A polysilicon abnormality monitoring method, device and related equipment

Abstract

The application provides a polysilicon anomaly monitoring method and device and related equipment, wherein the method comprises: acquiring a first monitoring image, wherein the first monitoring image comprises an image of a first position, and the first position is a position in a reaction furnace for placing a silicon rod; performing image analysis on the first monitoring image to obtain a plurality of candidate points; determining a pixel point corresponding to a pixel coordinate in a preset interval in the plurality of candidate points as an abnormal point, wherein the preset interval is used to indicate the first position, and the abnormal point is used to indicate a silicon rod bright spot; and marking the abnormal point on the first monitoring image. The plurality of candidate points with abnormal pixel values are obtained from the first monitoring image through image analysis; and the candidate points in the preset interval are determined as the abnormal points through coordinate matching, so as to replace the manual inspection monitoring mode and improve the monitoring effect on the silicon rod bright spot.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of polysilicon production, in particular to a polysilicon abnormality monitoring method and device and related equipment. BACKGROUND

[0002] The polysilicon reduction process is a key link in the production process, and the reduction workshop includes multiple reduction furnaces. In order to timely monitor the reaction conditions in each reduction furnace, on-site personnel need to regularly inspect the reduction furnace, observe the growth form of the silicon rod in the furnace, the clarity in the furnace, the surface color, the rod dumping situation, and the like, and judge whether the silicon rod growth in the reduction furnace is abnormal in combination with the observation situation and past experience.

[0003] Among them, the silicon rod bright spot problem is a problem that needs to be focused on in the inspection process. The silicon rod bright spot can be understood as an abnormally high temperature point generated at the lower end position of the silicon rod (i.e., the insertion position of the silicon rod in the reaction furnace) due to production failure problems. This abnormally high temperature point will appear in the field of vision in the form of a bright light point. If this abnormally high temperature point is not identified and disposed of in time, the lower end of the silicon rod will appear high-temperature fusing, which will cause the silicon rod to dump and cause serious economic losses.

[0004] It is found in applications that the above-mentioned manual inspection method for monitoring the reaction conditions in the reduction furnace is greatly disturbed by human factors, and is prone to miss the silicon rod bright spot. That is, the related technology has poor monitoring effect on the silicon rod bright spot. SUMMARY

[0005] The purpose of the embodiments of the present application is to provide a polysilicon abnormality monitoring method and device and related equipment, which can solve the problem of poor monitoring effect in the related art in monitoring the silicon rod bright spot.

[0006] In a first aspect, the embodiments of the present application provide a polysilicon abnormality monitoring method, which comprises:

[0007] obtaining a first monitoring image, wherein the first monitoring image comprises an image of a first position, and the first position is a position in the reaction furnace for placing a silicon rod;

[0008] performing image analysis on the first monitoring image to obtain a plurality of candidate points, wherein the candidate points are pixel points in the first monitoring image with pixel values greater than or equal to a pixel threshold value;

[0009] determining, as abnormal points, pixel points in the plurality of candidate points with corresponding pixel coordinates located in a preset interval, wherein the preset interval is used to represent a pixel interval corresponding to the first position in the first monitoring image, and the abnormal points are used to represent pixel points corresponding to the silicon rod bright spot;

[0010] Labeling the abnormal point on the first monitoring image.

[0011] Optionally, after the pixel point corresponding to the pixel coordinate in the preset interval in the plurality of candidate points is determined as the abnormal point, the method further comprises:

[0012] Comparing the pixel value of the abnormal point with the pixel value of a plurality of reference points respectively to obtain a plurality of similarity parameters, the plurality of similarity parameters and the plurality of reference points correspond one by one, each reference point in the plurality of reference points corresponds to a temperature interval of a silicon rod bright spot;

[0013] Determining the reference point corresponding to the similarity parameter with the largest parameter value as a target point;

[0014] Determining the bright spot information of the abnormal point according to the bright spot information of the target point, wherein the bright spot information includes temperature information of the corresponding silicon rod bright spot and processing flow information of the corresponding silicon rod bright spot.

[0015] Optionally, after the bright spot information of the abnormal point is determined according to the bright spot information of the target point, the method further comprises:

[0016] In the case that the plurality of similarity parameters are all less than or equal to a similarity threshold, storing the abnormal point as a new reference point.

[0017] Optionally, the first monitoring image comprises:

[0018] Obtaining an infrared image;

[0019] Performing image analysis on the infrared image to obtain an analysis result;

[0020] In the case that the analysis result indicates that the temperature difference between the first position and the average temperature of the silicon rod is greater than or equal to a temperature difference value, obtaining the first monitoring image.

[0021] Optionally, the time interval between the collection time of the first monitoring image and the initial time is less than or equal to 40 hours, and the initial time is the startup time of the reaction furnace.

[0022] In a second aspect, the embodiments of the present application further provide a polysilicon abnormality monitoring device, the device comprises:

[0023] An image acquisition module is configured to acquire a first monitoring image, wherein the first monitoring image comprises an image of a first position, and the first position is a position in a reaction furnace for placing a silicon rod;

[0024] an image analysis module, configured to perform image analysis on the first monitoring image to obtain a plurality of candidate points, wherein the candidate points are pixel points in the first monitoring image with pixel values greater than or equal to a pixel threshold value;

[0025] an anomaly positioning module, configured to determine, as an anomaly point, a pixel point in the plurality of candidate points with a corresponding pixel coordinate in a preset interval, wherein the preset interval represents a pixel interval corresponding to the first position in the first monitoring image, and the anomaly point represents a pixel point corresponding to a silicon rod bright spot;

[0026] a display module, configured to mark the anomaly point on the first monitoring image.

[0027] Optionally, the device further includes:

[0028] a comparison module, configured to perform similarity comparison between a pixel value of the anomaly point and pixel values of a plurality of reference points respectively to obtain a plurality of similarity parameters, wherein the plurality of similarity parameters correspond to the plurality of reference points one by one, and each reference point in the plurality of reference points corresponds to a silicon rod bright spot in a temperature interval;

[0029] a determination module, configured to determine, as a target point, a reference point corresponding to a similarity parameter with a maximum parameter value;

[0030] an information acquisition module, configured to determine bright spot information of the anomaly point according to bright spot information of the target point, wherein the bright spot information includes temperature information of a corresponding silicon rod bright spot and processing flow information of the corresponding silicon rod bright spot.

[0031] Optionally, the device further includes:

[0032] an adding module, configured to store the anomaly point as a new reference point in a case where the plurality of similarity parameters are all less than or equal to a similarity threshold value.

[0033] In a third aspect, an embodiment of the present application further provides an electronic device, including a processor, a memory, and a computer program stored in the memory and capable of running on the processor, and the computer program, when executed by the processor, implements steps of the polycrystalline silicon anomaly monitoring method.

[0034] In a fourth aspect, an embodiment of the present application further provides a computer readable storage medium, and the computer readable storage medium stores a computer program, and the computer program, when executed by a processor, implements steps of the polycrystalline silicon anomaly monitoring method.

[0035] In the embodiment of the present application, the pixel value abnormal candidate points are obtained from the first monitoring image by image analysis, and the candidate points in the preset interval are determined as the abnormal points for representing the silicon rod bright spots by coordinate matching, so as to replace the manual inspection monitoring mode, avoid the interference of human factors, reduce the occurrence probability of problems such as missing detection of the silicon rod bright spots, and improve the monitoring effect of the silicon rod bright spots. BRIEF DESCRIPTION OF DRAWINGS

[0036] Figure 1 is a flowchart of a polysilicon abnormality monitoring method provided by the embodiment of the present application;

[0037] Figure 2 is a structural schematic diagram of a polysilicon abnormality monitoring device provided by the embodiment of the present application;

[0038] Figure 3 is a structural schematic diagram of an electronic device provided by the embodiment of the present application. DETAILED DESCRIPTION

[0039] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are some of the embodiments of the present application, but not all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work fall within the scope of protection of the present application.

[0040] The embodiment of the present application provides a polysilicon abnormality monitoring method, referring to Figure 1 , Figure 1 is a flowchart of a polysilicon abnormality monitoring method provided by the embodiment of the present application, as shown in Figure 1 , comprising the following steps:

[0041] Step 101, obtaining a first monitoring image.

[0042] The first monitoring image includes an image of a first position, and the first position is a position in a reaction furnace for placing a silicon rod.

[0043] The first monitoring image can be an in-furnace image (referring to a color image) obtained by a vision mirror of a silicon rod reaction furnace. The image acquisition device can be a fixed camera arranged opposite to the vision mirror of the silicon rod reaction furnace, or a camera mounted on an inspection robot (the inspection robot periodically inspects a plurality of reaction furnaces in a reaction workshop according to a preset program).

[0044] For example, the acquisition frequency of the first monitoring image can be 1 second, 5 seconds or 1 minute, etc. The user can adaptively select the acquisition frequency of the first monitoring image according to the actual demand, and the embodiment of the present application does not limit this.

[0045] It should be noted that the reaction furnace is provided with a plurality of grooves for inserting silicon rods, and the first position is used to indicate the position of the groove, that is, the lower end position of the part of the silicon rod protruding from the groove after the silicon rod is inserted into the groove.

[0046] Step 102, image analysis is performed on the first monitoring image to obtain a plurality of candidate points.

[0047] Among them, the candidate point is a pixel point with a pixel value greater than or equal to a pixel threshold in the first monitoring image.

[0048] Exemplarily, the process of image analysis on the first monitoring image to obtain a plurality of candidate points can be: performing grayscale processing on the first monitoring image to obtain a grayscale image; and then performing binaryzation processing on the grayscale image, that is, obtaining a plurality of candidate points.

[0049] In the process of grayscale processing on the first monitoring image, the maximum value method can be used for image grayscale processing, the average value method can also be used for image grayscale processing, and the weighted average value method can also be used for image grayscale processing. The specific algorithm used for image grayscale processing is not limited in the embodiment of the application.

[0050] In the process of binaryzation processing on the grayscale image, a global threshold value method (that is, the pixel value of each pixel point in the grayscale image is compared with the pixel threshold value, and at this time, the pixel threshold value compared by each pixel point in the grayscale image is the same) can be applied, or a local adaptive dynamic threshold algorithm can be applied (that is, the pixel threshold value to be compared by each pixel point is dynamically calculated, and at this time, the pixel threshold value compared by each pixel point in the grayscale image can be the same or different), which is not limited in the embodiment of the application.

[0051] Step 103, determining a pixel point in the plurality of candidate points as an abnormal point if the corresponding pixel coordinate of the pixel point is located in a preset interval.

[0052] Among them, the preset interval is used to represent the corresponding pixel interval of the first position in the first monitoring image, and the abnormal point is used to represent the pixel point corresponding to the silicon rod bright spot.

[0053] As described above, since the position of the sight glass in the reaction furnace is fixed (i.e. the shooting position of the first monitoring image is fixed), the corresponding pixel interval of the first position in the first monitoring image is relatively fixed. Before the first monitoring image is collected, the coordinate range covered by the preset interval can be determined by the user in a manual marking manner. Then, the preset interval is applied to screen the multiple candidate points obtained in step 102, so as to identify the pixel points with pixel abnormalities (i.e. pixel values greater than or equal to a pixel threshold) and located at the first position as abnormal points, thereby reducing the probability of misidentification and improving the accuracy of the determined abnormal points.

[0054] Step 104: marking the abnormal points on the first monitoring image.

[0055] As described above, after the abnormal points are determined, the abnormal points can be marked by highlighting or framing the abnormal points on the first monitoring image, so that the user (e.g. the inspection personnel in the workshop where the reaction furnace is located) can accurately locate the position of the silicon rod bright spot and timely handle the silicon rod bright spot.

[0056] In the embodiments of the present application, multiple candidate points with pixel value abnormalities are obtained from the first monitoring image by image analysis. Then, the candidate points located in the preset interval are determined as abnormal points for representing the silicon rod bright spot by coordinate matching, so as to replace the monitoring mode of manual inspection, avoid the interference of human factors, reduce the probability of problems such as missing the silicon rod bright spot, and improve the monitoring effect of the silicon rod bright spot.

[0057] It should be noted that in actual application, after step 104 is executed, the position of the silicon rod bright spot and other information can be timely informed to the user by generating bright spot alarm information (e.g. in the form of voice broadcast, graphic display, etc.), so as to improve the identification timeliness of the silicon rod bright spot and reduce the adverse effects caused by the silicon rod bright spot.

[0058] In an optional embodiment, in addition to the screening of the multiple candidate points obtained in step 102 by the preset interval, the multiple candidate points obtained in step 102 can also be screened by a quantity threshold, i.e. multiple adjacent candidate points in the multiple candidate points are determined as a candidate point group, and the candidate point groups with a number of candidate points less than or equal to the quantity threshold are filtered out, so as to further improve the accuracy of the determined abnormal points.

[0059] In another embodiment, the multiple candidate points can be preliminarily screened based on the quantity threshold, and the multiple candidate points after the preliminary screening are further screened by the preset interval, so as to finally determine the abnormal points, which can significantly improve the accuracy of the determined abnormalities.

[0060] Optionally, after the pixel points with the corresponding pixel coordinates in the plurality of candidate points located in the preset interval are determined as the abnormal points, the method further comprises:

[0061] performing similarity comparison on the pixel value of the abnormal point and the pixel value of the plurality of reference points respectively to obtain a plurality of similarity parameters, the plurality of similarity parameters and the plurality of reference points correspond to each other, and each reference point in the plurality of reference points corresponds to a temperature interval of a silicon rod bright spot;

[0062] determining the reference point corresponding to the similarity parameter with the largest parameter value as a target point;

[0063] determining the bright spot information of the abnormal point according to the bright spot information of the target point, wherein the bright spot information includes temperature information of the corresponding silicon rod bright spot and processing flow information of the corresponding silicon rod bright spot.

[0064] In the application, the silicon rod bright spots in different temperature intervals have different pixel values corresponding to the image, and the processing flows also have differences. Therefore, the reference point information corresponding to different temperatures and the corresponding processing flow information are collected in the historical production period, and the abnormal point determined in the current production period is compared with the reference points in terms of similarity to determine the reference point closest to the abnormal point determined in the current production period, that is, to determine the target point, and then the bright spot information of the abnormal point is determined by referring to the bright spot information of the target point.

[0065] Based on the above manner, the bright spot information determination process of the abnormal point determined in the current production period can be effectively simplified, the processing efficiency of the abnormal point is improved, and the adverse effects of the silicon rod bright spot corresponding to the abnormal point are further reduced.

[0066] It should be noted that, in an example, the bright spot information of the target point can be directly used as the bright spot information of the abnormal point; and in another example, the bright spot information of the target point can be used as an initial template of the bright spot information of the abnormal point, so that the user can revise or add or delete the initial template according to the actual situation, so that the bright spot information of the determined abnormal point is adapted to the temperature and processing flow of the actual silicon rod bright spot.

[0067] The processing flow includes but is not limited to changing the temperature value in the reaction furnace, changing the ratio of hydrogen and trichlorosilane in the reaction furnace, changing the hydrogen input amount in the reaction furnace, changing the current value in the reaction furnace, changing the trichlorosilane input amount in the reaction furnace, and furnace shutdown processing.

[0068] In some optional embodiments, the gray-scale image corresponding to each reference point can also be compared with the gray-scale image corresponding to the first reference image in terms of image similarity, and an image similarity parameter of the gray-scale image corresponding to each reference point is obtained, and then the reference point corresponding to the image similarity parameter with the largest value among the plurality of image similarity parameters is determined as the target point.

[0069] Optionally, after the bright spot information of the target point is determined, the method further comprises:

[0070] In a case where the plurality of similarity parameters are all less than or equal to the similarity threshold, the abnormal point is stored as a new reference point.

[0071] As described above, after the abnormal point and the plurality of reference points are compared and the similarity parameter corresponding to each reference point among the plurality of reference points is obtained, if the plurality of similarity parameters obtained are all less than or equal to the similarity threshold, that is, the abnormal point and the first monitoring image collected in the current production period have a large difference with the data of the plurality of reference points stored in the database, the abnormal point can be stored in the database as a new reference point, so as to iteratively enrich the reference point data stored in the database, and the data accuracy of the bright spot information of the abnormal point determined subsequently is further improved.

[0072] Optionally, the first monitoring image is obtained by:

[0073] An infrared image is obtained.

[0074] An image analysis is performed on the infrared image to obtain an analysis result.

[0075] In a case where the analysis result indicates that the difference between the temperature of the first position and the average temperature of the silicon rod is greater than or equal to a temperature difference value, the first monitoring image is obtained.

[0076] As described above, since the image analysis difficulty of the infrared image is lower than that of the first monitoring image and the computing resources consumed are less, the method of periodically obtaining the infrared image and performing image analysis on the infrared image, and only in a case where the analysis result of the infrared image indicates that the difference between the temperature of the first position and the average temperature of the silicon rod is greater than or equal to a temperature difference value, the first monitoring image is continued to be collected, can reduce the acquisition frequency of the first monitoring image, and further reduce the energy consumption in the process of monitoring the bright spot of the silicon rod, so as to reduce the cost of monitoring the bright spot of the silicon rod.

[0077] It should be noted that the temperature of the first position can be obtained by counting the average value of the spectral energy of the preset interval in the infrared image, and the average temperature of the silicon rod can be obtained by counting the average value of the spectral energy of the target interval corresponding to the silicon rod in the infrared image; wherein the target area corresponding to the silicon rod is consistent with the setting mode of the preset interval.

[0078] Optionally, the time interval between the acquisition time of the first monitoring image and the initial time is less than or equal to 40 hours, and the initial time is the starting time of the reaction furnace.

[0079] It is found in the application that the silicon rod bright spot usually appears within 40 hours before a single production period, therefore, by limiting the time interval between the acquisition time of the first monitoring image and the initial time to be less than or equal to 40 hours, the actual appearance period of the silicon rod bright spot is adapted, and the invalid use of resources is avoided.

[0080] Wherein, the initial time should be understood as the time point of 0 time of the current production period, that is, the acquisition time of the first monitoring image is less than or equal to the time point of 40 time of the current production period.

[0081] Referring to Figure 2 , Figure 2 is a structure diagram of a polysilicon abnormality monitoring device 200 provided by the embodiment of the application, as Figure 2 shown, the polysilicon abnormality monitoring device 200 comprises:

[0082] An image acquisition module 201 is configured to acquire a first monitoring image, wherein the first monitoring image comprises an image of a first position, and the first position is a position in a reaction furnace for placing a silicon rod.

[0083] An image analysis module 202 is configured to perform image analysis on the first monitoring image to obtain a plurality of candidate points, wherein the candidate points are pixel points in the first monitoring image with pixel values greater than or equal to a pixel threshold value.

[0084] An abnormality positioning module 203 is configured to determine a pixel point with a corresponding pixel coordinate in the plurality of candidate points located in a preset interval as an abnormal point, wherein the preset interval is used to represent a pixel interval corresponding to the first position in the first monitoring image, and the abnormal point is used to represent a pixel point corresponding to a silicon rod bright spot.

[0085] A display module 204 is configured to mark the abnormal point on the first monitoring image.

[0086] Optionally, the device 200 further comprises:

[0087] The comparison module is used to compare the pixel value of the abnormal point with the pixel value of multiple reference points to obtain multiple similarity parameters. The multiple similarity parameters correspond one-to-one with the multiple reference points. Each of the multiple reference points corresponds to a bright spot of the silicon rod in a temperature range.

[0088] The determination module is used to determine the reference point corresponding to the similarity parameter with the largest parameter value as the target point;

[0089] The information acquisition module is used to determine the bright spot information of the abnormal point based on the bright spot information of the target point, wherein the bright spot information includes the temperature information of the corresponding silicon rod bright spot and the processing flow information of the corresponding silicon rod bright spot.

[0090] Optionally, the device 200 further includes:

[0091] A new module is added to store the outlier as a new reference point when all of the multiple similarity parameters are less than or equal to the similarity threshold.

[0092] Optionally, the image acquisition module 201 shown includes:

[0093] Infrared acquisition unit, used to acquire infrared images;

[0094] An infrared analysis unit is used to perform image analysis on the infrared image and obtain analysis results;

[0095] An image acquisition unit is configured to acquire the first monitoring image when the analysis results indicate that the temperature difference between the first location and the average temperature of the silicon rod is greater than or equal to the temperature difference value.

[0096] Optionally, the time interval between the acquisition time of the first monitoring image and the initial time is less than or equal to 40 hours, and the initial time is the start-up time of the reactor.

[0097] The polysilicon anomaly monitoring device 200 provided in this application embodiment can realize the various processes in the above method embodiments, and will not be described again here to avoid repetition.

[0098] Please see Figure 3 , Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application, such as... Figure 3 As shown, the electronic device includes: a processor 301, a memory 302, and a program 3021 stored in the memory 302 and executable on the processor 301.

[0099] When program 3021 is executed by processor 301, it can achieve the following: Figure 1Any step in the corresponding method embodiments and to achieve the same beneficial effects, hereinafter will not be repeated.

[0100] Those skilled in the art can understand that all or part of the steps of the method of the above embodiments can be completed by program instructions related to hardware, and the program can be stored in a readable medium.

[0101] The embodiments of the present application also provide a readable storage medium, the readable storage medium stores a computer program, and the computer program is executed by a processor to realize the above Figure 1 Any step in the corresponding method embodiments and to achieve the same technical effects, to avoid repetition, here will not be repeated.

[0102] The computer readable storage medium of the embodiments of the present application can adopt 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. The computer readable storage medium may, for example, be an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or apparatus, or any combination thereof. More specific examples (non-exhaustive list) of the computer readable storage medium include: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this document, the 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, device or apparatus.

[0103] The computer readable signal medium can include a data signal propagated in a baseband or as a part of a carrier wave, in which a computer readable program code is carried. Such a propagated data signal can take various forms, including but not limited to an electromagnetic signal, an optical signal or any suitable combination thereof. The computer readable signal medium can also be any computer readable medium other than the computer readable storage medium, which can send, propagate or transmit a program for use by or in conjunction with an instruction execution system, device or apparatus.

[0104] The program code contained in the storage medium can be transmitted by any suitable medium, including but not limited to wireless, wire, optical cable, RF, etc., or any suitable combination thereof.

[0105] Computer program code for carrying out operations of the present application can be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider).

[0106] The preferred embodiments of the present application have been described above with the understanding that modifications and alterations will be made by those skilled in the art based on the teachings herein. Such modifications and alterations are thus considered within the scope of this application.

Claims

1. A polysilicon abnormality monitoring method characterized by comprising: The method comprises: acquiring a first monitoring image, wherein the first monitoring image comprises an image of a first position, the first position being a position in a reaction furnace for placing a silicon rod; performing image analysis on the first monitoring image to obtain a plurality of candidate points, wherein the candidate points are pixel points in the first monitoring image with pixel values greater than or equal to a pixel threshold value; determining, as an abnormal point, a pixel point in the plurality of candidate points with a corresponding pixel coordinate located in a preset interval, wherein the preset interval is used to represent a corresponding pixel interval of the first position in the first monitoring image, and the abnormal point is used to represent a pixel point of a corresponding silicon rod bright spot; after the determination of the pixel point in the plurality of candidate points with the corresponding pixel coordinate located in the preset interval as the abnormal point, the method further comprises: performing similarity comparison of pixel values of the abnormal point and a plurality of reference points respectively to obtain a plurality of similarity parameters, the plurality of similarity parameters and the plurality of reference points correspond to each other one by one, each reference point in the plurality of reference points corresponds to a silicon rod bright spot of a temperature interval; determining, as a target point, a reference point corresponding to a similarity parameter with a maximum parameter value; and determining, according to bright spot information of the target point, bright spot information of the abnormal point, wherein the bright spot information comprises temperature information of a corresponding silicon rod bright spot and processing flow information of the corresponding silicon rod bright spot; marking the abnormal point on the first monitoring image.

2. The method of claim 1, wherein, after the determination of the bright spot information of the abnormal point according to the bright spot information of the target point, the method further comprises: in a case where the plurality of similarity parameters are all less than or equal to a similarity threshold value, storing the abnormal point as a new reference point.

3. The method of claim 1, wherein, The acquisition of the first monitoring image comprises: acquiring an infrared image; performing image analysis on the infrared image to obtain an analysis result; in a case where the analysis result indicates that a temperature difference between the first position and an average temperature of the silicon rod is greater than or equal to a temperature difference value, acquiring the first monitoring image.

4. The method of claim 1, wherein, A time interval between a collection time point of the first monitoring image and an initial time point is less than or equal to 40 hours, and the initial time point is a start time point of the reaction furnace.

5. A polysilicon abnormality monitoring apparatus characterized by comprising: comprises: an image acquisition module configured to acquire a first monitoring image, wherein the first monitoring image comprises an image of a first position, the first position being a position in a reaction furnace for placing a silicon rod; an image analysis module configured to perform image analysis on the first monitoring image to obtain a plurality of candidate points, wherein the candidate points are pixel points in the first monitoring image with pixel values greater than or equal to a pixel threshold value; an abnormal positioning module configured to determine, as an abnormal point, a pixel point in the plurality of candidate points with a corresponding pixel coordinate located in a preset interval, wherein the preset interval is used to represent a corresponding pixel interval of the first position in the first monitoring image, and the abnormal point is used to represent a pixel point of a corresponding silicon rod bright spot; The device further comprises a comparison module configured to compare the pixel value of the abnormal point with the pixel value of each of a plurality of reference points respectively to obtain a plurality of similarity parameters, wherein the plurality of similarity parameters correspond to the plurality of reference points one by one, and each of the plurality of reference points corresponds to a bright spot of a silicon rod in a temperature interval; a determination module configured to determine a reference point corresponding to a similarity parameter with the largest parameter value as a target point; and an information acquisition module configured to determine bright spot information of the abnormal point according to the bright spot information of the target point, wherein the bright spot information comprises temperature information of a corresponding bright spot of a silicon rod and processing flow information of the corresponding bright spot of the silicon rod. The device further comprises a display module configured to mark the abnormal point on the first monitoring image.

6. The apparatus of claim 5, wherein, The device further comprises: An adding module configured to store the abnormal point as a new reference point in a case where all the plurality of similarity parameters are less than or equal to a similarity threshold.

7. An electronic device, comprising: A computer program product comprising a processor, a memory, and a computer program stored on the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the steps of the polysilicon abnormality monitoring method according to any one of claims 1 to 4.

8. A readable storage medium, characterized by, A readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the polysilicon abnormality monitoring method according to any one of claims 1 to 4.

Images