Visual inspection method for printed materials of mobile phone battery cover based on hundred-grid knife test

Abstract

The present invention relates to the technical fields of signal transmission, computer vision, image recognition and printing, and provides a visual inspection method for mobile phone battery cover printing materials based on a hundred-grid knife test. The method comprises the following steps: sampling to obtain inspection samples of film plates of mobile phone battery covers in a batch of mobile phone battery cover printing materials, removing the film to obtain a bare plate to be inspected, using a hundred-grid knife test process to obtain a bare plate showing a coating peeling state, obtaining an appearance picture of the bare plate showing the coating peeling state, performing machine vision identification on the coating peeling defect of the bare plate through the appearance picture of the bare plate showing the coating peeling state, and counting the defect amount of the bare plate with the coating peeling defect. When the defect amount of the bare plate exceeds a preset bare plate defect threshold, the batch of mobile phone battery cover printing materials is returned, thereby improving the inspection efficiency and accuracy of the mobile phone battery cover printing materials and improving the printing quality control.

Description

Technical Field

[0001] The present invention relates to the technical fields of signal transmission, computer vision, image recognition and printing, and in particular to a visual inspection method for printed materials of mobile phone battery covers based on a hundred-grid knife test. Background Art

[0002] The mobile phone battery cover is a protective shell that covers the mobile phone battery and other internal components. It is used to protect the internal components of the mobile phone from physical damage and foreign matter intrusion, and provide the appearance and feel of the mobile phone. In order to achieve the appearance and feel of the mobile phone, various colors, textures and patterns need to be printed on the mobile phone battery cover. In the specific printing process, in order to evaluate the coating adhesion of the mobile phone battery cover, the hundred-grid knife test process is used to test the incoming materials of the mobile phone battery cover. The hundred-grid knife test mainly cuts a regular grid pattern on the coating surface, and then uses tape to tear off part of the coating to observe the peeling of the coating. At present, the hundred-grid knife test process mainly relies on manual work, which is not only inefficient, but also has low inspection accuracy, which is not conducive to the printing quality control of mobile phone battery covers.

[0003] In summary, the existing hundred-grid knife testing technology has technical problems such as low efficiency, low accuracy, and is not conducive to printing quality control. Summary of the invention

[0004] In view of the deficiencies in the above-mentioned prior art, the present invention provides a visual inspection method for mobile phone battery cover printing materials based on a hundred-grid knife test, so as to improve the inspection efficiency and accuracy of mobile phone battery cover printing materials and improve printing quality control.

[0005] The present invention provides a visual inspection method for mobile phone battery cover printed materials based on a hundred-grid knife test, comprising:

[0006] Randomly sampling from a batch of mobile phone battery cover printing materials to obtain a test sample of a film sheet of the mobile phone battery cover, and tearing off a protective film of the film sheet in the test sample of the film sheet to obtain a bare sheet to be tested;

[0007] Using a grid knife to cut grid-shaped scratches on the surface of the bare plate to be tested, and using tape to stick the grid area of ​​the grid-shaped scratches to obtain a bare plate showing the coating peeling state;

[0008] Obtain an appearance picture of a bare plate showing a coating peeling state, perform machine vision identification on the coating peeling defect of the bare plate through the appearance picture of the bare plate showing a coating peeling state, and count the number of defects of the bare plate with coating peeling defects; when the number of defects of the bare plate exceeds a preset bare plate defect threshold, return the batch of mobile phone battery cover printing materials.

[0009] Further, the coating peeling defect of the bare plate is identified by machine vision through the appearance picture of the bare plate showing the coating peeling state, including:

[0010] Configuring a compliant bare sheet image library, wherein the compliant bare sheet image library includes normal bare sheets of different models;

[0011] Automatically matching the model of the currently detected bare plate with different models of the normal bare plate to obtain a normal bare plate of the corresponding model;

[0012] The appearance picture of the normal bare plate of the corresponding model in the bare plate picture library is compared with the appearance picture of the bare plate currently being tested to identify the coating peeling defect of the bare plate.

[0013] Further, the coating peeling defect of the bare plate is identified by machine vision through the appearance picture of the bare plate showing the coating peeling state, including:

[0014] Training an AI recognition model for identifying coating peeling defects of the bare plate;

[0015] The appearance picture of the bare plate currently being inspected is input into the trained AI recognition model of coating peeling defects of the bare plate to identify the coating peeling defects of the bare plate.

[0016] Furthermore, the coating peeling defects on the bare plate include: complete peeling of the coating, partial peeling of the coating and cracking of the coating; the complete peeling of the coating is manifested as the coating in the grid area is completely peeled off from the substrate; the partial peeling of the coating is manifested as the coating in the grid area is partially peeled off, and the substrate is partially exposed; the coating cracking is manifested as fine cracks on the coating surface in the grid area.

[0017] Furthermore, when the defect amount of the bare plate is lower than a preset bare plate defect threshold, machine vision inspection is performed on the auxiliary materials in the batch of mobile phone battery cover printing materials to obtain qualified auxiliary materials for packaging the printed bare plate, and unqualified auxiliary materials are isolated; in each batch of mobile phone battery cover printing materials, each batch of the film plate is matched with the corresponding auxiliary materials.

[0018] Furthermore, the auxiliary materials include a PET protective film, and when the auxiliary materials in the batch of mobile phone battery cover printing materials are subjected to machine vision inspection, the following steps are included:

[0019] Obtain an appearance picture of the PET protective film of the mobile phone battery cover, and use machine vision to identify the appearance defects of the PET protective film through the appearance picture of the PET protective film to obtain a PET protective film without appearance defects for film packaging of the bare sheet after printing, and isolate the PET protective film with appearance defects.

[0020] Further, after obtaining the appearance picture of the PET protective film of the mobile phone battery cover, it also includes:

[0021] Performing machine vision recognition on the size of the PET protective film of the mobile phone battery cover from the appearance picture of the PET protective film;

[0022] Compare the identified size of the PET protective film with a preset compliance size, and when the comparison value between the size of the PET protective film and the preset compliance size is less than a preset negligible deviation value, determine that the PET protective film has no size defect, and transport the PET protective film without size defect and appearance defect to a packaging station for film packaging of the bare plate after printing;

[0023] When the comparison value between the size of the PET protective film and the preset compliant size is greater than the preset negligible deviation value, it is determined that the PET protective film has a size defect, and the PET protective film with the size defect is isolated.

[0024] Further, the appearance defects of the PET protective film are identified by machine vision through the appearance picture of the PET protective film, including:

[0025] Configure a compliant PET protective film image library, wherein the compliant PET protective film image library includes different models of compliant PET protective films;

[0026] Automatically match the model of the currently detected PET protective film with different models of compliant PET protective films in the compliant PET protective film image library to obtain a compliant PET protective film of the corresponding model in the compliant PET protective film image library;

[0027] The compliant PET protective film of the corresponding model is compared with the appearance picture of the PET protective film currently being tested to identify the appearance defects of the PET protective film.

[0028] Further, the appearance defects of the PET protective film are identified by machine vision through the appearance picture of the PET protective film, including:

[0029] Training an AI recognition model for identifying appearance defects of the PET protective film;

[0030] The appearance picture of the PET protective film currently being inspected is input into the trained AI recognition model of the appearance defects of the PET protective film to identify the appearance defects of the PET protective film.

[0031] Furthermore, the auxiliary materials include supporting foam, and when the auxiliary materials in the batch of mobile phone battery cover printing materials are subjected to machine vision inspection, the following steps are included:

[0032] Obtaining an appearance picture of the supporting foam of the mobile phone battery cover, and performing machine vision recognition on the size of the supporting foam of the mobile phone battery cover;

[0033] Comparing the identified size of the supporting foam with a preset compliant size, and when the comparison value between the size of the supporting foam and the preset compliant size is less than a preset negligible deviation value, determining that the supporting foam does not have a size defect, and conveying the supporting foam without a size defect to a packaging station for packaging the bare plate after printing;

[0034] When the comparison value between the size of the supporting foam and the preset compliant size is greater than the preset negligible deviation value, it is determined that the supporting foam has a size defect, and the supporting foam with the size defect is isolated.

[0035] Compared with the prior art, the present invention has the following beneficial effects:

[0036] The present invention provides a visual inspection method for mobile phone battery cover printing materials based on a grid knife test. The method comprises the following steps: randomly sampling a sample from a batch of mobile phone battery cover printing materials to obtain a test sample of a film plate of the mobile phone battery cover, tearing off a protective film of the film plate in the test sample of the film plate to obtain a bare plate to be inspected, using a grid knife to cut grid-shaped scratches on the surface of the bare plate to be inspected, pasting a grid area of ​​the grid-shaped scratches with an adhesive tape to obtain a bare plate reflecting a coating peeling state, obtaining an appearance picture of the bare plate reflecting a coating peeling state, performing machine vision recognition on the coating peeling defect of the bare plate through the appearance picture of the bare plate reflecting a coating peeling state, and counting the defect amount of the bare plate with the coating peeling defect. When the defect amount of the bare plate exceeds a preset bare plate defect threshold, the batch of mobile phone battery cover printing materials is returned, thereby improving the inspection efficiency and accuracy of mobile phone battery cover printing materials and improving printing quality control. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of the present invention. The exemplary embodiments of the present invention and their description are used to explain the present invention and do not constitute an improper limitation of the present invention. Some specific embodiments of the present invention will be described in detail in an exemplary and non-restrictive manner with reference to the drawings. The same reference numerals in the drawings indicate the same or similar components or parts. It should be understood by those skilled in the art that these drawings are not necessarily drawn to scale. In the drawings:

[0038] Figure 1 It is a flow chart of a visual inspection method for mobile phone battery cover printing materials based on the hundred-grid knife test according to an embodiment of the present invention;

[0039] Figure 2 It is a schematic diagram of a process of forming grid-like scratches by cutting with a grid knife according to an embodiment of the present invention;

[0040] Figure 3 It is a schematic diagram of a process of sticking a grid area of ​​a grid-shaped scratch with an adhesive tape according to an embodiment of the present invention. DETAILED DESCRIPTION

[0041] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiment of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiment of the present invention. Obviously, the described embodiment is only an embodiment of a part of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work should fall within the scope of protection of the present invention.

[0042] See also Figure 1-Figure 3The embodiment of the present invention provides a visual inspection method for mobile phone battery cover printed materials based on a hundred-grid knife test. In the visual inspection method, the mobile phone battery cover printed materials include film sheets; the visual inspection method for mobile phone battery cover printed materials based on the hundred-grid knife test includes steps S101, S102 and S103, wherein random samples are taken from a batch of mobile phone battery cover printed materials to obtain a test sample of the film sheet of the mobile phone battery cover, the protective film of the film sheet in the test sample of the film sheet is torn off to obtain a bare sheet to be inspected, and a hundred-grid knife is used to cut the surface of the bare sheet to be inspected. Cut out grid-shaped scratches, and stick the grid areas of the grid-shaped scratches with tape to obtain a bare plate showing a coating peeling state, obtain an appearance picture of the bare plate showing a coating peeling state, perform machine vision recognition on the coating peeling defect of the bare plate through the appearance picture of the bare plate showing a coating peeling state, and count the defect amount of the bare plate with coating peeling defect, when the defect amount of the bare plate exceeds a preset bare plate defect threshold, return the batch of mobile phone battery cover printing materials, thereby improving the detection efficiency and accuracy of mobile phone battery cover printing materials and improving printing quality control.

[0043] In step S101, in a batch of mobile phone battery cover printing materials, the appearance pictures of the film sheet of the mobile phone battery cover are sampled and obtained, and the film sheet includes a sheet and a protective film attached to the surface of the sheet. Among them, in a batch of mobile phone battery cover printing materials, when sampling and obtaining the appearance pictures of the film sheet of the mobile phone battery cover, it can be specifically implemented in the following ways: adjusting the settings of the image acquisition device, such as focal length, exposure, etc., to ensure that clear and accurate appearance pictures are obtained; transporting the film sheet of the mobile phone battery cover to the shooting area of ​​the image acquisition device through the feeding transmission mechanism; triggering the image acquisition device to shoot, and sampling and obtaining the appearance pictures of the film sheet of the mobile phone battery cover in the batch of mobile phone battery cover printing materials for saving. It should be noted that in this embodiment, by obtaining the appearance pictures of the film sheet, the protective film can be subsequently inspected for appearance, so as to achieve efficient and accurate automated appearance inspection and reduce the errors and costs of manual inspection.

[0044] In step S102, a grid-shaped scratch is cut on the surface of the bare plate to be inspected using a grid knife, and the grid area of ​​the grid-shaped scratch is pasted with tape to obtain a bare plate showing a coating peeling state.

[0045] In some preferred embodiments, a grid-shaped scratch is cut on the surface of the bare plate to be tested using a grid knife, including: step S1020, fixing the bare plate to be tested on a workbench, and using a grid knife to evenly cut the surface of the bare plate to form a group of parallel scratches; step S1021, rotating the grid knife 90 degrees, cutting again, forming a group of vertical scratches, the group of vertical scratches and the group of parallel scratches intersect vertically to form grid-shaped scratches. It should be noted that in this embodiment, by fixing the plate and using a grid knife to evenly cut, it can be ensured that the scratches on each sample have consistent depth and spacing, thereby avoiding human errors and ensuring the reliability and comparability of the test results. In addition, the standardization of the operating steps of fixing and rotating the grid knife can simplify the operating process, so that different operators can repeat the same test steps at different time points to ensure the repeatability of the test results. It can be understood that the uniform grid-shaped scratches make the coating in each grid subject to the same stress conditions, so that the adhesion and peeling resistance of the coating can be more accurately evaluated. Grid-shaped scratches can cover most areas of the plate surface, allowing the test to comprehensively evaluate the adhesion and durability of the coating at different locations, avoiding deviations that may be caused by local testing. In addition, after the tape sticking and peeling test, the grid-shaped scratches make the area where the coating peels off more obvious, which helps the machine vision system to identify coating peeling defects more quickly and accurately, and improves detection efficiency. Moreover, the grid-shaped scratches make the peeling coating area have a certain regularity, which is convenient for subsequent image processing and quantitative analysis, so that the area and location of coating peeling can be more accurately counted, providing detailed data support for quality control.

[0046] In some preferred embodiments, the distance between each scratch in the set of parallel scratches is 1-2 mm; the distance between each scratch in the set of vertical scratches is 1-2 mm. The depth of each scratch in the set of parallel scratches is consistent with the depth of each scratch in the set of vertical scratches. It should be noted that in this embodiment, by specifying a spacing of 1-2 mm and a consistent scratch depth, the consistency of the test conditions can be ensured, thereby reducing the impact of variables and making the test results more comparable. It can be understood that in this embodiment, by setting the scratches with uniform spacing and depth, the coating in each grid can be subjected to uniform stress, so that the adhesion and peeling of the coating can be more accurately evaluated. In addition, the consistent scratch depth and spacing can ensure that the conditions of the test sample in each grid are consistent, which helps to reduce the test errors caused by inconsistent depth or spacing and improve the detection accuracy. At the same time, the uniform grid scratches facilitate the machine vision system to perform image processing and analysis, and can more accurately identify and count coating peeling defects, thereby improving the automation and efficiency of detection.

[0047] In some preferred embodiments, the bare plate to be tested is fixed on a workbench, and a grid knife is used to evenly cut the surface of the bare plate to form a group of parallel scratches, including: conveying the bare plate to be tested to the loading station of the workbench, and when the bare plate to be tested on the loading station is detected, controlling the adjustable clamp to clamp and fix the bare plate to be tested; after the bare plate to be tested is fixed, controlling the cutting head equipped with the grid knife to cut the surface of the bare plate with a preset parallel cutting route and cutting depth to form a group of parallel scratches. Further, after the cutting of the group of parallel scratches is completed, controlling the cutting head equipped with the grid knife to cut the surface of the bare plate with a preset vertical cutting route and cutting depth to form a group of vertical scratches. It should be noted that in this embodiment, the automatic fixing of the bare plate to be tested is achieved by the loading station and the adjustable clamp, which can reduce the complexity and error of manual operation and improve production efficiency. Using an automated control system to control the cutting head of the grid knife to cut according to the preset route and depth can ensure the consistency and accuracy of the cutting process. In addition, by presetting parallel and vertical cutting routes and consistent cutting depth, the scratch conditions of each test sample can be ensured to be consistent, reducing the uncertainty of human operation.

[0048] In some preferred embodiments, the grid area of ​​the grid-shaped scratch is pasted with tape, including: step S1022, pasting one end of the tape on an edge of the grid area by a glue sticking machine, controlling the pressure roller of the glue sticking machine to move along the surface of the tape, and automatically compacting the tape to fit tightly on the entire grid area; step S1023, after the glue sticking machine compacts the tape on the grid area, controlling the tape tearing arm of the glue sticking machine to tear off the tape that fits on the entire grid area. It should be noted that in this embodiment, the use of a glue sticking machine to automatically complete the pasting and tearing of the tape can reduce the inconsistency and error in manual operation and improve the standardization of operation. In addition, the automated equipment can quickly and accurately complete the pasting and tearing operations of the tape, which can significantly improve the efficiency of the detection process. In addition, by moving the pressure roller along the surface of the tape, it is ensured that the tape applies pressure evenly on the entire grid area, so that the tape fits tightly on the surface of the board, and the consistency of the peeling test is ensured. Using the tape removal arm to automatically remove the tape can ensure that the force and angle of each removal are consistent, avoiding the uncertainty caused by manual operation and ensuring the reliability of the test results.

[0049] In step S103, an appearance picture of a bare plate showing a coating peeling state is obtained, and the coating peeling defect of the bare plate is identified by machine vision through the appearance picture of the bare plate showing a coating peeling state, and the defect quantity of the bare plate with coating peeling defect is counted. When the defect quantity of the bare plate exceeds a preset bare plate defect threshold, the batch of mobile phone battery cover printing materials is returned, thereby improving the inspection efficiency and accuracy of mobile phone battery cover printing materials and improving printing quality control.

[0050] In some preferred embodiments, the coating peeling defect of the bare plate is machine-visually identified by the appearance picture of the bare plate reflecting the coating peeling state, including: configuring a compliant bare plate picture library, the compliant bare plate picture library includes normal bare plates of different models; automatically matching the model of the bare plate currently detected with the different models of the normal bare plate to obtain a normal bare plate of the corresponding model; comparing the appearance picture of the normal bare plate of the corresponding model in the bare plate picture library with the appearance picture of the bare plate currently detected to identify the coating peeling defect of the bare plate. It should be noted that in this embodiment, by establishing a compliant bare plate picture library, it can be ensured that each model of bare plate has a standard reference image, and there is a consistent comparison standard when performing defect identification. At the same time, different models of mobile phone battery covers use different coating materials and processes, and the coating peeling states they show are different. Therefore, matching the normal bare plate picture library pictures of the corresponding model can ensure the accuracy of the comparison benchmark. If the model matching is not performed, using the reference picture that does not meet the model for comparison may lead to misjudgment or missed judgment. In addition, by automatically matching the model of the current inspection plate, manual intervention can be reduced and the automation and efficiency of the inspection process can be improved.

[0051] In some preferred embodiments, the coating peeling defect of the bare plate is machine-visually identified through the appearance picture of the bare plate reflecting the coating peeling state, including: training an AI recognition model for identifying the coating peeling defect of the bare plate; inputting the appearance picture of the bare plate currently being detected into the trained AI recognition model for the coating peeling defect of the bare plate to identify the coating peeling defect of the bare plate. It should be noted that in this embodiment, the AI ​​recognition model is trained with a large amount of coating peeling defect picture data, so that it can accurately identify various coating peeling defects and improve the accuracy and consistency of recognition. Among them, the AI ​​recognition model can automatically and quickly identify defects, reduce errors caused by human operation, and ensure the reliability of the detection results. In addition, the AI ​​recognition model can process a large number of pictures in a short time, realize rapid recognition and judgment, and significantly improve the detection efficiency. The AI ​​recognition model can recognize various types of coating peeling defects through training, adapt to the detection needs of different coatings and plates, and has strong adaptability. Preferably, the coating peeling defects on the bare plate include: complete peeling of the coating, partial peeling of the coating and cracking of the coating; the complete peeling of the coating is manifested as the coating in the grid area is completely peeled off from the substrate; the partial peeling of the coating is manifested as partial peeling of the coating in the grid area, and the substrate is partially exposed; the coating cracking is manifested as the appearance of fine cracks on the coating surface in the grid area. It should also be noted that the AI ​​recognition model for identifying the coating peeling defects of the bare plate can adopt a CNN model or a visual Transformer in the Transformer model. The CNN model or visual Transformer is trained by using pictures of bare plates with complete peeling of the coating, partial peeling of the coating and cracking of the coating. After successful training, the appearance picture of the bare plate currently being tested is input into the trained CNN model or visual Transformer to identify the coating peeling defects of the bare plate.

[0052] In some preferred embodiments, when the defect amount of the bare sheet material with coating peeling defects is lower than the preset bare sheet material defect threshold, the auxiliary materials in the batch of mobile phone battery cover printing materials are subjected to machine vision inspection to obtain qualified auxiliary materials for packaging the printed bare sheet material, and the unqualified auxiliary materials are isolated; in each mobile phone battery cover printing material, each film sheet material is matched with the corresponding auxiliary materials. It should be noted that in this embodiment, by inspecting the auxiliary materials, the problem of affecting the quality of the final product due to unqualified auxiliary materials can be avoided. In addition, in this embodiment, the auxiliary materials are only inspected when the bare sheet material is qualified, which can reduce unnecessary inspection work and improve the overall inspection efficiency. The unqualified auxiliary materials are isolated to prevent them from entering the subsequent packaging process and improve the quality control of the overall product.

[0053] In a further preferred embodiment, the auxiliary materials include a PET protective film, and when the auxiliary materials in the batch of mobile phone battery cover printing materials are subjected to machine vision inspection, it includes: obtaining an appearance picture of the PET protective film of the mobile phone battery cover, and performing machine vision identification on the appearance defects of the PET protective film through the appearance picture of the PET protective film, so as to obtain a PET protective film without appearance defects for film packaging of the bare sheet after printing, and the PET protective film with appearance defects is isolated. It should be noted that the PET protective film is used as a packaging material, and its quality inspection can ensure the packaging quality of the final product. Among them, the appearance defects of the PET protective film, such as scratches, bubbles, and pollution, will affect the packaging effect and the appearance of the product. By detecting the appearance defects of the PET protective film, it can be ensured that only qualified protective films are used for packaging, thereby improving the quality and aesthetics of the final product. In this embodiment, the use of machine vision inspection instead of manual inspection can greatly improve the inspection efficiency and consistency. In addition, if a PET protective film with appearance defects is used for packaging, the defective rate will increase. In this embodiment, by isolating the PET protective film with appearance defects, unqualified PET protective film can be prevented from entering the packaging process, the generation of defective products can be reduced, and the yield rate of the production line can be improved.

[0054] In a further preferred embodiment, after obtaining the appearance picture of the PET protective film of the mobile phone battery cover, it also includes: performing machine vision recognition on the size of the PET protective film of the mobile phone battery cover from the appearance picture of the PET protective film; comparing the size of the identified PET protective film with the preset compliant size, and when the comparison value between the size of the PET protective film and the preset compliant size is less than the preset negligible deviation value, it is determined that the PET protective film does not have a size defect, and the PET protective film without size defects and appearance defects is transported to the packaging station for film packaging of the printed bare sheet; when the comparison value between the size of the PET protective film and the preset compliant size is greater than the preset negligible deviation value, it is determined that the PET protective film has a size defect, and the PET protective film with a size defect is isolated. It should be noted that in addition to appearance defects, the size of the PET protective film is also crucial. A protective film with unqualified size may not fit properly on the mobile phone battery cover, affecting the packaging effect. In this embodiment, by detecting the size, it is ensured that the PET protective film not only has a qualified appearance, but also meets the requirements in size, thereby improving the overall quality of the packaging. In addition, simple appearance inspection cannot cover all possible defects. By adding size inspection, the quality of PET protective film can be more comprehensively guaranteed. In addition, PET protective film with unqualified size will cause waste in subsequent use. Through early inspection and isolation treatment, the production process can be optimized and resources can be saved.

[0055] In a further preferred embodiment, the appearance defects of the PET protective film are machine-visually identified through the appearance picture of the PET protective film, including: configuring a compliant PET protective film picture library, the compliant PET protective film picture library includes compliant PET protective films of different models; automatically matching the model of the PET protective film currently being tested with the different models of compliant PET protective films in the compliant PET protective film picture library to obtain a compliant PET protective film of the corresponding model in the compliant PET protective film picture library; comparing the compliant PET protective film of the corresponding model with the appearance picture of the PET protective film currently being tested to identify the appearance defects of the PET protective film. It should be noted that there are differences between different models of PET protective films. Using a unified standard picture library can ensure that each test has a consistent benchmark, which can improve the accuracy of the test. In this embodiment, by comparing with the compliant picture library, false detections and missed detections are reduced, and the accuracy and consistency of the test results can be improved. In addition, in this embodiment, through automated matching and comparison, not only the detection speed is improved, but also the errors of human operation are reduced, ensuring an efficient and reliable detection process. In addition, configuring compliance image libraries of different models and performing automatic matching can flexibly adapt to the detection needs of various models and improve the adaptability and flexibility of the system.

[0056] In a further preferred embodiment, the appearance defects of the PET protective film are machine-visually identified through the appearance picture of the PET protective film, including: training an AI recognition model for identifying the appearance defects of the PET protective film; inputting the appearance picture of the PET protective film currently being detected into the trained AI recognition model for the appearance defects of the PET protective film to identify the appearance defects of the PET protective film. It should be noted that traditional detection methods are difficult to accurately identify complex or subtle appearance defects, while the AI ​​model can have higher recognition accuracy by learning a large number of defect samples. In this embodiment, by training the AI ​​model, various appearance defects can be more accurately identified, improving the accuracy and reliability of detection. In addition, the AI ​​model can automatically process and analyze images, greatly reducing manual intervention and improving detection efficiency. In addition, the AI ​​model can be continuously improved and upgraded with the introduction of more defect samples, adapting to new defect types and changes, and improving the intelligence of detection.

[0057] In a further preferred embodiment, the auxiliary material includes supporting foam, and when the auxiliary material in the batch of mobile phone battery cover printing materials is subjected to machine vision inspection, it includes: obtaining the appearance picture of the supporting foam of the mobile phone battery cover, and performing machine vision identification on the size of the supporting foam of the mobile phone battery cover; comparing the identified size of the supporting foam with the preset compliance size, and when the comparison value of the size of the supporting foam with the preset compliance size is less than the preset negligible deviation value, it is determined that the supporting foam does not have a size defect, and the supporting foam without a size defect is transported to the packaging station for packaging the bare plate after printing; when the comparison value of the size of the supporting foam with the preset compliance size is greater than the preset negligible deviation value, it is determined that the supporting foam has a size defect, and the supporting foam with a size defect is isolated. It should be noted that the size of the supporting foam directly affects its function in the packaging process, such as fixing and protecting the mobile phone battery cover. If the size is unqualified, it will affect the packaging effect and even damage the product. In this embodiment, by strictly testing the size of the supporting foam, it is ensured that it can play the expected role during use and improve the quality and reliability of the packaging. In addition, in this embodiment, by using machine vision inspection, a large amount of support foam can be processed in a short time, thereby improving the inspection speed and efficiency. In addition, if support foam with unqualified size is used for packaging, it will lead to an increase in the defective rate. By detecting and isolating unqualified products in advance, the defective rate can be reduced.

[0058] It should be pointed out that the above embodiments are only preferred specific implementation modes of the present invention, and the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by any technician familiar with the technical field within the technical scope disclosed by the present invention should be covered within the protection scope of the present invention. The protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A visual inspection method for mobile phone battery cover printing materials based on the hundred-grid knife test, characterized in that: include: Randomly sampling from a batch of mobile phone battery cover printing materials to obtain a test sample of a film sheet of the mobile phone battery cover, and tearing off a protective film of the film sheet in the test sample of the film sheet to obtain a bare sheet to be tested; Using a grid knife to cut grid-shaped scratches on the surface of the bare plate to be tested, and using tape to stick the grid area of ​​the grid-shaped scratches to obtain a bare plate showing the coating peeling state; Obtaining an appearance picture of a bare plate showing a coating peeling state, performing machine vision recognition on the coating peeling defect of the bare plate through the appearance picture of the bare plate showing a coating peeling state, and counting the number of defects of the bare plate with coating peeling defects, and when the number of defects of the bare plate exceeds a preset bare plate defect threshold, returning the batch of mobile phone battery cover printing materials; The coating peeling defects on the bare plate include: complete peeling of the coating, partial peeling of the coating and cracking of the coating; the complete peeling of the coating is manifested as the coating in the grid area is completely peeled off from the substrate; the partial peeling of the coating is manifested as the coating in the grid area is partially peeled off, and the substrate is partially exposed; the coating cracking is manifested as fine cracks appearing on the coating surface in the grid area; the AI ​​recognition model for identifying the coating peeling defects of the bare plate adopts the visual Transformer in the Transformer model, and the visual Transformer is trained by the bare plate pictures of the coating completely peeling off, the coating partially peeling off and the coating cracking. After the training is successful, the appearance picture of the bare plate currently being detected is input into the trained visual Transformer to identify the coating peeling defects of the bare plate; When the defect amount of the bare sheet with coating peeling defect is lower than the preset bare sheet defect threshold, the auxiliary materials in the batch of mobile phone battery cover printing materials are subjected to machine vision inspection to obtain qualified auxiliary materials for packaging the printed bare sheet, and unqualified auxiliary materials are isolated; in each batch of mobile phone battery cover printing materials, each film sheet is matched with the corresponding auxiliary materials; The auxiliary materials include PET protective films. When the auxiliary materials in the batch of mobile phone battery cover printing materials are subjected to machine vision inspection, the method includes: obtaining an appearance picture of the PET protective film of the mobile phone battery cover, and performing machine vision identification of appearance defects of the PET protective film through the appearance picture of the PET protective film, so as to obtain a PET protective film without appearance defects for film packaging of the bare plate after printing, and performing isolation treatment on the PET protective film with appearance defects; the appearance defects of the PET protective film include scratches, bubbles and pollution; After obtaining the appearance picture of the PET protective film of the mobile phone battery cover, it also includes: performing machine vision recognition on the size of the PET protective film of the mobile phone battery cover from the appearance picture of the PET protective film; comparing the identified size of the PET protective film with a preset compliant size, and when the comparison value between the size of the PET protective film and the preset compliant size is less than a preset negligible deviation value, it is determined that the PET protective film has no size defects, and the PET protective film without size defects and appearance defects is transported to a packaging station for film packaging of the printed bare sheet; when the comparison value between the size of the PET protective film and the preset compliant size is greater than a preset negligible deviation value, it is determined that the PET protective film has a size defect, and the PET protective film with the size defect is isolated.

2. The visual inspection method for printed materials of mobile phone battery covers based on the hundred-grid knife test as claimed in claim 1, characterized in that: Use a grid knife to cut grid-like scratches on the surface of the bare plate to be tested, including: Fix the bare plate to be tested on the workbench, and use a grid knife to evenly cut the surface of the bare plate to form a set of parallel scratches; The grid knife is rotated 90 degrees and cut again to form a group of vertical scratches, wherein the group of vertical scratches and the group of parallel scratches are vertically intersected to form grid-like scratches.

3. The visual inspection method for mobile phone battery cover printing materials based on the hundred-grid knife test as claimed in claim 2 is characterized in that: In the group of parallel scratches, the distance between each scratch is 1-2 mm; in the group of vertical scratches, the distance between each scratch is 1-2 mm.

4. The visual inspection method for mobile phone battery cover printing materials based on the hundred-grid knife test as claimed in claim 2 is characterized in that: The depth of each scratch in the set of parallel scratches is consistent with the depth of each scratch in the set of perpendicular scratches.

5. The visual inspection method for mobile phone battery cover printing materials based on the hundred-grid knife test as claimed in claim 2, characterized in that: Fix the bare plate to be tested on the workbench and use a grid knife to evenly cut the surface of the bare plate to form a set of parallel scratches, including: The bare plate to be inspected is transported to a loading station of a workbench, and when the bare plate to be inspected on the loading station is detected, the adjustable clamp is controlled to clamp and fix the bare plate to be inspected; After the bare plate to be inspected is fixed, the cutting head equipped with a grid knife is controlled to cut the surface of the bare plate at a preset parallel cutting route and cutting depth to form a group of parallel scratches.

6. The visual inspection method for mobile phone battery cover printing materials based on the hundred-grid knife test as claimed in claim 5 is characterized in that: After the group of parallel scratch cutting is completed, the cutting head equipped with the grid knife is controlled to cut the surface of the bare plate with a preset vertical cutting route and cutting depth to form a group of vertical scratches.

7. The visual inspection method for mobile phone battery cover printing materials based on the hundred-grid knife test according to any one of claims 1 to 6, characterized in that: Tape the scratched grid area of ​​the grid, including: A glue sticking machine is used to stick one end of the adhesive tape to an edge of the grid area, and a pressure roller of the glue sticking machine is controlled to move along the surface of the adhesive tape to automatically compact the adhesive tape to fit tightly on the entire grid area; After the glue sticking machine compacts the adhesive tape on the grid area, the adhesive tape tearing arm of the glue sticking machine is controlled to tear off the adhesive tape attached to the entire grid area.

Images