Method, device and related equipment for predicting production quality and output of reduction furnace

Abstract

In the embodiment of the present application, by obtaining the first equipment parameter of the first reduction furnace, the first equipment parameter includes: at least one of the furnace barrel diameter, furnace top shape and nozzle distribution; based on the first relationship model and the first equipment parameter, the first target information of the first reduction furnace is predicted, and the first target information includes: the quality information and output information of the polysilicon produced by the first reduction furnace. In this way, under the same working conditions, according to the first relationship model between the equipment parameters of different reduction furnaces and the quality and output information of the polysilicon produced by different reduction furnaces, the quality and output of the polysilicon produced by the reduction furnaces with different equipment parameters are predicted, and a more accurate prediction result is obtained. According to the more accurate prediction result, multiple reduction furnaces with different equipment parameters are arranged for production, which can save production resources.

Description

Technical Field

[0001] The present application relates to the technical field of polysilicon, and in particular to a method, device and related equipment for predicting the production quality and output of a reduction furnace. Background Art

[0002] In the production process of polysilicon, many factors will affect the quality and output of polysilicon. Polysilicon manufacturers need to respond to changes in market demand to produce polysilicon. Reduction furnaces with different equipment parameters, under the same working conditions (the total flow of chlorosilane and hydrogen input to the reduction furnace is the same and the current input to the reduction furnace is the same), the quality and output of the polysilicon produced are also different. Polysilicon manufacturers usually select reduction furnaces with different equipment parameters to produce polysilicon based on manual experience. In order to ensure that the quality and output of the produced polysilicon meet market demand, when predicting the production quality and output information of reduction furnaces with different equipment parameters through manual experience, it is usually necessary to make a large redundant prediction, that is, when only 30 tons of polysilicon need to be produced, the total amount of polysilicon produced by the selected reduction furnace is predicted to be 35 tons through manual experience.

[0003] Therefore, predicting and selecting reduction furnaces with different equipment parameters to produce polysilicon based on manual experience will lead to a waste of production resources. Summary of the invention

[0004] The purpose of the embodiments of the present application is to provide a method, device and related equipment for predicting the production quality and output of a reduction furnace, so as to solve the problem of wasting production resources by predicting and selecting reduction furnaces with different equipment parameters to produce polysilicon based on manual experience.

[0005] In a first aspect, an embodiment of the present application provides a method for predicting production quality and output of a reduction furnace, comprising:

[0006] Acquiring first equipment parameters of the first reduction furnace, the first equipment parameters comprising: at least one of a furnace barrel diameter, a furnace top shape, and a nozzle distribution;

[0007] Under the same working conditions, based on the first relationship model and the first equipment parameters, the first target information of the first reduction furnace is predicted, the first target information includes: the quality information and output information of the polysilicon produced by the first reduction furnace, the first relationship model is used to characterize the correlation between the equipment parameters of the reduction furnace and the quality information and output information of the polysilicon produced by the reduction furnace, and the working conditions include: the total flow rate of input chlorosilane and the total flow rate of hydrogen and the input current.

[0008] Optionally, before predicting the first target information of the first reduction furnace based on the first relationship model and the first equipment parameter, the method further includes:

[0009] Obtain historical data of different reduction furnaces under the same working conditions, including equipment parameters, operating status information, and polysilicon quality and output information;

[0010] According to the equipment parameters and the operation status information, a second relationship model is established, where the second relationship model is used to characterize the association relationship between the equipment parameters of the reduction furnace and the operation status information of the reduction furnace;

[0011] A third relationship model is established according to the operation status information and the quality and yield information of the polysilicon, wherein the third relationship model is used to characterize the correlation between the operation status information of the reduction furnace and the quality and yield information of the polysilicon produced by the reduction furnace;

[0012] A first relationship model is established according to the second relationship model and the third relationship model.

[0013] Optionally, the equipment parameters include a furnace diameter, and the operation status information includes a silicon rod temperature; and establishing the second relationship model according to the equipment parameters and the operation status information includes:

[0014] According to the furnace diameter and the silicon rod temperature, a first sub-relationship model is established, and the first sub-relationship model is used to characterize the correlation between the furnace diameter and the silicon rod temperature.

[0015] Optionally, the equipment parameters include nozzle distribution, and the operation status information includes uniformity of gas distribution; and establishing the second relationship model according to the equipment parameters and the operation status information includes:

[0016] According to the nozzle distribution situation and the uniformity of gas distribution, a second sub-relationship model is established, and the second sub-relationship model is used to characterize the correlation relationship between the nozzle distribution situation and the uniformity of gas distribution.

[0017] Optionally, the operation status information includes silicon rod temperature, and the quality and yield information of polysilicon includes cauliflower ratio of polysilicon; and establishing the third relationship model according to the operation status information and the quality and yield information of polysilicon includes:

[0018] According to the silicon rod temperature and the cauliflower ratio of polysilicon, a third sub-relationship model is established, and the third sub-relationship model is used to characterize the correlation between the silicon rod temperature and the cauliflower ratio of polysilicon.

[0019] Optionally, after predicting the first target information of the first reduction furnace based on the first relationship model and the first equipment parameter, the method further includes:

[0020] Obtaining a deviation value between quality information and yield information of polysilicon actually produced by the first reduction furnace and quality information and yield information of polysilicon produced by the first reduction furnace;

[0021] The first relationship model is calibrated according to the deviation value.

[0022] In a second aspect, an embodiment of the present application provides a device for predicting production quality and output of a reduction furnace, comprising:

[0023] An acquisition module, used to acquire first equipment parameters of the first reduction furnace, the first equipment parameters including: at least one of a furnace barrel diameter, a furnace top shape, and a nozzle distribution;

[0024] A prediction module is used to predict the first target information of the first reduction furnace under the same working conditions based on the first relationship model and the first equipment parameters, the first target information including: the quality information and output information of the polysilicon produced by the first reduction furnace, the first relationship model is used to characterize the correlation between the equipment parameters of the reduction furnace and the quality information and output information of the polysilicon produced by the reduction furnace, and the working conditions include: the total flow rate of the input chlorosilane and the total flow rate of the hydrogen and the input current.

[0025] Optionally, the device for predicting the production quality and output of the reduction furnace further includes:

[0026] The second acquisition module is used to acquire historical data of different reduction furnaces under the same working conditions, the historical data including: equipment parameters, operating status information, and quality and output information of polysilicon, and the working conditions including: total flow rate of input chlorosilane and total flow rate of hydrogen and input current;

[0027] A first establishing module is used to establish a second relationship model according to the equipment parameters and the operating status information, wherein the second relationship model is used to characterize the association relationship between the equipment parameters of the reduction furnace and the operating status information of the reduction furnace;

[0028] A second establishing module is used to establish a third relationship model according to the operation status information and the quality and yield information of polysilicon, wherein the third relationship model is used to characterize the correlation between the operation status information of the reduction furnace and the quality and yield information of polysilicon produced by the reduction furnace;

[0029] The third establishing module is used to establish the first relationship model according to the second relationship model and the third relationship model.

[0030] In a third aspect, an embodiment of the present application provides an electronic device comprising: a memory, a processor, and a program stored in the memory and executable on the processor, the processor being used to execute the program in the memory to implement the steps of any of the above-mentioned methods for predicting the production quality and output of a reduction furnace.

[0031] In a fourth aspect, an embodiment of the present application provides a readable storage medium for storing a program, which, when executed by a processor, implements the steps of any of the above-mentioned methods for predicting the production quality and output of a reduction furnace.

[0032] In the embodiment of the present application, by obtaining the first equipment parameter of the first reduction furnace, the first equipment parameter includes: at least one of the furnace barrel diameter, furnace top shape and nozzle distribution; based on the first relationship model and the first equipment parameter, predicting the first target information of the first reduction furnace, the first target information includes: the quality information and output information of the polysilicon produced by the first reduction furnace, the first relationship model is used to characterize the correlation between the equipment parameters of the reduction furnace and the quality information and output information of the polysilicon produced by the reduction furnace. In this way, under the same working conditions, according to the first relationship model between the equipment parameters of different reduction furnaces and the quality and output information of the polysilicon produced by different reduction furnaces, the quality and output of the polysilicon produced by the reduction furnaces with different equipment parameters are predicted, and a more accurate prediction result is obtained. According to the more accurate prediction result, multiple reduction furnaces with different equipment parameters are arranged for production, which can save production resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the description of the embodiments of the present application will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0034] Figure 1 It is a flow chart of a method for predicting the production quality and output of a reduction furnace provided in an embodiment of the present application;

[0035] Figure 2 It is a structural schematic diagram of a device for predicting the production quality and output of a reduction furnace provided in an embodiment of the present application;

[0036] Figure 3 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0037] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0038] Unless otherwise defined, the technical terms or scientific terms used in this application should be understood by people with ordinary skills in the field to which this application belongs. The words "first", "second" and similar words used in this application do not indicate any order, quantity or importance, but are only used to distinguish different components. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship also changes accordingly.

[0039] like Figure 1 As shown, the embodiment of the present application provides a method for predicting the production quality and output of a reduction furnace, comprising:

[0040] Step 101, obtaining first equipment parameters of a first reduction furnace, the first equipment parameters including: at least one of a furnace barrel diameter, a furnace top shape, and a nozzle distribution;

[0041] It should be understood that the first reduction furnace is the reduction furnace for which quality information and yield information of polycrystalline silicon produced currently need to be predicted.

[0042] Optionally, the number of the first reduction furnace may be one or more.

[0043] Exemplarily, the furnace diameter and nozzle distribution of the first reduction furnace are obtained.

[0044] Step 102: Based on the first relationship model and the first equipment parameters, predict the first target information of the first reduction furnace, the first target information including: quality information and output information of the polysilicon produced by the first reduction furnace, and the first relationship model is used to characterize the correlation between the equipment parameters of the reduction furnace and the quality information and output information of the polysilicon produced by the reduction furnace.

[0045] In the embodiments of the present application, the quality and yield of polysilicon produced by different reduction furnaces are predicted under the same working conditions.

[0046] Furthermore, the same working conditions refer to that the total flow rate of chlorosilane, the total flow rate of hydrogen and the input current into different reduction furnaces are the same, the quantity and proportion of raw materials for producing polysilicon in different reduction furnaces are the same, and the current input into different reduction furnaces is the same.

[0047] It should be understood that the quality information of polysilicon includes: cauliflower ratio and black spots of polysilicon.

[0048] Optionally, the first relationship model includes: the larger the diameter of the reduction furnace drum, the higher the cauliflower ratio of polysilicon, and the higher the output of polysilicon; the more uniform the nozzle distribution of the reduction furnace, the lower the cauliflower ratio of polysilicon, and the higher the output of polysilicon.

[0049] In the embodiment of the present application, by obtaining the first equipment parameter of the first reduction furnace, the first equipment parameter includes: at least one of the furnace barrel diameter, furnace top shape and nozzle distribution; based on the first relationship model and the first equipment parameter, predicting the first target information of the first reduction furnace, the first target information includes: the quality information and output information of the polysilicon produced by the first reduction furnace, the first relationship model is used to characterize the correlation between the equipment parameters of the reduction furnace and the quality information and output information of the polysilicon produced by the reduction furnace. In this way, under the same working conditions, according to the first relationship model between the equipment parameters of different reduction furnaces and the quality and output information of the polysilicon produced by different reduction furnaces, the quality and output of the polysilicon produced by the reduction furnaces with different equipment parameters are predicted, and a more accurate prediction result is obtained. According to the more accurate prediction result, multiple reduction furnaces with different equipment parameters are arranged for production, which can save production resources.

[0050] It should be noted that, since the method for predicting the production quality and output of the reduction furnace can predict the quality and output of polysilicon produced by the reduction furnace more accurately, the polysilicon manufacturer can also implement the production scheduling of the reduction furnace based on the more accurate prediction results to improve the comprehensive utilization rate of the reduction furnace.

[0051] For example, the polysilicon produced by a reduction furnace with one equipment parameter is of higher quality but lower output. When the market demand is for higher quality, the reduction furnace with this equipment parameter can be used to produce polysilicon. The polysilicon produced by a reduction furnace with another equipment parameter is of lower quality but higher output. When the market demand is for lower price, the reduction furnace with this equipment parameter can be used to produce polysilicon. This can improve the comprehensive utilization rate of the reduction furnace.

[0052] Optionally, before predicting the first target information of the first reduction furnace based on the first relationship model and the first equipment parameter, the method further includes:

[0053] Obtain historical data of different reduction furnaces under the same working conditions. The historical data includes: equipment parameters, operating status information, and quality and output information of polysilicon. The working conditions include: total input chlorosilane flow rate, total hydrogen flow rate, and input current size.

[0054] It should be understood that the historical data are all obtained from reduction furnaces with different equipment parameters under the same working conditions.

[0055] Furthermore, the historical data includes at least operating status information of the reduction furnace from two different equipment parameters and quality and yield information of the produced polysilicon.

[0056] According to the equipment parameters and the operation status information, a second relationship model is established, where the second relationship model is used to characterize the association relationship between the equipment parameters of the reduction furnace and the operation status information of the reduction furnace;

[0057] It should be understood that the second relationship model is not the relationship between two quantities within a group, but the relationship between at least two groups of two quantities.

[0058] Exemplarily, the second relationship model may represent that the larger the diameter of the reduction furnace drum is, the lower the temperature of the silicon rod is;

[0059] The more uniform the nozzle distribution of the reduction furnace, the better the uniformity of the gas distribution.

[0060] A third relationship model is established according to the operation status information and the quality and yield information of the polysilicon, wherein the third relationship model is used to characterize the correlation between the operation status information of the reduction furnace and the quality and yield information of the polysilicon produced by the reduction furnace;

[0061] It should be understood that the third relationship model is not the relationship between two quantities within a group, but the relationship between at least two groups of two quantities.

[0062] Exemplarily, the third relationship model can represent that the higher the temperature of the silicon rods in the reduction furnace, the higher the proportion of cauliflower produced by the polycrystalline silicon; the better the uniformity of the gas distribution, the lower the proportion of cauliflower produced.

[0063] A first relationship model is established according to the second relationship model and the third relationship model.

[0064] For example, the larger the diameter of the furnace barrel, the higher the temperature of the silicon rod, the higher the temperature of the silicon rod, the higher the cauliflower ratio of the produced polysilicon, so it can be concluded that the larger the diameter of the furnace barrel, the higher the cauliflower ratio of the produced polysilicon; the more uniform the nozzle distribution of the reduction furnace, the better the uniformity of the gas distribution in the reduction furnace, the better the uniformity of the gas distribution in the reduction furnace, the lower the cauliflower ratio of the produced polysilicon, so it can be concluded that the more uniform the nozzle distribution of the reduction furnace, the lower the cauliflower ratio of the produced polysilicon.

[0065] For example, the larger the diameter of the furnace barrel, the higher the temperature of the silicon rod, and the higher the temperature of the silicon rod, the higher the output of polysilicon produced. Therefore, it can be concluded that the larger the diameter of the furnace barrel, the higher the output of polysilicon produced. The more uniform the nozzle distribution of the reduction furnace, the better the uniformity of the gas distribution in the reduction furnace, the better the uniformity of the gas distribution in the reduction furnace, the higher the output of polysilicon produced. Therefore, it can be concluded that the more uniform the nozzle distribution of the reduction furnace, the higher the output of polysilicon produced.

[0066] Optionally, the equipment parameters include a furnace diameter, and the operation status information includes a silicon rod temperature; and establishing the second relationship model according to the equipment parameters and the operation status information includes:

[0067] According to the furnace diameter and the silicon rod temperature, a first sub-relationship model is established, and the first sub-relationship model is used to characterize the correlation between the furnace diameter and the silicon rod temperature.

[0068] Among them, the furnace diameter is an important parameter that characterizes the volume size of the reduction furnace.

[0069] For example, the larger the furnace diameter is, the higher the silicon rod temperature is.

[0070] Optionally, the equipment parameters include nozzle distribution, and the operation status information includes uniformity of gas distribution; and establishing the second relationship model according to the equipment parameters and the operation status information includes:

[0071] According to the nozzle distribution situation and the uniformity of gas distribution, a second sub-relationship model is established, and the second sub-relationship model is used to characterize the correlation relationship between the nozzle distribution situation and the uniformity of gas distribution.

[0072] Among them, the function of the nozzle is to release the gas raw materials required for the production of polysilicon.

[0073] Among them, the uniformity of gas distribution refers to the uniformity of the spatial distribution of gas raw materials in the reduction furnace.

[0074] Illustratively, the more uniform the nozzle distribution is, the better the uniformity of the gas distribution in the reduction furnace is.

[0075] Optionally, the operation status information includes silicon rod temperature, and the quality and yield information of polysilicon includes cauliflower ratio of polysilicon; and establishing the third relationship model according to the operation status information and the quality and yield information of polysilicon includes:

[0076] According to the silicon rod temperature and the cauliflower ratio of polysilicon, a third sub-relationship model is established, and the third sub-relationship model is used to characterize the correlation between the silicon rod temperature and the cauliflower ratio of polysilicon.

[0077] Exemplarily, the higher the silicon rod temperature, the higher the cauliflower ratio of the polycrystalline silicon.

[0078] Optionally, after predicting the first target information of the first reduction furnace based on the first relationship model and the first equipment parameter, the method further includes:

[0079] Obtaining a deviation value between quality information and yield information of polysilicon actually produced by the first reduction furnace and quality information and yield information of polysilicon produced by the first reduction furnace;

[0080] The first relationship model is calibrated according to the deviation value.

[0081] It should be understood that the quality information and yield information of the polysilicon actually produced by the first reduction furnace are obtained by taking out the polysilicon from the first reduction furnace after production is completed and weighing it to obtain the actual yield information; and performing image recognition analysis on the taken out polysilicon to obtain its quality information.

[0082] For example, the actual output of polysilicon produced by the first reduction furnace is 100 kg, while the output information of polysilicon produced by the first reduction furnace through the first relationship model is 90 kg, and the deviation value between the two is 10 kg.

[0083] Furthermore, the polysilicon output information corresponding to the equipment parameters of the first reduction furnace in the first relationship model is increased by 10 kilograms.

[0084] like Figure 2 As shown, the embodiment of the present application provides a device 200 for predicting the production quality and output of a reduction furnace, comprising:

[0085] A first acquisition module 201 is used to acquire first equipment parameters of a first reduction furnace, where the first equipment parameters include: at least one of a furnace barrel diameter, a furnace top shape, and a nozzle distribution;

[0086] Prediction module 202 is used to predict the first target information of the first reduction furnace under the same working conditions based on the first relationship model and the first equipment parameters, the first target information including: the quality information and output information of the polysilicon produced by the first reduction furnace, the first relationship model is used to characterize the correlation between the equipment parameters of the reduction furnace and the quality information and output information of the polysilicon produced by the reduction furnace, and the working conditions include: the total flow rate of input chlorosilane and the total flow rate of hydrogen and the input current.

[0087] Optionally, the reduction furnace production quality and output prediction device 200 further includes:

[0088] The second acquisition module is used to acquire historical data of different reduction furnaces under the same working conditions, the historical data including: equipment parameters, operating status information, and quality and output information of polysilicon, and the working conditions including: total flow rate of input chlorosilane and total flow rate of hydrogen and input current;

[0089] A first establishing module is used to establish a second relationship model according to the equipment parameters and the operating status information, wherein the second relationship model is used to characterize the association relationship between the equipment parameters of the reduction furnace and the operating status information of the reduction furnace;

[0090] A second establishing module is used to establish a third relationship model according to the operation status information and the quality and yield information of polysilicon, wherein the third relationship model is used to characterize the correlation between the operation status information of the reduction furnace and the quality and yield information of polysilicon produced by the reduction furnace;

[0091] The third establishing module is used to establish the first relationship model according to the second relationship model and the third relationship model.

[0092] Optionally, the first establishing module includes:

[0093] The first establishing submodule is used to establish a first sub-relationship model according to the furnace diameter and the silicon rod temperature, and the first sub-relationship model is used to characterize the correlation between the furnace diameter and the silicon rod temperature.

[0094] Optionally, the second establishing module includes:

[0095] The second establishing submodule is used to establish a second sub-relationship model according to the nozzle distribution situation and the uniformity of gas distribution, and the second sub-relationship model is used to characterize the correlation relationship between the nozzle distribution situation and the uniformity of gas distribution.

[0096] Optionally, the third establishing module includes:

[0097] The third submodule is used to establish a third sub-relationship model according to the silicon rod temperature and the cauliflower ratio of polysilicon. The third relationship model is used to characterize the correlation between the silicon rod temperature and the cauliflower ratio of polysilicon.

[0098] Optionally, the reduction furnace production quality and output prediction device 200 further includes:

[0099] A third acquisition module is used to obtain a deviation value between the quality information and yield information of the polysilicon actually produced by the first reduction furnace and the quality information and yield information of the polysilicon produced by the first reduction furnace;

[0100] The calibration module is used to calibrate the first relationship model according to the deviation value.

[0101] The device 200 for predicting the production quality and output of a reduction furnace provided in the embodiment of the present application can implement each process in the above method embodiment, and will not be described again here to avoid repetition.

[0102] See also Figure 3 , Figure 3 is a schematic diagram of the structure of an electronic device provided in an embodiment of the present 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 .

[0103] When the program 3021 is executed by the processor 301, it can achieve Figure 1 Any steps in the corresponding method embodiments and achieving the same beneficial effects will not be repeated here.

[0104] Those skilled in the art will appreciate that all or part of the steps of implementing the above-mentioned embodiment method can be completed by hardware associated with program instructions, and the program can be stored in a readable medium.

[0105] The present application also provides a readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the above-mentioned Figure 1 Any steps in the corresponding method embodiments can achieve the same technical effect and will not be repeated here to avoid repetition.

[0106] The computer-readable storage medium of the embodiment of the present application can adopt any combination of one or more computer-readable media. Computer-readable media can be computer-readable signal media or computer-readable storage media. Computer-readable storage media can be, for example, a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, 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 of the above. In this document, a computer-readable storage medium can be any tangible medium containing or storing a program, which can be used by an instruction execution system, a device or a device or used in combination with it.

[0107] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0108] The program code contained on the storage medium may be transmitted using any appropriate medium, including but not limited to wireless, wire, optical cable, RF, etc., or any suitable combination of the foregoing.

[0109] Computer program code for performing the operation of the present application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "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 an independent software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or terminal. In the case of a remote computer, 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 can be connected to an external computer (e.g., using an Internet service provider to connect through the Internet).

[0110] The above is a preferred implementation of the embodiment of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles described in the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for predicting the production quality and output of a reduction furnace, It is characterized in that The method comprises: Acquire first equipment parameters of the first reduction furnace, wherein the first equipment parameters include: at least one of a furnace barrel diameter, a furnace top shape, and a nozzle distribution; Under the same working conditions, based on the first relationship model and the first equipment parameters, predicting the first target information of the first reduction furnace, the first target information including: quality information and yield information of the polysilicon produced by the first reduction furnace, the first relationship model being used to characterize the correlation between the equipment parameters of the reduction furnace and the quality information and yield information of the polysilicon produced by the reduction furnace, the working conditions including: the total flow rate of the input chlorosilane and the total flow rate of the hydrogen and the magnitude of the input current; Before predicting the first target information of the first reduction furnace based on the first relationship model and the first equipment parameters, the method also includes: acquiring historical data of different reduction furnaces under the same working conditions, the historical data including: equipment parameters, operating status information, and quality and yield information of polysilicon; establishing a second relationship model based on the equipment parameters and the operating status information, the second relationship model being used to characterize the association between the equipment parameters of the reduction furnace and the operating status information of the reduction furnace; establishing a third relationship model based on the operating status information and the quality and yield information of the polysilicon, the third relationship model being used to characterize the association between the operating status information of the reduction furnace and the quality and yield information of the polysilicon produced by the reduction furnace; and establishing the first relationship model based on the second relationship model and the third relationship model.

2. The method for predicting the production quality and output of a reduction furnace according to claim 1, It is characterized in that The equipment parameters include the furnace diameter, and the operation status information includes the silicon rod temperature; and establishing the second relationship model according to the equipment parameters and the operation status information includes: A first sub-relationship model is established according to the furnace drum diameter and the silicon rod temperature, and the first sub-relationship model is used to characterize the correlation between the furnace drum diameter and the silicon rod temperature.

3. The method for predicting the production quality and output of a reduction furnace according to claim 1, It is characterized in that The equipment parameters include the nozzle distribution, and the operation status information includes the uniformity of gas distribution; and establishing the second relationship model according to the equipment parameters and the operation status information includes: A second sub-relationship model is established according to the nozzle distribution situation and the uniformity of the gas distribution. The second sub-relationship model is used to characterize the correlation relationship between the nozzle distribution situation and the uniformity of the gas distribution.

4. The method for predicting the production quality and output of a reduction furnace according to claim 1, It is characterized in that The operation status information includes silicon rod temperature, and the quality and yield information of polysilicon includes cauliflower ratio of the polysilicon; and establishing a third relationship model according to the operation status information and the quality and yield information of the polysilicon includes: A third sub-relationship model is established according to the silicon rod temperature and the cauliflower ratio of the polysilicon. The third sub-relationship model is used to characterize the correlation between the silicon rod temperature and the cauliflower ratio of the polysilicon.

5. The method for predicting the production quality and output of a reduction furnace according to claim 1, It is characterized in that After predicting the first target information of the first reduction furnace based on the first relationship model and the first equipment parameter, the method further includes: Obtaining a deviation value between quality information and yield information of polycrystalline silicon actually produced by the first reduction furnace and quality information and yield information of polycrystalline silicon produced by the first reduction furnace; The first relationship model is calibrated according to the deviation value.

6. A device for predicting the production quality and output of a reduction furnace, It is characterized in that include: A first acquisition module is used to acquire first equipment parameters of the first reduction furnace, wherein the first equipment parameters include at least one of a furnace barrel diameter, a furnace top shape, and a nozzle distribution condition; A prediction module, configured to predict first target information of the first reduction furnace under the same working conditions based on a first relationship model and the first equipment parameters, wherein the first target information includes: quality information and yield information of polysilicon produced by the first reduction furnace, the first relationship model is used to characterize the correlation between the equipment parameters of the reduction furnace and the quality information and yield information of the polysilicon produced by the reduction furnace, and the working conditions include: the total flow rate of chlorosilane and the total flow rate of hydrogen input and the magnitude of the input current; The prediction device for the production quality and output of the reduction furnace also includes: a second acquisition module, which is used to acquire historical data of different reduction furnaces under the same working conditions, wherein the historical data includes: equipment parameters, operating status information, and quality and output information of polysilicon, and the working conditions include: input total flow rate of chlorosilane and total flow rate of hydrogen and input current; a first establishment module, which is used to establish a second relationship model according to the equipment parameters and operating status information, wherein the second relationship model is used to characterize the correlation between the equipment parameters of the reduction furnace and the operating status information of the reduction furnace; a second establishment module, which is used to establish a third relationship model according to the operating status information and the quality and output information of the polysilicon, wherein the third relationship model is used to characterize the correlation between the operating status information of the reduction furnace and the quality and output information of the polysilicon produced by the reduction furnace; The third establishing module is used to establish the first relationship model according to the second relationship model and the third relationship model.

7. An electronic device, include: A memory, a processor, and a program stored in the memory and executable on the processor, wherein the processor is used to execute the program in the memory to implement the steps of a method for predicting the production quality and output of a reduction furnace as described in any one of claims 1 to 5.

8. A readable storage medium for storing a program, It is characterized in that When the program is executed by a processor, the steps of the method for predicting the production quality and output of a reduction furnace according to any one of claims 1 to 5 are implemented.

Images