Graphene heat-conducting film material inferior product screening system based on image recognition

Through the screening system for poor product of graphene thermal film based on image recognition, the surface inhomogeneity, defects and impurities of graphene thermal film are detected, and the problem of failure to comprehensively detect the surface quality of graphene thermal film materials in the prior art is solved, and the problem of failure to fully detect the surface quality of graphene thermal film materials is realized. More comprehensive quality assessment and inferior product screening have been achieved, improving product reliability and production efficiency.

CN119006458APending Publication Date: 2024-11-22ZHEJIANG LINGTUO TECH CO LTD

Patent Information

Application Number
CN202411480722.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-10-23
Publication Date
2024-11-22

AI Technical Summary

Technical Problem

The existing methods for detecting graphene thermal film materials mainly focus on thermal conductivity detection, and do not involve surface quality detection and inferior product screening, resulting in incomplete quality evaluation, which cannot guarantee the surface quality of graphene thermal film materials, affecting its heat dissipation performance and products. reliability.

Method used

The poor product screening system of graphene thermal conductive film materials based on image recognition is used to detect the surface inhomogeneity, defects and quality evaluation modules of graphene thermal conductive films through image acquisition, preprocessing, unevenness analysis, defects and quality evaluation modules. Impurities, generate quality inspection reports, and screen out inferior products.

Benefits of technology

The quality evaluation system of graphene thermal film materials has been improved to ensure surface quality, avoid degradation of heat dissipation performance and reduced product reliability, and help manufacturers optimize processes and improve production efficiency and product quality.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119006458A_ABST
    Figure CN119006458A_ABST
Patent Text Reader

Abstract

The invention relates to the field of graphene heat-conducting film material detection, and particularly discloses a graphene heat-conducting film material inferior product screening system based on image recognition. Based on an image of a graphene heat-conducting film, a graphene heat-conducting film surface thickness non-uniform coefficient and a graphene heat-conducting film component distribution non-uniform coefficient are obtained; analyzing the surface non-uniformity of the graphene heat-conducting film; acquiring surface hole, crack, wrinkle, ripple and edge defect information of the graphene heat-conducting film, and analyzing surface defects of the graphene heat-conducting film; acquiring surface foreign matter, oxidation and corrosion information of the graphene heat-conducting film, and analyzing surface impurities of the graphene heat-conducting film; and further comprehensively evaluating the surface quality of the graphene heat-conducting film, judging whether the surface quality of the graphene heat-conducting film is qualified or not, screening inferior products, generating a quality inspection report, and detecting and evaluating the appearance of the graphene heat-conducting film from multiple dimensions, so that the surface quality of the graphene heat-conducting film material is guaranteed.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention relates to the field of graphene thermal conductive film material detection, and in particular to a graphene thermal conductive film material inferior product screening system based on image recognition. Background Art

[0002] With the continuous development of electronic technology, the integration of electronic equipment is getting higher and higher, the power is increasing, and the heating problem is becoming more and more prominent. Efficient heat dissipation materials are crucial to ensure the performance, stability and service life of electronic equipment. Traditional heat dissipation materials such as copper and aluminum are gradually unable to meet the heat dissipation needs in some high-end application scenarios. Graphene, as a new material with excellent performance, has extremely high thermal conductivity, electrical conductivity, good mechanical strength and flexibility, etc. It has shown great application potential in many fields such as electronics, energy, aerospace, etc., which makes graphene thermal conductive film materials a research hotspot and key development direction in the field of thermal management.

[0003] Testing graphene thermal conductive film materials can not only accurately evaluate their performance and ensure that the thermal conductivity of the product meets the design and application requirements, but also discover potential defects, timely screen out defective inferior products, prevent products with quality problems from entering the market, and improve the overall quality level of products. It also helps manufacturers understand the stability and reliability of the production process, discover problems and deficiencies in the process, optimize and improve the production process, improve production efficiency and product quality, and reduce production costs, which is of great significance.

[0004] However, the existing graphene thermal conductive film material detection methods still have some limitations and shortcomings in practical applications.

[0005] For example, the existing Chinese patent with the authorization announcement number CN110887864B discloses a test method for graphene thermal conductive film, including the following steps: sampling of the sample to be tested, creation of the test environment, placement of the sample to be tested, placement of the heating block, placement of the temperature measuring element, collection of temperature data, acquisition of multiple sets of data, and analysis of temperature data. The invention can accurately test the thermal conductivity of the graphene film and distinguish the performance differences of graphene films of different thicknesses. It is simple to operate, less time-consuming, and has high test efficiency, and is suitable for large-scale monitoring and testing.

[0006] The above-mentioned patent mainly focuses on the thermal conductivity of graphene thermal conductive film materials, but does not involve the detection of surface quality of graphene thermal conductive film materials and the screening of inferior products, which makes the quality assessment system of graphene thermal conductive film materials incomplete and unable to guarantee the surface quality of graphene thermal conductive film materials. Poor surface quality of graphene thermal conductive film materials may lead to a decrease in the heat dissipation performance of the graphene thermal conductive film, affect its combination with other components, and even reduce the reliability and service life of the product. Summary of the invention

[0007] In view of the above problems, the present invention proposes a graphene thermal conductive film material inferior product screening system based on image recognition, which realizes the function of detecting graphene thermal conductive film materials.

[0008] The technical solution adopted by the present invention to solve its technical problem is: the present invention provides a graphene thermal conductive film material inferior product screening system based on image recognition, including: a graphene thermal conductive film image acquisition module: used for randomly sampling the graphene thermal conductive film of the current production batch, obtaining each graphene thermal conductive film sample, and further acquiring the image of each graphene thermal conductive film sample.

[0009] Graphene thermal conductive film image preprocessing module: used to preprocess the images of each graphene thermal conductive film sample, wherein the preprocessing includes graying, denoising and contrast enhancement.

[0010] Graphene thermal conductive film surface non-uniformity analysis module: used to obtain the thickness non-uniformity coefficient and component distribution non-uniformity coefficient of the surface of each graphene thermal conductive film sample according to the image of each graphene thermal conductive film sample, and analyze the surface non-uniformity index of each graphene thermal conductive film sample.

[0011] Graphene thermal conductive film surface defect analysis module: used to obtain the surface defect information of each graphene thermal conductive film sample based on the image of each graphene thermal conductive film sample, wherein the surface defect information includes the number of holes, crack length, wrinkle area, corrugation area, and edge defect degree, and analyze the surface defect index of each graphene thermal conductive film sample.

[0012] Graphene thermal conductive film surface impurity analysis module: used to obtain the surface impurity information of each graphene thermal conductive film sample based on the image of each graphene thermal conductive film sample, wherein the surface impurity information includes the surface foreign matter area, oxidation area and corrosion area, and analyze the surface impurity index of each graphene thermal conductive film sample.

[0013] Graphene thermal conductive film surface quality evaluation module: used to analyze the surface quality evaluation index of each graphene thermal conductive film sample according to the surface unevenness index, surface defect index and surface impurity index of each graphene thermal conductive film sample.

[0014] Graphene thermal conductive film inferior product screening and processing module: used to judge whether the surface quality of each graphene thermal conductive film sample is qualified according to the surface quality evaluation index of each graphene thermal conductive film sample, screen out the inferior graphene thermal conductive film, and generate the quality inspection report of the current production batch of graphene thermal conductive film for feedback.

[0015] Database: used to store sample images of various adverse characteristics on the surface of graphene thermal conductive films.

[0016] On the basis of the above-mentioned embodiment, the specific working process of the graphene thermal conductive film surface non-uniformity analysis module includes: marking each detection point on the surface of the graphene thermal conductive film according to a preset principle, obtaining the thickness of each detection point on the surface of each graphene thermal conductive film sample according to the image of each graphene thermal conductive film sample, and recording it as ,in Indicates The number of the graphene thermal conductive film samples, , Indicates The number of the test point, .

[0017] By analyzing the formula Obtain the thickness unevenness coefficient of each graphene thermal conductive film sample surface ,in represents the number of detection points, Indicates The surface of the graphene thermal conductive film sample The thickness at each test point, Represents the preset thickness deviation threshold between detection points on the surface of the graphene thermal conductive film sample.

[0018] According to the images of each graphene thermal conductive film sample, the gray value, brightness and texture of each region of each graphene thermal conductive film sample image are obtained. If the difference between the gray value, brightness or texture of a region of a graphene thermal conductive film sample image and its adjacent region is greater than the corresponding set threshold, the region is recorded as an inconsistent region. The cumulative number of inconsistent regions of each graphene thermal conductive film sample image is counted and recorded as .

[0019] By analyzing the formula Obtain the component distribution unevenness coefficient on the surface of each graphene thermal conductive film sample ,in Indicates the impact factor corresponding to the preset unit quantity inconsistency area.

[0020] On the basis of the above-mentioned embodiment, the specific working process of the graphene thermal conductive film surface non-uniformity analysis module further includes: calculating the thickness non-uniformity coefficient of each graphene thermal conductive film sample surface and the coefficient of component distribution heterogeneity Substitute into the analysis formula Get the surface unevenness index of each graphene thermal conductive film sample ,in They represent the weight factors of the preset thickness unevenness coefficient and component distribution unevenness coefficient, .

[0021] Based on the above embodiments, the specific working process of the graphene thermal conductive film surface defect analysis module includes: extracting sample images of various types of bad characteristics on the surface of the graphene thermal conductive film stored in the database, and screening to obtain sample images of holes, cracks, wrinkles and ripples on the surface of the graphene thermal conductive film.

[0022] The image of each graphene thermal conductive film sample is compared with the sample image of the holes on the surface of the graphene thermal conductive film. If the similarity between the image of a certain area in a graphene thermal conductive film sample image and the sample image of the holes on the surface of the graphene thermal conductive film is greater than a preset similarity threshold, the area in the graphene thermal conductive film sample image is recorded as the hole area, and the number of holes in each graphene thermal conductive film sample is counted and recorded as .

[0023] Similarly, according to the analysis method of the number of holes in each graphene thermal conductive film sample, the crack length, wrinkle area, and ripple area of ​​each graphene thermal conductive film sample are obtained and recorded as .

[0024] According to the sample images of various types of bad characterizations on the surface of the graphene thermal conductive film, sample images of edge damage and burrs of the graphene thermal conductive film are screened, and the images of each graphene thermal conductive film sample are compared with the sample images of edge damage and burrs of the graphene thermal conductive film to obtain the damage area and burr area of ​​the edge of each graphene thermal conductive film sample, and substitute them into the preset relationship function between the edge damage area and burr area of ​​the graphene thermal conductive film and the edge defect degree to obtain the edge defect degree of each graphene thermal conductive film sample, which is recorded as .

[0025] On the basis of the above-mentioned embodiment, the specific working process of the graphene thermal conductive film surface defect analysis module further includes: calculating the number of holes of each graphene thermal conductive film sample; , crack length , wrinkle area , corrugation area , Edge defect degree Substitute into the analysis formula Get the surface defect index of each graphene thermal conductive film sample ,in , They represent the influence factors corresponding to the preset number of unit holes and unit crack length, They respectively represent the thresholds of the preset wrinkle area, corrugation area and edge defect degree.

[0026] On the basis of the above-mentioned embodiment, the specific working process of the graphene thermal conductive film surface impurity analysis module includes: using image processing technology to obtain each gray value of each graphene thermal conductive film sample image, and compare it with a preset reference range of the gray value of the graphene thermal conductive film image. If a gray value of a certain graphene thermal conductive film sample image does not belong to the reference range of the gray value of the graphene thermal conductive film image, then the area where the gray value is located is recorded as a foreign matter area, and the area of ​​each foreign matter area on the surface of each graphene thermal conductive film sample is obtained and accumulated to obtain the surface foreign matter area of ​​each graphene thermal conductive film sample, which is recorded as .

[0027] According to the sample images of various types of bad characteristics on the surface of the graphene thermal conductive film, the sample images of oxidation and corrosion of the graphene thermal conductive film are screened, and the images of each graphene thermal conductive film sample are compared with the sample images of oxidation and corrosion of the graphene thermal conductive film to obtain the oxidation area and corrosion area of ​​each graphene thermal conductive film sample, which are recorded as .

[0028] On the basis of the above-mentioned embodiment, the specific working process of the graphene thermal conductive film surface impurity analysis module further includes: calculating the surface foreign matter area of ​​each graphene thermal conductive film sample; , Oxidation area and corrosion area Substitute into the analysis formula Get the surface impurity index of each graphene thermal conductive film sample ,in represents a natural constant, They represent the influence factors corresponding to the preset unit foreign matter area, unit oxidation area and unit corrosion area, respectively. They represent the weights corresponding to the preset foreign matter area, oxidation area and corrosion area respectively. .

[0029] Compared with the prior art, the inferior graphene thermal conductive film material screening system based on image recognition described in the present invention has the following beneficial effects: 1. The present invention detects and evaluates the surface quality of the graphene thermal conductive film from multiple dimensions such as surface unevenness, surface defects and surface impurities of the graphene thermal conductive film, and then improves the quality evaluation system of the graphene thermal conductive film material, thereby ensuring the surface quality of the graphene thermal conductive film material and avoiding the situation where the heat dissipation performance of the graphene thermal conductive film, product reliability and service life are reduced due to poor surface quality.

[0030] 2. The present invention detects various indicators of the appearance level of the graphene thermal conductive film, comprehensively evaluates the surface quality of the graphene thermal conductive film to determine whether it is qualified, and further generates a quality inspection report based on the production qualification rate of the graphene thermal conductive film and the proportion of inferior products of various appearance defect types, which is conducive to tracing the quality problems of the graphene thermal conductive film, and helps production enterprises understand the stability and reliability of the production process, discover problems and deficiencies in the process, and optimize and improve the production process. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for describing the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0032] Figure 1 This is a system module connection diagram of the present invention. DETAILED DESCRIPTION

[0033] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0034] See also Figure 1 As shown, the present invention provides a graphene thermal conductive film material inferior product screening system based on image recognition, including a graphene thermal conductive film image acquisition module, a graphene thermal conductive film image preprocessing module, a graphene thermal conductive film surface unevenness analysis module, a graphene thermal conductive film surface defect analysis module, a graphene thermal conductive film surface impurity analysis module, a graphene thermal conductive film surface quality assessment module, a graphene thermal conductive film inferior product screening processing module, and a database.

[0035] The graphene thermal conductive film image preprocessing module is respectively connected to the graphene thermal conductive film image acquisition module, the graphene thermal conductive film surface non-uniformity analysis module, the graphene thermal conductive film surface defect analysis module and the graphene thermal conductive film surface impurity analysis module; the graphene thermal conductive film surface quality assessment module is respectively connected to the graphene thermal conductive film surface non-uniformity analysis module, the graphene thermal conductive film surface defect analysis module and the graphene thermal conductive film surface impurity analysis module; the graphene thermal conductive film inferior product screening and processing module is connected to the graphene thermal conductive film surface quality assessment module; and the database is respectively connected to the graphene thermal conductive film surface defect analysis module and the graphene thermal conductive film surface impurity analysis module.

[0036] The graphene thermal conductive film image acquisition module is used to randomly sample the graphene thermal conductive film of the current production batch, obtain each graphene thermal conductive film sample, and further acquire an image of each graphene thermal conductive film sample.

[0037] Furthermore, the specific working process of the graphene thermal conductive film image acquisition module is: randomly extracting a set number of graphene thermal conductive films from the current production batch of graphene thermal conductive films according to a preset random sampling principle to obtain each graphene thermal conductive film sample, and collecting the image of each graphene thermal conductive film sample through an imaging device.

[0038] As a preferred solution, images of each graphene thermal conductive film sample can be collected by imaging equipment such as an optical microscope, a scanning electron microscope, and an atomic force microscope.

[0039] In a specific embodiment, a high-definition camera is installed in a production line of a graphene thermal conductive film, and the interval at which the high-definition camera collects images is set to obtain images of each graphene thermal conductive film sample.

[0040] The graphene thermal conductive film image preprocessing module is used to preprocess the image of each graphene thermal conductive film sample, wherein the preprocessing includes graying, denoising and contrast enhancement.

[0041] As a preferred solution, image preprocessing operations such as grayscale, denoising and contrast enhancement are relatively mature existing technologies and will not be described in detail here.

[0042] The graphene thermal conductive film surface non-uniformity analysis module is used to obtain the thickness non-uniformity coefficient and the component distribution non-uniformity coefficient of the surface of each graphene thermal conductive film sample according to the image of each graphene thermal conductive film sample, and analyze the surface non-uniformity index of each graphene thermal conductive film sample.

[0043] Furthermore, the specific working process of the graphene thermal conductive film surface non-uniformity analysis module includes: marking each detection point on the surface of the graphene thermal conductive film according to a preset principle, obtaining the thickness of each detection point on the surface of each graphene thermal conductive film sample according to the image of each graphene thermal conductive film sample, and recording it as ,in Indicates The number of the graphene thermal conductive film samples, , Indicates The number of the test point, .

[0044] By analyzing the formula Obtain the thickness unevenness coefficient of each graphene thermal conductive film sample surface ,in represents the number of detection points, Indicates The surface of the graphene thermal conductive film sample The thickness at each test point, Represents the preset thickness deviation threshold between detection points on the surface of the graphene thermal conductive film sample.

[0045] As a preferred solution, the thickness of the graphene thermal conductive film sample can be identified to be inconsistent, that is, some areas are thick and some areas are thin, which may be caused by uneven coating during the preparation process, unstable drying conditions, etc. For example, under an optical microscope or electron microscope image of a graphene thermal conductive film sample, the undulations and thickness differences on the film surface can be clearly observed, which in turn affects the uniform conduction of heat.

[0046] According to the images of each graphene thermal conductive film sample, the gray value, brightness and texture of each region of each graphene thermal conductive film sample image are obtained. If the difference between the gray value, brightness or texture of a region of a graphene thermal conductive film sample image and its adjacent region is greater than the corresponding set threshold, the region is recorded as an inconsistent region. The cumulative number of inconsistent regions of each graphene thermal conductive film sample image is counted and recorded as .

[0047] As a preferred solution, the graphene thermal conductive film should have a uniform distribution of graphene, but inferior products may show graphene aggregation or uneven dispersion in the image. The graphene content in the aggregated area is too high, while the graphene content in the sparsely dispersed area is insufficient, which will lead to local differences in thermal conductivity, which are manifested as differences in color, brightness or texture in different areas on the image.

[0048] By analyzing the formula Obtain the component distribution unevenness coefficient on the surface of each graphene thermal conductive film sample ,in Indicates the impact factor corresponding to the preset unit quantity inconsistency area.

[0049] Furthermore, the specific working process of the graphene thermal conductive film surface non-uniformity analysis module also includes: calculating the thickness non-uniformity coefficient of each graphene thermal conductive film sample surface and the coefficient of component distribution heterogeneity Substitute into the analysis formula Get the surface unevenness index of each graphene thermal conductive film sample ,in They represent the weight factors of the preset thickness unevenness coefficient and component distribution unevenness coefficient, .

[0050] The graphene thermal conductive film surface defect analysis module is used to obtain the surface defect information of each graphene thermal conductive film sample according to the image of each graphene thermal conductive film sample, wherein the surface defect information includes the number of holes, crack length, wrinkle area, corrugation area, and edge defect degree, and analyze the surface defect index of each graphene thermal conductive film sample.

[0051] Furthermore, the specific working process of the graphene thermal conductive film surface defect analysis module includes: extracting sample images of various types of bad characteristics on the surface of the graphene thermal conductive film stored in the database, and screening to obtain sample images of holes, cracks, wrinkles and ripples on the surface of the graphene thermal conductive film.

[0052] The image of each graphene thermal conductive film sample is compared with the sample image of the holes on the surface of the graphene thermal conductive film. If the similarity between the image of a certain area in a graphene thermal conductive film sample image and the sample image of the holes on the surface of the graphene thermal conductive film is greater than a preset similarity threshold, the area in the graphene thermal conductive film sample image is recorded as the hole area, and the number of holes in each graphene thermal conductive film sample is counted and recorded as .

[0053] Similarly, according to the analysis method of the number of holes in each graphene thermal conductive film sample, the crack length, wrinkle area, and ripple area of ​​each graphene thermal conductive film sample are obtained and recorded as .

[0054] According to the sample images of various types of bad characterizations on the surface of the graphene thermal conductive film, sample images of edge damage and burrs of the graphene thermal conductive film are screened, and the images of each graphene thermal conductive film sample are compared with the sample images of edge damage and burrs of the graphene thermal conductive film to obtain the damage area and burr area of ​​the edge of each graphene thermal conductive film sample, and substitute them into the preset relationship function between the edge damage area and burr area of ​​the graphene thermal conductive film and the edge defect degree to obtain the edge defect degree of each graphene thermal conductive film sample, which is recorded as .

[0055] As a preferred solution, in the graphene thermal conductive film image, holes appear as blank areas or circular or elliptical gaps on the film, and cracks appear as linear cracks or gaps.

[0056] As a preferred solution, if the graphene thermal conductive film is subjected to uneven stress or temperature during the preparation or processing, wrinkles and ripples may occur. In the graphene thermal conductive film image, these appear as ups and downs and bends on the film surface, which will affect the fit between the film and the heating element and reduce the heat dissipation effect.

[0057] As a preferred solution, problems such as uneven edges, damage or burrs on graphene thermal conductive films are also common manifestations of inferior graphene thermal conductive films. This may be caused by improper operation during the cutting or processing process. Edge defects will affect the installation and performance of the film.

[0058] Furthermore, the specific working process of the graphene thermal conductive film surface defect analysis module also includes: calculating the number of holes in each graphene thermal conductive film sample , crack length , wrinkle area , corrugation area , Edge defect degree Substitute into the analysis formula Get the surface defect index of each graphene thermal conductive film sample ,in , They represent the influence factors corresponding to the preset number of unit holes and unit crack length, They respectively represent the thresholds of the preset wrinkle area, corrugation area and edge defect degree.

[0059] The graphene thermal conductive film surface impurity analysis module is used to obtain the surface impurity information of each graphene thermal conductive film sample according to the image of each graphene thermal conductive film sample, wherein the surface impurity information includes the surface foreign matter area, oxidation area and corrosion area, and analyze the surface impurity index of each graphene thermal conductive film sample.

[0060] Furthermore, the specific working process of the graphene thermal conductive film surface impurity analysis module includes: using image processing technology to obtain each gray value of each graphene thermal conductive film sample image, and comparing it with a preset reference range of the gray value of the graphene thermal conductive film image. If a gray value of a certain graphene thermal conductive film sample image does not belong to the reference range of the gray value of the graphene thermal conductive film image, then the area where the gray value is located is recorded as a foreign matter area, and the area of ​​each foreign matter area on the surface of each graphene thermal conductive film sample is obtained and accumulated to obtain the surface foreign matter area of ​​each graphene thermal conductive film sample, which is recorded as .

[0061] According to the sample images of various types of bad characteristics on the surface of the graphene thermal conductive film, the sample images of oxidation and corrosion of the graphene thermal conductive film are screened, and the images of each graphene thermal conductive film sample are compared with the sample images of oxidation and corrosion of the graphene thermal conductive film to obtain the oxidation area and corrosion area of ​​each graphene thermal conductive film sample, which are recorded as .

[0062] As a preferred solution, foreign particles different from the material of the graphene thermal conductive film itself may appear in the graphene thermal conductive film image. These particles may be impurities or contaminants mixed in during the preparation process, which will hinder the transfer of heat and reduce the thermal conductivity. They appear as bright or dark spots of different shapes and sizes on the graphene thermal conductive film image.

[0063] As a preferred solution, if the graphene thermal conductive film is oxidized or corroded, color changes or surface corrosion products may be seen in the graphene thermal conductive film image, such as yellowing or darkening, which will affect the thermal conductivity and stability of the film.

[0064] Furthermore, the specific working process of the graphene thermal conductive film surface impurity analysis module also includes: calculating the surface foreign matter area of ​​each graphene thermal conductive film sample , Oxidation area and corrosion area Substitute into the analysis formula Get the surface impurity index of each graphene thermal conductive film sample ,in represents a natural constant, They represent the influence factors corresponding to the preset unit foreign matter area, unit oxidation area and unit corrosion area, respectively. They represent the weights corresponding to the preset foreign matter area, oxidation area and corrosion area respectively. .

[0065] The graphene thermal conductive film surface quality evaluation module is used to analyze the surface quality evaluation index of each graphene thermal conductive film sample according to the surface unevenness index, surface defect index and surface impurity index of each graphene thermal conductive film sample.

[0066] Furthermore, the specific working process of the graphene thermal conductive film surface quality evaluation module is: substituting the surface unevenness index, surface defect index, and surface impurity index of each graphene thermal conductive film sample into the preset relationship function between the surface unevenness index, surface defect index, surface impurity index and surface quality evaluation index of the graphene thermal conductive film to obtain the surface quality evaluation index of each graphene thermal conductive film sample.

[0067] As a preferred solution, the larger the surface unevenness index, the larger the surface defect index, and the larger the surface impurity index of the graphene thermal conductive film, the smaller the surface quality evaluation index.

[0068] It should be noted that the present invention detects and evaluates the surface quality of the graphene thermal conductive film from multiple dimensions such as surface unevenness, surface defects and surface impurities of the graphene thermal conductive film, and then improves the quality evaluation system of the graphene thermal conductive film material, thereby ensuring the surface quality of the graphene thermal conductive film material and avoiding the situation where poor surface quality causes the heat dissipation performance of the graphene thermal conductive film to decrease, and the product reliability and service life to decrease.

[0069] The inferior graphene thermal conductive film screening and processing module is used to judge whether the surface quality of each graphene thermal conductive film sample is qualified according to the surface quality evaluation index of each graphene thermal conductive film sample, screen out the inferior graphene thermal conductive film, and generate a quality inspection report for the current production batch of graphene thermal conductive films for feedback.

[0070] Furthermore, the specific working process of the inferior graphene thermal conductive film screening and processing module is: comparing the surface quality evaluation index of each graphene thermal conductive film sample with a preset surface quality evaluation index threshold; if the surface quality evaluation index of a certain graphene thermal conductive film sample is less than the preset surface quality evaluation index threshold, the surface quality of the graphene thermal conductive film sample is unqualified, and it is recorded as an inferior graphene thermal conductive film; statistics are collected on the inferior graphene thermal conductive film samples, and the qualified rate of the graphene thermal conductive film samples is further analyzed, and it is used as the qualified rate of the current production batch of graphene thermal conductive films.

[0071] The surface unevenness index, surface defect index and surface impurity index of each graphene thermal conductive film sample are compared with their corresponding set thresholds, the number of graphene thermal conductive film samples with surface unevenness, surface defects and surface impurities are analyzed, and the proportion of graphene thermal conductive film samples with surface unevenness, surface defects and surface impurities is obtained, which is used as the proportion of graphene thermal conductive film with surface unevenness, surface defects and surface impurities in the current production batch of graphene thermal conductive film.

[0072] Based on the qualified rate of the current production batch of graphene thermal conductive films and the proportion of graphene thermal conductive films with uneven surfaces, surface defects and surface impurities, a quality inspection report of the current production batch of graphene thermal conductive films is generated and feedback is provided.

[0073] It should be noted that the present invention detects various indicators of the appearance level of the graphene thermal conductive film, comprehensively evaluates the surface quality of the graphene thermal conductive film to determine whether it is qualified, and further generates a quality inspection report based on the production qualification rate of the graphene thermal conductive film and the proportion of inferior products of each type of appearance defect, which is conducive to tracing the quality problems of the graphene thermal conductive film, and helps production enterprises understand the stability and reliability of the production process, discover problems and deficiencies in the process, and optimize and improve the production process.

[0074] The database is used to store sample images of various types of adverse characteristics on the surface of the graphene thermal conductive film.

[0075] The above contents are merely examples and explanations of the concept of the present invention. Those skilled in the art may make various modifications or additions to the specific embodiments described or replace them in a similar manner. As long as they do not deviate from the concept of the invention or exceed the scope defined by the present invention, they shall all fall within the protection scope of the present invention.

Claims

1. A graphene thermal conductive film material inferior product screening system based on image recognition, characterized in that: include: Graphene thermal conductive film image acquisition module: used to randomly sample the graphene thermal conductive film of the current production batch, obtain each graphene thermal conductive film sample, and further collect images of each graphene thermal conductive film sample; Graphene thermal conductive film image preprocessing module: used to preprocess the images of each graphene thermal conductive film sample, wherein the preprocessing includes graying, denoising and contrast enhancement; Graphene thermal conductive film surface non-uniformity analysis module: used to obtain the thickness non-uniformity coefficient and component distribution non-uniformity coefficient of the surface of each graphene thermal conductive film sample according to the image of each graphene thermal conductive film sample, and analyze the surface non-uniformity index of each graphene thermal conductive film sample; Graphene thermal conductive film surface defect analysis module: used to obtain the surface defect information of each graphene thermal conductive film sample according to the image of each graphene thermal conductive film sample, wherein the surface defect information includes the number of holes, crack length, wrinkle area, corrugation area, edge defect degree, and analyze the surface defect index of each graphene thermal conductive film sample; Graphene thermal conductive film surface impurity analysis module: used to obtain surface impurity information of each graphene thermal conductive film sample according to the image of each graphene thermal conductive film sample, wherein the surface impurity information includes the surface foreign matter area, oxidation area and corrosion area, and analyze the surface impurity index of each graphene thermal conductive film sample; Graphene thermal conductive film surface quality evaluation module: used to analyze the surface quality evaluation index of each graphene thermal conductive film sample according to the surface unevenness index, surface defect index and surface impurity index of each graphene thermal conductive film sample; Graphene thermal conductive film inferior product screening and processing module: used to judge whether the surface quality of each graphene thermal conductive film sample is qualified according to the surface quality evaluation index of each graphene thermal conductive film sample, screen out each graphene thermal conductive film inferior product, and generate a quality inspection report of the current production batch of graphene thermal conductive film for feedback; Database: used to store sample images of various adverse characteristics on the surface of graphene thermal conductive films.

2. According to claim 1, a graphene thermal conductive film material inferior product screening system based on image recognition is characterized in that: The specific working process of the graphene thermal conductive film image acquisition module is as follows: According to a preset random sampling principle, a set number of graphene thermally conductive films are randomly selected from the graphene thermally conductive films of the current production batch to obtain each graphene thermally conductive film sample, and an image of each graphene thermally conductive film sample is collected by an imaging device.

3. The inferior graphene thermal conductive film material screening system based on image recognition according to claim 1 is characterized in that: The specific working process of the graphene thermal conductive film surface non-uniformity analysis module includes: According to the preset principle, each detection point is marked on the surface of the graphene thermal conductive film, and the thickness at each detection point on the surface of each graphene thermal conductive film sample is obtained according to the image of each graphene thermal conductive film sample, which is recorded as ,in Indicates The number of the graphene thermal conductive film samples, , Indicates The number of the test point, ; By analyzing the formula Obtain the thickness unevenness coefficient of each graphene thermal conductive film sample surface ,in represents the number of detection points, Indicates The surface of the graphene thermal conductive film sample The thickness at each test point, Indicates the preset deviation threshold of the thickness between the detection points on the surface of the graphene thermal conductive film sample; According to the images of each graphene thermal conductive film sample, the gray value, brightness and texture of each region of each graphene thermal conductive film sample image are obtained. If the difference between the gray value, brightness or texture of a region of a graphene thermal conductive film sample image and its adjacent region is greater than the corresponding set threshold, the region is recorded as an inconsistent region. The cumulative number of inconsistent regions of each graphene thermal conductive film sample image is counted and recorded as ; By analyzing the formula Obtain the component distribution unevenness coefficient on the surface of each graphene thermal conductive film sample ,in Indicates the impact factor corresponding to the preset unit quantity inconsistency area.

4. The inferior graphene thermal conductive film material screening system based on image recognition according to claim 3 is characterized in that: The specific working process of the graphene thermal conductive film surface non-uniformity analysis module also includes: The thickness unevenness coefficient of each graphene thermal conductive film sample surface and the coefficient of component distribution heterogeneity Substitute into the analysis formula Get the surface unevenness index of each graphene thermal conductive film sample ,in They represent the weight factors of the preset thickness unevenness coefficient and component distribution unevenness coefficient, .

5. The inferior graphene thermal conductive film material screening system based on image recognition according to claim 2 is characterized in that: The specific working process of the graphene thermal conductive film surface defect analysis module includes: Extract sample images of various types of bad characteristics on the surface of graphene thermal conductive film stored in the database, and screen out sample images of holes, cracks, wrinkles and ripples on the surface of graphene thermal conductive film; The image of each graphene thermal conductive film sample is compared with the sample image of the holes on the surface of the graphene thermal conductive film. If the similarity between the image of a certain area in a graphene thermal conductive film sample image and the sample image of the holes on the surface of the graphene thermal conductive film is greater than a preset similarity threshold, the area in the graphene thermal conductive film sample image is recorded as the hole area, and the number of holes in each graphene thermal conductive film sample is counted and recorded as ; Similarly, according to the analysis method of the number of holes in each graphene thermal conductive film sample, the crack length, wrinkle area, and ripple area of ​​each graphene thermal conductive film sample are obtained and recorded as ; According to the sample images of various types of bad characterizations on the surface of the graphene thermal conductive film, sample images of edge damage and burrs of the graphene thermal conductive film are screened, and the images of each graphene thermal conductive film sample are compared with the sample images of edge damage and burrs of the graphene thermal conductive film to obtain the damage area and burr area of ​​the edge of each graphene thermal conductive film sample, and substitute them into the preset relationship function between the edge damage area and burr area of ​​the graphene thermal conductive film and the edge defect degree to obtain the edge defect degree of each graphene thermal conductive film sample, which is recorded as .

6. The inferior graphene thermal conductive film material screening system based on image recognition according to claim 5 is characterized in that: The specific working process of the graphene thermal conductive film surface defect analysis module also includes: The number of holes in each graphene thermal conductive film sample , crack length , wrinkle area , corrugation area , Edge defect degree Substitute into the analysis formula Get the surface defect index of each graphene thermal conductive film sample ,in , They represent the influence factors corresponding to the preset number of unit holes and unit crack length, They respectively represent the thresholds of the preset wrinkle area, corrugation area and edge defect degree.

7. The inferior graphene thermal conductive film material screening system based on image recognition according to claim 2 is characterized in that: The specific working process of the graphene thermal conductive film surface impurity analysis module includes: The grayscale values ​​of each graphene thermal conductive film sample image are obtained by using image processing technology, and compared with the preset reference range of the grayscale value of the graphene thermal conductive film image. If a grayscale value of a graphene thermal conductive film sample image does not belong to the reference range of the grayscale value of the graphene thermal conductive film image, the area where the grayscale value is located is recorded as the foreign matter area, and the area of ​​each foreign matter area on the surface of each graphene thermal conductive film sample is obtained and accumulated to obtain the surface foreign matter area of ​​each graphene thermal conductive film sample, which is recorded as ; According to the sample images of various types of bad characteristics on the surface of the graphene thermal conductive film, the sample images of oxidation and corrosion of the graphene thermal conductive film are screened, and the images of each graphene thermal conductive film sample are compared with the sample images of oxidation and corrosion of the graphene thermal conductive film to obtain the oxidation area and corrosion area of ​​each graphene thermal conductive film sample, which are recorded as .

8. The inferior graphene thermal conductive film material screening system based on image recognition according to claim 7 is characterized in that: The specific working process of the graphene thermal conductive film surface impurity analysis module also includes: The surface foreign matter area of ​​each graphene thermal conductive film sample , Oxidation area and corrosion area Substitute into the analysis formula Get the surface impurity index of each graphene thermal conductive film sample ,in represents a natural constant, They represent the influence factors corresponding to the preset unit foreign matter area, unit oxidation area and unit corrosion area, respectively. They represent the weights corresponding to the preset foreign matter area, oxidation area and corrosion area respectively. .

9. The inferior graphene thermal conductive film material screening system based on image recognition according to claim 1, characterized in that: The specific working process of the graphene thermal conductive film surface quality assessment module is as follows: The surface unevenness index, surface defect index and surface impurity index of each graphene thermal conductive film sample are substituted into the preset relationship function between the surface unevenness index, surface defect index, surface impurity index and surface quality evaluation index of the graphene thermal conductive film to obtain the surface quality evaluation index of each graphene thermal conductive film sample.

10. The inferior graphene thermal conductive film material screening system based on image recognition according to claim 1, characterized in that: The specific working process of the graphene thermal conductive film inferior product screening and processing module is as follows: Compare the surface quality evaluation index of each graphene thermal conductive film sample with a preset surface quality evaluation index threshold value; if the surface quality evaluation index of a graphene thermal conductive film sample is less than the preset surface quality evaluation index threshold value, the surface quality of the graphene thermal conductive film sample is unqualified, and it is recorded as a bad graphene thermal conductive film; count the bad graphene thermal conductive film samples, further analyze the qualified rate of the graphene thermal conductive film samples, and use it as the qualified rate of the graphene thermal conductive film of the current production batch; The surface unevenness index, surface defect index, and surface impurity index of each graphene thermal conductive film sample are compared with the corresponding set threshold values, respectively, the number of graphene thermal conductive film samples with surface unevenness, surface defects, and surface impurities is analyzed, and the proportion of graphene thermal conductive film samples with surface unevenness, surface defects, and surface impurities is obtained, which is used as the proportion of graphene thermal conductive film with surface unevenness, surface defects, and surface impurities in the current production batch of graphene thermal conductive film; Based on the qualified rate of the current production batch of graphene thermal conductive films and the proportion of graphene thermal conductive films with uneven surfaces, surface defects and surface impurities, a quality inspection report of the current production batch of graphene thermal conductive films is generated and feedback is provided.

Citation Information

Patent Citations

  • A test method for graphene thermally conductive films

    CN110887864B

  • Surface flaw detecting method and device

    CN101419176A

  • Sheet inspection device

    CN105973909A

  • System and method for intelligently detecting coating film thickness uniformity of optical coating machine

    CN114322796A

  • Solar cell coating defect detection method

    CN114677384A

Cited By

  • Method for analyzing commodity package inspection based on AI algorithm and video acquisition

    CN119904445A

  • A method for evaluating the sintering quality of an artificial heat-conducting film

    CN119920378B