Diamond powder sand mold grade identification method and device

Abstract

The invention relates to a diamond powder sand mold grade identification method and device. The method comprises the steps that a to-be-recognized image collected by image collection equipment is obtained, and the to-be-recognized image comprises to-be-detected diamond powder particles; image recognition is conducted on the to-be-recognized image, a recognition result is obtained, and the recognition result represents a sand mold of the to-be-detected diamond powder particles; and determining the sharpness grade of the to-be-detected diamond powder according to the identification result. According to the scheme provided by the invention, the detection efficiency and the consistency between different batches can be improved, and the labor intensity of personnel is reduced.

Description

Technical Field

[0001] This application relates to the field of diamond wire technology, and in particular to a method and apparatus for identifying the grade of diamond powder. Background Technology

[0002] Electroplated diamond wire saws, also known as diamond wire saws, are widely used in silicon wafer cutting in the photovoltaic industry and are a key auxiliary material in silicon wafer cutting. With the continuous advancement of the photovoltaic industry towards larger wafers, thinner wires, and less wire consumption, the requirements for diamond wire cutting performance are becoming increasingly stringent. For example, with the application of thinner wires, the breaking tensile strength of the diamond wire is decreasing, and the corresponding cutting tension setting is reduced accordingly. However, the size of the silicon wafer and wire consumption do not decrease accordingly. According to the basic cutting principle: P (cutting pressure) = F (cutting tension) / S (base area), to maintain cutting capability, a smaller contact area is required under lower cutting tension conditions, which places higher demands on the morphology of the diamond micron powder.

[0003] In related technologies, the main method for testing diamond powder sand molds is to examine the diamond powder using an electron microscope and observe the morphological differences of the powder visually to count the different types of sand molds and then classify them by grade. However, the subjective judgment of the testers is strong, the efficiency is low, and there are inconsistencies in the judgment between batches. Summary of the Invention

[0004] To address or partially address the problems existing in related technologies, this application provides a method and apparatus for identifying the grade of diamond powder, which can improve detection efficiency and consistency between different batches, and reduce the labor intensity of personnel.

[0005] The first aspect of this application provides a method for identifying the grade of diamond powder molds, including: Acquire the image to be identified captured by the image acquisition device, wherein the image to be identified includes the diamond powder particles to be tested; Image recognition is performed on the image to be identified to obtain the recognition result, which characterizes the sand pattern of the diamond powder particles to be tested; The sharpness level of the diamond powder to be tested is determined based on the identification results.

[0006] Furthermore, determining the sharpness grade of the diamond powder to be tested based on the identification results includes: Determine the ratio of the number of diamond powder particles to the total number of diamond powder particles in each sand mold. When the ratio meets the corresponding set range, the diamond powder to be tested is determined to be the sharpness grade represented by the corresponding set range.

[0007] Furthermore, the sand shape of the diamond powder particles to be tested includes sharp, flake, and spherical shapes.

[0008] Furthermore, before acquiring the image to be identified by the image acquisition device, the method further includes: Obtain a training image set, which includes diamond powder particles; The training image set is input into the image recognition model for training to learn the characteristics of different sand types of diamond powder particles.

[0009] Furthermore, the step of inputting the training image set into the image recognition model for training to learn the characteristics of different sand types of diamond powder particles includes: Diamond powder particles of different sand types were labeled in the training image set; Input the labeled training image set into the image recognition model; Adjust the corresponding parameters based on the output of the image recognition model.

[0010] Furthermore, after determining the sharpness grade of the diamond powder to be tested based on the identification results, the method further includes: The quality of the diamond powder to be tested is determined based on its sharpness level.

[0011] The second aspect of this application provides a diamond powder mold grade identification device, comprising: The acquisition module is used to acquire the image to be identified acquired by the image acquisition device, wherein the image to be identified includes the diamond powder particles to be tested; The recognition module is used to perform image recognition on the image to be recognized and obtain the recognition result, which characterizes the sand pattern of the diamond powder particles to be tested. The judgment module is used to determine the sharpness level of the diamond powder to be tested based on the recognition results.

[0012] A third aspect of this application provides an electronic device, comprising: A processor; and a memory having executable code stored thereon, which, when executed by the processor, causes the processor to perform the method described in any of the preceding claims.

[0013] A fourth aspect of this application provides a computer-readable storage medium having executable code stored thereon, which, when executed by a processor of an electronic device, causes the processor to perform the method described in any of the preceding claims.

[0014] The fifth aspect of this application provides a computer program product, including a computer program that, when executed by a processor, implements the method described in any of the preceding claims.

[0015] The technical solution provided in this application can include the following beneficial effects: acquiring an image to be identified by an image acquisition device, wherein the image to be identified includes diamond powder particles to be tested; performing image recognition on the image to be identified to obtain a recognition result, which characterizes the sand pattern of the diamond powder particles to be tested; determining the sharpness grade of the diamond powder to be tested based on the recognition result; thus, the above solution can automatically complete the identification and classification of the sharpness grade of the diamond powder to be tested without manual visual observation, thereby improving detection efficiency and consistency between different batches, and reducing the labor intensity of personnel.

[0016] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application. Attached Figure Description

[0017] The above and other objects, features and advantages of this application will become more apparent from the following description of exemplary embodiments of this application in conjunction with the accompanying drawings, wherein the same reference numerals generally represent the same components in the exemplary embodiments of this application.

[0018] Figure 1 This is a schematic flowchart illustrating the diamond powder sand mold grade identification method shown in the embodiments of this application; Figure 2 This is the image to be identified of the diamond powder to be tested, as shown in the embodiments of this application; Figure 3 This is an image of the diamond powder particles to be tested, with the sand mold being a sharp type, as shown in the embodiments of this application; Figure 4 This is an image of a diamond powder particle to be tested, which is in the form of a flake, as shown in an embodiment of this application. Figure 5 This is an image of another type of diamond powder particles to be tested, which is in the form of flakes, as shown in the embodiments of this application. Figure 6 This is an image of the diamond powder particles to be tested, which are spherical in shape, shown in the embodiments of this application; Figure 7 These are images of the training image set shown in the embodiments of this application; Figure 8 These are the manually labeled training images and the training images recognized by the image recognition model shown in the embodiments of this application; Figure 9 This is a schematic diagram of the structure of an electronic device shown in an embodiment of this application. Detailed Implementation

[0019] Embodiments of this application will now be described in more detail with reference to the accompanying drawings. While embodiments of this application are shown in the drawings, it should be understood that this application may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided to make this application more thorough and complete, and to fully convey the scope of this application to those skilled in the art.

[0020] The terminology used in this application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. The singular forms “a,” “the,” and “the” used in this application and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any or all possible combinations of one or more of the associated listed items.

[0021] It should be understood that although the terms "first," "second," "third," etc., may be used in this application to describe various information, this information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, without departing from the scope of this application, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this application, "multiple" means two or more, unless otherwise explicitly specified.

[0022] In related technologies, the main method for testing diamond powder sand molds is to examine the diamond powder using an electron microscope and observe the morphological differences of the powder visually to count the different types of sand molds and then classify them by grade. However, the subjective judgment of the testers is strong, the efficiency is low, and there are inconsistencies in the judgment between batches.

[0023] To address the aforementioned issues, this application provides a method for identifying the grade of diamond powder sand, which can improve detection efficiency and consistency between different batches, while reducing the labor intensity of personnel.

[0024] The technical solutions of the embodiments of this application are described in detail below with reference to the accompanying drawings.

[0025] Figure 1 This is a schematic flowchart illustrating the diamond powder sand mold grade identification method shown in the embodiments of this application.

[0026] like Figure 1 As shown in the embodiment of this application, a method for identifying the grade of diamond powder sand molds is provided, including the following steps: S100. Acquire the image to be identified acquired by the image acquisition device, wherein the image to be identified includes the diamond powder particles to be tested.

[0027] In S100, the image acquisition device can be an electron microscope. Figure 2 The image shown in the embodiments of this application is of the diamond powder to be tested, which can be scanned by an electron microscope to obtain the image. Figure 2 The image shown contains the diamond powder particles to be identified.

[0028] Specifically, a sample can be prepared first. Take 0.2g of the diamond powder sample to be tested and place it on the testing stage (with conductive adhesive applied beforehand). Blow away any excess sand sample to remove any floating dust from the testing stage. Then, scan the sample with an electron microscope to acquire an image of the diamond powder sample to be tested. Try to make the sand powder in the electron microscope field of view uniformly dispersed, without overlapping sand, and with clear boundaries between particles. Use an electron microscope with a magnification of 2500 and take three photos. Select one with the best image for image recognition.

[0029] S200. Perform image recognition on the image to be recognized to obtain the recognition result, which characterizes the sand pattern of the diamond powder particles to be tested.

[0030] In the S200, an image recognition model can be used to identify the sand pattern of each particle in the diamond powder being tested by performing image recognition on the image to be identified. The image recognition model can employ a deep learning model, which, by constructing a deep neural network, can automatically extract feature information from the image and perform classification, recognition, and other processing. The image recognition model can use the YOLO (You Only Look Once) algorithm, the Faster R-CNN algorithm, or the MASK R-CNN system.

[0031] S300. Determine the sharpness grade of the diamond powder to be tested based on the identification results.

[0032] In S300, the sharpness of diamond powder varies depending on the sand type of the particles being tested. The more sharp particles in the diamond powder, the sharper the powder, and the higher its sharpness grade. The sharpness grade can be determined based on the proportion of the corresponding sand type in the identification results. For example, sharpness grades can be categorized as excellent, good, and unacceptable. A higher sharpness grade indicates a smaller contact area during cutting and better cutting performance.

[0033] The diamond powder sand mold grade identification method provided in this application involves acquiring an image to be identified by an image acquisition device, wherein the image to be identified includes diamond powder particles to be tested; performing image recognition on the image to be identified to obtain an identification result, which characterizes the sand mold of the diamond powder particles to be tested; and determining the sharpness grade of the diamond powder to be tested based on the identification result. Thus, the above scheme can automatically complete the identification and classification of the sharpness grade of the diamond powder to be tested without manual visual observation, thereby improving detection efficiency and consistency between different batches, and reducing the labor intensity of personnel.

[0034] In some embodiments, the sand shape of the diamond powder particles to be tested includes sharp, flake, and spherical shapes.

[0035] Figure 3 This is an image of the diamond powder particles to be tested, shown in an embodiment of this application, where the sand mold is sharp. (Example:) Figure 3 As shown, the sharp diamond powder particles to be tested have a multi-faceted, angular block structure; their geometric characteristics are: three faces emerge from the vertex, the three faces have equal areas, and the faces intersect with each other with edges, which appear as thin, bright white lines in the figure.

[0036] Figure 4 This is an image of a diamond powder particle to be tested, with the sand mold being of a flake type, as shown in an embodiment of this application. Figure 4 As shown, the plate-shaped diamond powder particles to be tested are visually flat with a large surface area and a small thickness, exhibiting a flat plate structure; its geometric characteristics are: three faces emerge from the vertex, and the area of ​​one of the faces is greater than or equal to the area of ​​the two adjacent faces.

[0037] Figure 5 This is an image of another type of diamond powder particles, the form of which is flake-shaped, as shown in an embodiment of this application. Figure 5 As shown, the sheet-like diamond powder particles to be tested have a prismatic or cuboid structure; their geometric features are: three faces emerge from the vertex, the areas of the first two faces are basically equal and much larger than the area of ​​the third face.

[0038] Figure 6 This is an image of the diamond powder particles to be tested, with the sand mold being spherical, as shown in the embodiments of this application. Figure 6 As shown, the spherical diamond powder particles to be tested have many pits on the surface and a spherical structure; their geometric characteristics are: more than three vertices leading out, and the polygon formed by connecting the bottom projection points has ≥6 sides.

[0039] In some embodiments, S300 above, determining the sharpness grade of the diamond powder to be tested based on the identification result, includes: S301. Determine the ratio of the number of diamond powder particles to be tested in each sand mold to the total number of diamond powder particles to be tested.

[0040] Specifically, for example, based on the identification results, the proportions of sharp, flake-shaped, and spherical diamond powder particles to the total number of diamond powder particles to be tested are calculated respectively. The proportion of sharp diamond powder particles to the total number of diamond powder particles to be tested is A, the proportion of flake-shaped diamond powder particles to the total number of diamond powder particles to be tested is B, and the proportion of spherical diamond powder particles to the total number of diamond powder particles to be tested is C.

[0041] Calculation formulas are as follows: A = (Total number of particles - Number of flaky particles - Number of spherical particles) ÷ Total number of particles × 100%; B = Number of flaky particles ÷ Total number of particles × 100%; C = Number of spherical particles ÷ Total number of particles × 100%.

[0042] S302. When the ratio meets the corresponding set range, the diamond powder to be tested is determined to be the sharpness grade represented by the corresponding set range.

[0043] For example, the standard for an excellent sharpness grade can be set as: A ≥ 90%, B ≤ 5%, and C ≤ 5%. The standard for a good sharpness grade can be set as: A ≥ 85%, B ≤ 7%, and C ≤ 8%. The standard for an unsatisfactory sharpness grade can be set as: A < 85%, B > 7%, and C > 8%. In actual implementation, the specific range of each ratio for different sharpness grades can be set according to the actual situation, such as the size of the diamond wire or the size of the silicon wafer to be cut.

[0044] In some embodiments, before S100 above, when acquiring the image to be identified acquired by the image acquisition device, the method further includes: S110. Obtain a training image set, wherein the training image set includes diamond powder particles.

[0045] Figure 7 These are images of the training image set shown in the embodiments of this application, which can be obtained by scanning diamond powder with an electron microscope. Figure 7 The training image set shown includes multiple images containing diamond powder particles.

[0046] S120. Input the training image set into the image recognition model for training to learn the characteristics of different sand types of diamond powder particles.

[0047] Image recognition models can employ algorithms such as YOLO (You Only Look Once), Faster R-CNN, or the MASK R-CNN system. The characteristics of diamond powder particles from different sand types include the shape and structural features of the diamond powder particles from different sand types, for example... Figures 3 to 6 The shape and structural characteristics of diamond powder particles with different sand types are analyzed. The trained image recognition model is then applied to the identification of diamond powder sand type grades, which allows the execution of the steps in S100 described above.

[0048] In some embodiments, the above-described S120, inputting the training image set into the image recognition model for training to learn the characteristics of different sand types of diamond powder particles, includes: S121. Label diamond powder particles of different sand types in the training image set.

[0049] Specifically, the process begins with manual labeling, such as distinguishing diamond powder particles of different shapes (sharp, flake, and spherical) in the image.

[0050] S122. Input the labeled training image set into the image recognition model.

[0051] The manually labeled training image set is used as a learning template for the image recognition model to perform deep learning.

[0052] S123. Adjust the corresponding parameters according to the output results of the image recognition model.

[0053] Figure 8 These are the manually labeled training images and the training images recognized by the image recognition model shown in the embodiments of this application, such as... Figure 8 As shown in the figure, the photo on the left is a manually labeled training image, and the photo on the right is a training image recognized by the image recognition model. In the manually labeled training image, diamond powder particles of different sand types are circled with different colored lines. In the training image recognized by the image recognition model, different colors are used to represent diamond powder particles of different sand types: blue for sharp type, yellow for flake type, and green for spherical type.

[0054] The proportion of each sand type in the manually labeled training images is compared with the output of the image recognition model multiple times. The confidence interval and other parameters of the image recognition model are continuously corrected to improve the consistency between its output and human judgment.

[0055] After continuous learning and result comparison between the training and testing groups, a reliable model is finally obtained, with a consistency of over 95% between human judgment and model judgment. After that, the model can be officially used for judgment.

[0056] In some embodiments, after step S300 above, where the sharpness grade of the diamond powder to be tested is determined based on the identification result, the method further includes: S400. Determine whether the diamond powder to be tested is qualified based on its sharpness grade. If the sharpness grade is unqualified, the diamond powder to be tested is deemed unqualified.

[0057] Corresponding to the aforementioned application function implementation method embodiments, this application also provides a diamond powder sand mold grade identification device, electronic device, and corresponding embodiments.

[0058] This application embodiment also provides a diamond powder sand mold grade identification device, including: The acquisition module is used to acquire the image to be identified acquired by the image acquisition device, wherein the image to be identified includes the diamond powder particles to be tested; The recognition module is used to perform image recognition on the image to be recognized and obtain the recognition result, which characterizes the sand pattern of the diamond powder particles to be tested. The judgment module is used to determine the sharpness level of the diamond powder to be tested based on the recognition results.

[0059] In some embodiments, the determination module includes: The first determining module is used to determine the ratio of the number of diamond powder particles to be tested in each sand mold to the total number of diamond powder particles to be tested.

[0060] The second determining module is used to determine the sharpness level of the diamond powder to be tested as represented by the corresponding set range when the ratio relationship meets the corresponding set range.

[0061] In some embodiments, the sand shape of the diamond powder particles to be tested includes sharp, flake, and spherical shapes.

[0062] In some embodiments, the diamond powder sand mold grade identification device further includes: The acquisition module is used to acquire a training image set, which includes diamond powder particles.

[0063] The training module is used to input the training image set into the image recognition model for training, so as to learn the characteristics of different sand types of diamond powder particles.

[0064] In some embodiments, the training module is used to label diamond powder particles of different sand types in the training image set; input the labeled training image set into the image recognition model; and adjust the corresponding parameters according to the output of the image recognition model.

[0065] The diamond powder sand mold grade identification device provided in this application acquires an image to be identified by an image acquisition device, wherein the image to be identified includes diamond powder particles to be tested; performs image recognition on the image to be identified to obtain an identification result, which characterizes the sand mold of the diamond powder particles to be tested; and determines the sharpness grade of the diamond powder to be tested based on the identification result. Thus, the above scheme can automatically complete the identification and classification of the sharpness grade of the diamond powder to be tested without manual visual observation, thereby improving detection efficiency and consistency between different batches, and reducing the labor intensity of personnel.

[0066] In addition, there are specialized testing devices on the market to detect the morphology of diamond powder particles, but these devices are expensive. In this embodiment, the sharpness is distinguished by combining necessary electron microscopy testing with image analysis, which can save the cost of purchasing such testing devices.

[0067] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated further here.

[0068] Figure 9 This is a schematic diagram of the structure of an electronic device shown in an embodiment of this application.

[0069] See Figure 9 The electronic device 1000 includes a memory 1010 and a processor 1020.

[0070] The processor 1020 can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor.

[0071] Memory 1010 may include various types of storage units, such as system memory, read-only memory (ROM), and permanent storage devices. ROM may store static data or instructions required by processor 1020 or other modules of the computer. Permanent storage devices may be read-write storage devices. Permanent storage devices may be non-volatile storage devices that retain stored instructions and data even when the computer is powered off. In some embodiments, permanent storage devices use mass storage devices (e.g., magnetic or optical disks, flash memory) as permanent storage devices. In other embodiments, permanent storage devices may be removable storage devices (e.g., floppy disks, optical drives). System memory may be a read-write storage device or a volatile read-write storage device, such as dynamic random access memory. System memory may store some or all of the instructions and data required by the processor during operation. Furthermore, memory 1010 may include any combination of computer-readable storage media, including various types of semiconductor memory chips (e.g., DRAM, SRAM, SDRAM, flash memory, programmable read-only memory), and disks and / or optical disks may also be used. In some embodiments, the memory 1010 may include a removable storage device that is readable and / or writable, such as a laser disc (CD), a read-only digital multifunction optical disc (e.g., DVD-ROM, dual-layer DVD-ROM), a read-only Blu-ray disc, an ultra-high density optical disc, a flash memory card (e.g., SD card, mini SD card, Micro-SD card, etc.), a magnetic floppy disk, etc. Computer-readable storage media do not contain carrier waves or transient electronic signals transmitted wirelessly or via wired connections.

[0072] The memory 1010 stores executable code, which, when processed by the processor 1020, can cause the processor 1020 to execute part or all of the methods described above.

[0073] Furthermore, the method according to this application can also be implemented as a computer program or computer program product, which includes computer program code instructions for performing some or all of the steps in the method described above.

[0074] Alternatively, this application may be implemented as a computer-readable storage medium (or a non-transitory machine-readable storage medium or a machine-readable storage medium) storing executable code (or computer program or computer instruction code) thereon, which, when executed by a processor of an electronic device (or server, etc.), causes the processor to perform part or all of the steps of the methods described above according to this application.

[0075] The various embodiments of this application have been described above. These descriptions are exemplary and not exhaustive, nor are they limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen to best explain the principles, practical application, or improvement of the technology in the market, or to enable others skilled in the art to understand the embodiments disclosed herein.

Claims

1. A method for identifying the grade of diamond powder sand molds, characterized in that, include: Acquire the image to be identified captured by the image acquisition device, wherein the image to be identified includes the diamond powder particles to be tested; Image recognition is performed on the image to be identified to obtain the recognition result, which characterizes the sand pattern of the diamond powder particles to be tested; The sharpness level of the diamond powder to be tested is determined based on the identification results.

2. The method for identifying the grade of diamond powder sand as described in claim 1, characterized in that, The process of determining the sharpness grade of the diamond powder to be tested based on the identification results includes: Determine the ratio of the number of diamond powder particles to the total number of diamond powder particles in each sand mold. When the ratio meets the corresponding set range, the diamond powder to be tested is determined to be the sharpness grade represented by the corresponding set range.

3. The method for identifying the grade of diamond powder sand according to claim 1, characterized in that, The sand shape of the diamond powder particles to be tested includes sharp, flake, and spherical.

4. The method for identifying the grade of diamond powder sand molds according to claim 1, characterized in that, Before acquiring the image to be identified captured by the image acquisition device, the method further includes: Obtain a training image set, which includes diamond powder particles; The training image set is input into the image recognition model for training to learn the characteristics of different sand types of diamond powder particles.

5. The method for identifying the grade of diamond powder sand according to claim 4, characterized in that, The step of inputting the training image set into the image recognition model for training to learn the characteristics of different sand types of diamond powder particles includes: Diamond powder particles of different sand types were labeled in the training image set; Input the labeled training image set into the image recognition model; Adjust the corresponding parameters based on the output of the image recognition model.

6. The method for identifying the grade of diamond powder sand according to claim 1, characterized in that, After determining the sharpness grade of the diamond powder to be tested based on the identification results, the method further includes: The quality of the diamond powder to be tested is determined based on its sharpness level.

7. A diamond powder sand mold grade identification device, characterized in that, include: The acquisition module is used to acquire the image to be identified acquired by the image acquisition device, wherein the image to be identified includes the diamond powder particles to be tested; The recognition module is used to perform image recognition on the image to be recognized and obtain the recognition result, which characterizes the sand pattern of the diamond powder particles to be tested. The judgment module is used to determine the sharpness level of the diamond powder to be tested based on the recognition results.

8. An electronic device, characterized in that, include: processor; as well as A memory having executable code stored thereon, which, when executed by the processor, causes the processor to perform the method as described in any one of claims 1-6.

9. A computer-readable storage medium having executable code stored thereon, which, when executed by a processor of an electronic device, causes the processor to perform the method as described in any one of claims 1-6.

10. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method of any one of claims 1-6.

Images