Multifunctional circular knife machine control method and device based on image recognition
Through the multi-functional round knife machine control method based on image recognition, image recognition technology is used to analyze the finished product profile and burrs, which solves the problem of difficult to judge the finished product quality during the operation of the round knife machine, and realizes timely abnormal monitoring and finished product operation of the round knife machine The accuracy of quality analysis reduces the generation of unqualified finished products.
Patent Information
- Application Number
- CN202411323725.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-23
- Publication Date
- 2024-11-22
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
During the operation of the circular tool machine, due to high speed and complex components, the quality of the finished product processing is difficult to judge, and it is difficult for staff to detect abnormal operation in a timely manner, which leads to the production of a large number of unqualified finished products.
The multi-functional round knife machine control method based on image recognition is adopted to obtain the finished product image through preset time intervals, determine the finished product profile and position relationship, identify the burr, and calculate the quality influence points based on this information to determine whether there are abnormalities in the operation of the round knife machine.
Timely abnormal monitoring of the operation of the circular tool machine is realized, the convenience and accuracy of finished product quality analysis is improved, and the generation of unqualified finished products is reduced.
Smart Images

Figure CN118990656A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of die-cutting machines, and in particular to a control method and device for a multifunctional circular knife machine based on image recognition. Background Art
[0002] The circular knife machine is a circular knife die-cutting machine. It is a mechanical device used to die-cut various materials. It is widely used in many fields such as pharmaceuticals, such as batch processing and shearing of plasters. This equipment uses a rolling knife (cylindrical die seat) to continuously rotate and die-cut, extrude and split materials to form finished products, and has high production efficiency.
[0003] However, due to the high transmission speed and processing speed of each component and high processing efficiency of the finished product during the operation of the circular knife machine, it is not convenient to judge the processing quality of the finished product during the operation of the circular knife machine and to monitor and judge whether there is any abnormality in the operation of the circular knife machine based on the processing quality. It is not easy for the staff to find the abnormality in the operation of the circular knife machine in time. If there is an abnormality and it runs in an abnormal state, it is not easy for the staff to find the abnormality in time, which leads to the production of a large number of unqualified finished products. Summary of the invention
[0004] In order to facilitate abnormal monitoring of a circular knife machine in operation and timely discover abnormal operation of the circular knife machine, the present application provides a multifunctional circular knife machine control method and equipment based on image recognition.
[0005] In the first aspect, the present application provides a multifunctional circular knife machine control method based on image recognition, which adopts the following technical solution: The multifunctional circular knife machine control method based on image recognition includes: Acquire first images of multiple groups of finished products produced by the circular knife machine at preset time intervals, each group of finished products including at least two finished products; Controlling the light source to emit light of a preset color to each finished product, and obtaining a second image of each group of finished products illuminated by the light of the preset color; Determine the contour of each finished product in each group of finished products and the positional relationship between each finished product based on the first image, and determine a first quality impact score based on the contour and the positional relationship; Identify burrs on each finished product in each group of finished products based on the second image, and determine a second quality impact score of the burrs on the finished product based on the burrs; Based on the first quality impact score and the second quality impact score, it is determined whether there is an abnormality in the current operation of the circular knife machine.
[0006] By adopting the above technical scheme, the first images of multiple groups of finished products are obtained at preset time intervals, so that it is convenient to analyze the quality of the finished products according to the first image, and then judge whether there is any abnormality in the operation of the circular knife machine according to the quality of the finished products, control the light source to emit light of a preset color and obtain the second image of the finished product at this time, and the contour of the finished product and the positional relationship between the finished products can be determined according to the first image. The quality of the contour and the positional relationship both represent whether there is any abnormality in the circular knife machine when processing the finished product. For example, multiple finished products should be in a side-by-side state and the front and back positions should be consistent. If they are inconsistent, it means that the extrusion force is uneven, adhesion occurs during the extrusion process, etc. Therefore, the first quality influence score can be determined according to the contour and the positional relationship, and burrs can be identified through the second image. The occurrence of burrs affects the quality of the finished product. Therefore, the second quality influence score is determined according to the specific situation of the burrs, and then the first quality influence score and the second quality influence score are comprehensively considered and analyzed to accurately judge whether there is any abnormality in the current operation of the circular knife machine, and the quality of the finished product is analyzed at the same time during the operation of the circular knife machine. It is more convenient and timely to judge whether there is any abnormality in the circular knife machine according to the quality of the finished product.
[0007] In another possible implementation manner, determining the first mass influence score based on the shape and position relationship includes: Calculating a first similarity between the outline of each finished product in each group of finished products and a preset outline, and determining an average similarity of each group of finished products based on the first similarity; Determine the center point of each finished product in each group of finished products, and determine a second similarity between a connecting line of the center points of each finished product and a preset line segment, wherein the connecting line represents the positional relationship; The first quality impact score is determined based on the average similarity, the second similarity, and respective corresponding coefficients.
[0008] In another possible implementation, the step of identifying the burr on each finished product in each group of finished products based on the second image includes: Performing grayscale transformation on the second image to obtain a grayscale image; Determine the background grayscale value and the finished product grayscale value, and extract the finished product area corresponding to the finished product grayscale value; Determining a clean edge segment of each finished product from the finished product area; Extending and filling the neat edge segments to obtain the edge profile of each finished product; The range of the edge contour is determined, and the area corresponding to the finished product grayscale value outside the range is determined as the burr.
[0009] In another possible implementation, determining a second quality impact score of the burr on the finished product based on the burr includes: determining a first number of burrs on each edge of each finished product and a length of each burr; Determine the width of each burr where the root meets the edge of the finished product; Determine the impact of each burr on the quality of the finished product based on the length and width; Determine the average value of the sub-quality influence score on each edge; Determine a second number of burrs whose sub-quality impact score reaches a first preset score, and determine a first ratio of the second number to the first number; Determine the quality impact of each edge on the finished product based on the first quantity, the average value, the first ratio and the respective corresponding coefficients; The second quality influence score is obtained by summing up the quality influence scores of all edges of each finished product.
[0010] In another possible implementation, judging whether there is an abnormality in the current operation of the circular knife machine based on the first quality impact score and the second quality impact score includes: The third quality impact score of each group of products is obtained by summing up the second quality impact score of each finished product in each group of products; Determine a total quality impact score for each group of products based on the first quality impact score, the third quality impact score, and their respective corresponding weights; Map the total quality impact of each group of finished products to a preset coordinate system according to the time sequence of completion of processing of each group of finished products and generate a line graph; Determine a change trend of the total quality impact score based on the line graph, where the change trend includes increasing, unchanged, and decreasing; If the change trend is increasing, determining the rate of increase based on the line graph; If the increasing rate reaches the preset rate, it is determined that the current operation of the circular knife machine is abnormal.
[0011] In another possible implementation, the determining that the circular knife machine is currently running abnormally may then include: Determine whether there is a target finished product in each finished product of each group of finished products, wherein the target finished product has a margin where the quality impact score reaches a second preset score; Determine the die-cutting area on the die-cutting base corresponding to each target finished product, wherein the die-cutting base is provided with die-cutting areas in the axial direction thereof that are consistent with the number of finished products in each set of products; Determining a third quantity of target finished products corresponding to each die-cutting area; determining a second ratio of the third quantity to the number of groups of the plurality of groups of products; If there is a target die-cutting area where the second ratio reaches the preset ratio, it is determined that there is an abnormality in the target die-cutting area.
[0012] In another possible implementation, the determining that the target die-cutting area has an abnormality may then include: Prompt information is output based on the target die-cutting area.
[0013] In the second aspect, the present application provides a multifunctional circular knife machine control device based on image recognition, which adopts the following technical solution: Multifunctional circular knife machine control device based on image recognition, including: A first acquisition module is used to acquire first images of multiple groups of finished products produced by the circular knife machine at preset time intervals, each group of finished products including at least two finished products; A control module, used to control the light source to emit light of a preset color to each finished product, and to obtain a second image of each group of finished products illuminated by the light of the preset color; A first determination module, configured to determine the contour of each finished product in each group of finished products and the positional relationship between each finished product based on the first image, and determine a first quality influence score based on the contour and the positional relationship; A second determination module is used to identify the burrs on each finished product in each group of finished products based on the second image, and determine a second quality influence score of the burrs on the finished product based on the burrs; The first judgment module is used to judge whether there is an abnormality in the current operation of the circular knife machine based on the first quality impact score and the second quality impact score.
[0014] By adopting the above technical solution, the first acquisition module acquires the first images of multiple groups of finished products at preset time intervals, so that it is convenient to analyze the quality of the finished products according to the first image, and then judge whether there is any abnormality in the operation of the circular knife machine according to the quality of the finished products. The control module controls the light source to emit light of a preset color and acquires the second image of the finished product at this time. The first determination module can determine the contour of the finished product and the positional relationship between the finished products according to the first image. The quality of the contour and the positional relationship both represent whether there is any abnormality in the circular knife machine when processing the finished product. For example, multiple finished products should be in a side-by-side state and the front and back positions are consistent. If they are inconsistent, it means that there is uneven extrusion force, adhesion during the extrusion process, etc. Therefore, the first determination module can determine the first quality influence score according to the contour and the positional relationship. The second determination module can identify burrs through the second image. The occurrence of burrs affects the quality of the finished product. Therefore, the second determination module determines the second quality influence score according to the specific situation of the burrs. Then the first judgment module comprehensively considers and analyzes the first quality influence score and the second quality influence score, so as to accurately judge whether there is any abnormality in the current operation of the circular knife machine, and the quality of the finished product is analyzed at the same time during the operation of the circular knife machine. It is more convenient and timely to judge whether there is any abnormality in the circular knife machine according to the quality of the finished product.
[0015] In another possible implementation manner, when the first determining module determines the first quality impact score based on the shape and the position relationship, it is specifically configured to: Calculating a first similarity between the outline of each finished product in each group of finished products and a preset outline, and determining an average similarity of each group of finished products based on the first similarity; Determine the center point of each finished product in each group of finished products, and determine a second similarity between a connecting line of the center points of each finished product and a preset line segment, wherein the connecting line represents the positional relationship; The first quality impact score is determined based on the average similarity, the second similarity, and respective corresponding coefficients.
[0016] In another possible implementation, when the second determination module identifies the burr on each finished product in each group of finished products based on the second image, it is specifically configured to: Performing grayscale transformation on the second image to obtain a grayscale image; Determine the background grayscale value and the finished product grayscale value, and extract the finished product area corresponding to the finished product grayscale value; Determining a clean edge segment of each finished product from the finished product area; Extending and filling the neat edge segments to obtain the edge profile of each finished product; The range of the edge contour is determined, and the area corresponding to the finished product grayscale value outside the range is determined as the burr.
[0017] In another possible implementation, when the second determination module determines the second quality impact of the burr on the finished product based on the burr, it is specifically configured to: determining a first number of burrs on each edge of each finished product and a length of each burr; Determine the width of each burr where the root meets the edge of the finished product; Determine the impact of each burr on the quality of the finished product based on the length and width; Determine the average value of the sub-quality influence score on each edge; Determine a second number of burrs whose sub-quality impact score reaches a first preset score, and determine a first ratio of the second number to the first number; Determine the quality impact of each edge on the finished product based on the first quantity, the average value, the first ratio and the respective corresponding coefficients; The second quality influence score is obtained by summing up the quality influence scores of all edges of each finished product.
[0018] In another possible implementation, when the first judgment module judges whether there is an abnormality in the current operation of the circular knife machine based on the first quality impact score and the second quality impact score, it is specifically used to: The third quality impact score of each group of products is obtained by summing up the second quality impact score of each finished product in each group of products; Determine a total quality impact score for each group of products based on the first quality impact score, the third quality impact score, and their respective corresponding weights; Map the total quality impact of each group of finished products to a preset coordinate system according to the time sequence of completion of processing of each group of finished products and generate a line graph; Determine a change trend of the total quality impact score based on the line graph, where the change trend includes increasing, unchanged, and decreasing; If the change trend is increasing, determining the rate of increase based on the line graph; If the increasing rate reaches the preset rate, it is determined that the current operation of the circular knife machine is abnormal.
[0019] In another possible implementation, the device further includes: The second judgment module is used to judge whether there is a target finished product in each finished product of each group of finished products, and the target finished product has a quality impact score that reaches a second preset score. A fourth determination module is used to determine the die-cutting area corresponding to each target finished product on the die-cutting seat, wherein the die-cutting area is provided in the axial direction of the die-cutting seat with the same number of finished products in each group of finished products; A fifth determination module, used to determine a third quantity of target finished products corresponding to each die-cutting area; a sixth determining module, configured to determine a second ratio of the third quantity to the number of groups of the plurality of groups of finished products; The seventh determination module is used to determine that an abnormality exists in the target die-cutting area when there is a target die-cutting area whose second ratio reaches a preset ratio.
[0020] In another possible implementation, the device further includes: An output module is used to output prompt information based on the target die-cutting area.
[0021] In a third aspect, the present application provides an electronic device, which adopts the following technical solution: An electronic device, comprising: at least one processor; Memory; At least one application, wherein at least one application is stored in a memory and configured to be executed by at least one processor, and at least one is configured to: execute a multifunctional circular knife machine control method based on image recognition as shown in any possible implementation of the first aspect.
[0022] In a fourth aspect, the present application provides a computer-readable storage medium, which adopts the following technical solution: A computer-readable storage medium, when the computer program is executed in a computer, enables the computer to execute the multifunctional circular knife machine control method based on image recognition as described in any one of the first aspects.
[0023] In summary, the present application includes at least one of the following beneficial technical effects: The first images of multiple groups of finished products are obtained at preset time intervals, so that the quality of the finished products can be analyzed according to the first image, and then whether there is any abnormality in the operation of the circular knife machine can be judged according to the quality of the finished products. The light source is controlled to emit light of a preset color and a second image of the finished product at this time is obtained. The contour of the finished product and the positional relationship between the finished products can be determined according to the first image. The quality of the contour and the positional relationship both represent whether there is any abnormality in the circular knife machine when processing the finished product. For example, multiple finished products should be in a side-by-side state and the front and back positions should be consistent. If they are inconsistent, it means that the extrusion force is uneven, adhesion occurs during the extrusion process, etc. Therefore, the first quality influence score can be determined according to the contour and the positional relationship, and burrs can be identified through the second image. The occurrence of burrs affects the quality of the finished product. Therefore, the second quality influence score is determined according to the specific situation of the burrs. Then, based on the first quality influence score and the second quality influence score, a comprehensive analysis is performed to accurately judge whether there is any abnormality in the current operation of the circular knife machine, and the quality of the finished product is analyzed simultaneously during the operation of the circular knife machine. It is more convenient and timely to judge whether there is any abnormality in the circular knife machine according to the quality of the finished product. BRIEF DESCRIPTION OF THE DRAWINGS
[0024] Figure 1 It is a flow chart of a multifunctional circular knife machine control method based on image recognition in an embodiment of the present application.
[0025] Figure 2 This is an example diagram of burrs on the edge of a finished product in an embodiment of the present application.
[0026] Figure 3 It is a structural schematic diagram of a multifunctional circular knife machine control device based on image recognition in an embodiment of the present application.
[0027] Figure 4 It is a structural schematic diagram of an electronic device according to an embodiment of the present application.
[0028] Figure numerals: 2, burr; 3, width; 40, multifunctional circular knife machine control device based on image recognition; 401, first acquisition module; 402, control module; 403, first determination module; 404, second determination module; 405, first judgment module; 50, electronic device; 501, processor; 502, bus; 503, memory; 504, transceiver. DETAILED DESCRIPTION
[0029] The present application is further described in detail below in conjunction with the accompanying drawings.
[0030] After reading this specification, those skilled in the art may make non-creative modifications to this embodiment as needed, but such modifications are protected by patent law as long as they are within the scope of the claims of this application.
[0031] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.
[0032] In addition, the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article, unless otherwise specified, generally means that the associated objects before and after are in an "or" relationship.
[0033] The embodiments of the present application are further described in detail below in conjunction with the drawings in the specification.
[0034] The embodiment of the present application provides a multifunctional circular knife machine control method based on image recognition, which is executed by an electronic device, which can be a server or a terminal device, wherein the server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides cloud computing services. The terminal device can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc., but is not limited to this. The terminal device and the server can be directly or indirectly connected via wired or wireless communication, and the embodiment of the present application does not limit this. Figure 1 As shown, the method includes step S101, step S102, step S103, step S104 and step S105, wherein: S101, acquiring first images of multiple groups of finished products produced by a circular knife machine at preset time intervals.
[0035] Wherein, each set of products includes at least two finished products.
[0036] For the embodiment of the present application, the electronic device is connected to the circular knife machine through a wire. When the staff starts the circular knife machine, the circular knife machine outputs a signal to the electronic device. After receiving the signal, the electronic device knows that the circular knife machine has started to run. At this time, the first image of multiple groups of finished products produced by the circular knife machine is obtained according to the preset time interval. The preset time interval can be set by the staff through the visual operation interface as needed and stored in the electronic device, such as every five minutes, every half an hour, every hour, etc. A camera device is arranged directly above the finished product discharge of the circular knife machine, and an optical coupler and an infrared radiation device can be arranged at the discharge of the circular knife machine to detect whether a finished product is generated. The camera device and the infrared radiation device are both connected to the electronic device through a wire. When the appearance of a finished product is detected, the infrared radiation device outputs a detection signal. After receiving the detection signal, the electronic device sends a control signal to the camera device so that the camera device collects the first image of each group of finished products.
[0037] The die holder of the circular knife machine is a cylindrical structure. In order to improve the production efficiency of finished products, one or more die-cutting blocks are arranged along the circumference of the die holder surface, and multiple die-cutting areas are arranged along the axis. The die holder rolls and extrude the material to obtain the finished product. Therefore, the die holder can generate at least two finished products at the same time when extruding the material, that is, each group of finished products includes at least two finished products.
[0038] S102, controlling the light source to emit light of a preset color to each finished product, and acquiring a second image of each group of finished products illuminated by the light of the preset color.
[0039] For the embodiment of the present application, a light source is also provided directly above the discharge of the circular knife machine. For example, the light source is green, and the green light source illuminates the finished product. The finished product can highlight the defects on the edge of the finished product under the illumination of green light. Similarly, after acquiring the first image of each group of finished products, the electronic device sends a control signal to the light source so that the light source emits green light and controls the camera device to capture the second image at this time. The second image under the illumination of green light is convenient for analyzing the defects on the edge of the finished product, and then it is convenient to analyze the die-cutting quality.
[0040] S103, determining the outline of each finished product in each group of finished products and the positional relationship between each finished product based on the first image, and determining a first quality influence score based on the outline and the positional relationship.
[0041] For the embodiment of the present application, after the electronic device acquires the first image, it can perform edge detection on the first image, first perform denoising on the first image, then perform grayscale transformation to obtain a grayscale image, and then determine the place where the grayscale value step occurs in the grayscale image as the edge of each finished product, thereby obtaining the outline of each finished product. After determining the outline of each finished product, the electronic device determines the positional relationship between the finished products based on the position of the outline of each finished product. The outline characterizes the shape of the finished product after die-cutting, and the shape characterizes the quality of die-cutting. Since multiple finished products in a group of finished products are die-cut at the same time, the finished products after die-cutting produce a certain displacement under the action of the extrusion force. Multiple finished products should be in a side-by-side state and the front and back positions are consistent. If they are inconsistent, it means that there is uneven extrusion force, adhesion during extrusion, etc., which affects the die-cutting quality. Therefore, the electronic device can determine the first quality impact score of each group of finished products based on the outline and positional relationship.
[0042] S104, identifying burrs on each finished product in each group of finished products based on the second image, and determining a second quality influence score of the burrs on the finished product based on the burrs.
[0043] For the embodiment of the present application, the circular knife machine is usually used in the pharmaceutical field, such as cutting plasters, and the plasters are usually made of textile fabrics such as fibers. If there is an abnormality during the operation of the circular knife machine, burrs will appear on the finished product, thereby affecting the quality of the finished product. Since the second image has a high resolution for the burrs on the finished product, the electronic device identifies the burrs on each finished product in each group of finished products from the second image. The formation of burrs affects the die-cutting quality and the quality of the finished product. Therefore, after the electronic device identifies the burrs, it is convenient to determine the second quality impact score that affects the quality of the finished product based on the burrs.
[0044] S105, judging whether there is any abnormality in the current operation of the circular knife machine based on the first quality impact score and the second quality impact score.
[0045] For the embodiment of the present application, the first quality impact score characterizes the influence of the contour of the finished product and the positional relationship between the finished products on the quality of the finished product, and the second quality impact score characterizes the influence of the burr on the quality of the finished product, that is, the first quality impact score and the second quality impact score can both characterize the die-cutting quality, that is, whether there is an abnormality during the operation of the circular knife machine. Therefore, the electronic device can make a comprehensive judgment based on the first quality score and the second quality score to determine whether there is an abnormality in the circular knife machine more accurately, conveniently and timely.
[0046] In a possible implementation of the embodiment of the present application, the first mass influence score is determined based on the shape and position relationship in step S103, specifically including step S1031 (not shown in the figure), step S1032 (not shown in the figure) and step S1033 (not shown in the figure), wherein: S1031, calculating a first similarity between the outline of each finished product in each group of finished products and a preset outline, and determining an average similarity of each group of finished products based on the first similarity.
[0047] For the embodiment of the present application, after the electronic device determines the outline of each finished product, it calculates the first similarity between the outline of each finished product and the preset outline. The preset outline represents the outline of a qualified finished product. The electronic device can input the outline and the preset outline into a trained network model for similarity calculation, thereby obtaining the similarity between the outline and the preset outline. The network model can be a convolutional neural network model, a recurrent neural network model, or other types of network models. Alternatively, by cosine similarity calculation, that is, the outline and the preset outline are both represented as vectors, and the similarity is characterized by calculating the cosine distance between the vectors. The first similarity can also be calculated by a histogram, or by other methods, which are not limited here. After the electronic device determines the first similarity corresponding to each finished product in each group of finished products, the first similarity of each group of finished products is calculated using the average value calculation formula to obtain the average similarity corresponding to each group of finished products.
[0048] S1032, determining the center point of each finished product in each group of finished products, and determining a second similarity between the connecting line of the center point of each finished product and a preset line segment.
[0049] Among them, the connecting line represents the positional relationship.
[0050] For the embodiment of the present application, after the electronic device determines the outline of each finished product, it maps the outline to a coordinate system to obtain all the vertices that constitute the outline, calculates the average horizontal coordinate and the vertical coordinate of each vertex, obtains the coordinates of a point based on the average horizontal coordinate and the average vertical coordinate, and marks the point in the coordinate plane, which is the center point of the polygon. Or the outline is input into a trained network model for center point identification. After the electronic device determines the center point, it connects the center point of each finished product, and the preset line segment is a straight line segment, which indicates that the center points of multiple finished products are all on a straight line, that is, there is no uneven extrusion pressure and adhesion of the material during the die-cutting process, and the die-cutting quality is qualified. The electronic device calculates the second similarity between the above-obtained connection line and the preset line segment, and the second similarity can be obtained by calculating the cosine distance. The greater the second similarity, the closer the positional relationship between the multiple finished products is to the positional relationship between the finished products corresponding to the preset line segment, and the more qualified the die-cutting quality is.
[0051] If the number of finished products in each group of finished products is two, the electronic device can also calculate the angle between the line connecting the center points of the two finished products and the preset line segment, and represent the positional relationship through the angle.
[0052] S1033: Determine a first quality impact score based on the average similarity, the second similarity, and their corresponding coefficients.
[0053] For the embodiment of the present application, since the average similarity and the second similarity are both key factors for characterizing whether there are abnormalities in the die-cutting process and the quality of the finished product, and the degree of influence on the quality of the finished product is different. Therefore, the staff can set different coefficients for the average similarity and the second similarity and store them in the internal storage medium of the electronic device. The average similarity and the second similarity are both expressed in percentages. The higher the percentage, the higher the die-cutting quality and the higher the finished product quality. Therefore, the electronic device uses 100% to subtract the average similarity to obtain the first difference, and uses 100% to subtract the second similarity to obtain the second difference. Then the electronic device performs a weighted calculation on the first difference, the second difference and the corresponding coefficients to obtain the first quality impact score. The larger the first quality impact score, the greater the degree of influence on the quality of the finished product in terms of the positional relationship between the contour and the finished product, and the worse the quality of the finished product.
[0054] In a possible implementation of the embodiment of the present application, in step S104, burrs on each finished product in each group of finished products are identified based on the second image, specifically including step S1 (not shown in the figure), step S2 (not shown in the figure), step S3 (not shown in the figure), step S4 (not shown in the figure) and step S5 (not shown in the figure), wherein: S1, performing grayscale transformation on the second image to obtain a grayscale image.
[0055] For the embodiment of the present application, after the electronic device obtains the second image, it first performs denoising on the second image to make subsequent identification of burrs more accurate. Then the electronic device performs grayscale processing on the denoised second image to obtain a grayscale image.
[0056] S2, determining the background grayscale value and the finished product grayscale value, and extracting the finished product area corresponding to the finished product grayscale value.
[0057] In the embodiment of the present application, the electronic device extracts the grayscale value of the background and the grayscale value of the finished product, and screens and peels off the background area based on the background grayscale value, thereby extracting the finished product area corresponding to the finished product grayscale value.
[0058] S3, determining a neat edge segment of each finished product from the finished product area.
[0059] For the embodiment of the present application, the grayscale value in the finished product area is consistent, including the burr part. Since not all positions of the edge have burrs, the electronic device identifies and scans each edge of the finished product area to obtain a straight line segment on each edge, that is, a neat edge segment.
[0060] S4, extending and filling the neat edge segments to obtain the edge contour of each finished product.
[0061] For the embodiment of the present application, after the electronic device determines the neat edge segments, it simulates each neat edge segment, extends and completes each neat edge segment, thereby obtaining a closed figure, and then obtaining the edge contour of each finished product in the second image.
[0062] S5, determining the range of the edge contour, and determining the area corresponding to the gray value of the finished product outside the range as a burr.
[0063] For the embodiment of the present application, after the electronic device determines the edge contour, it removes the pixels within the edge contour range, that is, retains the area outside the edge contour range, and the area outside the range is the burr.
[0064] In other embodiments, after the electronic device determines the outline in the first image, since the first image is not sensitive to burrs, after the electronic device determines the outline of the finished product based on the first image, the outline in the first image can be mapped into the second image, and the area corresponding to the grayscale value outside the outline can be determined as a burr.
[0065] In a possible implementation of the embodiment of the present application, in step S104, determining the second quality impact of the burr on the finished product based on the burr specifically includes step Sa (not shown in the figure), step Sb (not shown in the figure), step Sc (not shown in the figure), step Sd (not shown in the figure), step Se (not shown in the figure), step Sf (not shown in the figure) and step Sg (not shown in the figure), wherein: Sa, determining a first number of burrs on each edge of each finished product and a length of each burr.
[0066] For the embodiment of the present application, the electronic device counts the burrs on each edge of each finished product to obtain the first number of burrs on each edge. If no burrs are identified on an edge, the first number of burrs on the edge is determined to be 0. The electronic device determines the outline of each burr, and counts the pixels from the free end (tip) of the burr on the outline to the root of the burr (the transition connection between the burr and the edge of the finished product). The number of pixels can represent the length of the burr. The more burrs there are and the longer the burrs are, the worse the die-cutting effect and the worse the quality of the finished product are. There may be abnormal conditions such as blunt die cutting and insufficient downward pressure on the die cutting.
[0067] Sb, determines the width of each burr where the root connects to the finished edge.
[0068] For the embodiment of the present application, when burrs are generated, they will be pulled out from the edge of the finished product under the action of tension, which will cause the edge of the finished product to be uneven. The greater the degree of unevenness, the worse the quality of the finished product. The greater the width of the connection between the root of the burr and the edge of the finished product, the greater the force of pulling out the burr and the greater the damage to the flatness of the edge of the finished product. Figure 2 As shown, Figure 2The middle burr 2 is located outside the edge and is pulled out from the edge of the finished product. Figure 2 The middle dotted line represents the width 3 at the connection between the root of the burr and the edge of the finished product. The larger the width 3, the greater the damage to the flatness of the edge of the finished product, that is, the greater the impact on the quality of the finished product.
[0069] Sc, determines the impact of each burr on the quality of the finished product based on its length and width.
[0070] For the embodiments of the present application, since the length of the burr and the width of the connection between the root of the burr and the edge of the finished product are key factors that characterize whether there are abnormalities in the die-cutting process and the quality of the finished product, and the degree of influence on the quality of the finished product is different. Therefore, the staff can set different coefficients for the length and width and store them in the internal storage medium of the electronic device. The larger the length and the larger the width, the worse the die-cutting quality and the lower the quality of the finished product. Then the electronic device performs a weighted calculation on the length, width and the corresponding coefficients to obtain the sub-quality impact score of each burr. The larger the sub-quality impact score, the greater the impact of the burr on the quality of the finished product, and the worse the quality of the finished product.
[0071] Sd, determines the average value of the sub-quality contribution on each edge.
[0072] For the embodiment of the present application, after the electronic device determines the sub-quality impact score of each burr, it determines the burrs on each edge, and calculates the average value of the sub-quality impact scores based on the sub-quality impact scores of the burrs on each edge. The average value is used to more accurately characterize the degree of influence of the burrs on each edge on the quality of the finished product.
[0073] Se, determining a second number of burrs whose sub-quality impact score reaches a first preset score, and determining a first ratio of the second number to the first number.
[0074] For the embodiment of the present application, the first preset score represents the demarcation point of whether the burr has a greater impact on the quality of the finished product. If the sub-quality impact score of a burr reaches the first preset score, it means that the burr has a more serious impact on the quality of the finished product. The more burrs that reach the first preset score, the worse the quality of the finished product, and the greater the degree of abnormal operation of the circular knife machine. Therefore, the electronic device counts the burrs that reach the first preset score on each edge to obtain a second number, and then determines the first ratio of the second number to the total number of burrs on the edge. The larger the first ratio, the worse the edge quality.
[0075] Sf, determines the quality impact of each edge on the finished product based on the first quantity, the average value, the first ratio and the respective corresponding coefficients.
[0076] For the embodiment of the present application, since the first quantity, average value and first ratio are all key factors that characterize the quality of a finished product edge, and the degree of influence on the quality of the finished product edge is different. Therefore, the staff can set different coefficients for the first quantity, average value and first ratio and store them in the internal storage medium of the electronic device, and then the electronic device can perform weighted calculation on the first quantity, average value, first ratio and the corresponding coefficients to obtain the quality influence score of each edge on the finished product. The larger the quality influence score, the greater the influence on the quality of the finished product at the edge, and the worse the quality of the finished product.
[0077] Sg, the second quality influence score is obtained by summing up the quality influence scores of all edges of each finished product.
[0078] For the embodiment of the present application, after the electronic device determines the quality impact score of each edge, since each finished product is composed of multiple edges, the electronic device sums the quality impact score of each edge to obtain the second quality impact score of each finished product. The second quality impact score of the burr on the quality of the finished product is accurately determined by analyzing the number, length, and width of the connection of the burr, and finally performing a comprehensive calculation based on the first number, the average value, and the first ratio.
[0079] In a possible implementation of the embodiment of the present application, in step S105, it is determined whether there is an abnormality in the current operation of the circular knife machine based on the first quality impact score and the second quality impact score, specifically including step S1051 (not shown in the figure), step S1052 (not shown in the figure), step S1053 (not shown in the figure), step S1054 (not shown in the figure), step S1055 (not shown in the figure) and step S1056 (not shown in the figure), wherein: S1051, summing up the second quality impact score of each finished product in each component product to obtain the third quality impact score of each component product.
[0080] For the embodiment of the present application, since each group of finished products includes multiple individual finished products, after the electronic device determines the third quality influence score of each finished product, the second quality influence score of each finished product is summed up by a summation function to obtain the third quality influence score of each group of finished products.
[0081] S1052: Determine a total quality impact score for each group of products based on the first quality impact score, the third quality impact score, and their corresponding weights.
[0082] For the embodiment of the present application, after the electronic device determines the first quality impact score and the third quality impact score of each group, since the first quality impact score and the second quality impact score have different degrees of impact on the quality of each group of finished products, the electronic device sets different weights for the first quality impact score and the second quality impact score and then stores them in the electronic device. After determining the first quality impact score and the third quality impact score, the electronic device retrieves their corresponding weights, and then performs weighted calculation on the first quality impact score, the third quality impact score and their corresponding weights to obtain the total quality impact score of each group of finished products.
[0083] S1053, mapping the total quality impact score of each group of finished products to a preset coordinate system according to the time sequence of completion of processing of each group of finished products and generating a line graph.
[0084] For the embodiment of the present application, the preset coordinate system is a coordinate system of the total quality score changing with time, which is set by a staff member and stored in an electronic device. After the electronic device acquires the first image and the second image, the acquisition time is marked, and the time is the time when each group of finished products is processed. After determining the total quality impact score, the electronic device determines the correspondence between the total quality impact score and the processing completion time, and then the electronic device maps the total quality impact score to the preset coordinate system according to the time sequence of each group of finished products. A line graph can be obtained by connecting the points in the coordinate system in sequence.
[0085] S1054: Determine a change trend of the total quality impact score based on the line graph.
[0086] Among them, the changing trends include increasing, unchanged and decreasing.
[0087] For the embodiment of the present application, the electronic device can perform linear fitting on the line graph to obtain a closest linear function, and then determine the slope of the linear function, and judge the change trend as increasing, unchanged or decreasing based on the positive or negative value of the slope.
[0088] S1055: If the changing trend is increasing, determine the increasing rate based on the line graph.
[0089] For the embodiment of the present application, after the electronic device determines that the changing trend is increasing, the specific value of the slope can be used to represent the increasing rate of the total mass influence score.
[0090] S1056: If the increasing rate reaches the preset rate, it is determined that there is an abnormality in the current operation of the circular knife machine.
[0091] For the embodiment of the present application, the preset rate is used as the dividing point for whether the total mass influence score increases too fast. The electronic device compares the determined increase rate with the preset rate. If the preset rate is reached, it means that the increase rate is too large and the circular knife machine is operating abnormally. If the increase rate does not reach the preset rate, it means that the circular knife machine is currently operating normally. It is more accurate to comprehensively determine the total mass influence score of each group of finished products through the first mass influence score and the second mass influence score, and further map the total mass influence score to the preset coordinate system to analyze the change trend of the total mass influence score. When the change trend is increasing, it is more accurate to judge whether the increase rate reaches the preset rate to judge whether the circular knife machine is operating abnormally.
[0092] In a possible implementation of the embodiment of the present application, step S1056 includes step S106 (not shown in the figure), step S107 (not shown in the figure), step S108 (not shown in the figure), step S109 (not shown in the figure) and step S110 (not shown in the figure), wherein: S106, determining whether the target finished product exists in each finished product of each component.
[0093] There is a margin in the target finished product where the quality impact score reaches a second preset score.
[0094] For the embodiment of the present application, the second preset score serves as the dividing point for whether the edge quality is too poor. If a finished product has an edge whose quality impact score reaches the second preset score, it means that the overall quality of the finished product is unqualified. Therefore, the electronic device determines that the target finished product has an edge that reaches the second preset score.
[0095] S107, determining the die-cutting area on the die holder corresponding to each target finished product.
[0096] Among them, a die-cutting area is arranged in the axial direction of the die-cutting seat, the number of which is consistent with the number of finished products in each component.
[0097] For the embodiment of the present application, the die cutter seat is cylindrical, and the material is extruded during the rotation process to produce the finished product. Since the surface of the die cutter seat has multiple die-cutting areas arranged along the axis, each finished product inside is arranged according to the corresponding die-cutting area after each group of finished products is processed. The electronic device can number each die-cutting area on the die cutter seat, and then determine the die-cutting area corresponding to each finished product according to the arrangement order of each group of finished products. If there is a target finished product, it means that there is an abnormality in the die-cutting area corresponding to the target finished product, resulting in poor quality of the target finished product. For example, there are situations such as the mold becoming blunt and the local downward pressure of the die cutter seat being abnormal.
[0098] S108, determining a third quantity of target finished products corresponding to each die-cutting area.
[0099] For the embodiment of the present application, after the electronic device determines all the target finished products, it determines the die-cutting area to which each target finished product belongs, thereby obtaining the third quantity of target finished products generated corresponding to each die-cutting area.
[0100] S109, determining a second ratio of the third quantity to the number of groups of the plurality of groups of products.
[0101] For the embodiment of the present application, after the electronic device determines the third number, it calculates a second ratio of the third number to the number of groups, which ratio represents the proportion of the target finished products produced in the die-cutting area. The larger the second ratio, the more serious the abnormality of the die-cutting area and the higher the possibility of the abnormality in the die-cutting area.
[0102] S110: If there is a target die-cutting area whose second ratio reaches a preset ratio, it is determined that there is an abnormality in the target die-cutting area.
[0103] For the embodiment of the present application, if the second ratio is too small, it means that the appearance of the target finished product is an accidental situation, and it does not mean that there is an abnormality in the die-cutting area. Therefore, a preset ratio is set, and the preset ratio serves as a dividing point for whether the second ratio is too large or too small. After the electronic device determines the second ratio of each die-cutting area, it compares the second ratio with the preset ratio. If there is a target die-cutting area that reaches the preset ratio, it means that there is an abnormality in the target die-cutting area. By determining the target finished products with poor quality produced by each die-cutting area, and determining the second ratio of the number of target finished products to the total number of finished products produced in the die-cutting area, it is more convenient and accurate to judge whether there is an abnormality in the die-cutting area by comparing the relationship between the second ratio and the preset ratio.
[0104] In a possible implementation manner of the embodiment of the present application, step S110 includes step S111 (not shown in the figure), wherein
[0105] S111, outputting prompt information based on the target die-cutting area.
[0106] For the embodiment of the present application, after the electronic device determines the target die-cutting area, taking step S107 as an example, the staff has numbered each die-cutting area on the electronic device. After the electronic device determines the target die-cutting area, it can output the number of the target die-cutting area to the staff's terminal device as prompt information, or control the display screen device on the circular knife machine to display the number of the target die-cutting area, thereby reminding the staff that there is an abnormality, so that the staff can discover the abnormality in time.
[0107] The above-mentioned embodiment introduces the multifunctional circular knife machine control method based on image recognition from the perspective of method flow, and the following embodiment introduces the multifunctional circular knife machine control device based on image recognition from the perspective of virtual module or virtual unit. For details, please refer to the following embodiment.
[0108] The embodiment of the present application provides a multifunctional circular knife machine control device 40 based on image recognition, such as Figure 3 As shown, the multifunctional circular knife machine control device 40 based on image recognition may specifically include: The first acquisition module 401 is used to acquire first images of multiple groups of finished products produced by the circular knife machine at preset time intervals, each group of finished products including at least two finished products; The control module 402 is used to control the light source to emit light of a preset color to each finished product, and obtain a second image of each group of finished products illuminated by the light of the preset color; A first determination module 403 is used to determine the contour of each finished product in each group of finished products and the positional relationship between each finished product based on the first image, and determine a first quality impact score based on the contour and the positional relationship; A second determination module 404 is used to identify the burrs on each finished product in each group of finished products based on the second image, and determine a second quality impact score of the burrs on the finished product based on the burrs; The first judgment module 405 is used to judge whether there is an abnormality in the current operation of the circular knife machine based on the first quality impact score and the second quality impact score.
[0109] The embodiment of the present application discloses a multifunctional circular knife machine control device 40 based on image recognition, wherein a first acquisition module 401 acquires first images of multiple groups of finished products at preset time intervals, so as to analyze the quality of the finished products according to the first images, and then judge whether there are abnormal conditions during the operation of the circular knife machine according to the quality of the finished products. The control module 402 controls the light source to emit light of a preset color and acquires a second image of the finished product at this time. The first determination module 403 can determine the contour of the finished product and the positional relationship between the finished products according to the first image. The quality of the contour and the positional relationship both indicate whether there are abnormal conditions when the circular knife machine processes the finished product. For example, multiple finished products should be in a side-by-side state and the front and back positions should be consistent. If they are inconsistent, This means that there are situations such as uneven extrusion force and adhesion during the extrusion process. Therefore, the first determination module 403 can determine the first quality influence score according to the contour and position relationship. The second determination module 404 can identify burrs through the second image. The presence of burrs affects the quality of the finished product. Therefore, the second determination module 404 determines the second quality influence score according to the specific situation of the burrs. Then the first judgment module 405 comprehensively considers and analyzes the first quality influence score and the second quality influence score, so as to accurately determine whether there is any abnormality in the current operation of the circular knife machine, and analyzes the quality of the finished product at the same time during the operation of the circular knife machine. It is more convenient and timely to determine whether there is any abnormality in the circular knife machine according to the quality of the finished product.
[0110] In a possible implementation manner of the embodiment of the present application, when the first determination module 403 determines the first quality impact score based on the shape and position relationship, it is specifically configured to: Calculating a first similarity between the outline of each finished product in each group of finished products and a preset outline, and determining an average similarity of each group of finished products based on the first similarity; Determine the center point of each finished product in each group of finished products, and determine the second similarity between the connecting line of the center point of each finished product and the preset line segment, wherein the connecting line represents the position relationship; A first quality influence score is determined based on the average similarity, the second similarity, and the respective corresponding coefficients.
[0111] In a possible implementation of the embodiment of the present application, when the second determination module 404 identifies the burrs on each finished product in each group of finished products based on the second image, it is specifically used to: Performing grayscale transformation on the second image to obtain a grayscale image; Determine the background grayscale value and the finished product grayscale value, and extract the finished product area corresponding to the finished product grayscale value; Determining a clean edge segment of each finished product from the finished product area; Extend and fill the neat edge segments to obtain the edge contour of each finished product; The range of the edge contour is determined, and the area corresponding to the finished product gray value outside the range is determined as a burr.
[0112] In a possible implementation of the embodiment of the present application, when the second determination module 404 determines the second quality impact of the burr on the finished product based on the burr, it is specifically configured to: determining a first number of burrs on each edge of each finished product and a length of each burr; Determine the width of each burr where the root meets the edge of the finished product; Determine the impact of each burr on the quality of the finished product based on length and width; Determine the average value of the sub-quality influence score on each edge; Determine a second number of burrs whose sub-quality impact score reaches a first preset score, and determine a first ratio of the second number to the first number; Determine the quality impact of each edge on the finished product based on the first quantity, the average value, the first ratio, and the respective corresponding coefficients; The second quality influence score is obtained by summing up the quality influence scores of all edges of each finished product.
[0113] In a possible implementation of the embodiment of the present application, when the first judgment module 405 judges whether there is an abnormality in the current operation of the circular knife machine based on the first quality impact score and the second quality impact score, it is specifically used to: The third quality impact score of each group of products is obtained by summing up the second quality impact score of each finished product in each group of products; Determine the total quality impact score of each group of products based on the first quality impact score, the third quality impact score and their corresponding weights; Map the total quality impact of each group of finished products to a preset coordinate system according to the time sequence of completion of processing of each group of finished products and generate a line graph; Determine the change trend of the total quality impact score based on the line graph, and the change trend includes increasing, unchanged and decreasing; If the trend is increasing, the rate of increase is determined based on the line graph; If the increasing rate reaches the preset rate, it is determined that there is an abnormality in the current operation of the circular knife machine.
[0114] In a possible implementation manner of the embodiment of the present application, the device 40 further includes: The second judgment module is used to judge whether there is a target finished product in each finished product of each group of finished products, and whether there is a target finished product whose quality impact score reaches a second preset score. A fourth determination module is used to determine the die-cutting area on the die holder corresponding to each target finished product, and the die holder is provided with die-cutting areas in the axial direction thereof that are consistent with the number of finished products in each group of finished products; A fifth determination module, used to determine a third quantity of target finished products corresponding to each die-cutting area; a sixth determining module, configured to determine a second ratio of the third quantity to the number of groups of the plurality of groups of finished products; The seventh determination module is used to determine that an abnormality exists in the target die-cutting area when there is a target die-cutting area whose second ratio reaches a preset ratio.
[0115] In a possible implementation manner of the embodiment of the present application, the device 40 further includes: The output module is used to output prompt information based on the target die-cutting area.
[0116] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the multifunctional circular knife machine control device 40 based on image recognition described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.
[0117] An electronic device is provided in an embodiment of the present application, such as Figure 4 As shown, Figure 4 The electronic device 50 shown includes: a processor 501 and a memory 503. The processor 501 and the memory 503 are connected, such as through a bus 502. Optionally, the electronic device 50 may also include a transceiver 504. It should be noted that in actual applications, the transceiver 504 is not limited to one, and the structure of the electronic device 50 does not constitute a limitation on the embodiments of the present application.
[0118] Processor 501 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It may implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of this application. Processor 501 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.
[0119] The bus 502 may include a path to transmit information between the above components. The bus 502 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus 502 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 4 Only one thick line is used in the diagram, but it does not mean that there is only one bus or only one type of bus.
[0120] The memory 503 may be a ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory) or other types of dynamic storage devices that can store information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, optical disk storage (including compressed optical disk, laser disk, optical disk, digital versatile disk, Blu-ray disk, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto.
[0121] The memory 503 is used to store the application code for executing the solution of the present application, and the execution is controlled by the processor 501. The processor 501 is used to execute the application code stored in the memory 503 to implement the contents shown in the above method embodiment.
[0122] The electronic devices include, but are not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), and fixed terminals such as digital TVs, desktop computers, etc. It can also be a server, etc. Figure 4 The electronic device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.
[0123] An embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer-readable storage medium is run on a computer, the computer can execute the corresponding content in the aforementioned method embodiment. Compared with the related art, in the embodiment of the present application, first images of multiple groups of finished products are obtained at preset time intervals, so that it is convenient to analyze the quality of the finished products according to the first image, and then judge whether there is any abnormality in the operation of the circular knife machine according to the quality of the finished products, control the light source to emit light of a preset color and obtain the second image of the finished product at this time, and the contour of the finished product and the positional relationship between the finished products can be determined according to the first image. The quality of the contour and the positional relationship both represent whether there is any abnormality in the circular knife machine when processing the finished product. For example, multiple finished products should be in a side-by-side state and the front and back positions should be consistent. If they are inconsistent, it means that the extrusion force is uneven, adhesion occurs during the extrusion process, etc. Therefore, the first quality influence score can be determined according to the contour and the positional relationship, and burrs can be identified through the second image. The occurrence of burrs affects the quality of the finished product. Therefore, the second quality influence score is determined according to the specific situation of the burrs, and then the first quality influence score and the second quality influence score are comprehensively considered and analyzed to accurately judge whether there is any abnormality in the current operation of the circular knife machine, and the quality of the finished product is analyzed at the same time during the operation of the circular knife machine. It is more convenient and timely to judge whether there is any abnormality in the circular knife machine according to the quality of the finished product.
[0124] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.
[0125] The above description is only a partial implementation method of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.
Claims
1. A multifunctional circular knife machine control method based on image recognition, characterized in that: include: Acquire first images of multiple groups of finished products produced by the circular knife machine at preset time intervals, each group of finished products including at least two finished products; Controlling the light source to emit light of a preset color to each finished product, and obtaining a second image of each group of finished products illuminated by the light of the preset color; Determine the contour of each finished product in each group of finished products and the positional relationship between each finished product based on the first image, and determine a first quality impact score based on the contour and the positional relationship; Identify burrs on each finished product in each group of finished products based on the second image, and determine a second quality impact score of the burrs on the finished product based on the burrs; Based on the first quality impact score and the second quality impact score, it is determined whether there is an abnormality in the current operation of the circular knife machine.
2. The multifunctional circular knife machine control method based on image recognition according to claim 1 is characterized in that: The determining of the first quality influence score based on the shape and the position relationship comprises: Calculating a first similarity between the outline of each finished product in each group of finished products and a preset outline, and determining an average similarity of each group of finished products based on the first similarity; Determine the center point of each finished product in each group of finished products, and determine a second similarity between a connecting line of the center points of each finished product and a preset line segment, wherein the connecting line represents the positional relationship; The first quality impact score is determined based on the average similarity, the second similarity, and respective corresponding coefficients.
3. The multifunctional circular knife machine control method based on image recognition according to claim 1 is characterized in that: The step of identifying the burr on each finished product in each group of finished products based on the second image includes: Performing grayscale transformation on the second image to obtain a grayscale image; Determine the background grayscale value and the finished product grayscale value, and extract the finished product area corresponding to the finished product grayscale value; Determining a clean edge segment of each finished product from the finished product area; Extending and filling the neat edge segments to obtain the edge profile of each finished product; The range of the edge contour is determined, and the area corresponding to the finished product grayscale value outside the range is determined as the burr.
4. The multifunctional circular knife machine control method based on image recognition according to claim 1 is characterized in that: The determining, based on the burr, a second quality impact score of the burr on the finished product includes: determining a first number of burrs on each edge of each finished product and a length of each burr; Determine the width of each burr where the root meets the edge of the finished product; Determine the impact of each burr on the quality of the finished product based on the length and width; Determine the average value of the sub-quality influence score on each edge; Determine a second number of burrs whose sub-quality impact score reaches a first preset score, and determine a first ratio of the second number to the first number; Determine the quality impact of each edge on the finished product based on the first quantity, the average value, the first ratio and the respective corresponding coefficients; The second quality influence score is obtained by summing up the quality influence scores of all edges of each finished product.
5. The multifunctional circular knife machine control method based on image recognition according to claim 1 is characterized in that: The determining whether there is an abnormality in the current operation of the circular knife machine based on the first quality impact score and the second quality impact score includes: The third quality impact score of each group of products is obtained by summing up the second quality impact score of each finished product in each group of products; Determine a total quality impact score for each group of products based on the first quality impact score, the third quality impact score, and their respective corresponding weights; Map the total quality impact of each group of finished products to a preset coordinate system according to the time sequence of completion of processing of each group of finished products and generate a line graph; Determine a change trend of the total quality impact score based on the line graph, where the change trend includes increasing, unchanged, and decreasing; If the change trend is increasing, determining the rate of increase based on the line graph; If the increasing rate reaches the preset rate, it is determined that the current operation of the circular knife machine is abnormal.
6. The multifunctional circular knife machine control method based on image recognition according to claim 5 is characterized in that: The step of determining that the circular knife machine is currently running abnormally comprises: Determine whether there is a target finished product in each finished product of each group of finished products, wherein the target finished product has a margin where the quality impact score reaches a second preset score; Determine the die-cutting area on the die-cutting base corresponding to each target finished product, wherein the die-cutting base is provided with die-cutting areas in the axial direction thereof that are consistent with the number of finished products in each set of products; Determine a third quantity of target finished products corresponding to each die-cutting area; determining a second ratio of the third quantity to the number of groups of the plurality of groups of products; If there is a target die-cutting area where the second ratio reaches the preset ratio, it is determined that there is an abnormality in the target die-cutting area.
7. The multifunctional circular knife machine control method based on image recognition according to claim 6 is characterized in that: The step of determining that an abnormality exists in the target die-cutting area comprises: Prompt information is output based on the target die-cutting area.
8. A multifunctional circular knife machine control device based on image recognition, characterized in that: include: A first acquisition module is used to acquire first images of multiple groups of finished products produced by the circular knife machine at preset time intervals, each group of finished products including at least two finished products; A control module, used to control the light source to emit light of a preset color to each finished product, and to obtain a second image of each group of finished products illuminated by the light of the preset color; A first determination module, configured to determine the contour of each finished product in each group of finished products and the positional relationship between each finished product based on the first image, and determine a first quality influence score based on the contour and the positional relationship; A second determination module is used to identify the burrs on each finished product in each group of finished products based on the second image, and determine a second quality influence score of the burrs on the finished product based on the burrs; The first judgment module is used to judge whether there is an abnormality in the current operation of the circular knife machine based on the first quality impact score and the second quality impact score.
9. An electronic device, characterized in that: It includes: at least one processor; Memory; At least one application, wherein the at least one application is stored in the memory and is configured to be executed by the at least one processor, and the at least one application is used to execute the multifunctional circular knife machine control method based on image recognition according to any one of claims 1 to 7.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed in a computer, the computer is caused to execute the multifunctional circular knife machine control method based on image recognition as described in any one of claims 1 to 7.
