Automatic material cutting method and system for injection molding machine based on artificial intelligence

Abstract

The invention discloses an automatic material cutting method and system of an injection molding machine based on artificial intelligence, and relates to the technical field of material cutting management of injection molding machines, and the method comprises the following steps: carrying out data matching processing on material characteristics of a to-be-cut material, and determining the material cutting speed of the injection molding machine; and obtaining a material image of the to-be-cut material, performing feature analysis processing on the material image of the to-be-cut material, and determining the position coordinates of the defect of the material. According to the method, the material cutting speed of the injection molding machine is determined by carrying out data matching on the material characteristics of the to-be-cut material, because if the cutting speed is too high or too low, the temperature of the cutting position is too high, the cutting position of the material is deformed, and if the deformed material is used for manufacturing a product, the yield is reduced; and then feature analysis is carried out through the material image of the to-be-cut material, the position of the material defect is determined, when the material is cut, the position of the material defect is avoided, the use of the material with the defect for manufacturing a product is avoided, and the yield is improved.

Description

TECHNICAL FIELD

[0001] The application relates to the technical field of cutting management of injection molding machines, in particular to an automatic cutting method and system of an injection molding machine based on artificial intelligence. BACKGROUND

[0002] The injection molding machine is also called an injection molding machine or an injection molding machine, and is main molding equipment for making various plastic products by using thermoplastic or thermosetting plastic through a plastic molding mold.

[0003] The raw material used by the injection molding machine is integrated, and needs to be cut for use in use, but the cut raw material may have defects, and if the raw material with defects is used for product manufacturing, the yield of the product will be reduced. SUMMARY

[0004] To solve the above technical problems, an automatic cutting method and system of an injection molding machine based on artificial intelligence are provided, which solves the problem that if the raw material with defects is used for product manufacturing, the yield of the product will be reduced.

[0005] To achieve the above purpose, the technical scheme adopted by the application is as follows: An automatic cutting method of an injection molding machine based on artificial intelligence, comprising: obtaining material characteristics of the material to be cut, performing data matching processing on the material characteristics of the material to be cut, and determining the cutting speed of the material by the injection molding machine; obtaining a material image of the material to be cut, performing feature analysis processing on the material image of the material to be cut, and determining the defect position coordinates of the material; based on the cutting speed of the material by the injection molding machine and the defect position coordinates of the material, performing parameter adjustment processing on the injection molding machine, and determining the material cutting path of the injection molding machine.

[0006] Preferably, the step of obtaining the material characteristics of the material to be cut, performing data matching processing on the material characteristics of the material to be cut, and determining the cutting speed of the material comprises the following steps: performing data retrieval processing on the task manager of the injection molding machine, and obtaining all the cutting tasks of the injection molding machine; performing parameter reading processing on all the cutting tasks of the injection molding machine, and obtaining the number information of each cutting task of the injection molding machine; performing data reading processing on the database system, and obtaining the task sorting mode of the injection molding machine; based on the task sorting mode of the injection molding machine, performing screening processing on the number information of each cutting task of the injection molding machine, and determining the earliest cutting task of the injection molding machine; performing task content analysis processing on the earliest cutting task of the injection molding machine, and determining the cutting speed of the material by the injection molding machine.

[0007] Preferably, the task content analysis processing of the earliest to-be-cut task of the injection molding machine determines the cutting speed of the injection molding machine on the material, and specifically includes the following steps: The content reading processing is performed on the earliest to-be-cut task of the injection molding machine to obtain the material properties of the to-be-cut material. Based on the material properties of the to-be-cut material, data matching processing is performed on the database system to determine the completed cutting task data of the same material. The data reading processing is performed on the completed cutting task data of the same material to obtain product parameters of different cutting tasks; the product parameters of different cutting tasks include the number of good products of different cutting tasks and the total number of cutting products of different cutting tasks. The product parameters of different cutting tasks are calculated and analyzed to determine the cutting speed of the injection molding machine on the material.

[0008] Preferably, the calculation and analysis processing of the product parameters of different cutting tasks to determine the cutting speed of the injection molding machine on the material specifically includes the following steps: The number of good products of different cutting tasks and the total number of cutting products of different cutting tasks are calculated and analyzed to determine the yield rate of different cutting tasks. Based on the maximum function, the yield rates of different cutting tasks are sorted to determine the maximum value of the yield rate. The data reading processing is performed on the completed cutting task data corresponding to the maximum value of the yield rate to obtain the cutting speed corresponding to the maximum value of the yield rate. The cutting speed corresponding to the maximum value of the yield rate is set as the cutting speed of the injection molding machine on the material.

[0009] Preferably, the material image of the to-be-cut material is obtained, and the feature analysis processing is performed on the material image of the to-be-cut material to determine the defect position coordinates of the material, specifically including the following steps: The image acquisition processing is performed on the to-be-cut material by the image shooting device to obtain the material image of the to-be-cut material. The lower left corner of the material image of the to-be-cut material is taken as the coordinate origin, the horizontal direction of the material image of the to-be-cut material is taken as the X-axis, and the vertical direction of the material image of the to-be-cut material is taken as the Y-axis to construct a rectangular coordinate system. Based on the edge detection algorithm, the position determination processing is performed on the material image of the to-be-cut material to determine the defect position coordinates of the material.

[0010] Preferably, the position determination processing is performed on the material image of the to-be-cut material based on the edge detection algorithm to determine the defect position coordinates of the material, specifically including the following steps: Based on the Sobel operator, the pixel values ​​in the pixel coordinates of the material image to be cut are convolved to determine the horizontal gradient values ​​and vertical gradient values ​​of multiple sets of pixels. The horizontal gradient values ​​and vertical gradient values ​​of multiple sets of pixels are calculated and processed to determine the gradient values ​​of multiple pixels. Based on the inverse trigonometric function, the horizontal gradient value and the vertical gradient value of multiple sets of pixels are calculated in the inverse trigonometric function to determine the gradient direction of multiple pixels. Based on the maximum value function, the gradient values ​​of multiple pixels are filtered to determine the target pixel, and the gradient value of the target pixel is the maximum value of the gradient values ​​of multiple pixels. Based on the target pixel, position matching processing is performed on the pixel coordinates and Cartesian coordinate system of the material image to be cut to determine the X-axis and Y-axis coordinates of the target pixel; Set the X-axis and Y-axis coordinates of the target pixel to the coordinates of the location of the defect in the material.

[0011] Preferably, the step of adjusting the parameters of the injection molding machine based on the cutting speed of the material and the coordinates of the location of the defects in the material to determine the material cutting path of the injection molding machine specifically includes the following steps: The earliest cutting task of the injection molding machine is read and processed to determine the cutting length of the material; The material image to be cut is read and processed to determine the image scaling ratio; Based on the image scaling ratio, the cutting length of the material is reduced to determine the reduced cutting length of the material; Based on the reduced cutting length of the material and the coordinates of the location of the defects in the material, the material image of the material to be cut is processed to determine the cutting position coordinates of the injection molding machine; The cutting speed and cutting position coordinates of the material are input into the injection molding machine. The injection molding machine then controls the cutting speed to cut the material based on the cutting position coordinates.

[0012] Preferably, the step of performing positioning processing on the material image of the material to be cut based on the reduced cutting length of the material and the coordinates of the location of the defects in the material to determine the cutting position coordinates of the injection molding machine specifically includes the following steps: Based on the reduced cutting length of the material, the material image of the material to be cut is marked to determine the mark coordinates of the image; The coordinates of the marked points in the image are compared with the coordinates of the location of the defects in the material. If the coordinates of the marker in the image coincide with the coordinates of the material defect, the maximum value of the material defect coordinates will be used as the cutting position coordinates of the injection molding machine. If the coordinates of the image marker do not coincide with the coordinates of the material defect location, set the coordinates of the image marker to the cutting position coordinates of the injection molding machine.

[0013] Furthermore, an AI-based automatic material cutting system for injection molding machines is proposed to implement the aforementioned AI-based automatic material cutting method for injection molding machines, including: The intelligent analysis terminal is used to control each module to perform data matching, data calculation, and parameter adjustment on the material characteristics and material image of the material to be cut, and to determine the material cutting path of the injection molding machine. The intelligent analysis terminal is also used to control the data transmission and information interaction between the various modules. The database system is used to store the task sorting method of the injection molding machine and the data of completed cutting tasks of the same material; The task filtering module filters the number information of each task to be cut by the injection molding machine according to the task sorting method of the injection molding machine, and determines the earliest task to be cut by the injection molding machine. The cutting speed determination module is used to calculate and process the number of good products cut for different cutting tasks and the total number of products cut for different cutting tasks, and to determine the cutting speed of the injection molding machine on the material. An image capturing device is used to acquire and process images of the material to be cut, thereby obtaining an image of the material to be cut. A coordinate system construction module, which constructs a rectangular coordinate system based on the material image to be cut; The defect determination module performs position determination processing on the material image of the material to be cut using an edge detection algorithm to determine the coordinates of the location of the defect in the material. The cutting path determination module performs path planning processing on the location coordinates of the material defects based on the cutting position coordinates of the injection molding machine, thereby determining the material cutting path of the injection molding machine.

[0014] Compared with existing technologies, the present invention provides an automatic material cutting method and system for injection molding machines based on artificial intelligence, which has the following beneficial effects: This invention first determines the cutting speed of the injection molding machine by matching data on the material properties of the material to be cut. This is because if the cutting speed is too fast or too slow, the temperature at the cutting position will be too high, causing deformation of the material at the cutting position. If deformed material is used to make products, the yield rate will be reduced. Secondly, feature analysis is performed on the material image of the material to be cut to determine the location of material defects. When cutting the material, the location of material defects is avoided, thus avoiding the use of defective material to make products and improving the yield rate. Attached Figure Description

[0015] Figure 1 This is a flowchart illustrating steps S100-S300 in an artificial intelligence-based automatic material cutting method for injection molding machines proposed in this invention. Figure 2 This is a structural block diagram of an automatic material cutting system for injection molding machines based on artificial intelligence, as proposed in this invention. Detailed Implementation

[0016] The following description is intended to disclose the invention and enable those skilled in the art to implement it. The preferred embodiments described below are merely examples, and other obvious variations will occur to those skilled in the art.

[0017] Reference Figure 1 As shown, an automatic material cutting method for injection molding machines based on artificial intelligence includes: S100: Obtain the material characteristics of the material to be cut, perform data matching processing on the material characteristics of the material to be cut, and determine the cutting speed of the injection molding machine on the material; S200: Obtain the image of the material to be cut, perform feature analysis on the image of the material to be cut, and determine the coordinates of the location of the defect in the material. S300: Based on the cutting speed of the injection molding machine and the coordinates of the location of the material defects, the parameters of the injection molding machine are adjusted to determine the material cutting path of the injection molding machine. Those skilled in the art will understand that when an injection molding machine uses materials to manufacture products, it needs to cut parts of the material. However, during the cutting process, the cutting speed needs to be controlled. If the cutting speed is too fast or too slow, the temperature of the cutting area will be too high. If the temperature of the cutting area is too high, the material will deform. If deformed material is used to make products, the product yield will be reduced. Secondly, the raw materials used by the injection molding machine may have certain defects. If defective materials are used to make products, the product yield will also be reduced. Therefore, it is necessary not only to control the cutting speed of the injection molding machine, but also to determine the location of defects in the material in order to cut the material and carry out subsequent production.

[0018] Example 1 Step S100: Obtain the material properties of the material to be cut, perform data matching processing on the material characteristics of the material to be cut, and determine the cutting speed of the material. This specifically includes the following steps: S101. Perform data retrieval processing on the injection molding machine's task manager to obtain all the cutting tasks of the injection molding machine; S102. Perform parameter reading and processing on all tasks to be cut on the injection molding machine to obtain the number information of each task to be cut on the injection molding machine. S103. Perform data reading and processing on the database system to obtain the task sorting method of the injection molding machine; S104. Based on the task sorting method of the injection molding machine, the number information of each task to be cut on the injection molding machine is filtered and processed to determine the earliest task to be cut on the injection molding machine. S105. Analyze and process the earliest cutting task of the injection molding machine to determine the cutting speed of the material by the injection molding machine. It is understandable that an injection molding machine executes more than one task at a time; it stores multiple tasks, but the execution order of each task is different. Therefore, the earliest task to be cut needs to be determined by the task sorting method of the injection molding machine. However, the products produced by each task may be different, and the materials used will also be different. Different materials have different properties, so different cutting speeds need to be set. If the same cutting speed is used to cut different materials, it may cause some materials to deform. Step S105, which involves analyzing the earliest cutting task of the injection molding machine to determine the cutting speed of the material, specifically includes the following steps: S1051. Read the contents of the earliest cutting task of the injection molding machine to obtain the material characteristics of the material to be cut; S1052. Based on the material characteristics of the material to be cut, perform data matching processing on the database system to determine the data of completed cutting tasks for the same material; S1053. Read and process the data of completed cutting tasks of the same material to obtain product parameters of different cutting tasks; the product parameters of different cutting tasks include the number of good cut products of different cutting tasks and the total number of cut products of different cutting tasks. S1054. Calculate and analyze the product parameters for different cutting tasks to determine the cutting speed of the injection molding machine for the material. Understandably, to accurately determine the cutting speed of an injection molding machine, it is necessary to use the task data that the injection molding machine has already completed. This task data contains the cutting speed of different materials. Therefore, the cutting speed of the injection molding machine for materials can be determined by filtering the task data that the injection molding machine has already completed.

[0019] Step S1054, which involves calculating and analyzing the product parameters for different cutting tasks to determine the cutting speed of the injection molding machine for the material, specifically includes the following steps: S10541. Calculate and process the number of good products cut for different cutting tasks and the total number of cut products for different cutting tasks to determine the yield rate for different cutting tasks. S10542. Based on the maximum value function, sort the yield rates of different cutting tasks and determine the maximum yield rate. S10543. Read and process the data of the completed cutting tasks corresponding to the maximum yield rate to obtain the cutting speed corresponding to the maximum yield rate. S10544. Set the cutting speed corresponding to the maximum yield rate as the cutting speed of the injection molding machine on the material; Understandably, to determine the cutting speed of an injection molding machine on materials, it is necessary to filter out the completed cutting data of the same material, then sort the yield rates of these tasks, and the cutting speed corresponding to the highest yield rate is the cutting speed of the injection molding machine on the material.

[0020] Example 2 Step S200: Obtain the material image to be cut, perform feature analysis processing on the material image to determine the coordinates of the material defects. This specifically includes the following steps: S201. Obtain an image of the material to be cut by using an image capturing device to acquire and process the image of the material to be cut. S202. Construct a rectangular coordinate system with the lower left corner of the material image to be cut as the origin, the horizontal direction of the material image to be cut as the X-axis, and the vertical direction of the material image to be cut as the Y-axis. S203. Based on the edge detection algorithm, perform position determination processing on the material image of the material to be cut to determine the coordinates of the location of the defect in the material. It is understandable that the raw materials used in injection molding machines cannot be guaranteed to be 100% free of defects. Therefore, before using raw materials, it is necessary to determine whether the raw materials are defective in order to avoid using defective materials to make products and reduce the yield rate. Specifically, step S203, which involves determining the location coordinates of defects in the material image based on an edge detection algorithm, includes the following steps: S2031. Based on the Sobel operator, perform convolution calculation on the pixel values ​​in the pixel coordinates of the material image to be cut to determine the horizontal gradient values ​​and vertical gradient values ​​of multiple sets of pixels. S2032. Calculate and process the horizontal gradient values ​​and vertical gradient values ​​of multiple sets of pixels to determine the gradient values ​​of multiple pixels. S2033. Based on the inverse trigonometric function, perform inverse trigonometric calculation on the horizontal gradient values ​​and vertical gradient values ​​of multiple sets of pixels to determine the gradient direction of multiple pixels. S2034. Based on the maximum value function, the gradient values ​​of multiple pixels are filtered to determine the target pixel, wherein the gradient value of the target pixel is the maximum value of the gradient values ​​of multiple pixels. S2035. Based on the target pixel, perform position matching processing on the pixel coordinates and Cartesian coordinate system of the material image to be cut, and determine the X-axis coordinates and Y-axis coordinates of the target pixel. S2036. Set the X-axis and Y-axis coordinates of the target pixel to the coordinates of the location of the material defect. In this embodiment, the pixel values ​​of material defects are different from those of normal materials. Therefore, the gradient values ​​of pixels in the material image of the material to be cut are calculated using an edge detection algorithm. The calculated gradient values ​​are then compared, and the pixel with the largest gradient value is the location of the material defect we need. Because the pixel values ​​of material defects are different from those of normal materials, the gradient values ​​between the pixel values ​​in the image will differ greatly. The gradient direction can determine which part is the material defect and which part is the normal material. Since the defect appears on the normal material, the gradient direction can be used to determine the material defect. Once the material defect is determined, we only need to determine the coordinate information of the material defect in the Cartesian coordinate system to determine the coordinates of the location of the material defect.

[0021] Example 3 Step S300: Based on the cutting speed of the injection molding machine and the coordinates of the material defect location, adjust the parameters of the injection molding machine to determine the material cutting path. This specifically includes the following steps: S301: Read and process the data of the earliest cutting task of the injection molding machine to determine the cutting length of the material; S302. Perform data reading and processing on the material image to be cut, and determine the image scaling ratio; S303. Based on the image scaling ratio, reduce the cutting length of the material to determine the reduced cutting length of the material; S304. Based on the reduced cutting length of the material and the coordinates of the location of the defects in the material, perform positioning processing on the material image of the material to be cut to determine the cutting position coordinates of the injection molding machine; S305. Input the material cutting speed and the cutting position coordinates of the injection molding machine into the injection molding machine. The injection molding machine controls the material cutting speed according to the cutting position coordinates of the injection molding machine to cut the material. It is understandable that the length of the raw material used may be different each time a product is made. Therefore, it is necessary to read and process the data of the earliest cutting task of the injection molding machine to determine the cutting length of the material. For the convenience of calculation, the length of the material image to be cut is analyzed. That is, the cutting length of the material image to be cut is used to calculate and analyze the cutting position coordinates of the injection molding machine.

[0022] Specifically, step S304, which involves performing positioning processing on the material image of the material to be cut based on the reduced cutting length of the material and the coordinates of the location of the defects in the material, and determining the cutting position coordinates of the injection molding machine, includes the following steps: S3041. Based on the reduced cutting length of the material, mark the material image of the material to be cut and determine the mark coordinates of the image; S3042. Compare the coordinates of the marked points in the image with the coordinates of the location of the defects in the material. S3043. If the coordinates of the marker in the image coincide with the coordinates of the material defect, the maximum value of the coordinates of the material defect shall be used as the cutting position coordinates of the injection molding machine. It is understandable that if the defect in the material is located at the cutting position, then the cut material will be defective. To avoid using defective materials to make products, the defective material must be removed. Cutting at the maximum value of the coordinates of the defect location can completely remove the defect. S3044. If the marker coordinates of the image do not coincide with the location coordinates of the material defect, set the marker coordinates of the image to the cutting position coordinates of the injection molding machine. Understandably, using defective materials to make products will result in scrap. Therefore, it is necessary to determine the location of the defect in the material. When using the material to make products, it is necessary to avoid the location of the defect, or to remove the raw materials containing the defect and use normal materials to make products in order to improve the yield rate.

[0023] Reference Figure 2 As shown, an artificial intelligence-based automatic material cutting system for injection molding machines is used to implement the aforementioned artificial intelligence-based automatic material cutting method for injection molding machines, including: The intelligent analysis terminal is used to control each module to perform data matching, data calculation, and parameter adjustment on the material characteristics and material image of the material to be cut, and to determine the material cutting path of the injection molding machine. The intelligent analysis terminal is also used to control the data transmission and information interaction between the various modules. The database system is used to store the task sorting method of the injection molding machine and the data of completed cutting tasks of the same material; The task filtering module filters the number information of each task to be cut by the injection molding machine according to the task sorting method of the injection molding machine, and determines the earliest task to be cut by the injection molding machine. The cutting speed determination module is used to calculate and process the number of good products cut for different cutting tasks and the total number of products cut for different cutting tasks, and to determine the cutting speed of the injection molding machine on the material. An image capturing device is used to acquire and process images of the material to be cut, thereby obtaining an image of the material to be cut. A coordinate system construction module, which constructs a rectangular coordinate system based on the material image to be cut; The defect determination module performs position determination processing on the material image of the material to be cut using an edge detection algorithm to determine the coordinates of the location of the defect in the material. The cutting path determination module performs path planning processing on the location coordinates of the material defects based on the cutting position coordinates of the injection molding machine, thereby determining the material cutting path of the injection molding machine.

[0024] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely principles of the invention. Various changes and modifications can be made to the invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the claimed invention. The scope of protection claimed by the appended claims and their equivalents is defined.

Claims

1. An automatic material cutting method for injection molding machines based on artificial intelligence, characterized in that, include: Obtain the material properties of the material to be cut, perform data matching processing on the material characteristics of the material to be cut, and determine the cutting speed of the injection molding machine on the material; Acquire an image of the material to be cut, perform feature analysis on the image, and determine the coordinates of the location of the defects in the material. Based on the cutting speed of the injection molding machine and the coordinates of the location of the material defects, the parameters of the injection molding machine are adjusted to determine the material cutting path.

2. The automatic material cutting method for injection molding machines based on artificial intelligence according to claim 1, characterized in that, The process of obtaining the material properties of the material to be cut, performing data matching processing on the material characteristics of the material to be cut, and determining the cutting speed of the material specifically includes the following steps: Perform data retrieval and processing on the injection molding machine's task manager to obtain all the cutting tasks awaiting completion from the injection molding machine; The parameters of all tasks to be cut on the injection molding machine are read and processed to obtain the number information of each task to be cut on the injection molding machine. Perform data reading and processing on the database system to obtain the task sorting method of the injection molding machine; Based on the task sorting method of the injection molding machine, the number information of each task to be cut is filtered and processed to determine the earliest task to be cut. The earliest cutting task of the injection molding machine is analyzed and processed to determine the cutting speed of the material by the injection molding machine.

3. The automatic material cutting method for injection molding machines based on artificial intelligence according to claim 2, characterized in that, The process of analyzing the earliest cutting task of the injection molding machine to determine the cutting speed of the material includes the following steps: The earliest cutting task of the injection molding machine is read and processed to obtain the material characteristics of the material to be cut; Based on the material characteristics of the material to be cut, the database system is used for data matching to determine the data of completed cutting tasks for the same material; Data reading and processing are performed on the completed cutting task data of the same material to obtain product parameters for different cutting tasks; the product parameters for different cutting tasks include the number of good cut products for different cutting tasks and the total number of cut products for different cutting tasks. The product parameters for different cutting tasks are calculated and analyzed to determine the cutting speed of the injection molding machine for the material.

4. The automatic material cutting method for injection molding machines based on artificial intelligence according to claim 3, characterized in that, The calculation and analysis of product parameters for different cutting tasks to determine the cutting speed of the injection molding machine for the material specifically includes the following steps: The yield rate of different cutting tasks is determined by calculating the number of good products and the total number of products cut for different cutting tasks. Based on the maximum value function, the yield rates of different cutting tasks are sorted to determine the maximum yield rate; The data of completed cutting tasks corresponding to the maximum yield rate is read and processed to obtain the cutting speed corresponding to the maximum yield rate. Set the cutting speed corresponding to the maximum yield rate as the cutting speed of the injection molding machine on the material.

5. The automatic material cutting method for injection molding machines based on artificial intelligence according to claim 1, characterized in that, The process of acquiring a material image to be cut, performing feature analysis on the material image, and determining the coordinates of the material defects specifically includes the following steps: The material to be cut is captured and processed using an image acquisition device to obtain an image of the material to be cut. A rectangular coordinate system is constructed with the lower left corner of the material image to be cut as the origin, the horizontal direction of the material image to be cut as the X-axis, and the vertical direction of the material image to be cut as the Y-axis. Based on the edge detection algorithm, the material image of the material to be cut is processed to determine the location coordinates of the defects in the material.

6. The automatic material cutting method for injection molding machines based on artificial intelligence according to claim 5, characterized in that, The process of determining the location coordinates of defects in the material image based on the edge detection algorithm includes the following steps: Based on the Sobel operator, the pixel values ​​in the pixel coordinates of the material image to be cut are convolved to determine the horizontal gradient values ​​and vertical gradient values ​​of multiple sets of pixels. The horizontal gradient values ​​and vertical gradient values ​​of multiple sets of pixels are calculated and processed to determine the gradient values ​​of multiple pixels. Based on the inverse trigonometric function, the horizontal gradient value and the vertical gradient value of multiple sets of pixels are calculated in the inverse trigonometric function to determine the gradient direction of multiple pixels. Based on the maximum value function, the gradient values ​​of multiple pixels are filtered to determine the target pixel, and the gradient value of the target pixel is the maximum value of the gradient values ​​of multiple pixels. Based on the target pixel, position matching processing is performed on the pixel coordinates and Cartesian coordinate system of the material image to be cut to determine the X-axis and Y-axis coordinates of the target pixel; Set the X-axis and Y-axis coordinates of the target pixel to the coordinates of the location of the defect in the material.

7. The automatic material cutting method for injection molding machines based on artificial intelligence according to claim 1, characterized in that, The process of adjusting the parameters of the injection molding machine based on its cutting speed and the coordinates of material defects to determine the material cutting path includes the following steps: The earliest cutting task of the injection molding machine is read and processed to determine the cutting length of the material; The material image to be cut is read and processed to determine the image scaling ratio; Based on the image scaling ratio, the cutting length of the material is reduced to determine the reduced cutting length of the material; Based on the reduced cutting length of the material and the coordinates of the location of the defects in the material, the material image of the material to be cut is processed to determine the cutting position coordinates of the injection molding machine; The cutting speed and cutting position coordinates of the material are input into the injection molding machine. The injection molding machine then controls the cutting speed to cut the material based on the cutting position coordinates.

8. The automatic material cutting method for injection molding machines based on artificial intelligence according to claim 7, characterized in that, The process of determining the cutting position coordinates of the injection molding machine by locating the material image based on the reduced cutting length and the location coordinates of material defects includes the following steps: Based on the reduced cutting length of the material, the material image of the material to be cut is marked to determine the mark coordinates of the image; The coordinates of the marked points in the image are compared with the coordinates of the location of the defects in the material. If the coordinates of the marker in the image coincide with the coordinates of the material defect, the maximum value of the material defect coordinates will be used as the cutting position coordinates of the injection molding machine. If the coordinates of the image marker do not coincide with the coordinates of the material defect location, set the coordinates of the image marker to the cutting position coordinates of the injection molding machine.

9. An artificial intelligence-based automatic material cutting system for injection molding machines, used to implement the artificial intelligence-based automatic material cutting method for injection molding machines as described in any one of claims 1-8, characterized in that, include: The intelligent analysis terminal is used to control each module to perform data matching, data calculation, and parameter adjustment on the material characteristics and material image of the material to be cut, and to determine the material cutting path of the injection molding machine. The intelligent analysis terminal is also used to control the data transmission and information interaction between the various modules. The database system is used to store the task sorting method of the injection molding machine and the data of completed cutting tasks of the same material; The task filtering module filters the number information of each task to be cut by the injection molding machine according to the task sorting method of the injection molding machine, and determines the earliest task to be cut by the injection molding machine. The cutting speed determination module is used to calculate and process the number of good products cut for different cutting tasks and the total number of products cut for different cutting tasks, and to determine the cutting speed of the injection molding machine on the material. An image capturing device is used to acquire and process images of the material to be cut, thereby obtaining an image of the material to be cut. A coordinate system construction module, which constructs a rectangular coordinate system based on the material image to be cut; The defect determination module performs position determination processing on the material image of the material to be cut using an edge detection algorithm to determine the coordinates of the location of the defect in the material. The cutting path determination module performs path planning processing on the location coordinates of the material defects based on the cutting position coordinates of the injection molding machine, thereby determining the material cutting path of the injection molding machine.

Images