A method, apparatus and related device for monitoring a silicon rod

Abstract

The application provides a silicon rod monitoring method and device and related equipment, wherein the method comprises: acquiring a first monitoring image of a to-be-detected silicon rod; performing image analysis on the first monitoring image to determine a number parameter of black spot regions in the first monitoring image and an area parameter of the black spot regions in the first monitoring image; and generating a warning information in a case where the number parameter is greater than or equal to a first threshold value and / or the area parameter is greater than or equal to a second threshold value. Through the acquisition of the first monitoring image of the to-be-detected silicon rod, the extraction of the number parameter and the area parameter of the black spot regions in the first monitoring image, and the generation of the warning information in a case where the number parameter and / or the area parameter indicate that the proportion of the black spots in the to-be-detected silicon rod is too large, an automatic monitoring mode is used to replace a manual inspection monitoring mode, human factors are avoided, the probability of false judgment of abnormal silicon rods or missed judgment of abnormal silicon rods is reduced, and the monitoring effect on the growth of the silicon rod is improved.

Description

Technical Field

[0001] This application relates to the field of polysilicon production technology, specifically to a silicon rod monitoring method, apparatus, and related equipment. Background Technology

[0002] The polysilicon reduction process is a critical step in the production process. The reduction workshop includes multiple reduction furnaces. In order to monitor the reaction status (i.e. the growth status of silicon rods in the furnace) in a timely manner, on-site personnel need to regularly inspect the reduction furnaces, observe the growth morphology of silicon rods in the furnace, the clarity of the furnace, the surface color, the condition of the rods being turned over, etc., and judge whether there are any abnormalities in the growth of silicon rods in the reduction furnace based on the observations and past experience.

[0003] In application, it was found that the above-mentioned manual inspection method for monitoring the reaction status in the reduction furnace is greatly affected by human factors, and is prone to misjudging abnormal silicon rods or missing abnormal silicon rods. In other words, the related technology has poor monitoring effect on the growth status of silicon rods. Summary of the Invention

[0004] The purpose of this application is to provide a silicon rod monitoring method, apparatus, and related equipment to solve the problem of poor monitoring effect in related technologies when monitoring the growth status of silicon rods.

[0005] In a first aspect, embodiments of this application provide a silicon rod monitoring method, the method comprising:

[0006] Acquire the first monitoring image of the silicon rod to be inspected;

[0007] Image analysis is performed on the first monitoring image to determine the number of black spot regions in the first monitoring image and the area of ​​the black spot regions in the first monitoring image.

[0008] A warning message is generated if the number parameter is greater than or equal to a first threshold, and / or the area parameter is greater than or equal to a second threshold.

[0009] Optionally, the step of performing image analysis on the first monitoring image to determine the number of dark spot regions in the first monitoring image and the area of ​​the dark spot regions in the first monitoring image includes:

[0010] The first monitoring image is converted to grayscale to obtain a grayscale image;

[0011] Perform connected component analysis on the silicon rod image included in the grayscale image to determine at least one black spot patch included in the silicon rod image;

[0012] Based on the at least one black spot patch, determine the number parameter of black spot regions in the first monitoring image and the area parameter of black spot regions in the first monitoring image.

[0013] Optionally, the method further includes:

[0014] Acquire a second monitoring image of the silicon rod to be tested and a time parameter corresponding to the second monitoring image, wherein the time parameter is used to indicate the growth time of the silicon rod to be tested;

[0015] The similarity of the reference image corresponding to the time parameter is compared with the silicon rod image included in the second monitoring image to obtain the comparison result. The reference image is used to indicate the loose silicon rod.

[0016] Based on the comparison results, the quality information of the silicon rod to be tested is determined.

[0017] Optionally, a similarity comparison is performed between the reference image corresponding to the time parameter and the silicon rod image included in the second monitoring image to obtain a comparison result, including:

[0018] The similarity of at least two reference images corresponding to the time parameters is compared with the silicon rod image included in the second monitoring image to obtain the comparison parameters corresponding to each of the at least two reference images;

[0019] The comparison parameters corresponding to each of the at least two reference images are averaged to obtain the comparison result.

[0020] Optionally, determining the quality information of the silicon rod to be tested based on the comparison result includes:

[0021] If the comparison result indicates that the silicon rod corresponding to the image to be detected is a loose silicon rod, a connected component analysis is performed on the silicon rod image included in the second monitoring image to determine N gap patches. The gap patches are used to indicate the gaps between multiple silicon particles on the surface of the silicon rod to be detected, where N is an integer greater than or equal to 1.

[0022] The quality information of the silicon rod to be tested is determined based on the area of ​​the M gap blocks, wherein the M gap blocks are the first M gap blocks arranged from largest to smallest area among the N gap blocks.

[0023] Secondly, embodiments of this application also provide a silicon rod monitoring device, the device comprising:

[0024] The first acquisition module is used to acquire the first monitoring image of the silicon rod to be inspected;

[0025] The first analysis module is used to perform image analysis on the first monitoring image to determine the number of black spot regions in the first monitoring image and the area of ​​the black spot regions in the first monitoring image.

[0026] The warning module is used to generate a warning message when the number parameter is greater than or equal to a first threshold and / or the area parameter is greater than or equal to a second threshold.

[0027] Optionally, the first analysis module includes:

[0028] The grayscale processing submodule is used to perform grayscale processing on the first monitoring image to obtain a grayscale image;

[0029] The connected component analysis submodule is used to perform connected component analysis on the silicon rod image included in the grayscale image to determine at least one black spot patch included in the silicon rod image;

[0030] The parameter determination submodule is used to determine the number parameter of black spot regions in the first monitoring image and the area parameter of black spot regions in the first monitoring image based on the at least one black spot patch.

[0031] Optionally, the silicon rod monitoring device further includes:

[0032] The second acquisition module is used to acquire a second monitoring image of the silicon rod to be tested and a time parameter corresponding to the second monitoring image, wherein the time parameter is used to indicate the growth time of the silicon rod to be tested;

[0033] An image comparison module is used to compare the similarity between a reference image corresponding to the time parameter and the silicon rod image included in the second monitoring image to obtain a comparison result. The reference image is used to indicate the loose silicon rod.

[0034] The quality analysis module is used to determine the quality information of the silicon rod to be tested based on the comparison results.

[0035] Thirdly, embodiments of this application also provide an electronic device, including a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the steps of the silicon rod monitoring method described above.

[0036] Fourthly, embodiments of this application also provide a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the silicon rod monitoring method described above.

[0037] In this embodiment of the application, an automated monitoring method is used to replace the manual inspection monitoring method by acquiring a first monitoring image of the silicon rod to be inspected, extracting the number and area parameters of the reported black spot areas in the first monitoring image, and generating warning information when the number and / or area parameters indicate that the proportion of black spots in the silicon rod to be inspected is too large. This avoids interference from human factors, reduces the probability of misjudging or missing abnormal silicon rods, and improves the monitoring effect on the growth status of silicon rods. Attached Figure Description

[0038] Figure 1 This is a flowchart of a silicon rod monitoring method provided in an embodiment of this application;

[0039] Figure 2 This is a schematic diagram of a silicon rod image included in a second monitoring image provided in an embodiment of this application;

[0040] Figure 3 This is a schematic diagram of the structure of a silicon rod monitoring device provided in an embodiment of this application;

[0041] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0042] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0043] This application provides a method for monitoring silicon rods. See also... Figure 1 , Figure 1 This is a flowchart of the silicon rod monitoring method provided in the embodiments of this application, such as... Figure 1 As shown, it includes the following steps:

[0044] Step 101: Obtain the first monitoring image of the silicon rod to be tested.

[0045] The first monitoring image can be an image inside the silicon rod reduction furnace captured by an image acquisition device through the sight glass of the silicon rod reduction furnace. The image acquisition device can be a fixed camera set directly opposite the sight glass of the silicon rod reduction furnace, or it can be a camera mounted on an inspection robot (the inspection robot periodically inspects multiple reaction furnaces in the reaction workshop according to a preset program).

[0046] For example, the acquisition frequency of the first monitoring image can be once per second, once every 5 seconds, or once per minute, etc. The user can adaptively select the acquisition frequency of the first monitoring image according to actual needs, and this application embodiment does not limit this.

[0047] Step 102: Perform image analysis on the first monitoring image to determine the number of black spot regions in the first monitoring image and the area of ​​the black spot regions in the first monitoring image.

[0048] After acquiring the first monitoring image, image analysis can be performed on the first monitoring image to distinguish the background patches, normal silicon rod patches, and silicon rod black spot patches included in the first monitoring image. Based on the distinction results, the number parameter and area parameter corresponding to the silicon rod black spot patches can be determined. The number parameter corresponding to the silicon rod black spot patches (i.e., the number parameter of black spot areas in the first monitoring image) can be understood as the total number of silicon rod black spot patches included in the first monitoring image, and the area parameter corresponding to the silicon rod black spot patches (i.e., the area parameter of black spot areas in the first monitoring image) can be understood as the patch area of ​​each silicon rod black spot patch among the multiple silicon rod black spot patches included in the first monitoring image.

[0049] For example, image analysis of the first monitoring image can be performed based on a connected component algorithm, which can be a two-pass method or a seed-filling method.

[0050] Step 103: If the number parameter is greater than or equal to the first threshold, and / or the area parameter is greater than or equal to the second threshold, generate a warning message.

[0051] By setting a first threshold and a second threshold in combination, the abnormal growth of silicon rods caused by excessive spread of black spots inside the silicon rods is quantified. Silicon rods with an excessive number of black spots and / or silicon rods with excessively large black spot areas are identified as silicon rods in an abnormal growth state, and corresponding warning messages are generated to remind the staff in the reaction workshop to take timely measures to deal with silicon rods in an abnormal growth state (such as increasing the amount of hydrogen in the reactor or reducing the temperature in the reactor), so as to prevent the black spot problem in the silicon rods under test from deteriorating further.

[0052] It should be noted that the above area parameter can be understood as the area of ​​the largest black spot region among the multiple black spot regions included in the first monitoring image, or as the sum of the areas of the multiple black spot regions included in the first monitoring image. Users can determine the meaning of the above area parameter according to actual needs, and this application embodiment does not limit it in this way.

[0053] For example, if the first monitoring image includes two black spot areas, one of which has a block area of ​​25 and the other has a block area of ​​20, then the aforementioned area parameter can be 25 or 45.

[0054] As described above, an automated monitoring method is used to acquire a first monitoring image of the silicon rod to be inspected, extract the number and area parameters of the reported black spot regions in the first monitoring image, and generate warning information when the number and / or area parameters indicate that the proportion of black spots in the silicon rod to be inspected is too large. This method replaces the monitoring method of manual inspection, avoids interference from human factors, reduces the probability of misjudging or missing abnormal silicon rods, and improves the monitoring effect on the growth status of silicon rods.

[0055] In some implementations, if the first monitoring image is an image captured by a camera mounted on the inspection robot, a warning message is generated. After the staff handles the silicon rod in an abnormal growth condition, the inspection robot can return to the furnace sight glass indicated by the aforementioned warning message to re-inspect the silicon rod to be inspected. If the re-inspection passes, the periodic inspection mode is restored. If the re-inspection fails, a warning message is generated again.

[0056] Optionally, the step of performing image analysis on the first monitoring image to determine the number of dark spot regions in the first monitoring image and the area of ​​the dark spot regions in the first monitoring image includes:

[0057] The first monitoring image is converted to grayscale to obtain a grayscale image;

[0058] Perform connected component analysis on the silicon rod image included in the grayscale image to determine at least one black spot patch included in the silicon rod image;

[0059] Based on the at least one black spot patch, determine the number parameter of black spot regions in the first monitoring image and the area parameter of black spot regions in the first monitoring image.

[0060] The grayscale processing of the first monitoring image serves two purposes: firstly, to facilitate subsequent connected component analysis and ensure its accuracy; and secondly, to filter out background noise present in the first monitoring image.

[0061] For example, the process of performing connected component analysis on the silicon rod image included in the grayscale image to determine at least one black patch included in the silicon rod image can be as follows:

[0062] Perform a first connected component analysis on the grayscale image to determine the silicon rod image included in the grayscale image;

[0063] The silicon rod image included in the grayscale image is subjected to inverse binarization and second connected component analysis to determine at least one black spot patch included in the silicon rod image.

[0064] In the above process, the silicon rod image included in the grayscale image is determined first in order to avoid interference from background patches and improve the extraction efficiency and accuracy of black spot patches.

[0065] The process of performing inverse binarization on the silicon rod image included in the grayscale image can be as follows: compare the pixel value of each pixel block in the silicon rod image included in the grayscale image with a pixel threshold, set the pixel value of the pixel block greater than the pixel threshold to 0 (i.e., black), and set the pixel value of the pixel block less than or equal to the pixel threshold to 255 (i.e., white).

[0066] During the second connected component analysis, multiple adjacent zero-value pixel blocks will be identified as a black spot patch. At this time, the number of black spot regions in the first monitoring image can be obtained accordingly. Then, by counting the number of pixel blocks included in each black spot patch, the area parameter of the black spot region in the first monitoring image can be determined.

[0067] Optionally, the method further includes:

[0068] Acquire a second monitoring image of the silicon rod to be tested and a time parameter corresponding to the second monitoring image, wherein the time parameter is used to indicate the growth time of the silicon rod to be tested;

[0069] The similarity of the reference image corresponding to the time parameter is compared with the silicon rod image included in the second monitoring image to obtain the comparison result. The reference image is used to indicate the loose silicon rod.

[0070] Based on the comparison results, the quality information of the silicon rod to be tested is determined.

[0071] Finished silicon rods are generally divided into two categories: dense silicon rods (superior quality) and loose silicon rods (good quality). Loose silicon rods are also known as cauliflower-shaped silicon rods. Since the appearance of loose silicon rods varies significantly at different growth stages, this application embodiment will determine the quality information of the silicon rod to be tested by acquiring a second monitoring image and comparing the similarity between a reference image matching the time parameters of the second monitoring image and the second monitoring image, that is, determining whether the silicon rod to be tested is a loose silicon rod.

[0072] In one example, the time parameter can be the growth stage of the silicon rod under test when the second monitoring image is captured, wherein the growth stage includes a first stage (0-30 hours), a second stage (30-60 hours), a third stage (60-80 hours), and a fourth stage (80-100 hours), and the total growth time of the silicon rod is 100 hours.

[0073] In another example, the time parameter can also be the growth time of the silicon rod under test when the second monitoring image is captured, such as 5 hours, 27 hours, 36 hours, etc.

[0074] The reference image corresponding to the time parameter can be understood as any image whose image acquisition time / segment is consistent with the time parameter being retrieved from a preset image database based on the time parameter. Each image acquisition time / segment in the image database corresponds to at least 50 images.

[0075] The process of determining the quality information of the silicon rod to be tested based on the comparison results can be as follows:

[0076] If the comparison result indicates that the reference image corresponding to the time parameter is relatively similar to the second monitoring image (meaning the similarity parameter is greater than or equal to the similarity threshold), the silicon rod to be detected is identified as a loose silicon rod; if the comparison result indicates that the reference image corresponding to the time parameter is significantly different from the second monitoring image (meaning the similarity parameter is less than the similarity threshold), the silicon rod to be detected is identified as a dense silicon rod. The similarity parameter can be understood as a parameter obtained by comparing the similarity of multiple reference images corresponding to the time parameter with the silicon rod images included in the second monitoring image, and the similarity parameter is included in the comparison result.

[0077] When the quality information of the silicon rod to be tested indicates that the silicon rod to be tested is a loose silicon rod, a prompt message can be generated to provide feedback to relevant personnel. This allows the relevant personnel to locate the loose silicon rod based on the prompt message and take timely action to minimize the production quantity of loose silicon rods and improve the overall yield of high-quality products in the reaction workshop.

[0078] Optionally, a similarity comparison is performed between the reference image corresponding to the time parameter and the silicon rod image included in the second monitoring image to obtain a comparison result, including:

[0079] The similarity of at least two reference images corresponding to the time parameters is compared with the silicon rod image included in the second monitoring image to obtain the comparison parameters corresponding to each of the at least two reference images;

[0080] The comparison parameters corresponding to each of the at least two reference images are averaged to obtain the comparison result.

[0081] As described above, by calculating the average of multiple comparison parameters to determine the similarity value (i.e., the aforementioned similarity parameters), and generating the comparison result based on the similarity value, the bias problem inherent in comparing a single reference image can be avoided, thus improving the accuracy of the finally determined similarity parameters. The comparison parameters can be understood as parameters obtained by comparing the similarity between the corresponding reference image and the silicon rod image included in the second monitoring image.

[0082] For example, if the at least two reference images corresponding to the time parameter are a first reference image and a second parameter image, and the parameter value obtained by comparing the silicon rod image included in the first reference image and the second monitoring image is 0.7, and the parameter value obtained by comparing the silicon rod image included in the second reference image and the second monitoring image is 0.9, then the similarity value corresponding to the comparison result is 0.8.

[0083] Optionally, determining the quality information of the silicon rod to be tested based on the comparison result includes:

[0084] If the comparison result indicates that the silicon rod corresponding to the image to be detected is a loose silicon rod, a connected component analysis is performed on the silicon rod image included in the second monitoring image to determine N gap patches. The gap patches are used to indicate the gaps between multiple silicon particles on the surface of the silicon rod to be detected, where N is an integer greater than or equal to 1.

[0085] The quality information of the silicon rod to be tested is determined based on the area of ​​M gap patches, wherein the M gap patches are the first M gap patches arranged from largest to smallest area among the N gap patches, and M is a positive integer less than or equal to N.

[0086] As shown above, if the comparison results indicate that the silicon rod to be tested is a loose silicon rod, the second monitoring image can be further analyzed to determine the looseness of the silicon rod to be tested and generate corresponding warning information to guide the staff to take appropriate measures to match the looseness of the silicon rod to be tested.

[0087] Before performing connected component analysis on the silicon rod image included in the second monitoring image, dynamic threshold binarization can be performed on the second monitoring image to filter out some image noise and improve the accuracy of the subsequent connected component analysis.

[0088] like Figure 2 As shown, after dynamic threshold binarization, the gap blocks within the silicon rod image included in the second monitoring image can be clearly displayed. Figure 2 The block shown in the dashed box is the gap block, which is used to indicate the particle gaps between particles on the surface of the loose silicon rod.

[0089] It should be noted that in practical applications, after dynamic threshold binarization, the gap patch should be a white patch, while the non-gap patch area should be a black patch.

[0090] For example, when N is greater than or equal to 5, the specific value of M can be 5.

[0091] The process of determining the quality information of the silicon rod to be tested based on the area of ​​the M gap patches can be as follows:

[0092] Calculate the average area of ​​the M gap tiles to obtain the mean parameter;

[0093] The ratio of the mean parameter to the baseline parameter is determined as the quality parameter;

[0094] The quality information is generated based on the quality parameters.

[0095] The reference parameter can be understood as the maximum gap area that can be achieved between particles on the surface of the porous silicon rod. When the mass parameter is less than or equal to 35%, the mass information is used to indicate that the cauliflower condition of the silicon rod under test is in the early stage; when the mass parameter is between 35% and 65%, the mass information is used to indicate that the cauliflower condition of the silicon rod under test is in the middle stage; when the mass parameter is between 65% and 85%, the mass information is used to indicate that the cauliflower condition of the silicon rod under test is in the late stage; and when the mass parameter is greater than 85%, the mass information is used to indicate that the cauliflower condition of the silicon rod under test is in the final stage.

[0096] In applications, the silicon rod monitoring method provided in this application embodiment can reduce labor costs in the silicon rod production process, increase the annual output of dense silicon rods by 5% or more, and improve the atomization detection and control rate by 50% or more.

[0097] See Figure 3 , Figure 3 This is a structural diagram of the silicon rod monitoring device 300 provided in an embodiment of this application. Figure 3 As shown, the silicon rod monitoring device 300 includes:

[0098] The first acquisition module 301 is used to acquire a first monitoring image of the silicon rod to be inspected;

[0099] The first analysis module 302 is used to perform image analysis on the first monitoring image to determine the number parameters of black spot regions in the first monitoring image and the area parameters of black spot regions in the first monitoring image.

[0100] Warning module 303 is used to generate warning information when the number parameter is greater than or equal to a first threshold and / or the area parameter is greater than or equal to a second threshold.

[0101] Optionally, the first analysis module 302 includes:

[0102] The grayscale processing submodule is used to perform grayscale processing on the first monitoring image to obtain a grayscale image;

[0103] The connected component analysis submodule is used to perform connected component analysis on the silicon rod image included in the grayscale image to determine at least one black spot patch included in the silicon rod image;

[0104] The parameter determination submodule is used to determine the number parameter of black spot regions in the first monitoring image and the area parameter of black spot regions in the first monitoring image based on the at least one black spot patch.

[0105] Optionally, the silicon rod monitoring device 300 further includes:

[0106] The second acquisition module is used to acquire a second monitoring image of the silicon rod to be tested and a time parameter corresponding to the second monitoring image, wherein the time parameter is used to indicate the growth time of the silicon rod to be tested;

[0107] An image comparison module is used to compare the similarity between a reference image corresponding to the time parameter and the silicon rod image included in the second monitoring image to obtain a comparison result. The reference image is used to indicate the loose silicon rod.

[0108] The quality analysis module is used to determine the quality information of the silicon rod to be tested based on the comparison results.

[0109] Optionally, the image comparison module includes:

[0110] An image comparison unit is used to compare the similarity of at least two reference images corresponding to the time parameter with the silicon rod image included in the second monitoring image, and obtain the comparison parameter corresponding to each of the at least two reference images;

[0111] The mean calculation unit is used to calculate the mean of the comparison parameters corresponding to each of the at least two reference images to obtain the comparison result.

[0112] Optionally, the quality analysis module includes:

[0113] The first quality analysis unit is used to perform connected component analysis on the silicon rod image included in the second monitoring image when the comparison result indicates that the silicon rod corresponding to the image to be detected is a loose silicon rod, and to determine N gap patches. The gap patches are used to indicate the gaps between multiple silicon particles on the surface of the silicon rod to be detected, where N is an integer greater than or equal to 1.

[0114] The second quality analysis unit is used to determine the quality information of the silicon rod to be tested based on the area of ​​the M gap blocks, wherein the M gap blocks are the first M gap blocks arranged from largest to smallest area among the N gap blocks.

[0115] The silicon rod monitoring device 300 provided in this application embodiment can implement the various processes in the above method embodiments, and will not be described again here to avoid repetition.

[0116] Please see Figure 4 , Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application, such as... Figure 4 As shown, the electronic device includes: a processor 401, a memory 402, and a program 4021 stored in the memory 402 and executable on the processor 401.

[0117] When program 4021 is executed by processor 401, it can achieve the following: Figure 1 Any steps in the corresponding method embodiments and the achievement of the same beneficial effects will not be repeated here.

[0118] Those skilled in the art will understand that all or part of the steps of the methods described in the above embodiments can be implemented by hardware related to program instructions, and the program can be stored in a readable medium.

[0119] This application embodiment also provides a readable storage medium storing a computer program, which, when executed by a processor, can perform the above-described functions. Figure 1 Any step in the corresponding method embodiment can achieve the same technical effect, and will not be repeated here to avoid repetition.

[0120] The computer-readable storage medium of this application embodiment can be any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. For example, a computer-readable storage medium can be an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0121] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, capable of sending, propagating, or transmitting programs for use by or in connection with an instruction execution system, apparatus, or device.

[0122] The program code contained on the storage medium can be transmitted using any suitable medium, including but not limited to wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0123] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or terminal. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0124] The above description represents the preferred embodiments of this application. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles described in this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A method for monitoring silicon rods, characterized in that, The method includes: Acquire the first monitoring image of the silicon rod to be inspected; Image analysis is performed on the first monitoring image to determine the number of black spot regions in the first monitoring image and the area of ​​the black spot regions in the first monitoring image. If the number parameter is greater than or equal to a first threshold, and / or the area parameter is greater than or equal to a second threshold, a warning message is generated; The method further includes: Acquire a second monitoring image of the silicon rod to be tested and a time parameter corresponding to the second monitoring image, wherein the time parameter is used to indicate the growth time of the silicon rod to be tested; The similarity of the reference image corresponding to the time parameter is compared with the silicon rod image included in the second monitoring image to obtain the comparison result. The reference image is used to indicate the loose silicon rod. Based on the comparison results, the quality information of the silicon rod to be tested is determined; Determining the quality information of the silicon rod to be tested based on the comparison result includes: If the comparison result indicates that the silicon rod corresponding to the second monitoring image is a loose silicon rod, a connected component analysis is performed on the silicon rod image included in the second monitoring image to determine N gap patches. The gap patches are used to indicate the gaps between multiple silicon particles on the surface of the silicon rod to be detected, where N is an integer greater than or equal to 1. The quality information of the silicon rod to be tested is determined based on the area of ​​M gap patches, wherein the M gap patches are the first M gap patches arranged from largest to smallest area among the N gap patches, and M is a positive integer less than or equal to N; Specifically, when the quality parameter is less than or equal to 35%, the quality information indicates that the cauliflower-like condition of the silicon rod under test is in the early stage; when the quality parameter is between 35% and 65%, the quality information indicates that the cauliflower-like condition of the silicon rod under test is in the middle stage; when the quality parameter is between 65% and 85%, the quality information indicates that the cauliflower-like condition of the silicon rod under test is in the late stage; and when the quality parameter is greater than 85%, the quality information indicates that the cauliflower-like condition of the silicon rod under test is in the final stage. The quality parameter is the ratio of the mean parameter to the reference parameter. The mean parameter is the average area of ​​the M gap patches. The reference parameter is the maximum gap area that can be achieved between the particles on the surface of the loose silicon rod.

2. The method according to claim 1, characterized in that, The step of performing image analysis on the first monitoring image to determine the number of dark spot regions and the area of ​​dark spot regions in the first monitoring image includes: The first monitoring image is converted to grayscale to obtain a grayscale image; Perform connected component analysis on the silicon rod image included in the grayscale image to determine at least one black spot patch included in the silicon rod image; Based on the at least one black spot patch, determine the number parameter of black spot regions in the first monitoring image and the area parameter of black spot regions in the first monitoring image.

3. The method according to claim 1, characterized in that, The similarity of the reference image corresponding to the time parameter is compared with the silicon rod image included in the second monitoring image to obtain the comparison result, including: The similarity of at least two reference images corresponding to the time parameters is compared with the silicon rod image included in the second monitoring image to obtain the comparison parameters corresponding to each of the at least two reference images; The comparison parameters corresponding to each of the at least two reference images are averaged to obtain the comparison result.

4. A silicon rod monitoring device, characterized in that, The device includes: The first acquisition module is used to acquire the first monitoring image of the silicon rod to be inspected; The first analysis module is used to perform image analysis on the first monitoring image to determine the number of black spot regions in the first monitoring image and the area of ​​the black spot regions in the first monitoring image. The warning module is used to generate a warning message when the number parameter is greater than or equal to a first threshold, and / or the area parameter is greater than or equal to a second threshold; The silicon rod monitoring device also includes: The second acquisition module is used to acquire a second monitoring image of the silicon rod to be tested and a time parameter corresponding to the second monitoring image, wherein the time parameter is used to indicate the growth time of the silicon rod to be tested; An image comparison module is used to compare the similarity between a reference image corresponding to the time parameter and the silicon rod image included in the second monitoring image to obtain a comparison result. The reference image is used to indicate the loose silicon rod. A quality analysis module is used to determine the quality information of the silicon rod to be tested based on the comparison results. The quality analysis module includes: The first quality analysis unit is used to perform connected component analysis on the silicon rod image included in the second monitoring image when the comparison result indicates that the silicon rod corresponding to the second monitoring image is a loose silicon rod, and to determine N gap patches. The gap patches are used to indicate the gaps between multiple silicon particles on the surface of the silicon rod to be tested, where N is an integer greater than or equal to 1. The second quality analysis unit is used to determine the quality information of the silicon rod to be tested based on the area of ​​M gap blocks, wherein the M gap blocks are the first M gap blocks arranged from largest to smallest area among the N gap blocks, and M is a positive integer less than or equal to N; Specifically, when the quality parameter is less than or equal to 35%, the quality information indicates that the cauliflower-like condition of the silicon rod under test is in the early stage; when the quality parameter is between 35% and 65%, the quality information indicates that the cauliflower-like condition of the silicon rod under test is in the middle stage; when the quality parameter is between 65% and 85%, the quality information indicates that the cauliflower-like condition of the silicon rod under test is in the late stage; and when the quality parameter is greater than 85%, the quality information indicates that the cauliflower-like condition of the silicon rod under test is in the final stage. The quality parameter is the ratio of the mean parameter to the reference parameter. The mean parameter is the average area of ​​the M gap patches. The reference parameter is the maximum gap area that can be achieved between the particles on the surface of the loose silicon rod.

5. The apparatus according to claim 4, characterized in that, The first analysis module includes: The grayscale processing submodule is used to perform grayscale processing on the first monitoring image to obtain a grayscale image; The connected component analysis submodule is used to perform connected component analysis on the silicon rod image included in the grayscale image to determine at least one black spot patch included in the silicon rod image; The parameter determination submodule is used to determine the number parameter of black spot regions in the first monitoring image and the area parameter of black spot regions in the first monitoring image based on the at least one black spot patch.

6. An electronic device, characterized in that, It includes a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the steps of the silicon rod monitoring method as described in any one of claims 1 to 3.

7. A readable storage medium, characterized in that, The readable storage medium stores a computer program that, when executed by a processor, implements the steps of the silicon rod monitoring method as described in any one of claims 1 to 3.

Images