Solid-to-liquid ratio detection method, device and equipment for re-feeding of granular silicon material and storage medium

Abstract

The invention provides a solid-to-liquid ratio detection method, device and equipment for re-feeding of a granular silicon material and a storage medium. The method comprises the following steps: respectively shooting the liquid level of a crucible into which a granular silicon material is put by adopting different exposure degrees to obtain a first exposure degree image and a second exposure degree image, determining a liquid area in the first exposure degree image, determining a solid area in the second exposure degree image, and determining the solid area in the second exposure degree image; determining an area ratio of a solid region in the second exposure image to a liquid region in the first exposure image as a solid-to-liquid ratio of the liquid level; according to the method, the detection accuracy of the solid-to-liquid ratio is improved for re-feeding of the pure particle silicon material.

Description

Technical Field

[0001] The present application relates to the technical field of single crystal silicon production, and in particular to a method, device, equipment and storage medium for detecting the solid-to-liquid ratio of re-dosing granular silicon material. Background Art

[0002] In the production process of single crystal silicon, re-adding silicon material is a very critical step, and its main purpose is to ensure the quality and production efficiency of single crystal silicon rods. When the silicon material enters the silicon liquid in the crucible, it will be subjected to strong thermal effects and begin to melt gradually. In this process, the silicon materials gather together and eventually form large irregular shaped blocks.

[0003] In the scenario where the recycled silicon material is a block material or a mixture of block material and granular material, the existing technology uses a camera integrated with a charge-coupled device (CCD) to capture the real-time state of the crucible liquid surface, thereby obtaining an image of the solid-liquid shape of the silicon material. Subsequently, the image obtained by the CCD camera is processed and analyzed to obtain information such as the boundary and shape of the solid-liquid interface of the silicon material. Finally, based on this information, the ratio of solid to liquid is calculated.

[0004] However, when the re-dosed silicon material is pure granular material, the granular material has a smaller volume, a larger surface area at the same weight, and closer contact between particles. Therefore, it quickly melts and aggregates into one piece after being added, and the surface particles are smooth and undulating, which increases the difficulty of obtaining the solid-liquid ratio based on the image. Therefore, the existing solid-liquid ratio detection method has low solid-liquid ratio detection accuracy when re-dosing pure granular silicon material. Summary of the invention

[0005] The embodiments of the present application provide a solid-liquid ratio detection method, device, equipment and storage medium for re-dosing of granular silicon material, which are used to solve the problem of low detection accuracy of existing solid-liquid ratio detection methods when re-dosing pure granular silicon material.

[0006] In a first aspect, the present application provides a method for detecting the solid-liquid ratio of granular silicon material re-dosing, comprising:

[0007] Using different exposures to photograph the liquid surface of the crucible into which the granular silicon material is put, to obtain a first exposure image and a second exposure image; wherein the first exposure is lower than the second exposure;

[0008] determining a liquid region in the first exposure image, and determining a solid region in the second exposure image;

[0009] The area ratio of the solid region in the second exposure image to the liquid region in the first exposure image is determined as the solid-liquid ratio of the liquid surface.

[0010] Optionally, the step of photographing the liquid surface of the crucible into which the granular silicon material is placed at different exposures to obtain a first exposure image and a second exposure image comprises:

[0011] photographing the liquid surface at the first exposure level and the second exposure level to obtain a plurality of images at the first exposure level and a plurality of images at the second exposure level, wherein before and after each photographing at the first exposure level, photographing is performed once at the second exposure level;

[0012] The step of determining the area ratio of the solid region in the second exposure image to the liquid region in the first exposure image as the solid-liquid ratio of the liquid surface comprises:

[0013] For any first exposure image, a target second exposure image is obtained by screening two second exposure images adjacent to and before the first exposure image;

[0014] The area ratio of the solid region in the target second exposure image to the liquid region in the first exposure image is determined as the solid-liquid ratio of the liquid surface.

[0015] Optionally, the step of selecting two second exposure images adjacent to and before the first exposure image to obtain a target second exposure image includes:

[0016] Determine, based on at least one of the dynamic range, saturation, contrast and brightness of each of the two second exposure images adjacent to each other before and after the first exposure image, an image quality value of each of the two second exposure images adjacent to each other before and after the first exposure image;

[0017] Of the two second exposure images that are adjacent to each other before and after the first exposure image, the second exposure image with a higher image quality value is determined as the target second exposure image.

[0018] Optionally, determining the liquid area in the first exposure image includes:

[0019] Performing grayscale processing on the first exposure image to obtain a first grayscale image;

[0020] The liquid area in the first exposure image is determined according to the grayscale moment of each pixel in the first grayscale image.

[0021] Optionally, determining the liquid area in the first exposure image according to the grayscale moment of each pixel in the first grayscale image includes:

[0022] For any pixel point in the first grayscale image, if a change value of the grayscale moment of the pixel point and the grayscale moment of an adjacent pixel point exceeds a first threshold, the pixel point is determined as an edge pixel point;

[0023] For any area surrounded by the edge pixels, if the grayscale moment of the area exceeds a second threshold, the area is determined to be the liquid area.

[0024] Optionally, determining the solid area in the second exposure image includes:

[0025] grayscale the second exposure image, and perform denoising using a Gaussian white noise model to obtain a second grayscale image;

[0026] Performing Fourier transform on the second grayscale image and performing high-pass filtering to obtain frequency domain data;

[0027] Performing an inverse Fourier transform on the frequency domain data to obtain a second enhanced image;

[0028] The solid area is determined according to the grayscale moment of each pixel in the second enhanced image.

[0029] Optionally, determining the solid area according to the grayscale moment of each pixel in the second enhanced image includes:

[0030] For any pixel point in the second enhanced image, if a change value of the grayscale moment of the pixel point and the grayscale moment of an adjacent pixel point exceeds a third threshold, the pixel point is determined as an edge pixel point;

[0031] For any region enclosed by the edge pixels, if the grayscale moment of the region is less than a fourth threshold, the region is determined to be the solid region.

[0032] In a second aspect, the present application provides a solid-liquid ratio detection device for re-dosing granular silicon material, comprising:

[0033] A shooting module, used to shoot the liquid surface of the crucible into which the granular silicon material is put, using different exposures to obtain a first exposure image and a second exposure image; wherein the first exposure is lower than the second exposure;

[0034] a processing module, configured to determine a liquid region in the first exposure image and a solid region in the second exposure image;

[0035] The processing module is further used to determine the area ratio of the solid area in the second exposure image to the liquid area in the first exposure image as the solid-liquid ratio of the liquid surface.

[0036] Optionally, the shooting module is further used to shoot the liquid surface with the first exposure and the second exposure respectively, to obtain a plurality of images with the first exposure and a plurality of images with the second exposure, wherein before and after each shooting with the first exposure, a shooting with the second exposure is performed;

[0037] The processing module is further configured to select, for any first exposure image, two second exposure images adjacent to each other before and after the first exposure image to obtain a target second exposure image;

[0038] The processing module is further used to determine the area ratio of the solid area in the target second exposure image to the liquid area in the first exposure image as the solid-liquid ratio of the liquid surface.

[0039] Optionally, the processing module is further used to determine the image quality value of each of the two second exposure images adjacent to each other before and after the first exposure image based on at least one of the dynamic range, saturation, contrast and brightness of each of the two second exposure images adjacent to each other before and after the first exposure image;

[0040] The processing module is further used to determine the second exposure image with a higher image quality value among the two second exposure images adjacent to each other before and after the first exposure image as the target second exposure image.

[0041] Optionally, the processing module is further used to perform grayscale processing on the first exposure image to obtain a first grayscale image;

[0042] The processing module is further used to determine the liquid area in the first exposure image according to the grayscale moment of each pixel in the first grayscale image.

[0043] Optionally, the processing module is further configured to, for any pixel in the first grayscale image, determine the pixel as an edge pixel if a change value of the grayscale moment of the pixel and the grayscale moment of an adjacent pixel exceeds a first threshold;

[0044] The processing module is further configured to determine, for any area enclosed by the edge pixels, if the grayscale moment of the area exceeds a second threshold, the area as the liquid area.

[0045] Optionally, the processing module is further used to perform grayscale processing on the second exposure image and perform denoising using a Gaussian white noise model to obtain a second grayscale image;

[0046] The processing module is further used to perform Fourier transform and high-pass filtering on the second grayscale image to obtain frequency domain data;

[0047] The processing module is further used to perform inverse Fourier transform on the frequency domain data to obtain a second enhanced image;

[0048] The processing module is further used to determine the solid area according to the grayscale moment of each pixel in the second enhanced image.

[0049] Optionally, the processing module is further configured to, for any pixel in the second enhanced image, determine the pixel as an edge pixel if a change value of the grayscale moment of the pixel and the grayscale moment of an adjacent pixel exceeds a third threshold;

[0050] The processing module is further configured to determine, for any area enclosed by the edge pixels, if the grayscale moment of the area is less than a fourth threshold, the area as the solid area.

[0051] In a third aspect, the present application provides a solid-liquid ratio detection device for re-dosing granular silicon material, comprising: a memory, a processor;

[0052] The memory stores computer-executable instructions;

[0053] The processor executes the computer-executable instructions stored in the memory, so that the processor executes the solid-liquid ratio detection method for re-dosing of granular silicon material as described in the first aspect and / or various possible implementations of the first aspect.

[0054] In a fourth aspect, the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer execution instructions, which, when executed by a processor, are used to implement the solid-to-liquid ratio detection method for re-dosing of granular silicon material as described in the first aspect and / or various possible embodiments of the first aspect.

[0055] In a fifth aspect, the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the solid-to-liquid ratio detection method for re-dosing of granular silicon material as described in the first aspect and / or various possible embodiments of the first aspect.

[0056] The present application provides a method for detecting the solid-to-liquid ratio of re-dosing of granular silicon material, which obtains a first exposure image and a second exposure image by photographing the liquid surface of a crucible into which granular silicon material is added at different exposures, wherein the first exposure is lower than the second exposure, and the liquid area in the first exposure image is determined, as well as the solid area in the second exposure image, and the area ratio of the solid area in the second exposure image to the liquid area in the first exposure image is determined as the solid-to-liquid ratio of the liquid surface; this method improves the detection accuracy of the solid-to-liquid ratio for re-dosing of pure granular silicon material. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0058] Figure 1 Schematic diagram of the process of solid-liquid ratio detection method for re-dosing granular silicon material provided in this application Figure 1 ;

[0059] Figure 2 Schematic diagram of the process of solid-liquid ratio detection method for re-dosing granular silicon material provided in this application Figure 2 ;

[0060] Figure 3 A composite image of pure granular silicon material provided in this application;

[0061] Figure 4 A schematic diagram of the structure of a solid-liquid ratio detection device for re-dosing of granular silicon material provided in the present application;

[0062] Figure 5 A schematic diagram of the structure of the electronic device provided in this application.

[0063] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0064] In order to make the purpose, technical solutions and advantages of this application clearer, the technical solutions in this application will be clearly and completely described below in conjunction with the drawings in this application. Obviously, the described embodiments are part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0065] The terms "first", "second", "third", "fourth", etc. (if any) in the description and claims of the present invention and the above drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in sequences other than those illustrated or described herein.

[0066] In the embodiments of the present application, the words "exemplary" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way.

[0067] With the existing solid-liquid ratio detection method, when the recycled silicon material is mainly block material, the surface of the agglomerated material block is uneven and has large fluctuations, and the reflectivity is relatively low. The information obtained by the CCD camera under such conditions is easier to analyze, thereby deriving the solid-liquid ratio.

[0068] However, this method is only applicable to scenarios where block materials or a mixture of block materials and granular materials are used. When the re-dosed silicon material is pure granular silicon material, the granular material has a smaller volume, a larger surface area at the same weight, and closer contact between particles. Therefore, it quickly melts and aggregates into a block after being added, and the surface particles are smooth and have a higher reflectivity. In this case, it becomes very difficult to obtain the true solid-liquid ratio of the material block. In summary, the existing technology has low accuracy in solid-liquid ratio detection when re-dosing pure granular materials.

[0069] In view of this, the present application proposes a method for detecting the solid-to-liquid ratio of re-dosing of granular silicon material, by photographing the liquid surface at low exposure and high exposure respectively, to obtain multiple low-exposure images and multiple high-exposure images; for the low-exposure image, a grayscale moment edge positioning method is used to determine the liquid area; for the high-exposure image, a Gaussian white noise model is used for denoising, and a Fourier transform is used to determine the solid area, and then the area ratio of the solid area in the high-exposure image to the liquid area in the low-exposure image is determined as the solid-to-liquid ratio of the liquid surface; this method improves the detection accuracy of the solid-to-liquid ratio for the re-dosing of pure granular silicon material.

[0070] The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0071] Figure 1 Schematic diagram of the process of detecting the solid-liquid ratio of the granular silicon material re-dosing provided in the embodiment of the present application Figure 1 , taking the solid-liquid ratio detection device of the granular silicon material re-dosing as an example, Figure 1 As shown, the solid-liquid ratio detection method for re-dosing of granular silicon material provided in this embodiment includes the following steps:

[0072] S101 , photographing the liquid surface of a crucible into which granular silicon material is put using different exposures to obtain a first exposure image and a second exposure image, wherein the first exposure is lower than the second exposure.

[0073] In the embodiment of the present application, the first exposure image and the second exposure image are images of the silicon material liquid level in the crucible obtained at low exposure and high exposure respectively at preset time intervals. Acquiring these two liquid level images with different exposures can capture different details and contrasts, thereby facilitating the observation and analysis of the granular silicon material liquid level in the crucible.

[0074] For example, six images can be taken within 1 second by a CCD camera, of which two are low-exposure first-exposure images to capture details of the brighter parts of the picture to avoid overexposure; and the other four are second-exposure images taken with high exposure to highlight the information of the darker areas in the picture. In this way, these six images with different exposures can ensure that the liquid surface image of the crucible into which the granular silicon material is placed is obtained, and corresponding clear content can be presented under different brightness conditions.

[0075] S102: Determine a liquid area in the first exposure image, and determine a solid area in the second exposure image.

[0076] The liquid region refers to the region occupied by the melted silicon material in the crucible, and the solid region refers to the region occupied by the solid silicon material that has not been completely melted on the surface of the molten silicon material.

[0077] For the first exposure image, since the brightness characteristics of the liquid area are more obvious at low exposure, the threshold segmentation method can be used to distinguish the liquid area from other areas in the first exposure image. For example, the grayscale value of each pixel in the first exposure image is compared with the first preset grayscale threshold, and based on the comparison result, the pixels are classified into liquid areas and other areas. Thereafter, the boundary of the liquid area is identified through an edge detection algorithm, thereby obtaining the liquid area in the first exposure image.

[0078] For the second exposure image, since the brightness characteristics of the solid area are more obvious under high exposure, the threshold segmentation method can be used to distinguish the solid area from other areas in the second exposure image. For example, the grayscale value of each pixel in the second exposure image is compared with the second preset grayscale value, and the pixels are classified into solid areas and other areas based on the comparison result. Then, the boundary of the solid area is identified through the edge detection algorithm, thereby obtaining the solid area in the second exposure image.

[0079] Optionally, the grayscale moment edge positioning method may be used for the first exposure image to depict the liquid area; the Gaussian white noise model may be used to denoise the second exposure image, and Fourier transform may be used to depict the solid area.

[0080] S103 , determining the area ratio of the solid region in the second exposure image to the liquid region in the first exposure image as the solid-liquid ratio of the liquid surface.

[0081] In the embodiments of the present application, the solid-to-liquid ratio refers to the ratio between the area occupied by the solid and the area occupied by the liquid on the surface of the crucible contents. The solid-to-liquid ratio can be used to control the power change of the single crystal furnace.

[0082] Exemplarily, the pixel area of ​​the solid area in the second exposure image and the pixel area of ​​the liquid area in the first exposure image are ratio-calculated to obtain the relative ratio of the solid and liquid on the liquid surface of the granular silicon material in the crucible. For example, the liquid area is 10,000 pixels, the solid area is 5,000 pixels, and the actual area corresponding to each pixel is 1 mm². Then, the area of ​​the liquid area is 10,000 mm², and the area of ​​the solid area is 5,000 mm². Then, the ratio of the area of ​​the solid area to the area of ​​the liquid area is calculated to obtain a solid-liquid ratio of 0.5 mm².

[0083] Therefore, by monitoring the solid-liquid ratio, the embodiment of the present application can understand the state of the molten silicon material in real time, ensure that the silicon material can crystallize evenly during the re-feeding process, thereby improving product quality; it can also monitor the solid-liquid ratio to accurately control the amount of silicon material re-fed each time, avoid too much or too little silicon material entering the furnace, thereby improving production efficiency.

[0084] The embodiment of the present application provides a method for detecting the solid-to-liquid ratio of re-dosing of granular silicon material, which improves the detection accuracy of the solid-to-liquid ratio for re-dosing of pure granular silicon material by photographing the liquid surface of a crucible into which the granular silicon material is added with different exposures to obtain a first exposure image and a second exposure image, wherein the first exposure is lower than the second exposure, and the liquid area in the first exposure image is determined, as well as the solid area in the second exposure image. The area ratio of the solid area in the second exposure image to the liquid area in the first exposure image is determined as the solid-to-liquid ratio of the liquid surface. This method improves the detection accuracy of the solid-to-liquid ratio for re-dosing of pure granular silicon material.

[0085] Figure 2 Schematic diagram of the process of solid-liquid ratio detection method for re-dosing granular silicon material provided in this application Figure 2 ,like Figure 2 As shown, in this embodiment Figure 1 Based on the embodiment, the solid-liquid ratio detection method of the granular silicon material re-dosing is described in detail. The solid-liquid ratio detection method of the granular silicon material re-dosing provided in this embodiment includes:

[0086] S201. Photographing the liquid surface at a first exposure and a second exposure, respectively, to obtain a plurality of first exposure images and a plurality of second exposure images, wherein before and after each photographing at the first exposure, a photograph is taken at the second exposure.

[0087] Among them, since the first exposure is lower than the second exposure, the first exposure refers to a low-exposure image, and the second exposure refers to a high-exposure image. In the case of high exposure, there may be a phenomenon of blurring. Therefore, in order to improve fault tolerance, there is a high-exposure image before and after each low-exposure image.

[0088] Exemplarily, six images can be taken by a CCD camera within 1 second in the exposure order of "high-low-high, high-low-high". In this way, "high-exposure image 1, low-exposure image 1, high-exposure image 2; high-exposure image 3, low-exposure image 2, high-exposure image 4" can be obtained in the shooting order. Among them, low-exposure image 1 and low-exposure image 2 are used to capture the details of the brighter part of the picture to avoid overexposure; and there are two high-exposure images before and after the low-exposure image 1 and the low-exposure image 2, respectively. These four second-exposure images are used to highlight the details of the darker area in the picture; in this way, these six images with different exposures can ensure that the liquid surface image of the crucible into which the granular silicon material is put is obtained, and corresponding clear content can be presented under different brightness conditions.

[0089] S202: grayscale the first exposure image to obtain a first grayscale image.

[0090] In the embodiment of the present application, a weighted average method can be used to perform weighted average processing on the RGB value of each pixel in the first exposure image to obtain a grayscale value, and then obtain a first grayscale image corresponding to the grayscale value.

[0091] It should be noted that, since the first exposure image is a low exposure image, and low exposure images usually have more noise, grayscale processing can reduce the impact of noise and make subsequent image processing steps more effective.

[0092] S203: Determine the liquid area in the first exposure image according to the grayscale moment of each pixel in the first grayscale image.

[0093] Among them, the grayscale moment edge location method can be used to determine the liquid area in the first exposure image. The grayscale moment edge location method is a method for describing the shape characteristics of the target in the image based on the distribution characteristics of the grayscale value of the image. The grayscale moment can be, for example, a zero-order moment, a first-order moment, a second-order moment, etc., which are used to describe the spatial correlation of the grayscale values ​​of pixels in the image.

[0094] It is understandable that in the first grayscale image, there are differences in the distribution of grayscale values ​​in different areas. For edge areas, the grayscale values ​​usually change greatly. The grayscale moment edge positioning method captures this change in grayscale value by calculating the grayscale moment of each pixel in the image and its neighborhood. The grayscale moment can reflect the center of gravity, variance and other characteristics of the grayscale value of the image. When moving from the non-edge area of ​​the image to the edge area, these characteristics of the grayscale moment will change significantly. For example, the center of gravity of the grayscale value will shift and the variance will increase. By analyzing and detecting these grayscale moment features, the location where the grayscale value changes dramatically can be determined, thereby achieving edge positioning.

[0095] Figure 3 The composite image of the pure granular silicon material provided in this embodiment is as follows: Figure 3 As shown in the figure, there is a transition edge from dark to light in the reprojected image. In the dark area A, the grayscale value is low, and the related features of the grayscale moment show a smaller value; while in the bright area B, the grayscale value is high, and the related features of the grayscale moment have a larger value. At the edge of the dark area A and the bright area B, due to the rapid change of the grayscale value, the characteristic value of the grayscale moment will also show an obvious jump, so that the position of the edge can be determined based on this.

[0096] Exemplarily, a specific implementation method for determining the liquid area in the first exposure image according to the grayscale moment of each pixel in the first grayscale image is provided herein: for any pixel in the first grayscale image, if the change value of the grayscale moment of the pixel and the grayscale moment of the adjacent pixel exceeds a first threshold, the pixel is determined as an edge pixel;

[0097] For any area surrounded by edge pixels, if the grayscale moment of the area exceeds the second threshold, the area is determined to be a liquid area.

[0098] In the embodiment of the present application, the first threshold and the second threshold are thresholds determined based on experimental data, and the embodiment of the present application does not limit the specific numerical values ​​corresponding to the first threshold and the second threshold; optionally, the first threshold can be, for example, 100, 200, 300, etc., and the second threshold can be, for example, 1000, 2000, etc.

[0099] For example, each pixel in the first grayscale image can be traversed first, and its grayscale moment in the preset window can be calculated. For example, for the pixel at position (1,1), its grayscale moment is 1600, and its grayscale moment change values ​​with adjacent pixels are calculated respectively: the grayscale moment of the upper pixel (0,1) is 1400, the grayscale moment of the lower pixel (2,1) is 1600, the grayscale moment of the left pixel (1,0) is 1400, and the grayscale moment of the right pixel (1,2) is 1600. At this time, the pixel at position (1,1) , and the grayscale moment change value of the upper pixel (0,1) and the left pixel (1,0) is 200, which exceeds the first threshold of 100. It can be determined that (1,1) is an edge pixel. Next, the change value of the grayscale moment of each pixel and the grayscale moment of its adjacent pixels is calculated to obtain all edge pixels in the first grayscale image, and the connected region analysis method is used to find the area surrounded by all edge pixels, thereby calculating the grayscale moment of each area. If it exceeds the second threshold of 2000, the area is determined to be a liquid area.

[0100] S204 , grayscale the second exposure image, and perform denoising using a Gaussian white noise model to obtain a second grayscale image.

[0101] In the embodiment of the present application, grayscale processing refers to the process of converting the color second exposure image into a grayscale image for subsequent image processing. Since the second exposure image is a high exposure image, the second exposure image is more susceptible to noise. By using a Gaussian white noise model, the random noise generated by high exposure can be removed, making the solid edges and details in the image more clearly discernible.

[0102] Exemplarily, the Gaussian filter parameters may be set first, including a kernel size of 3x3, 5x5, 7x7, etc., a standard deviation of 1, etc., and then Gaussian filtering is used to denoise the noisy second exposure image to obtain a second grayscale image.

[0103] S205 , performing Fourier transform on the second grayscale image and performing high-pass filtering to obtain frequency domain data.

[0104] Fourier transform can convert the information in the spatial domain (i.e. the second grayscale image) into frequency domain information. High-pass filtering is a method of processing images in the frequency domain, which mainly retains the high-frequency components in the image while suppressing or removing the low-frequency components.

[0105] It should be understood that in the frequency domain, different parts of the image correspond to different frequency components. For example, the edges and details in the image usually correspond to high-frequency components, while the smooth areas correspond to low-frequency components. Therefore, the high-pass filtering in this step is used to enhance the edges and details of the image.

[0106] S206: Perform inverse Fourier transform on the frequency domain data to obtain a second enhanced image.

[0107] The purpose of this step is to convert the filtered frequency domain data back to the spatial domain and visualize the processing results. Through the inverse Fourier transform, the enhanced high-frequency components can be restored to the spatial domain, thereby obtaining an enhanced image, that is, the second enhanced image.

[0108] S207: Determine a solid area according to the grayscale moment of each pixel in the second enhanced image.

[0109] Here, similar to the method for determining the liquid area in the first exposure image, the grayscale moment edge positioning method can also be used to determine the solid area in the second enhanced image.

[0110] Optionally, for any pixel point in the second enhanced image, if a change value of the grayscale moment of the pixel point and the grayscale moment of an adjacent pixel point exceeds a third threshold, the pixel point is determined as an edge pixel point;

[0111] For any region surrounded by edge pixels, if the grayscale moment of the region is less than the fourth threshold, the region is determined to be a solid region.

[0112] Among them, the third threshold and the fourth threshold are thresholds determined based on experimental data, and the embodiment of the present application does not limit the specific numerical values ​​corresponding to the third threshold and the fourth threshold; optionally, the third threshold can be, for example, 200, 300, 400, etc., and the fourth threshold can be, for example, 2000, 3000, etc. The specific implementation method is similar to step S203 and will not be repeated here.

[0113] S208 . For any first exposure image, select two second exposure images adjacent to and before the first exposure image to obtain a target second exposure image.

[0114] In a possible implementation, any one of the two second exposure images that are adjacent to the first exposure image before and after the first exposure image may be taken as the target second exposure image.

[0115] In another possible implementation, in order to improve the quality of the target second exposure image, the image quality value of each of the two second exposure images adjacent to each other before and after the first exposure image may be determined based on at least one of the dynamic range, saturation, contrast and brightness of each of the two second exposure images adjacent to each other before and after the first exposure image;

[0116] Of the two second exposure images that are adjacent to each other before and after the first exposure image, the second exposure image with a higher image quality value is determined as the target second exposure image.

[0117] In the embodiment of the present application, the larger the dynamic range of the image, the richer the light and dark levels of the image; the higher the saturation of the image, the brighter the color of the image; the higher the contrast, the clearer the details of the image; the brightness of a high-exposure image is too high, which will cause the image to be overexposed; therefore, weights can be assigned to the attributes of each second exposure image, and these weights reflect the importance of each attribute to the final image quality value. For example, the weight of the dynamic range is 0.4, the weight of the saturation is 0.3, the weight of the contrast is 0.2, and the weight of the brightness is 0.1. The actual dynamic range, actual saturation, actual contrast and actual brightness of each second exposure image are multiplied by the corresponding weights, and the sum of the products of all attributes and the corresponding weights is used as the image quality value of the image; finally, the image quality values ​​of the two second exposure images adjacent to each other before and after the first exposure image are compared, and the second exposure image with a higher image quality value is selected as the target second exposure image.

[0118] S209: Determine the area ratio of the solid region in the target second exposure image to the liquid region in the first exposure image as the solid-liquid ratio of the liquid surface.

[0119] It can be understood that the ratio of the area of ​​the liquid region determined from the low-exposure image to the area of ​​the solid region determined from the high-exposure image is used as the solid-liquid ratio of the liquid surface.

[0120] The solid-liquid ratio detection method for re-dosing of granular silicon material provided in an embodiment of the present application obtains multiple first exposure images and multiple second exposure images by taking a picture at a second exposure before and after each shooting at a first exposure, and determines the liquid area in the first exposure image based on a grayscale moment edge positioning method, performs Fourier transform, high-pass filtering and inverse Fourier transform processing on the multiple second exposure images to obtain a second enhanced image with enhanced image edges and details, and determines the solid area based on the grayscale moment of each pixel in the second enhanced image, and then selects a target second exposure image from two second exposure images adjacent to each other before and after any first exposure image, and determines the area ratio of the solid area in the target second exposure image to the liquid area in the first exposure image as the solid-liquid ratio of the liquid surface; the method improves the detection accuracy of the solid-liquid ratio for re-dosing of pure granular silicon material.

[0121] Figure 4 The schematic diagram of the structure of the solid-liquid ratio detection device for the re-dosing of granular silicon material provided in this application is as follows: Figure 4 As shown, the solid-liquid ratio detection device 400 for re-dosing granular silicon material provided in this embodiment includes:

[0122] The photographing module 401 is used to photograph the liquid surface of the crucible into which the granular silicon material is put at different exposures to obtain a first exposure image and a second exposure image; wherein the first exposure is lower than the second exposure;

[0123] A processing module 402, configured to determine a liquid region in the first exposure image and a solid region in the second exposure image;

[0124] The processing module 402 is further configured to determine the area ratio of the solid region in the second exposure image to the liquid region in the first exposure image as the solid-liquid ratio of the liquid surface.

[0125] Optionally, the shooting module 401 is further used to shoot the liquid surface with the first exposure and the second exposure respectively, to obtain a plurality of images with the first exposure and a plurality of images with the second exposure, wherein before and after each shooting with the first exposure, a shooting with the second exposure is performed;

[0126] The processing module 402 is further configured to select, for any of the first exposure images, two second exposure images adjacent to each other before and after the first exposure image to obtain a target second exposure image;

[0127] The processing module 402 is further configured to determine the area ratio of the solid region in the target second exposure image to the liquid region in the first exposure image as the solid-liquid ratio of the liquid surface.

[0128] Optionally, the processing module 402 is further configured to determine an image quality value of each of two second exposure images adjacent to each other before and after the first exposure image based on at least one of a dynamic range, a saturation, a contrast and a brightness of each of two second exposure images adjacent to each other before and after the first exposure image;

[0129] The processing module 402 is further configured to determine, among two second exposure images adjacent to each other before and after the first exposure image, the second exposure image with a higher image quality value as the target second exposure image.

[0130] Optionally, the processing module 402 is further configured to perform grayscale processing on the first exposure image to obtain a first grayscale image;

[0131] The processing module 402 is further configured to determine a liquid region in the first exposure image according to a grayscale moment of each pixel in the first grayscale image.

[0132] Optionally, the processing module 402 is further configured to, for any pixel in the first grayscale image, determine the pixel as an edge pixel if a change value of the grayscale moment of the pixel and the grayscale moment of an adjacent pixel exceeds a first threshold;

[0133] The processing module 402 is further configured to determine, for any area enclosed by the edge pixels, if the grayscale moment of the area exceeds a second threshold, the area as the liquid area.

[0134] Optionally, the processing module 402 is further configured to grayscale the second exposure image and perform denoising using a Gaussian white noise model to obtain a second grayscale image;

[0135] The processing module 402 is further used to perform Fourier transform and high-pass filtering on the second grayscale image to obtain frequency domain data;

[0136] The processing module 402 is further used to perform an inverse Fourier transform on the frequency domain data to obtain a second enhanced image;

[0137] The processing module 402 is further configured to determine the solid region according to the grayscale moment of each pixel in the second enhanced image.

[0138] Optionally, the processing module 402 is further configured to, for any pixel in the second enhanced image, determine the pixel as an edge pixel if a change value of the grayscale moment of the pixel and the grayscale moment of an adjacent pixel exceeds a third threshold;

[0139] The processing module 402 is further configured to determine, for any region enclosed by the edge pixels, if the grayscale moment of the region is less than a fourth threshold, the region as the solid region.

[0140] It should be noted that the specific implementation principle and effect of the solid-liquid ratio detection device for the re-dosing of granular silicon material can be found in the relevant description and effects corresponding to the above embodiments, and no further elaboration will be made here.

[0141] The present application also provides a schematic diagram of the structure of an electronic device. Figure 5 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application is shown in FIG. Figure 5 As shown, the electronic device may include: a processor 501 and a memory 502 communicatively connected to the processor; the memory 502 stores a computer program; the processor 501 executes the computer program stored in the memory 502, so that the processor 501 executes the method described in any of the above embodiments.

[0142] The memory 502 and the processor 501 may be connected via a bus 503 .

[0143] An embodiment of the present application further provides a computer-readable storage medium, which stores computer-executable instructions. When the computer-executable instructions are executed by a processor, they are used to implement the method described in any of the aforementioned embodiments of the present application.

[0144] An embodiment of the present application further provides a chip for executing instructions, wherein the chip is used to execute the method described in any of the aforementioned embodiments as executed by an electronic device in any of the aforementioned embodiments of the present application.

[0145] An embodiment of the present application further provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the method described in any of the aforementioned embodiments of the present application executed by an electronic device can be implemented.

[0146] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of modules is only a logical function division. There may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or modules, which can be electrical, mechanical or other forms.

[0147] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to implement the solution of this embodiment.

[0148] In addition, each functional module in each embodiment of the present application can be integrated into one processing unit, or each module can exist physically separately, or two or more modules can be integrated into one unit. The above-mentioned module-composed unit can be implemented in the form of hardware or in the form of hardware plus software functional units.

[0149] The above-mentioned integrated module implemented in the form of a software function module can be stored in a computer-readable storage medium. The above-mentioned software function module is stored in a storage medium, including a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to perform some steps of the method described in each embodiment of the present application.

[0150] It should be understood that the above processor can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. The general-purpose processor can be a microprocessor or the processor can be any conventional processor, etc. The steps of the method disclosed in the application can be directly embodied as being executed by a hardware processor, or can be executed by a combination of hardware and software modules in the processor.

[0151] The memory may include high-speed random access memory (RAM), and may also include non-volatile memory (NVM), such as at least one disk storage, and may also be a USB flash drive, a mobile hard disk, a read-only memory, a disk or an optical disk, etc.

[0152] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, the bus in the drawings of this application is not limited to only one bus or one type of bus.

[0153] The above storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. The storage medium can be any available medium that can be accessed by a general or special computer.

[0154] An exemplary storage medium is coupled to a processor so that the processor can read information from the storage medium and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and the storage medium can be located in an application specific integrated circuit (ASIC). Of course, the processor and the storage medium can also exist as discrete components in an electronic device or a main control device.

[0155] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily required by the present application.

[0156] It should be further noted that, although the various steps in the flowchart are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless there is a clear description in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowchart may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these sub-steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.

[0157] In the above embodiments, the description of each embodiment has its own emphasis. For the part not described in detail in a certain embodiment, please refer to the relevant description of other embodiments. The technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, all possible combinations of the technical features in the above embodiments are not described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0158] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. The present application is intended to cover any modification, use or adaptation of the present application, which follows the general principles of the present application and includes common knowledge or customary techniques in the art that are not disclosed in the present application. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present application are indicated by the claims.

[0159] The above is only a specific implementation of the embodiment of the present application, but the protection scope of the embodiment of the present application is not limited thereto, and any changes or replacements within the technical scope disclosed in the embodiment of the present application should be included in the protection scope of the embodiment of the present application. Therefore, the protection scope of the embodiment of the present application should be based on the protection scope of the claims.

Claims

1. A method for detecting the solid-liquid ratio of granular silicon material re-dosing, characterized in that: The method comprises: Using different exposures to photograph the liquid surface of the crucible into which the granular silicon material is put, to obtain a first exposure image and a second exposure image; wherein the first exposure is lower than the second exposure; determining a liquid region in the first exposure image, and determining a solid region in the second exposure image; The area ratio of the solid region in the second exposure image to the liquid region in the first exposure image is determined as the solid-liquid ratio of the liquid surface.

2. The method according to claim 1, characterized in that The method of photographing the liquid surface of the crucible into which the granular silicon material is put respectively with different exposures to obtain a first exposure image and a second exposure image comprises: photographing the liquid surface at the first exposure level and the second exposure level to obtain a plurality of images at the first exposure level and a plurality of images at the second exposure level, wherein before and after each photographing at the first exposure level, photographing is performed once at the second exposure level; The step of determining the area ratio of the solid region in the second exposure image to the liquid region in the first exposure image as the solid-liquid ratio of the liquid surface comprises: For any first exposure image, a target second exposure image is obtained by screening two second exposure images adjacent to and before the first exposure image; The area ratio of the solid region in the target second exposure image to the liquid region in the first exposure image is determined as the solid-liquid ratio of the liquid surface.

3. The method according to claim 2, characterized in that The step of selecting two second exposure images adjacent to each other before and after the first exposure image to obtain a target second exposure image includes: Determine, based on at least one of the dynamic range, saturation, contrast and brightness of each of the two second exposure images adjacent to each other before and after the first exposure image, an image quality value of each of the two second exposure images adjacent to each other before and after the first exposure image; Of the two second exposure images that are adjacent to each other before and after the first exposure image, the second exposure image with a higher image quality value is determined as the target second exposure image.

4. The method according to claim 1, characterized in that The determining of the liquid area in the first exposure image comprises: Performing grayscale processing on the first exposure image to obtain a first grayscale image; The liquid area in the first exposure image is determined according to the grayscale moment of each pixel in the first grayscale image.

5. The method according to claim 4, characterized in that The step of determining the liquid area in the first exposure image according to the grayscale moment of each pixel in the first grayscale image comprises: For any pixel point in the first grayscale image, if a change value of the grayscale moment of the pixel point and the grayscale moment of an adjacent pixel point exceeds a first threshold, the pixel point is determined as an edge pixel point; For any area surrounded by the edge pixels, if the grayscale moment of the area exceeds a second threshold, the area is determined to be the liquid area.

6. The method according to claim 1, characterized in that The determining of the solid area in the second exposure image comprises: grayscale the second exposure image, and perform denoising using a Gaussian white noise model to obtain a second grayscale image; Performing Fourier transform on the second grayscale image and performing high-pass filtering to obtain frequency domain data; Performing an inverse Fourier transform on the frequency domain data to obtain a second enhanced image; The solid area is determined according to the grayscale moment of each pixel in the second enhanced image.

7. The method according to claim 6, characterized in that The step of determining the solid region according to the grayscale moment of each pixel in the second enhanced image includes: For any pixel point in the second enhanced image, if a change value of the grayscale moment of the pixel point and the grayscale moment of an adjacent pixel point exceeds a third threshold, the pixel point is determined as an edge pixel point; For any region enclosed by the edge pixels, if the grayscale moment of the region is less than a fourth threshold, the region is determined to be the solid region.

8. A solid-liquid ratio detection device for re-dosing of granular silicon material, characterized in that: The device comprises: A shooting module, used to shoot the liquid surface of the crucible into which the granular silicon material is put, using different exposures to obtain a first exposure image and a second exposure image; wherein the first exposure is lower than the second exposure; a processing module, configured to determine a liquid region in the first exposure image and a solid region in the second exposure image; The processing module is further used to determine the area ratio of the solid area in the second exposure image to the liquid area in the first exposure image as the solid-liquid ratio of the liquid surface.

9. An electronic device, characterized in that: include: Memory, processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory, so that the processor executes the solid-liquid ratio detection method for re-dosing of granular silicon material as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the solid-to-liquid ratio detection method for re-dosing granular silicon material as described in any one of claims 1-7.

Images