Cleaning Control System and Method for Sapphire Double-Polished Wafer

Abstract

The present invention discloses a cleaning control system and method for sapphire double-polished wafers, belonging to the field of cleaning control of sapphire double-polished wafers. The present invention obtains cleaning data, obtains sapphire double-polished wafer images and data before and after cleaning, processes the images, constructs a cleaning effect evaluation model, imports scratch-related parameters and the number of surface particles before and after cleaning into the cleaning effect evaluation model for evaluation, constructs a brush wear degree evaluation model, imports the process parameters of the brush cleaning the sapphire double-polished wafer into the brush wear degree evaluation model to evaluate the brush wear degree, constructs a brush remaining life evaluation model, and imports the brush wear amount, the brush cleaning effect and the brush thickness into the brush remaining life evaluation model to evaluate the brush remaining life. The present invention monitors the brush wear condition by real-time monitoring of the cleaning effect and predicts the brush life based on the wear model, reducing the negative impact of the brush on the cleaning process of the double-polished wafer.

Description

Technical Field

[0001] The present invention belongs to the field of cleaning control of sapphire double-polished wafers, and specifically relates to a cleaning control system and method for sapphire double-polished wafers. Background Art

[0002] Sapphire double-polished wafers are widely used in fields such as LED substrates, optical windows, and semiconductor substrates. Their surface quality has an important impact on subsequent processing and device performance. During grinding, polishing, and cleaning processes, tiny particles, scratches, or other defects may remain on the surface of sapphire double-polished wafers. If the cleaning effect is not good, it may lead to device failure in subsequent processes and affect the product yield.

[0003] Traditional cleaning of sapphire double-polished wafers mainly relies on manual experience to judge the cleaning effect, and it is difficult to achieve quantitative control. In addition, the service life of the brush is mainly replaced at fixed intervals and cannot be dynamically adjusted according to the actual wear situation, resulting in premature replacement of the brush causing waste, or too late replacement affecting the cleaning quality. The present invention proposes a cleaning control system and method for sapphire double-polished wafers, which can monitor the cleaning effect in real time, evaluate the wear condition of the brush, and predict the brush life based on the wear model to ensure the stability of the cleaning process, and can replace the brush in time to reduce the negative impact of the brush on the cleaning process of the double-polished wafer. Summary of the Invention

[0004] In view of the deficiencies of the prior art, the present invention proposes a cleaning control system and method for sapphire double-polished wafers.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] A cleaning control method for sapphire double-polished wafers, which includes the following specific steps:

[0007] Obtain cleaning data, obtain images of sapphire double-polished wafers and data before and after cleaning, and process the images;

[0008] Construct a cleaning effect evaluation model, and import scratch-related parameters and the number of surface particles before and after cleaning into the cleaning effect evaluation model for evaluation;

[0009] Construct a brush wear degree evaluation model, and import the process parameters of the brush cleaning the sapphire double-polished wafer into the brush wear degree evaluation model to evaluate the brush wear degree;

[0010] Construct a brush remaining life evaluation model, and import the brush wear amount, the brush cleaning effect, and the brush thickness into the brush remaining life evaluation model to evaluate the brush remaining life.

[0011] Preferably, the steps of obtaining cleaning data, obtaining sapphire double-polished wafer images and data before and after cleaning, and processing the images include the following specific steps:

[0012] S11. Collect images of both sides of the sapphire double-polished wafer before and after double-sided cleaning through a high-resolution camera. Taking the center of the sapphire double-polished wafer as the coordinate origin, establish a rectangular coordinate system, and use a Gaussian filter to denoise the collected images of both sides of the sapphire double-polished wafer before and after brushing. Among them, the Gaussian filtering formula is: , where (x, y) are the pixel coordinates in the image, σ is the standard deviation, and k is the radius of the filtering window;

[0013] S12. Use the Otsu method to perform threshold segmentation on the image threshold. Traverse all possible gray thresholds, calculate the variance between the foreground and background classes under each threshold, and select the threshold corresponding to the maximum variance as the optimal segmentation threshold to separate the scratch area from the background. Then, remove the background of the image through image subtraction to highlight the scratch area. Take the absolute value after subtracting the two-dimensional image data of the two images to obtain the difference between the two images, and output a difference image data. Among them, the image subtraction calculation formula is: , where is the image after threshold segmentation, is the background reference image;

[0014] S13. Measure the depth, three-dimensional morphology, and quantity distribution of the scratches on the surface of the double-polished wafer after cleaning through a shape measurement laser microscopy system, and obtain the scratch positions through the established rectangular coordinate system;

[0015] S14. Detect the number of surface particles on the sapphire double-polished wafer before and after cleaning through a particle detector to obtain the number of surface particles before and after cleaning.

[0016] Preferably, the steps of constructing a cleaning effect evaluation model and importing the scratch-related parameters and the number of surface particles before and after cleaning into the cleaning effect evaluation model for evaluation include the following specific steps:

[0017] S21. Substitute the scratch-related parameters into the scratch comprehensive evaluation index calculation formula to evaluate the scratch degree. Among them, the scratch comprehensive evaluation index calculation formula is: , where S is the single-sided area of the sapphire double-polished wafer, d i is the depth of the i-th scratch, h i is the length of the i-th scratch, and n is the total number of double-sided scratches;

[0018] S22. Substitute the number of surface particles on the sapphire double-polished wafer before and after cleaning into the particle removal rate calculation formula to calculate the particle removal rate. Among them, the particle removal rate calculation formula is: , where D1 is the number of surface particles on both sides of the sapphire double-polished wafer before cleaning, and D2 is the number of surface particles on both sides of the sapphire double-polished wafer after cleaning.

[0019] Preferably, for constructing the evaluation model of the brush wear degree, importing the process parameters of the brush cleaning the sapphire double-polished wafer into the evaluation model of the brush wear degree to evaluate the brush wear degree includes the following specific steps:

[0020] S31. Compare the comprehensive scratch evaluation index with the scratch evaluation threshold. If the comprehensive scratch evaluation index is greater than the scratch evaluation threshold, immediately replace the brush. At the same time, compare the particle removal rate with the minimum particle removal rate threshold. If the particle removal rate is less than the minimum particle removal rate threshold, immediately replace the brush;

[0021] S32. If both the comprehensive scratch evaluation index and the particle removal rate are within the threshold range, substitute the process parameters of the brush cleaning the sapphire double-polished wafer into the brush wear amount calculation formula to calculate the brush wear amount. The brush wear amount calculation formula per unit time is obtained based on the Archard wear equation. Quantify the brush wear amount through the brush material characteristics, pressure, slip distance, and the corrosiveness of the cleaning liquid to the brush. Among them, the brush wear amount calculation formula per unit time is: , where K is the wear coefficient, F is the pressure applied by the brush, L is the slip distance between the brush and the sapphire wafer per unit time, Z is the hardness of the brush material, C is the corrosion coefficient of the cleaning liquid to the brush. Among them, the calculation formula for the slip distance is: , where r is the contact radius of the brush, v is the rotation speed of the brush, and t is the unit time.

[0022] Preferably, for constructing the evaluation model of the remaining life of the brush, importing the brush wear amount, the cleaning effect of the brush, and the brush thickness into the evaluation model of the remaining life of the brush to evaluate the remaining life of the brush includes the following specific steps:

[0023] S41. Substitute the brush wear amount and the brush thickness into the brush remaining life calculation formula to calculate the brush remaining life. Among them, the brush remaining life calculation formula is: , where is the cleaning evaluation factor, H0 is the real-time thickness of the brush, H min is the minimum allowable thickness of the brush. Among them, the calculation formula for the cleaning evaluation factor is: , where A is the comprehensive scratch evaluation index, Ar is the scratch evaluation threshold, P is the particle removal rate, P r is the particle removal rate threshold. By incorporating the comprehensive scratch evaluation index and the particle removal rate into the cleaning evaluation factor, comprehensively evaluate the influence of the actual working state of the brush on the remaining life;

[0024] S42. Compare the remaining life of the brush with the brush life threshold. If it is less than or equal to the threshold, replace the brush immediately. If it is close to the threshold, issue a reminder warning.

[0025] A cleaning control system for sapphire double-polished wafers, which is implemented based on the above-mentioned cleaning control method for sapphire double-polished wafers, specifically includes:

[0026] A data acquisition module, used to acquire sapphire double-polished wafer images and data before and after cleaning, and process the images;

[0027] A cleaning effect evaluation module, used to evaluate the cleaning effect through scratch-related parameters and the number of surface particles before and after cleaning;

[0028] A brush wear degree evaluation module, used to evaluate the brush wear degree through the process parameters of the brush cleaning the sapphire double-polished wafer;

[0029] A brush remaining life evaluation module, used to evaluate the brush remaining life through the brush wear amount, the brush cleaning effect, and the brush thickness.

[0030] An electronic device includes: a processor and a memory, wherein a computer program that can be called by the processor is stored in the memory;

[0031] The processor executes the above-mentioned cleaning control method for sapphire double-polished wafers by calling the computer program stored in the memory.

[0032] A computer-readable storage medium, characterized in that it stores instructions, and when the instructions run on a computer, the computer is made to execute the above-mentioned cleaning control method for sapphire double-polished wafers.

[0033] Compared with the prior art, the beneficial effects of the present invention are:

[0034] The present invention acquires cleaning data, acquires sapphire double-polished wafer images and data before and after cleaning, and processes the images, constructs a cleaning effect evaluation model, imports scratch-related parameters and the number of surface particles before and after cleaning into the cleaning effect evaluation model for evaluation, constructs a brush wear degree evaluation model, imports the process parameters of the brush cleaning the sapphire double-polished wafer into the brush wear degree evaluation model to evaluate the brush wear degree, constructs a brush remaining life evaluation model, imports the brush wear amount, the brush cleaning effect, and the brush thickness into the brush remaining life evaluation model to evaluate the brush remaining life. The present invention monitors the cleaning effect in real time to evaluate the brush wear condition, and predicts the brush life based on the wear model, reducing the negative impact of the brush on the double-polishing wafer cleaning process. Description of the Drawings

[0035] Figure 1Schematic diagram of the overall process of the cleaning control method for sapphire double-polished wafers in the present invention;

[0036] Figure 2 Flow chart for calculating the comprehensive evaluation index of scratches;

[0037] Figure 3 Flow chart for calculating the remaining life of the brush;

[0038] Figure 4 Schematic diagram of the overall framework of the cleaning control system for sapphire double-polished wafers in the present invention. Detailed implementation manners

[0039] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments.

[0040] Embodiment 1

[0041] Please refer to Figures 1 - 3 , an embodiment provided by the present invention: a cleaning control method for sapphire double-polished wafers, which includes the following specific steps:

[0042] Obtain cleaning data, obtain the images of sapphire double-polished wafers and the data before and after cleaning, and process the images;

[0043] Build a cleaning effect evaluation model, and import the scratch-related parameters and the number of surface particles before and after cleaning into the cleaning effect evaluation model for evaluation;

[0044] Build a brush wear degree evaluation model, and import the process parameters of the brush cleaning the sapphire double-polished wafers into the brush wear degree evaluation model to evaluate the brush wear degree;

[0045] Build a brush remaining life evaluation model, and import the brush wear amount, the brush cleaning effect, and the brush thickness into the brush remaining life evaluation model to evaluate the brush remaining life.

[0046] In this embodiment, it should be specifically noted that obtaining cleaning data, obtaining the images of sapphire double-polished wafers and the data before and after cleaning, and processing the images include the following specific steps:

[0047] S11. Collect the images of both sides of the sapphire double-polished wafer before and after cleaning through a high-resolution camera. Taking the center of the sapphire double-polished wafer as the coordinate origin, establish a rectangular coordinate system, and use a Gaussian filter to denoise the collected images of both sides of the sapphire double-polished wafer before and after brushing. Among them, the Gaussian filtering formula is: , where (x, y) is the pixel coordinate in the image, σ is the standard deviation, σ determines the smoothing degree of the filter, a larger σ makes the filtering effect smoother, and k is the radius of the filtering window;

[0048] S12. Use the Otsu method to perform threshold segmentation on the image threshold. Traverse all possible gray thresholds, calculate the variance between the foreground and background classes under each threshold, and select the threshold corresponding to the maximum variance as the optimal segmentation threshold to separate the scratch area from the background. Then, remove the background of the image by image subtraction to highlight the scratch area. Take the absolute value after subtracting the two-dimensional image data of the two images to obtain the difference between the two images and output a difference image data. Among them, the image subtraction calculation formula is: , where is the image after threshold segmentation, is the background reference image;

[0049] S13. Measure the depth, three-dimensional morphology, and quantity distribution of the scratches on the surface of the double-polished wafer after cleaning through a shape measurement laser microscopy system, and obtain the scratch positions through the established rectangular coordinate system;

[0050] S14. Detect the number of surface particles on the sapphire double-polished wafer before and after cleaning through a particle detector to obtain the number of surface particles before and after cleaning.

[0051] It should be specifically noted in this embodiment that constructing a cleaning effect evaluation model and importing the scratch-related parameters and the number of surface particles before and after cleaning into the cleaning effect evaluation model for evaluation includes the following specific steps:

[0052] S21. Substitute the scratch-related parameters into the scratch comprehensive evaluation index calculation formula to evaluate the scratch degree. Comprehensively evaluate the scratch degree after cleaning through the depth, length, and quantity of the double-sided scratches on the sapphire double-polished wafer after cleaning, and evaluate the negative impact generated by the brush during the cleaning process. Among them, the scratch comprehensive evaluation index calculation formula is: , where S is the single-sided area of the sapphire double-polished wafer, d i is the depth of the i-th scratch, h i is the length of the i-th scratch, n is the total number of double-sided scratches. The scratch depth and length directly reflect the severity of the damage to the surface of the double-polished wafer caused by the scratches. Longer or deeper scratches will penetrate a larger area of the surface of the double-polished wafer, increasing the negative impact on the surface quality. The formula comprehensively considers the depth, length of the scratches, and the overall area of the double-polished wafer. Larger scratch depth and length will result in an increase in the index value, indicating that the scratch situation is more serious, and a smaller index value indicates that the scratches have less impact on the surface quality of the double-polished wafer;

[0053] S22. Substitute the number of surface particles on the sapphire double-polished wafer before and after cleaning into the particle removal rate calculation formula to calculate the particle removal rate, and evaluate the particle removal effect of the brush during the cleaning process of the double-polished wafer. Reflect the change in cleanliness of the double-polished wafer after cleaning compared with before cleaning through the change in the number of particles before and after cleaning. Among them, the particle removal rate calculation formula is: , where D1 is the number of surface particles on both sides of the sapphire double-polished sheet before cleaning, and D2 is the number of surface particles on both sides of the sapphire double-polished sheet after cleaning.

[0054] In this embodiment, it should be specifically explained that constructing a brush wear degree evaluation model and importing the process parameters of brush cleaning sapphire double-polished sheets into the brush wear degree evaluation model to evaluate the brush wear degree includes the following specific steps:

[0055] S31. Compare the scratch comprehensive evaluation index with the scratch evaluation threshold. If the scratch comprehensive evaluation index is greater than the scratch evaluation threshold, replace the brush immediately. Meanwhile, compare the particle removal rate with the minimum particle removal rate threshold. If the particle removal rate is less than the minimum particle removal rate threshold, replace the brush immediately. The scratch evaluation threshold and the minimum particle removal rate threshold are determined based on the product quality standard of double-polished films and actual production experience. In the production and application of double-polished films, different products have different tolerances to scratches. Through the dual judgment of the scratch evaluation threshold and the minimum particle removal rate threshold, the brush life can be timely estimated.

[0056] S32. If the scratch comprehensive evaluation index and the particle removal rate are both within the threshold range, the process parameters of brush cleaning of sapphire double polishing sheet are substituted into the brush wear calculation formula to calculate the brush wear. The brush wear calculation formula per unit time is based on the Archard wear equation. The brush wear is quantified by the brush material properties, pressure, sliding distance and the corrosiveness of the cleaning fluid to the brush. The brush wear calculation formula per unit time is: , K is the wear coefficient, which is determined by the characteristics of the brush material, F is the pressure applied by the brush. The greater the pressure, the stronger the contact force between the brush and the double-polished surface, the stronger the friction, and the greater the wear amount. L is the sliding distance between the brush and the sapphire sheet per unit time, Z is the hardness of the brush material. The higher the hardness, the stronger the brush's ability to resist wear. C is the corrosion coefficient of the cleaning fluid on the brush. The calculation formula for the sliding distance is: , where r is the contact radius of the brush, v is the rotation speed of the brush, and t is the unit time. The contact radius is related to the shape of the brush and the range of action on the double-polished surface. A larger contact radius means that the brush covers a larger area per unit time, and the sliding distance increases accordingly. At the same time, the faster the rotation speed, the longer the distance the brush travels on the double-polished surface per unit time.

[0057] In this embodiment, it should be specifically explained that constructing a brush remaining life evaluation model, importing the brush wear amount, brush cleaning effect and brush thickness into the brush remaining life evaluation model to evaluate the brush remaining life includes the following specific steps:

[0058] S41. Substitute the brush wear amount and the brush thickness into the calculation formula for the remaining life of the brush to calculate the remaining life of the brush. The calculation formula for the remaining life of the brush is as follows: , where is the cleaning evaluation factor, H0 is the real-time thickness of the brush, obtained by an online thickness gauge, and H min is the minimum allowable thickness of the brush. The calculation formula for the cleaning evaluation factor is as follows: , where A is the comprehensive scratch evaluation index, Ar is the scratch evaluation threshold, P is the particle removal rate, and P r is the particle removal rate threshold. The comprehensive scratch evaluation index reflects the influence of the brush on the scratch condition of the surface of the double-polished wafer, and the particle removal rate reflects the cleaning effect of the brush. A lower particle removal rate means that the cleaning ability of the brush decreases, which will also affect its remaining life. By incorporating the comprehensive scratch evaluation index and the particle removal rate into the cleaning evaluation factor, the influence of the actual working state of the brush on the remaining life is comprehensively evaluated;

[0059] S42. Compare the remaining life of the brush with the brush life threshold. If it is less than or equal to the threshold, replace the brush immediately. If it is close to the threshold, issue a reminder warning to prompt the operator to pay attention to the brush status in a timely manner and prepare to replace the brush in advance to avoid production interruption caused by the sudden failure of the brush.

[0060] It should be noted here that the value-taking method of various set parameters in this embodiment is as follows: Obtain various parameters in the cleaning process of representative sapphire double-polished wafers, and at the same time obtain the surface state parameters of the double-polished wafers before and after cleaning, obtain the production requirements and quality standards of the double-polished wafers, and hire experts to manually judge the qualified state of the double-polished wafer cleaning. At the same time, substitute the obtained historical data into the calculation results and judgment results of each step in this embodiment into the fitting software to output the value-taking of various set parameters that meet the highest judgment accuracy rate;

[0061] The advantages of this embodiment compared with the prior art are as follows:

[0062] The present invention obtains cleaning data, obtains the images and data before and after cleaning of sapphire double-polished wafers, processes the images, constructs a cleaning effect evaluation model, imports the scratch-related parameters and the number of surface particles before and after cleaning into the cleaning effect evaluation model for evaluation, constructs a brush wear degree evaluation model, imports the process parameters of the brush cleaning the sapphire double-polished wafer into the brush wear degree evaluation model to evaluate the brush wear degree, constructs a brush remaining life evaluation model, and imports the brush wear amount, the cleaning effect of the brush and the brush thickness into the brush remaining life evaluation model to evaluate the remaining life of the brush. The present invention monitors the cleaning effect in real time to evaluate the brush wear condition, and predicts the brush life based on the wear model, reducing the negative impact of the brush on the cleaning process of the double-polished wafer.

[0063] Embodiment 2

[0064] As Figure 4 shown, the cleaning control system for sapphire double-polished wafers is implemented based on the above-mentioned cleaning control method for sapphire double-polished wafers, and specifically includes a data acquisition module, a cleaning effect evaluation module, a brush wear degree evaluation module, and a brush remaining life evaluation module. The data acquisition module is used to acquire sapphire double-polished wafer images and data before and after cleaning, and process the images; the cleaning effect evaluation module is used to evaluate the cleaning effect through scratch-related parameters and the number of surface particles before and after cleaning; the brush wear degree evaluation module is used to evaluate the brush wear degree through the process parameters of the brush cleaning the sapphire double-polished wafer; the brush remaining life evaluation module is used to evaluate the brush remaining life through the brush wear amount, the brush cleaning effect, and the brush thickness.

[0065] Embodiment 3

[0066] This embodiment provides an electronic device, including: a processor and a memory, where the memory stores a computer program that can be called by the processor;

[0067] The processor executes the above-mentioned cleaning control method for sapphire double-polished wafers by calling the computer program stored in the memory.

[0068] This electronic device may have relatively large differences due to different configurations or performances, and can include one or more processors (Central Processing Units, CPUs) and one or more memories. Among them, the memory stores at least one computer program, and this computer program is loaded and executed by the processor to implement the cleaning control method for sapphire double-polished wafers provided by the above method embodiments. This electronic device can also include other components for implementing device functions. For example, this electronic device can also have components such as wired or wireless network interfaces and input / output interfaces for data input and output. This embodiment will not be elaborated here.

[0069] Embodiment 4

[0070] This embodiment proposes a computer-readable storage medium, on which a rewritable computer program is stored;

[0071] When the computer program runs on a computer device, it causes the computer device to execute the above-mentioned cleaning control method for sapphire double-polished wafers.

[0072] For example, a computer-readable storage medium can be a read-only memory (ROM), a random access memory (RAM), a compact disc read-only memory (CD-ROM), magnetic tape, a floppy disk, an optical data storage device, and the like.

[0073] It should be understood that in various embodiments of the present application, the sequence numbers of the above processes do not imply the order of execution, and the execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0074] It should be understood that determining B based on A does not mean determining B only based on A, and B can also be determined based on A and / or other information.

[0075] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions according to the embodiments of the present invention are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via a wired network or / and a wireless network. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or a data center that contains one or more collections of available media. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, magnetic tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state drive.

Claims

1. A cleaning control method for sapphire double-polished wafers, characterized in that: It includes the following specific steps: Acquire cleaning data, obtain sapphire double-polished wafer images and data before and after cleaning, and process the images; Construct a cleaning effect evaluation model, and import scratch-related parameters and the number of surface particles before and after cleaning into the cleaning effect evaluation model for evaluation; A brush wear degree evaluation model is constructed, and the process parameters of brush cleaning of sapphire double polished sheets are introduced into the brush wear degree evaluation model to evaluate the brush wear degree, including the following specific steps: comparing the scratch comprehensive evaluation index with the scratch evaluation threshold, if the scratch comprehensive evaluation index is greater than the scratch evaluation threshold, the brush is replaced immediately, and the particle removal rate is compared with the minimum particle removal rate threshold, if the particle removal rate is less than the minimum particle removal rate threshold, the brush is replaced immediately, if the scratch comprehensive evaluation index and the particle removal rate are both within the threshold range, the process parameters of brush cleaning of sapphire double polished sheets are substituted into the brush wear amount calculation formula to calculate the brush wear amount, the brush wear amount per unit time calculation formula is obtained based on the Archard wear equation, and the brush wear amount is quantified by the brush material properties, pressure, sliding distance and the corrosiveness of the cleaning fluid to the brush; A brush remaining life evaluation model is constructed, and the brush wear, brush cleaning effect and brush thickness are introduced into the brush remaining life evaluation model to evaluate the brush remaining life, including the following specific steps: the brush wear and brush thickness are substituted into the brush remaining life calculation formula to calculate the brush remaining life, wherein the brush remaining life calculation formula is: ,in, is the cleaning evaluation factor, H0 is the real-time thickness of the brush, H min is the minimum thickness allowed by the brush, W is the amount of brush wear per unit time, and the calculation formula of the cleaning evaluation factor is: , where A is the comprehensive scratch evaluation index, Ar is the scratch evaluation threshold, P is the particle removal rate, P r is the particle removal rate threshold. The remaining life of the brush is compared with the brush life threshold. If it is less than or equal to the threshold, the brush is replaced immediately. If it is close to the threshold, a reminder warning is issued.

2. The cleaning control method for sapphire double-polished wafer according to claim 1, characterized in that: The step of obtaining cleaning data, obtaining a sapphire double-polished sheet image and data before and after cleaning, and processing the image comprises the following specific steps: S11, using a high-resolution camera to collect images of the sapphire double-polished sheet before and after double-sided washing, establishing a rectangular coordinate system with the center of the sapphire double-polished sheet as the coordinate origin, and using a Gaussian filter to perform denoising on the collected images of the sapphire double-polished sheet before and after double-sided washing; S12, using the maximum inter-class variance method to perform threshold segmentation on the image threshold, traverse all possible grayscale thresholds, calculate the variance between the foreground and background classes under each threshold, select the threshold corresponding to the maximum variance as the optimal segmentation threshold, separate the scratch area from the background, and remove the background of the image by image subtraction to highlight the scratch area, subtract the two two-dimensional image data and take the absolute value to obtain the difference between the two images, and output a difference image data; S13, measuring the depth, three-dimensional morphology and quantity distribution of scratches on the surface of the double-polished wafer after cleaning by a shape measurement laser microscope system, and obtaining the scratch position by an established rectangular coordinate system; S14, using a particle detector to detect the number of particles on the surface of the sapphire double-polished sheet before and after cleaning, to obtain the number of particles on the surface before and after cleaning.

3. The cleaning control method for sapphire double-polished wafer according to claim 2, characterized in that: The construction of the cleaning effect evaluation model and the importation of scratch-related parameters and the number of surface particles before and after cleaning into the cleaning effect evaluation model for evaluation include the following specific steps: S21. Substituting scratch-related parameters into the scratch comprehensive evaluation index calculation formula to evaluate the degree of scratches, comprehensively evaluating the degree of scratches after cleaning through the depth, length and number of scratches on both sides of the sapphire double-polished sheet after cleaning, and evaluating the negative impact of the bristles during the cleaning process; S22. Substitute the number of particles on the surface of the sapphire double-polished sheet before and after cleaning into the particle removal rate calculation formula to calculate the particle removal rate, evaluate the particle removal effect of the brush cleaning double-polished sheet, and reflect the change in the cleanliness of the double-polished sheet after cleaning compared to before cleaning through the change in the number of particles before and after cleaning.

4. A cleaning control system for sapphire double-polished wafers, which is implemented based on the cleaning control method for sapphire double-polished wafers according to any one of claims 1 to 3, characterized in that: Specifically include: The data acquisition module is used to acquire the sapphire double-polished wafer image and the data before and after cleaning, and process the image; A cleaning effect evaluation module is used to evaluate the cleaning effect through scratch-related parameters and the number of surface particles before and after cleaning; The brush wear degree evaluation module is used to evaluate the brush wear degree through the process parameters of brush cleaning sapphire double-polished wafers; The brush remaining life assessment module is used to assess the brush remaining life based on brush wear, brush cleaning effect and brush thickness.

5. An electronic device comprising: A processor and a memory, wherein the memory stores a computer program that can be called by the processor; It is characterized in that the processor executes the cleaning control method for sapphire double-polished wafers as described in any one of claims 1 to 3 by calling the computer program stored in the memory.

6. A computer-readable storage medium, characterized in that: Instructions are stored, and when the instructions are run on a computer, the computer executes the cleaning control method for sapphire double-polished wafers as described in any one of claims 1 to 3.

Images