on the data;

[0055] S3. Use radial basis function to build support vector machine model. The formula of support vector machine model is:

[0056] K(y i ,y)=exp(-γ‖y i -y‖ 2 ), where γ is a hyperparameter, ‖y i -y‖ 2 is the sample y i The square of the Euclidean distance to sample y, K(y i ,y) is the output value of radial basis function;

[0057] S4. Collect data containing qualified product labels to train the support vector machine model. During the training process, SVM determines the model parameters by solving the optimization problem. For the binary classification problem, its optimization goal is to maximize the classification interval. The corresponding Lagrangian function is:

[0058] Among them, ω is used to determine the feature, o is the number of samples, δ i is the slack variable, α i is the Lagrange multiplier, b is the bias term used to adjust the position of the decision boundary, and y i is the i-th eigenvector, Y iis the label of the i-th sample, C is the penalty parameter used to balance the model complexity and training error, and L(α, b, δ) is the output value of the Lagrangian function;

[0059] S5. Input the normalized real-time data into the trained support vector machine model for prediction, and determine the cutting quality based on the prediction results; the quality evaluation formula is:

[0060] Among them, o is the number of samples, α i is the Lagrange multiplier, b is the bias term used to adjust the decision boundary position, f(x) is the cutting quality evaluation value, K(y i ,y) is the output value of the radial basis function; when f(x) is positive, it means that the cutting quality is qualified, and when f(x) is negative, it means that the cutting quality is unqualified;

[0061] The visualization module obtains and analyzes the edge image information of the plastic mold to determine the cutting path;

[0062] The visualization module includes an image acquisition unit, an image preprocessing unit and a display unit connected in sequence. The image acquisition unit captures image information of the edge of the plastic mold through a camera, and the camera uses a high-definition camera; the image processing unit analyzes and processes the collected image and determines the cutting path; the display unit is used to display the processed image and the determined cutting path, which is convenient for the operator to view intuitively.

[0063] The image processing unit performs image analysis and processing as follows:

[0064] A1. Convert the collected image to grayscale using a weighted average algorithm, and then filter the converted image using a median filter algorithm to remove interference noise.

[0065] A2. Use the Canny edge detection algorithm to detect edges on the filtered image, retaining the true edges and removing the false edges;

[0066] During edge detection, the image is first smoothed by a two-dimensional Gaussian function, and then the Sobel operator is used to calculate the gradient of the image in the x and y directions respectively. Then, each pixel in the image is traversed. For the current pixel, it is determined whether its gradient direction is the largest in the area centered on the point. If not, the grayscale value of the pixel is set to 0, thereby refining the edge so that the edge width is only one pixel. The high threshold and low threshold of the gradient amplitude are set, and the high threshold is 2-3 times the low threshold. Pixels with gradient amplitude greater than the high threshold are determined as edge points, and pixels with gradient amplitude less than the low threshold are excluded. For pixels with gradient amplitude between the high threshold and the low threshold, if they are connected to the determined edge points, they are retained as edge points, otherwise they are discarded. This operation can effectively retain the true edges and remove false edges.

[0067] A3. Extract key features of the plastic mold edge based on the image after edge detection processing, and determine the cutting path based on the extracted features;

[0068] The key feature extraction process is as follows:

[0069] A31. Calculate the gradient of each pixel in the image in the x-direction and the y-direction, and calculate the autocorrelation matrix based on the calculated gradient values. The autocorrelation matrix calculation formula is:

[0070] Among them, M(x,y) is the autocorrelation matrix of pixel point (x,y), I x is the gradient of the pixel (x, y) in the x direction, I y is the gradient of the pixel point (x, y) in the y direction;

[0071] A32. Calculate the corner point response function value based on the autocorrelation matrix. The corner point response function value calculation formula is:

[0072] r=det(M)-k[trace(M)] 2 , where R is the corner point response function value, det(M) is the determinant of the matrix M, k is an empirical constant ranging from 0.04 to 0.06, and trace(M) is the trace of the matrix M. The larger the R value, the more likely the point is a corner point.

[0073] A33. Set a corner threshold and determine the pixel points whose corner response function values ​​are greater than the corner threshold as feature points, thereby extracting the key features of the edge of the plastic mold.

[0074] The corner threshold is automatically calculated based on the statistical distribution of the R value in the image, such as the mean, variance, and maximum value, so that the threshold changes dynamically with the image content. For example, when the corner threshold T is set based on the mean μ and the standard deviation σ, the corner threshold T setting formula is: T = μ + lσ (l is an empirical coefficient with a value of 1-3);

[0075] like Figure 3 As shown, the cutting path determination process is as follows:

[0076] B1. Divide the processed mold edge image into multiple sub-regions using a uniform grid, that is, divide the image into rectangular grids of equal size;

[0077] B2. Select one starting point and one target point in each sub-area as the cutting start point and cutting end point;

[0078] B3. Calculate the Euclidean distance from the cutting start point to the cutting end point based on the coordinates of the cutting start point and the cutting end point. The Euclidean distance calculation formula is:

[0079] Among them, h(n) is the Euclidean distance from the cutting start point to the cutting end point, (x goal ,y goal ) is the coordinate of the cutting end point, (x n -y n ) is the coordinate of the current cutting starting point;

[0080] B4. Plan multiple feasible movement paths from the cutting start point to the cutting end point. Count the number m of segments where two adjacent nodes are horizontal or vertical, and the number k of segments where two adjacent nodes are diagonal, on each path. Calculate the movement cost from the cutting start point to the cutting end point. The movement cost calculation formula is:

[0081] Among them, g(n) is the moving cost from the cutting starting point to the cutting end point, 1 is the moving unit distance between two adjacent nodes in the horizontal or vertical direction, is the Euclidean distance between two adjacent diagonal nodes;

[0082] B5. Calculate the total cost from the starting point to the end point of the cutting. The total cost calculation formula is:

[0083] f(n)=g(n)+h(n), where f(n) is the total cost from the starting point to the end point, g(n) is the moving cost from the starting point to the end point, and h(n) is the Euclidean distance from the starting point to the end point.

[0084] B6. Select the moving path with the minimum total cost in each sub-area and perform expansion and splicing. The spliced ​​path is the cutting path.

[0085] The motion control module generates control instructions based on the cutting path determined by the visualization module to ensure stable operation of the system;

[0086] The motion control module uses the PID control algorithm to generate control instructions. The PID control algorithm calculates the proportional term, integral term, and differential term based on the deviation between the motor set speed and the actual speed in the cutting execution module, and then adds the proportional term, integral term, and differential term to obtain the control quantity of the motor speed regulation. The calculation formula of the PID control algorithm is:

[0087] Among them, u(t) is the control quantity of motor speed regulation, e(t) is the deviation between the motor set speed and actual speed at time t, K p , K i and K d are the proportional coefficient, integral coefficient, and differential coefficient respectively. dτ is the small change in the integral variable τ, which is the cumulative sum of the small change dτ based on τ in the interval e(τ) from 0 to t; de(t) represents the small change in the speed deviation value e(t), and dt is the small change in time t.

[0088] The cutting execution module performs cutting operations on the edge of the plastic mold according to the control instructions generated by the motion control module, thereby ensuring the efficiency and accuracy of the cutting operation and extending the service life of the cutting tool;

[0089] The cutting execution module includes a cutting tool for cutting the edge of the plastic mold, a driving device for driving the cutting tool to move, and a cooling device for cooling the cutting tool. The driving motor is mainly composed of a transmission mechanism and a motor. The transmission mechanism uses a screw and a guide rail to drive the cutting tool to move. The motor is used to drive the screw to rotate. The cooling device removes the heat generated by the cutting tool through a coolant pump and a cooling pipe.

[0090] The fixture positioning module is connected to the motion control module to accurately fix and position the plastic module, and cooperates with the visualization module and motion control module to accurately position the plastic mold in the cutting area, providing a reliable foundation for high-quality cutting.

[0091] The fixture positioning module includes a fixture body for fixing the plastic mold, a positioning piece for achieving precise positioning of the plastic mold, and a photoelectric sensor for detecting the positioning status of the plastic mold. The positioning piece is installed on the fixture body, and the positioning piece includes a positioning pin and a positioning block. The photoelectric sensor transmits the positioning status to the motion control module through a signal line, and the plastic mold is clamped and fixed by the fixture body. The positioning piece ensures that the mold is in the correct position. The photoelectric sensor detects the positioning status of the mold in real time and feeds back the information to the motion control module to ensure that the cutting operation is carried out on the basis of stable positioning of the mold.

[0092] The parameter monitoring module collects key parameters of the cutting process in real time, converts and processes the collected parameter data, and transmits it to the data analysis and feedback module in the form of digital signals, providing accurate data support for real-time monitoring and adjustment of the system.

[0093] The parameter monitoring module includes a sensor module and a signal processing unit. The sensor module collects physical parameters during the cutting process, and the signal processing unit performs analog-to-digital conversion on the collected physical parameters and transmits them to the data analysis and feedback module. The sensor module includes a laser power sensor, a speed sensor, a temperature sensor and a displacement sensor. The laser power sensor, speed sensor, temperature sensor and displacement sensor are all connected to the signal processing unit. The laser power sensor is installed near the output end of the laser transmitter for real-time monitoring of the laser output power; the speed sensor is installed next to the cutting head motion guide rail to accurately measure the moving speed of the cutting head; the temperature sensor is deployed on the material surface in the cutting area and inside the cutting head respectively. The former monitors the surface temperature change of the material during the cutting process, and the latter grasps the working temperature of the cutting head in real time so as to detect overheating in time and make adjustments; the displacement sensor is installed on the motion guide rail of the cutting head, or at the mechanical structure linked to the cutting head, to accurately measure the displacement of the cutting head in the X, Y and Z axis directions to ensure the accuracy of the cutting path and the accuracy of edge trimming;

[0094] In the initial stage of system operation, the fixture positioning module accurately fixes and positions the plastic mold, the visualization module obtains the mold edge image information and processes and analyzes it, and then passes it to the motion control module after determining the cutting path. The motion control module generates control instructions based on the cutting path and drives the cutting execution module to cut the mold edge.

[0095] During the cutting process, the parameter monitoring module collects key parameters such as laser power and cutting speed in real time through various sensors, and transmits the data to the data analysis and feedback module. The data analysis and feedback module analyzes and processes the data and evaluates the cutting quality in real time. Once an abnormal parameter is found, such as the laser power fluctuation exceeds the set range, the data analysis and feedback module immediately generates a feedback instruction and sends it to the motion control module. The motion control module adjusts the cutting parameters according to the instruction, such as reducing or increasing the laser power, and feeds back the adjustment information to the visualization module. The visualization module updates the display content in real time to let the operator understand the changes in the cutting process.

[0096] In addition, the visualization module continuously monitors the cutting process and feeds real-time status information of the mold edge back to the motion control module and the data analysis and feedback module. The motion control module further optimizes the cutting path and speed based on this information to ensure that the cutting tool follows the optimal trajectory. The data analysis and feedback module combines real-time images and parameter data to more accurately assess cutting quality, identify potential problems in a timely manner, and take appropriate measures.

[0097] In summary, through the coordinated cooperation of the visualization module, motion control module, cutting execution module, fixture positioning module, parameter monitoring module and data analysis and feedback module, key cutting parameters can be monitored in real time, problems arising during the cutting process can be discovered and solved in a timely manner, thereby effectively improving the cutting quality of plastic mold edge trimming.

[0098] Finally, it should be noted that the above is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or make equivalent substitutions for some of the technical features therein. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. An efficient cutting system for trimming the edges of plastic molds, characterized by: Including visualization module, motion control module, cutting execution module, parameter monitoring module and data analysis and feedback module; The data analysis and feedback module is connected to the visualization module, motion control module, and parameter monitoring module respectively, and is used to receive and deeply analyze data in real time, evaluate cutting quality, and output feedback instructions to the motion control module and visualization module; The visualization module obtains and analyzes the edge image information of the plastic mold to determine the cutting path; The motion control module generates control instructions according to the cutting path determined by the visualization module; The cutting execution module performs a cutting operation on the edge of the plastic mold according to the control instruction generated by the motion control module; The parameter monitoring module collects key parameters in the cutting process in real time, converts and processes the collected parameter data, and transmits them to the data analysis and feedback module in the form of digital signals.

2. The high-efficiency cutting system for trimming the edge of a plastic mold according to claim 1, characterized in that: The data analysis and feedback module analyzes and processes the data and evaluates the cutting quality in real time. Once an abnormal parameter is found, the data analysis and feedback module immediately generates a feedback instruction and sends it to the motion control module. The motion control module adjusts the cutting parameters according to the instruction and feeds back the adjustment information to the visualization module. The visualization module updates the display content in real time.

3. The high-efficiency cutting system for trimming the edge of a plastic mold according to claim 2, characterized in that: The process of cutting quality evaluation in the data analysis and feedback module is as follows: S1. Set the window size and use the sliding average algorithm to smooth the received data; S2. Use the collected data as feature vectors and perform normalization on the data; S3. Use radial basis function to build support vector machine model. The formula of support vector machine model is: K(y i ,y)=exp(-γ‖y i -y‖ 2 ), where γ is a hyperparameter, ‖y i -y|| 2 is the sample y i The square of the Euclidean distance to sample y, K(y i ,y) is the output value of radial basis function; S4. Collect data containing qualified product labels to train the support vector machine model: S5. Input the normalized real-time data into the trained support vector machine model for prediction, and determine the cutting quality based on the prediction results.

4. The high-efficiency cutting system for trimming the edge of a plastic mold according to claim 3, characterized in that: The visualization module includes an image acquisition unit, an image preprocessing unit and a display unit connected in sequence. The image acquisition unit captures image information of the edge of the plastic mold through a camera, and the camera uses a high-definition camera; the image processing unit analyzes and processes the collected image and determines the cutting path; the display unit is used to display the processed image and the determined cutting path.

5. The high-efficiency cutting system for trimming the edge of a plastic mold according to claim 4, characterized in that: The image processing unit performs image analysis and processing as follows: A1. Convert the collected image to grayscale using a weighted average algorithm, and then filter the converted image using a median filter algorithm to remove interference noise. A2. Use the Canny edge detection algorithm to detect edges on the filtered image, retaining the true edges and removing the false edges; A3. Extract key features of the edge of the plastic mold based on the image after edge detection processing, and determine the cutting path based on the extracted features.

6. The high-efficiency cutting system for trimming the edge of a plastic mold according to claim 5, characterized in that: The key feature extraction process is as follows: A31. Calculate the gradient of each pixel in the image in the x-direction and the y-direction, and calculate the autocorrelation matrix based on the calculated gradient values. The autocorrelation matrix calculation formula is: Among them, M(x,y) is the autocorrelation matrix of pixel point (x,y), I x is the gradient of the pixel (x, y) in the x direction, I y is the gradient of the pixel point (x, y) in the y direction; A32. Calculate the corner point response function value based on the autocorrelation matrix. The corner point response function value calculation formula is: R=det(M)-k[trace(M)] 2 , where R is the corner point response function value, det(M) is the determinant of the matrix M, k is an empirical constant ranging from 0.04 to 0.06, and trace(M) is the trace of the matrix M. The larger the R value, the more likely the point is a corner point. A33. Set a corner threshold and determine the pixel points whose corner response function values ​​are greater than the corner threshold as feature points, thereby extracting the key features of the edge of the plastic mold.

7. The high-efficiency cutting system for trimming the edge of a plastic mold according to claim 6, characterized in that: The motion control module uses a PID control algorithm to generate control instructions. The PID control algorithm calculates the proportional term, integral term and differential term according to the deviation value between the motor set speed and the actual speed in the cutting execution module, and then adds the proportional term, integral term and differential term to obtain the control amount of motor speed regulation.

8. The high-efficiency cutting system for trimming the edge of a plastic mold according to claim 7, characterized in that: The process of determining the cutting path is as follows: B1. Divide the processed mold edge image into multiple sub-regions using a uniform grid; B2. Select one starting point and one target point in each sub-area as the cutting start point and cutting end point; B3. Calculate the Euclidean distance from the cutting start point to the cutting end point based on the coordinates of the cutting start point and the cutting end point; B4. Plan multiple feasible movement paths from the cutting start point to the cutting end point. Count the number of segments where two adjacent nodes are horizontal or vertical, and the number of segments where two adjacent nodes are diagonal, on each path. Calculate the movement cost from the cutting start point to the cutting end point. B5. Calculate the total cost from the starting point to the end point of the cutting. The total cost calculation formula is: f(n)=g(n)+h(n), where f(n) is the total cost from the starting point to the end point, g(n) is the moving cost from the starting point to the end point, and h(n) is the Euclidean distance from the starting point to the end point. B6. Select the moving path with the minimum total cost in each sub-area for expansion and splicing. The spliced ​​path is the cutting path.

9. The high-efficiency cutting system for trimming the edge of a plastic mold according to claim 8, characterized in that: The parameter monitoring module includes a sensor module and a signal processing unit. The sensor module collects physical parameters during the cutting process, and the signal processing unit converts the collected physical parameters into analog-to-digital values ​​and transmits them to the data analysis and feedback module. The sensor module includes a laser power sensor, a speed sensor, a temperature sensor and a displacement sensor.

10. An efficient cutting system for trimming the edge of a plastic mold according to any one of claims 1 to 9, characterized in that: It also includes a fixture positioning module, which is connected to the motion control module and is used to accurately fix and position the plastic module, and cooperate with the visualization module and the motion control module to accurately position the plastic mold in the cutting area.

Images