Reducing furnace charge list optimization method and device and polycrystalline silicon production method and system

Abstract

The invention discloses a reduction furnace burden list optimization method and device and a polycrystalline silicon production method and system, and relates to the technical field of polycrystalline silicon production. The reduction furnace burden list optimization method comprises the following steps: acquiring a target batch of a target reduction furnace; determining to-be-optimized information corresponding to the target batch and a plurality of first parameter values corresponding to the target batch, wherein the to-be-optimized information comprises at least one of a target optimization direction, a target influence interval, a target limiting amplitude, a target smoothing type, target locking data, target following information and a target optimization value; and according to the to-be-optimized information and the plurality of first parameter values, generating a target reduction furnace burden list of the target reduction furnace under the target batch. According to the embodiment of the invention, the method can improve the optimization efficiency and optimization accuracy of the reduction furnace charge meter.

Description

Technical Field

[0001] The present application belongs to the technical field of polysilicon production, and specifically relates to a method and device for optimizing a reduction furnace charge table, and a polysilicon production method and system. Background Art

[0002] The mainstream process of polysilicon production is the modified Siemens method, which is to pass trichlorosilane (TCS) and hydrogen (H2) into the reduction furnace, and a vapor deposition reaction occurs on the silicon core at 1000-1100°C to grow into polysilicon rods. In actual production, due to the continuous increase in the surface area of ​​the polysilicon rods, the material concentration around the silicon rods, and the thermal conditions in the reduction furnace, the amount of material in the polysilicon growth process cannot be a fixed value, and it is necessary to continuously optimize the flow, ratio and current amplitude of H2 and TCS based on production experience. At present, the industry is still mainly controlled by the Distributed Control System (DCS). The operator regularly issues material parameters according to the empirical reduction furnace material table, observes the situation in the furnace in real time, and manually optimizes the proportion of materials entering the furnace based on experience. Therefore, according to the operating characteristics of the reduction furnace, it is crucial to determine the appropriate material table before starting the furnace for the entire production process.

[0003] In the prior art, the process personnel usually perform a large amount of data retrieval and comparative analysis to optimize the reduction furnace charge table. The optimization process is complicated and there is the possibility of subjective errors. In other words, the reduction furnace charge table optimization method of the prior art has the problems of low optimization efficiency and low optimization accuracy. Summary of the invention

[0004] The technical problem to be solved by the present application is to provide a method and device for optimizing a reduction furnace charge table, and a polysilicon production method and system in view of the above-mentioned deficiencies in the prior art. The method does not require process personnel to perform a large amount of data retrieval and comparative analysis. Therefore, it can simplify the process of retrieval and comparative analysis of a large amount of data, and assist process personnel to optimize the reduction furnace charge table conveniently, save time, efficiently, and intelligently, that is, it can improve the optimization efficiency and optimization accuracy of the reduction furnace charge table.

[0005] In a first aspect, an embodiment of the present application provides a method for optimizing a reduction furnace charge table, comprising: obtaining a target batch of a target reduction furnace; determining information to be optimized corresponding to the target batch, and multiple first parameter values ​​corresponding to the target batch, the information to be optimized including at least one of a target optimization direction, a target influence interval, a target limit amplitude, a target smoothing type, a target locking data, a target following information, and a target optimization value; generating a target reduction furnace charge table under the target batch according to the information to be optimized and the multiple first parameter values.

[0006] In some embodiments of the first aspect, obtaining a target batch of a target reduction furnace includes searching for the target batch of the target reduction furnace from a reduction furnace production information management system based on at least one of a target furnace number and a batch number of the target reduction furnace.

[0007] In some embodiments of the first aspect, determining information to be optimized corresponding to a target batch and multiple first parameter values ​​corresponding to the target batch includes: obtaining the first parameter value corresponding to the target batch, the first parameter value including an actual parameter value and a preset parameter value of at least one of a material parameter, a voltage parameter, a current parameter, and a power parameter; determining an actual parameter value curve and a preset parameter value curve based on multiple actual parameter values ​​and multiple preset parameter values; determining the information to be optimized based on the actual parameter value curve and the preset parameter value curve.

[0008] In some implementations of the first aspect, obtaining a first parameter value corresponding to the target batch includes: determining a plurality of first parameter values ​​corresponding to the target batch in response to a first operation of a user.

[0009] In some embodiments of the first aspect, information to be optimized is determined based on an actual parameter value curve and a preset parameter value curve, including: the first parameter value also includes a first target parameter value of at least one of a material parameter, a voltage parameter, a current parameter and a power parameter; based on multiple first target parameter values, a first target parameter value curve is determined; multiple actual parameter values, multiple preset parameter values, multiple first target parameter values, an actual parameter value curve, a preset parameter value curve and a first target parameter value curve are displayed; in response to a second operation of the user, the information to be optimized corresponding to the target batch is determined.

[0010] In some embodiments of the first aspect, when the information to be optimized includes a target optimization direction and a target optimization value, the second operation includes a first sub-operation, the target optimization direction includes at least one of a first optimization direction and a second optimization direction, and the first optimization direction is opposite to the second optimization direction; in response to the second operation of the user, determining the information to be optimized corresponding to the target batch includes: in response to the first sub-operation of the user, determining the target optimization direction and the target optimization value corresponding to the target batch; and / or, when the information to be optimized includes a target influence interval and a target optimization value, the second operation includes a second sub-operation, the target influence interval is used to characterize the interval in which the moving point on the first target parameter value curve is located; in response to the second operation of the user, determining the information to be optimized corresponding to the target batch includes: in response to the second sub-operation of the user, determining the target influence interval and the target optimization value corresponding to the target batch; and / or, when the information to be optimized includes a target limit amplitude and a target optimization value, the second operation includes a third sub-operation; in response to the second operation of the user, determining the information to be optimized corresponding to the target batch includes: in response to the second sub-operation of the user In response to the user's third sub-operation, determine the target limit amplitude and target optimization value corresponding to the target batch; and / or, when the information to be optimized includes target locking data and target optimization value, the second operation includes a fourth sub-operation; in response to the user's second operation, determine the information to be optimized corresponding to the target batch, including: in response to the user's fourth sub-operation, determine the target locking data and target optimization value corresponding to the target batch; and / or, when the information to be optimized includes a target smoothing type and a target optimization value, the second operation includes a fifth sub-operation; the target smoothing type includes interval smoothing and overall smoothing; in response to the user's second operation, determine the information to be optimized corresponding to the target batch, including: in response to the user's fifth sub-operation, determine the target smoothing type and target optimization value corresponding to the target batch; and / or, when the information to be optimized includes target following information and target optimization value, the second operation includes a sixth sub-operation; in response to the user's second operation, determine the information to be optimized corresponding to the target batch, including: in response to the user's sixth sub-operation, determine the target following information and target optimization value corresponding to the target batch.

[0011] In some embodiments of the first aspect, the first parameter value includes a first target parameter value of at least one of a material parameter, a voltage parameter, a current parameter, and a power parameter; based on the information to be optimized and multiple first parameter values, a target reduction material table for a target reduction furnace under a target batch is generated, including: obtaining first-category information; based on the information to be optimized and the first-category information, optimizing the first target parameter value curve to obtain a second target parameter value curve, the first target parameter value curve being determined based on multiple first target parameter values; based on the second target parameter value curve, generating a target reduction material table for a target reduction furnace under a target batch.

[0012] In some embodiments of the first aspect, the information to be optimized includes a target optimization direction and a target optimization value, the target optimization direction includes at least one of a first optimization direction and a second optimization direction, and the first optimization direction is opposite to the second optimization direction; the first category of information includes a first target point on a first target parameter value curve; obtaining the first category of information includes: determining the first target point on the first target parameter value curve in response to a third operation of the user; optimizing the first target parameter value curve based on the information to be optimized and the first category of information to obtain a second target parameter value curve, including: optimizing the first target parameter value curve based on the target optimization direction, the first category of information and the target optimization value to obtain a second target parameter value curve.

[0013] In some embodiments of the first aspect, the first target parameter value curve is optimized according to the target optimization direction, the first type of information and the target optimization value to obtain the second target parameter value curve, including: optimizing the value of the first target point to the target optimization value, and optimizing all second target points in the first target parameter value curve in the target optimization direction of the first target point to obtain the second target parameter value curve.

[0014] In some embodiments of the first aspect, the information to be optimized includes a target influence interval and a target optimization value; based on the information to be optimized and the first type of information, the first target parameter value curve is optimized to obtain a second target parameter value curve, including: optimizing the value of the first target point to the target optimization value, and optimizing all third target points in the first target parameter value curve that are within the target influence interval to obtain a second target parameter curve.

[0015] In some embodiments of the first aspect, the information to be optimized includes a target limit range and a target optimization value; based on the information to be optimized and the first type of information, the first target parameter value curve is optimized to obtain a second target parameter value curve, including: optimizing the value of the first target point to the target optimization value, and within the target limit range, optimizing all fourth target points in the first target parameter value curve except the first target point to obtain the second target parameter curve.

[0016] In some embodiments of the first aspect, the information to be optimized includes target locking data and a target optimization value; based on the information to be optimized and the first type of information, the first target parameter value curve is optimized to obtain a second target parameter value curve, including: when the first target parameter value curve is not the first target parameter value curve corresponding to the target locking data, the value of the first target point is optimized to the target optimization value, and all fifth target points in the first target parameter value curve except the first target point are optimized to obtain the second target parameter curve.

[0017] In some embodiments of the first aspect, the information to be optimized includes a target smoothing type and a target optimization value; based on the information to be optimized and the first type of information, the first target parameter value curve is optimized to obtain a second target parameter value curve, including: optimizing the value of the first target point to the target optimization value, and performing smoothing processing corresponding to the target smoothing type to obtain the second target parameter curve.

[0018] In some implementations of the first aspect, after performing smoothing processing corresponding to the target smoothing type to obtain the second target parameter curve, the method further includes: displaying the second target parameter curve in response to a fourth operation of the user.

[0019] In some embodiments of the first aspect, the information to be optimized includes target following information and target optimization value; based on the information to be optimized and the first type of information, the first target parameter value curve is optimized to obtain the second target parameter value curve, including: based on the target following information, the first target point on the first target parameter value curve is optimized to obtain the second target parameter curve.

[0020] In some embodiments of the first aspect, the material parameters include at least one of hydrogen flow rate, trichlorosilane flow rate and the first ratio; and / or, the voltage parameters include at least one of phase voltage and total voltage; and / or, the current parameters include at least one of phase current and total current; and / or, the power parameters include at least one of phase power and total power.

[0021] Based on the same inventive concept, in the second aspect, an embodiment of the present application also provides a polysilicon production method, comprising: generating a target reduction charge table for a target reduction furnace under a target batch according to the reduction charge table optimization method of any one of the first aspects; and controlling polysilicon production according to the target reduction charge table.

[0022] Based on the same inventive concept, in the third aspect, an embodiment of the present application also provides a reduction furnace charge table optimization device, including: a first acquisition module, used to acquire a target batch of a target reduction furnace; a first determination module, connected to the first acquisition module, used to determine the information to be optimized corresponding to the target batch, and multiple first parameter values ​​corresponding to the target batch, the information to be optimized includes at least one of a target optimization direction, a target influence interval, a target limit amplitude, a target smoothing type, a target locking data, a target following information and a target optimization value; a first generation module, connected to the first determination module, used to generate a target reduction furnace charge table under the target batch for the target reduction furnace according to the information to be optimized and the multiple first parameter values.

[0023] Based on the same inventive concept, in the fourth aspect, an embodiment of the present application also provides a polysilicon production system, including: a reduction charge table optimization device as in any one of the third aspects, used to generate a target reduction charge table for a target reduction furnace under a target batch; a polysilicon production device, connected to the reduction charge table production device, used to control polysilicon production according to the target reduction charge table.

[0024] According to the reduction furnace charge table optimization method and device, polysilicon production method and system provided in the embodiments of the present application, the target batch of the target reduction furnace is first obtained, and then the information to be optimized and multiple first parameter values ​​corresponding to the target batch are determined, and then the target reduction furnace charge table under the target batch is generated according to the information to be optimized and the multiple first parameter values, that is, the information to be optimized is used to optimize some of the multiple first parameter values ​​to obtain the target reduction furnace charge table. In the above process, there is no need for process personnel to perform a large amount of data retrieval and comparative analysis. Therefore, it can simplify the process of a large amount of data retrieval and comparative analysis, and assist process personnel to conveniently, time-saving, efficiently, and intelligently optimize the reduction furnace charge table, that is, it can improve the optimization efficiency and optimization accuracy of the reduction furnace charge table. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 A schematic diagram showing a process of optimizing a reduction furnace material table provided in an embodiment of the present application;

[0026] Figure 2 A structural schematic diagram of a reduction furnace material table optimization system provided in an embodiment of the present application is shown;

[0027] Figure 3 Another schematic flow chart of the reduction furnace material table optimization method provided in the embodiment of the present application is shown;

[0028] Figure 4 A structural schematic diagram of a reduction furnace charge table optimization device provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0029] In order to enable those skilled in the art to better understand the technical solution of the present application, the present application is further described in detail below with reference to the accompanying drawings and embodiments.

[0030] The features and exemplary embodiments of various aspects of the present application will be described in detail below. In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only configured to explain the present application and are not configured to limit the present application. For those skilled in the art, the present application can be implemented without the need for some of these specific details. The following description of the embodiments is only to provide a better understanding of the present application by illustrating the examples of the present application.

[0031] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the statement "include..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0032] It should be understood that the term "and / or" used in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0033] Before introducing the reduction furnace charge table optimization method provided in the embodiment of the present application, the related technologies that may be involved in the embodiment of the present application are first described.

[0034] The optimization of the reduction furnace charge sheet usually needs to take into account the relationship between variables (such as power, voltage and current, ratio and TCS flow and H2 flow). For example, if the current of a certain phase of silicon rod in the charge sheet is adjusted, if the power and total power of this phase need to remain unchanged, the current and voltage of other phases need to be controlled in coordination. In addition, there are also highly specific reduction furnaces of the same type in the same plant, and exclusive charge sheets need to be formulated for specific reduction furnaces, making the optimization of the charge sheet time-consuming and labor-intensive, and it is difficult for process personnel to optimize and improve the reduction furnace charge sheet for each furnace in a timely and efficient manner.

[0035] Example 1

[0036] The reduction furnace charge table optimization method provided in the embodiment of the present application can be executed by a reduction furnace charge table optimization device and an electronic device, etc., and the following takes the reduction furnace charge table optimization method executed by an electronic device as an example for explanation. The electronic device can have a display screen, and the display screen can display a display interface.

[0037] like Figure 1 As shown, the reduction furnace material table optimization method provided in the embodiment of the present application may include steps S110 to S130.

[0038] S110, obtaining a target batch of a target reduction furnace.

[0039] S120. Determine information to be optimized corresponding to the target batch and multiple first parameter values ​​corresponding to the target batch, wherein the information to be optimized includes at least one of a target optimization direction, a target influence interval, a target limit amplitude, a target smoothing type, a target locking data, a target following information and a target optimization value.

[0040] S130. Generate a target reduction furnace charge table for a target reduction furnace under a target batch according to the information to be optimized and a plurality of first parameter values.

[0041] According to the reduction furnace charge table optimization method provided in the embodiment of the present application, the target batch of the target reduction furnace is first obtained, and then the information to be optimized and multiple first parameter values ​​corresponding to the target batch are determined, and then the target reduction furnace charge table under the target batch is generated according to the information to be optimized and the multiple first parameter values, that is, the information to be optimized is used to optimize some of the first parameter values ​​in the multiple first parameter values ​​to obtain the target reduction furnace charge table. In the above process, there is no need for process personnel to perform a large amount of data retrieval and comparative analysis. Therefore, it can simplify the process of a large amount of data retrieval and comparative analysis, and assist process personnel to conveniently, time-saving, efficiently, and intelligently optimize the reduction furnace charge table, that is, it can improve the optimization efficiency and optimization accuracy of the reduction furnace charge table.

[0042] The specific implementation methods of the above steps are introduced below.

[0043] In step S110, the target reduction furnace may be any reduction furnace for which the reduction furnace charge table optimization is required. For example, the types of the target reduction furnace may include a 24-pair rod reduction furnace, a 40-pair rod reduction furnace, and a 60-pair rod reduction furnace. The target batch may be the batch in which the target reduction furnace is located.

[0044] In some embodiments, obtaining a target batch of a target reduction furnace includes:

[0045] Based on at least one of a target furnace number and a batch number of the target reduction furnace, a target batch of the target reduction furnace is searched from a reduction furnace production information management system.

[0046] Exemplarily, the electronic device is in communication connection with the reduction furnace production information management system, and in response to the user's operation of selecting at least one of the target furnace number and the batch code of the target reduction furnace and the operation of searching for the target batch of the target reduction furnace based on the display interface of the electronic device, the target batch of the target reduction furnace is searched from the reduction furnace production information management system. In some examples, after searching for the target batch of the target reduction furnace from the reduction furnace production information management system, the electronic device may also jump to the display interface of the electronic device in response to the user's operation of clicking the optimize material list button based on the reduction furnace production information management system.

[0047] In other examples, the electronic device may pre-store a first mapping relationship between a target furnace number of a target reduction furnace and a target batch, and / or a second mapping relationship between a batch number of a target reduction furnace and a target batch, so as to automatically determine the target batch of the target reduction furnace based on at least one of the target furnace number and the batch number of the target reduction furnace and at least one of the first mapping relationship and the second mapping relationship.

[0048] In step S120, after obtaining the target batch of the target reduction furnace, the electronic device may also determine information to be optimized corresponding to the target batch, and a plurality of first parameter values ​​corresponding to the target batch.

[0049] Exemplarily, the first parameter value is used to characterize the parameters related to the initial reduction furnace material table of the optimized target reduction furnace. The first parameter value includes an actual parameter value, a preset parameter value and a first target parameter value of at least one of a material parameter, a voltage parameter, a current parameter and a power parameter.

[0050] In some examples, the material parameters include at least one of hydrogen flow, trichlorosilane flow and the first ratio; and / or, the voltage parameters include at least one of phase voltage and total voltage; and / or, the current parameters include at least one of phase current and total current; and / or, the power parameters include at least one of phase power and total power.

[0051] Exemplarily, the first ratio may be the ratio of hydrogen flow rate to trichlorosilane flow rate; the actual parameter value may be the parameter value in the actual operation of the target reduction furnace. The preset parameter value may be the parameter value preset in the initial reduction charge table of the target reduction furnace, that is, the initial reduction charge table value set before the target batch is started. The first target parameter value may be the initial value in the target reduction charge table before the initial reduction charge table is optimized. It should be noted that before the initial reduction charge table is optimized, that is, before step S130, the first target parameter value is equal to the preset parameter value, or the first target parameter value is equal to the actual parameter value.

[0052] Exemplarily, the phase voltage may include four-phase voltage, six-phase voltage, and eight-phase voltage, etc., the phase current may include four-phase current, six-phase current, and eight-phase current, etc., and the phase power may include four-phase power, six-phase power, and eight-phase power, etc. Specifically, the phase voltage, phase current, and phase power may be determined according to the number of rod pairs of the target reduction furnace. For example, when the number of rod pairs of the target reduction furnace is a 24-pair rod reduction furnace, the phase voltage is a four-phase voltage, the phase current is a four-phase current, and the phase power is a four-phase power; for another example, when the number of rod pairs of the target reduction furnace is a 40-pair rod reduction furnace, the phase voltage is a six-phase voltage, the phase current is a six-phase current, and the phase power is a six-phase power; for another example, when the number of rod pairs of the target reduction furnace is a 60-pair rod reduction furnace, the phase voltage is an eight-phase voltage, the phase current is an eight-phase current, and the phase power is an eight-phase power.

[0053] As an example, the material parameters include hydrogen flow rate; as another example, the material parameters include trichlorosilane flow rate and a first ratio; as yet another example, the material parameters include hydrogen flow rate, trichlorosilane flow rate, and the first ratio.

[0054] As an example, the voltage parameter includes a phase voltage; as another example, the voltage parameter includes a total voltage; as yet another example, the voltage parameter includes a phase voltage and a total voltage.

[0055] As an example, the current parameter includes a phase current; as another example, the current parameter includes a total current; as yet another example, the current parameter includes a phase current and a total current.

[0056] As an example, the first parameter value includes the actual parameter value, preset parameter value, and first target parameter value of the material parameter; as another example, the first parameter value includes the actual parameter value, preset parameter value, and first target parameter value of the material parameter, and the actual parameter value, preset parameter value, and first target parameter value of the voltage parameter; as yet another example, the first parameter value includes the material parameter, the actual parameter value, preset parameter value, and first target parameter value of the voltage parameter, the actual parameter value, preset parameter value, and first target parameter value of the current parameter, and the actual parameter value, preset parameter value, and first target parameter value of the power parameter.

[0057] In some embodiments, determining information to be optimized corresponding to the target batch and a plurality of first parameter values ​​corresponding to the target batch includes:

[0058] Obtaining a first parameter value corresponding to the target batch, the first parameter value including an actual parameter value and a preset parameter value of at least one of a material parameter, a voltage parameter, a current parameter, and a power parameter;

[0059] Based on the multiple actual parameter values ​​and the multiple preset parameter values, determining an actual parameter value curve and a preset parameter value curve;

[0060] According to the actual parameter value curve and the preset parameter value curve, the information to be optimized is determined.

[0061] Exemplarily, the target optimization direction may be the optimization direction of the first target parameter value curve corresponding to the first target parameter value. The target optimization direction may include at least one of the first optimization direction and the second optimization direction, and the first optimization direction is opposite to the second optimization direction. For example, the first optimization direction is the left direction, and the second optimization direction is the right direction. The abscissa of the first target parameter value curve is time, the time unit may be hours (h), and the ordinate may be the first target parameter value.

[0062] As an example, the target optimization direction may include a first optimization direction; as another example, the target optimization direction may include a second optimization direction; as yet another example, the target optimization direction may include a first optimization direction and a second optimization direction. It should be noted that when the target optimization direction includes only the first optimization direction, only the points on the first target parameter value curve in the first optimization direction are optimized; when the target optimization direction includes only the second optimization direction, only the points on the first target parameter value curve in the second optimization direction are optimized. The first target point may be any point to be adjusted on the target parameter value curve.

[0063] Exemplarily, the target impact interval is used to characterize the interval where the moving points on the first target parameter value curve are located. That is, points within the target impact interval can be moved, and points outside the target impact interval cannot be moved. For example, if the target impact interval is 5 hours, then the points 5 hours before and after the first target point on the first target parameter value curve can be moved, that is, a total of 10 hours of value can be moved.

[0064] Exemplarily, the target limit amplitude can be used to characterize the maximum amplitude of the vertical adjustment of the first target parameter value curve. For example, if the target limit amplitude is 10%, the point on the first target parameter value curve can be adjusted up or down by 10% of the value of the point at most.

[0065] Exemplarily, the target smoothing type may include interval smoothing and overall smoothing. Interval smoothing may be to select trend data of a certain interval range for smoothing, such as selecting the interval 10h to 30h, then only the first target parameter value curve of 10h to 30h is smoothed; overall smoothing is to smooth all values ​​of 110 hours in the initial reduction furnace charge table (i.e., all points on the corresponding first target parameter value curve).

[0066] Exemplarily, the target locking data may be unchanged data, that is, the parameters that affect each other may be selected in advance so that at least one of them does not change, such as adjusting a certain phase power. If the target locking data is the phase voltage, that is, the locked phase voltage remains unchanged, then the phase current changes with the adjustment of the phase power. The data locking function (i.e., target locking data) is implemented based on the formula M=nH2:nTCS and P=UI, and the functional relationship between H2 flow rate, TCS (i.e., trichlorosilane) flow rate, H2:TCS ratio (M, i.e., the first ratio) and power (P), voltage (U), and current (I) is pre-set in the electronic device.

[0067] Exemplarily, the target following information may be current position change information of an input device such as a mouse, and the position change information may include a current position movement track, etc. The target optimization value may be an optimization value corresponding to the first target point in the first target parameter value curve.

[0068] Exemplarily, a plurality of actual parameter values ​​may be used as ordinates, and a time corresponding to the plurality of actual parameter values ​​may be used as abscissa to generate an actual parameter value curve.

[0069] Exemplarily, a plurality of preset parameter values ​​may be used as ordinates, and a time corresponding to the plurality of preset parameter values ​​may be used as abscissas to generate a preset parameter value curve.

[0070] In some examples, obtaining a first parameter value corresponding to a target batch includes:

[0071] In response to a first operation of a user, a plurality of first parameter values ​​corresponding to the target batch are determined.

[0072] In this example, through the above method, multiple first parameter values ​​corresponding to the target batch can be accurately and individually determined, and the human-computer interaction experience can be improved.

[0073] Exemplarily, the first operation may be an operation capable of determining multiple first parameter values ​​corresponding to the target batch. For example, the first operation may be an operation in which a user inputs multiple first parameter values ​​corresponding to the target batch based on an input box on a display interface of an electronic device; or for another example, the first operation may be an operation in which a user selects multiple first parameter values ​​corresponding to the target batch based on multiple options on a display interface of an electronic device.

[0074] In other examples, the first parameter value corresponding to the target batch may be pre-stored in the electronic device for subsequent direct call.

[0075] In some examples, determining the information to be optimized according to the actual parameter value curve and the preset parameter value curve includes:

[0076] The first parameter value also includes a first target parameter value of at least one of a material parameter, a voltage parameter, a current parameter, and a power parameter;

[0077] Based on the plurality of first target parameter values, determining a first target parameter value curve;

[0078] Displaying a plurality of actual parameter values, a plurality of preset parameter values, a plurality of first target parameter values, an actual parameter value curve, a preset parameter value curve, and a first target parameter value curve;

[0079] In response to the second operation of the user, information to be optimized corresponding to the target batch is determined.

[0080] In this example, by determining the information to be optimized corresponding to the target batch in response to the user's second operation, the information to be optimized corresponding to the target batch can be accurately and personalized, and the human-computer interaction experience can be improved.

[0081] Exemplarily, a plurality of first target parameter values ​​may be used as ordinates, and a time at which the plurality of first target parameter values ​​correspond one to another may be used as abscissa to generate a first target parameter value curve.

[0082] Exemplarily, the actual parameter value curve, the preset parameter value curve and the first target parameter value curve corresponding to the same first parameter value are displayed with lines of different shades of the same color system.

[0083] Exemplarily, the second operation may be an operation capable of determining the information to be optimized corresponding to the target batch. For example, the second operation may be an operation in which the user inputs the information to be optimized corresponding to the target batch based on an input box on the electronic device display interface; for another example, the second operation may be an operation in which the user selects the information to be optimized corresponding to the target batch based on multiple options on the electronic device display interface.

[0084] In other examples, the electronic device may pre-store information to be optimized corresponding to the target batch so that it can be directly called later.

[0085] As an example, when the information to be optimized includes a target optimization direction and a target optimization value, the second operation includes a first sub-operation, the target optimization direction includes at least one of a first optimization direction and a second optimization direction, and the first optimization direction is opposite to the second optimization direction;

[0086] In response to the second operation of the user, determining the information to be optimized corresponding to the target batch includes:

[0087] In response to the first sub-operation of the user, a target optimization direction and a target optimization value corresponding to the target batch are determined.

[0088] In this example, by determining the target optimization direction and target optimization value corresponding to the target batch in response to the user's first sub-operation, the target optimization direction and target optimization value corresponding to the target batch can be accurately and personalized.

[0089] Exemplarily, the first sub-operation may be an operation capable of determining the target optimization direction and target optimization value corresponding to the target batch. For example, the first sub-operation may be an operation in which the user inputs the target optimization direction and target optimization value corresponding to the target batch based on an input box on the electronic device display interface; for another example, the first sub-operation may be an operation in which the user selects the target optimization direction and target optimization value corresponding to the target batch based on multiple options on the electronic device display interface.

[0090] As an example, in a case where the information to be optimized includes a target impact interval and a target optimization value, the second operation includes a second sub-operation, and the target impact interval is used to characterize an interval where a moving point on the first target parameter value curve is located;

[0091] In response to the second operation of the user, determining the information to be optimized corresponding to the target batch includes:

[0092] In response to the second sub-operation of the user, a target impact interval and a target optimization value corresponding to the target batch are determined.

[0093] In this example, by determining the target impact interval and the target optimization value corresponding to the target batch in response to the second sub-operation of the user, the target impact interval and the target optimization value corresponding to the target batch can be accurately and personalized determined.

[0094] Exemplarily, the second sub-operation may be an operation capable of determining the target impact interval and target optimization value corresponding to the target batch. For example, the second sub-operation may be an operation in which the user inputs the target impact interval and target optimization value corresponding to the target batch based on an input box on the electronic device display interface; for another example, the second sub-operation may be an operation in which the user selects the target impact interval and target optimization value corresponding to the target batch based on multiple options on the electronic device display interface.

[0095] As an example, in the case where the information to be optimized includes a target limit amplitude and a target optimization value, the second operation includes a third sub-operation;

[0096] In response to the second operation of the user, determining the information to be optimized corresponding to the target batch includes:

[0097] In response to a third sub-operation of the user, determining a target limit range and a target optimization value corresponding to the target batch;

[0098] In this example, by determining the target limit range and the target optimization value corresponding to the target batch in response to the third sub-operation of the user, the target limit range and the target optimization value corresponding to the target batch can be accurately and personalized determined.

[0099] Exemplarily, the third sub-operation may be an operation capable of determining the target limit range and target optimization value corresponding to the target batch. For example, the third sub-operation may be an operation in which the user inputs the target limit range and target optimization value corresponding to the target batch based on an input box on the electronic device display interface; for another example, the third sub-operation may be an operation in which the user selects the target limit range and target optimization value corresponding to the target batch based on multiple options on the electronic device display interface.

[0100] As an example, in the case where the information to be optimized includes target locking data and target optimization value, the second operation includes a fourth sub-operation;

[0101] In response to the second operation of the user, determining the information to be optimized corresponding to the target batch includes:

[0102] In response to a fourth sub-operation of the user, determining target locking data and target optimization values ​​corresponding to the target batch;

[0103] In this example, by determining the target locking data and the target optimization value corresponding to the target batch in response to the fourth sub-operation of the user, the target locking data and the target optimization value corresponding to the target batch can be accurately and personalized.

[0104] Exemplarily, the fourth sub-operation may be an operation capable of determining the target locking data and target optimization value corresponding to the target batch. For example, the fourth sub-operation may be an operation in which the user inputs the target locking data and target optimization value corresponding to the target batch based on an input box on the electronic device display interface; for another example, the fourth sub-operation may be an operation in which the user selects the target locking data and target optimization value corresponding to the target batch based on multiple options on the electronic device display interface.

[0105] As an example, in the case where the information to be optimized includes a target smoothing type and a target optimization value, the second operation includes a fifth sub-operation; the target smoothing type includes interval smoothing and overall smoothing;

[0106] In response to the second operation of the user, determining the information to be optimized corresponding to the target batch includes:

[0107] In response to a fifth sub-operation of the user, determining a target smoothing type and a target optimization value corresponding to the target batch;

[0108] In this example, by determining the target smoothing type and the target optimization value corresponding to the target batch in response to the fifth sub-operation of the user, the target smoothing type and the target optimization value corresponding to the target batch can be accurately and personalized determined.

[0109] Exemplarily, the fifth sub-operation may be an operation capable of determining the target smoothing type and target optimization value corresponding to the target batch. For example, the fifth sub-operation may be an operation in which the user inputs the target smoothing type and target optimization value corresponding to the target batch based on an input box on the display interface of the electronic device; for another example, the fifth sub-operation may be an operation in which the user selects the target smoothing type and target optimization value corresponding to the target batch based on multiple options on the display interface of the electronic device.

[0110] As an example, when the information to be optimized includes target following information and target optimization value, the second operation includes a sixth sub-operation;

[0111] In response to the second operation of the user, determining the information to be optimized corresponding to the target batch includes:

[0112] In response to a sixth sub-operation of the user, target following information and a target optimization value corresponding to the target batch are determined.

[0113] In this example, by determining the target following information and the target optimization value corresponding to the target batch in response to the sixth sub-operation of the user, the target following information and the target optimization value corresponding to the target batch can be accurately and personalized determined.

[0114] Exemplarily, the sixth sub-operation may be an operation capable of determining the target following information and the target optimization value corresponding to the target batch. For example, the sixth sub-operation may be an operation in which the user inputs the target following information and the target optimization value corresponding to the target batch based on an input box on the electronic device display interface; for another example, the sixth sub-operation may be an operation in which the user selects the target following information and the target optimization value corresponding to the target batch based on multiple options on the electronic device display interface.

[0115] In step S130, after determining the information to be optimized corresponding to the target batch and the multiple first parameter values ​​corresponding to the target batch, the electronic device can also generate a target reduction furnace material table under the target batch according to the information to be optimized and the multiple first parameter values.

[0116] In some embodiments, the first parameter value includes a first target parameter value of at least one of a material parameter, a voltage parameter, a current parameter, and a power parameter;

[0117] According to the information to be optimized and the multiple first parameter values, a target reduction furnace material table for a target reduction furnace under a target batch is generated, including:

[0118] Get the first type of information;

[0119] According to the information to be optimized and the first type of information, a first target parameter value curve is optimized to obtain a second target parameter value curve, wherein the first target parameter value curve is determined according to the plurality of first target parameter values;

[0120] According to the second target parameter value curve, a target reduction furnace charge table for the target reduction furnace under the target batch is generated.

[0121] Exemplarily, the second target parameter value curve may be a curve obtained by optimizing the first target parameter value curve.

[0122] Exemplarily, the initial values ​​corresponding to each hour on the initial reduction material table can be updated to the target values ​​corresponding to each hour on the second target parameter value curve to obtain the target reduction material table.

[0123] In some examples, the information to be optimized includes a target optimization direction and a target optimization value, and the target optimization direction includes a first optimization direction and a second optimization direction;

[0124] The first type of information includes a first target point on a first target parameter value curve;

[0125] Get the first type of information, including:

[0126] In response to a third operation of the user, determining a first target point on the first target parameter value curve;

[0127] Optimizing the first target parameter value curve according to the information to be optimized and the first type of information to obtain the second target parameter value curve includes:

[0128] According to the target optimization direction, the first type of information and the target optimization value, the first target parameter value curve is optimized to obtain the second target parameter value curve.

[0129] In this example, by determining the first target point on the first target parameter value curve in response to the user's third operation, the first type of information can be accurately and individually determined.

[0130] Exemplarily, the third operation may be an operation capable of determining the first type of information. For example, the third operation may be an operation in which the user inputs the first type of information based on an input box on the electronic device display interface; or for another example, the third operation may be an operation in which the user selects the first type of information based on multiple options on the electronic device display interface.

[0131] As an example, according to the target optimization direction, the first type of information and the target optimization value, optimizing the first target parameter value curve to obtain the second target parameter value curve includes:

[0132] The value of the first target point is optimized to a target optimization value, and all second target points in the first target parameter value curve in the target optimization direction of the first target point are optimized to obtain a second target parameter value curve.

[0133] Exemplarily, the second target point may be a point on the target optimization direction of the first target point.

[0134] That is, the value of the first target point is updated to the target optimization value.

[0135] Exemplarily, if the target optimization direction is the left direction, the value of the first target point is updated to the target optimization value, and all second target points in the first target parameter value curve that are located on the left side of the first target point are optimized to obtain the second target parameter value curve. For example, the optimized second target point may be the product of the second target point and the first ratio, and the first ratio may be the ratio of the target optimization value to the value of the first target point.

[0136] In other examples, the information to be optimized includes a target impact interval and a target optimization value;

[0137] Optimizing the first target parameter value curve according to the information to be optimized and the first type of information to obtain the second target parameter value curve includes:

[0138] The value of the first target point is optimized to a target optimization value, and all third target points in the first target parameter value curve that are within the target influence interval are optimized to obtain a second target parameter curve.

[0139] Exemplarily, the third target point is a point in the first target parameter value curve that is within the target influence area. The optimized third target point may be the product of the third target point and the first ratio.

[0140] In still other examples, the information to be optimized includes a target limit range and a target optimization value;

[0141] Optimizing the first target parameter value curve according to the information to be optimized and the first type of information to obtain the second target parameter value curve includes:

[0142] The value of the first target point is optimized to a target optimization value, and within a target limit range, all fourth target points except the first target point in the first target parameter value curve are optimized to obtain a second target parameter curve.

[0143] For example, the fourth target point may be a point in the first target parameter value curve other than the first target point. The optimized fourth target point may be the product of the fourth target point and the first ratio.

[0144] In still other examples, the information to be optimized includes target locking data and target optimization value;

[0145] Optimizing the first target parameter value curve according to the information to be optimized and the first type of information to obtain the second target parameter value curve includes:

[0146] When the first target parameter value curve is not the first target parameter value curve corresponding to the target locking data, the value of the first target point is optimized to the target optimization value, and all fourth target points except the first target point in the first target parameter value curve are optimized to obtain the second target parameter curve.

[0147] Exemplarily, when the first target parameter value curve is the first target parameter value curve corresponding to the target locking data, the first target parameter value curve is not optimized.

[0148] In yet other examples, the information to be optimized includes a target smoothing type and a target optimization value;

[0149] Optimizing the first target parameter value curve according to the information to be optimized and the first type of information to obtain the second target parameter value curve includes:

[0150] The value of the first target point is optimized to a target optimization value, and a smoothing process corresponding to the target smoothing type is performed to obtain a second target parameter curve.

[0151] Exemplarily, the smoothing process is implemented by using a simple moving average method to reduce fluctuations by calculating the average value of each point within a certain period of time while retaining the overall trend of the data.

[0152] In some examples, after performing smoothing processing corresponding to the target smoothing type to obtain the second target parameter curve, the method further includes:

[0153] In response to a fourth operation by the user, a second target parameter curve is displayed.

[0154] In this example, through the above method, the second target parameter curve can be previewed so that the user can check the second target parameter curve.

[0155] Exemplarily, the fourth operation may be an operation capable of displaying the second target parameter curve. For example, the fourth operation may be an operation of the user selecting a preview option based on a display interface of the electronic device.

[0156] Exemplarily, when the second target parameter curve is displayed, a confirmation option and an undo option may also be displayed; confirmation of the second target parameter curve may be completed in response to operations such as clicking and / or sliding by the user based on the confirmation option; or, the second target parameter curve may be undo in response to operations such as clicking and / or sliding by the user based on the undo option.

[0157] In some examples, the information to be optimized includes target following information and target optimization value;

[0158] Optimizing the first target parameter value curve according to the information to be optimized and the first type of information to obtain the second target parameter value curve includes:

[0159] According to the target following information, a first target point on the first target parameter value curve is optimized to obtain a second target parameter curve.

[0160] That is, the position of the cursor on the display interface of the electronic device can be dynamically adjusted according to the current position of the input device such as the mouse, so that the cursor moves with the input device such as the mouse. That is, the value of the first target point on the first target parameter value curve is updated to the value of the cursor position.

[0161] In some more specific embodiments, the reduction furnace material table optimization method provided in the embodiments of the present application can be as follows: Figure 2 The reduction furnace material table intelligent optimization system shown is executed. The reduction furnace material table intelligent optimization system may include at least one of a batch management module, a parameter selection module, a curve optimization model, a data optimization model, an optimization function module, and a material table export module. The reduction furnace material table intelligent optimization system is attached to the reduction furnace production information management system. The reduction furnace production information management system may include 40 pairs of rod reduction furnace production information management systems.

[0162] The batch management module is used to import the batch operation data of a reduction furnace that needs to be optimized for the material list, including the material list data (i.e., preset parameter values) and actual operation data (i.e., the actual parameter values ​​corresponding to the material parameters, voltage parameters and current parameters respectively) used in the current batch (i.e., the target batch) and the corresponding curves (i.e., the preset parameter value curve and the actual parameter value curve), which is beneficial for process personnel to analyze the direction of material list adjustment.

[0163] The parameter selection module is used to select the parameters to be optimized (i.e., the first parameter value), including material parameters (H2 flow, TCS flow, H2:TCS ratio), voltage parameters (six-phase voltage, total voltage), current parameters (six-phase current, total current), and power parameters (six-phase power, total power).

[0164] The curve optimization module is used to display and optimize data in the form of curves, including the real-time value curve of the selected parameters in the selected batch (i.e. the actual parameter value curve), the raw material table curve (i.e. the preset parameter value curve) and the adjusted new value curve (i.e. the second target parameter value curve). Optionally, the three curves of each parameter are distinguished by lines of different shades of the same color. The new value curve can be dragged with the mouse. Before adjustment, the new value curve can take the real-time value trend or the raw material table trend. All curves use the running time of the whole point as the horizontal coordinate.

[0165] The data optimization module is used to display and optimize data in the form of cells, including the real-time value, raw material table value, new value and corresponding increase value of the selected parameters in the selected batch. Optionally, the cells of the new value and its increase value can be typed and edited. The new value and the increase value can be taken as the real-time value or the raw material table value before adjustment. Furthermore, the curve optimization module is bound to the data optimization module, that is, the cell data is bound and moved with the curve trend. Among them, the increase value refers to the difference between the next moment and the previous moment of the same parameter, in units of 1 hour. For example, if the real-time value of hydrogen in the 5th hour of this batch is 100kg / h, and the real-time value of hydrogen in the 6th hour is 110kg / h, then the increase value is 10kg / h.

[0166] The optimization function module is used to limit the optimization conditions, including adjustment range (i.e. target optimization direction), influence range (i.e. target influence range), limit amplitude (i.e. target limit amplitude), data lock (i.e. target lock data), smoothing type (i.e. target smoothing type), mouse following (i.e. target following information), undo, preview and other functions.

[0167] Further, in the optimization function module, the adjustment range includes left adjustment, right adjustment, and both sides adjustment of the selected curve when the mouse is dragged. If the left adjustment is selected, when the mouse is placed on a point and dragged, only the left side of the point changes with the mouse drag, and the right side does not adjust. If the both sides are adjusted, when the mouse is dragged on a point, both the left and right sides of the point change with the mouse drag, and the range of influence on both sides is determined by the influence interval;

[0168] Furthermore, in the optimization function module, the impact interval refers to the number of corresponding points before and after the dragging curve affects the point. For example, if the impact interval is selected as 5, when the mouse drags a certain point on the curve, the curve 5 hours before and after the point will change with the mouse drag, that is, a total of 10 hours of values ​​will be affected;

[0169] Furthermore, in the optimization function module, the limit amplitude refers to the longitudinal draggable amplitude of the curve. For example, if the limit amplitude is selected as 10%, when the mouse drags a point, the maximum draggable amplitude is 10% above and below the value of the point;

[0170] Furthermore, in the optimization function module, the data locking means that one of the parameters that affect each other can be selected in advance to remain unchanged, such as adjusting a certain phase power. If the locked voltage remains unchanged, the current changes with the power adjustment. The data locking function is implemented based on the formula M=nH2:nTCS and P=UI, pre-setting the functional relationship between H2 flow, TCS flow, H2:TCS ratio (M) and power (P), voltage (U), and current (I);

[0171] Furthermore, in the optimization function module, the smoothing types include interval smoothing and overall smoothing. Interval smoothing is to select trend data within a certain interval for smoothing. For example, if the selected interval is 10 to 30 hours, only the curves of 10 to 30 hours are smoothed. Overall smoothing is to smooth the curves corresponding to all values ​​of 110 hours in the material table. The smoothing process is implemented by using the simple moving average method to reduce fluctuations by calculating the average value of each point within a certain period of time, while retaining the overall trend of the data;

[0172] Furthermore, in the optimization function module, the mouse following function, that is, the curve follows the position change of the mouse movement, is implemented by dynamically adjusting the position of the cursor on the page according to the current position of the mouse in the program so that it follows the mouse movement.

[0173] The material list export module is used to export the optimized new material list data according to the system default format, eliminating the steps of manually optimizing the material list and modifying the format, and avoiding the problem of mixing the six-phase current when manually modifying the material list format.

[0174] like Figure 3 As shown, the present invention also provides a method for optimizing a reduction furnace charge table, which includes the following steps S1 to S5.

[0175] S1. Determine the reduction furnace batch that needs to be optimized (i.e., the target batch of the target reduction furnace), search for the batch in the reduction furnace production information management system based on information such as the furnace number or batch number, click the optimize material list button, and jump to the reduction furnace material list intelligent optimization system interface.

[0176] S2, the parameter selection module checks the parameters that need to be adjusted (i.e., the first parameter value), clicks Update Analysis (i.e., OK), and the data optimization module and the curve optimization module can display the trend and corresponding values ​​of the selected parameters of the current batch [i.e., all data and change trends, including real-time values ​​(i.e., actual parameter values), raw material table values ​​(i.e., preset parameter values), and new values ​​(i.e., first target parameter values)]. Optionally, batch data and trends are displayed as one value per hour. The parameters include material parameters (H2 flow, TCS flow, H2:TCS ratio), voltage parameters (six-phase voltage, total voltage), current parameters (six-phase current, total current), and power parameters (six-phase power, total power).

[0177] S3. Use the mouse to drag and adjust a parameter trend line to the preset interval through the curve optimization module. Use the data optimization module to adjust the values ​​under the corresponding time coordinates in the data frame to revise the raw material table values ​​to the preset values ​​(i.e., the target optimization values). That is, analyze the adjustment ideas of the material table, determine the adjustment direction of the new material table (i.e., the target optimization direction) based on the deviation between the raw material table data trend and the actual operation trend, and comprehensively consider the on-site feedback during the production process.

[0178] In the curve optimization module, drag the mouse to move the trend line of the new material table to the preset interval, and the value in the data frame of the corresponding data optimization module will automatically change with the curve.

[0179] Optionally, the corresponding numerical value can be edited in the data box of the data optimization module, and the curve trend in the corresponding data optimization module can automatically change with the numerical value.

[0180] During data optimization or curve optimization, you can set adjustment range (i.e. target optimization direction), influence interval (i.e. target influence interval), limit amplitude (i.e. target limit amplitude), data lock (i.e. target lock data), smoothing type (i.e. target smoothing type), mouse following (i.e. target following information) and other functions in the optimization function module.

[0181] In one embodiment, the adjustment range that can be set in the optimization function module includes left adjustment, right adjustment, and both sides adjustment. If the left adjustment is selected, when the mouse is placed on a point and dragged, only the left side of the point changes with the mouse drag, and the right side does not adjust. If the both sides adjustment is selected, when the mouse is dragged on a point, both the left and right sides of the point change with the mouse drag, and the range of influence on both sides is determined by the influence interval;

[0182] In one embodiment, the influence interval that can be set in the optimization function module refers to the number of corresponding points before and after the dragging curve affects the point. For example, if the influence interval is selected as 5, when the mouse drags a certain point on the curve, the curve 5 hours before and after the point will change with the mouse drag, that is, a total of 10 hours of values ​​will be affected;

[0183] In one embodiment, the limit amplitude that can be set in the optimization function module refers to the longitudinal draggable amplitude of the curve. For example, if the limit amplitude is selected as 10%, when the mouse drags a point, the maximum draggable amplitude is 10% above and below the value of the point;

[0184] In one embodiment, the data lock that can be set in the optimization function module means that one of the parameters that affect each other can be selected in advance so that it does not change. For example, if the power of a certain phase is adjusted, if the locked voltage remains unchanged, the current changes with the power adjustment. The data lock function is implemented based on the formula M=nH2:nTCS and P=UI, and the functional relationship between H2 flow, TCS flow, H2:TCS ratio (M) and power (P), voltage (U), and current (I) is pre-set;

[0185] In one embodiment, the smoothing types that can be set in the optimization function module include interval smoothing and overall smoothing. Interval smoothing is to select trend data within a certain interval range for smoothing. For example, if the selected interval is 10 to 30 hours, only the curves of 10 to 30 hours are smoothed. Overall smoothing is to smooth the curves corresponding to all values ​​of 110 hours in the material table. The smoothing process is implemented by using the simple moving average method to reduce fluctuations by calculating the average value of each point within a certain period of time while retaining the overall trend of the data;

[0186] In one embodiment, the mouse following function that can be set in the optimization function module is that the curve follows the position change of the mouse movement, and the position of the cursor on the page is dynamically adjusted according to the current position of the mouse in the program so that it follows the mouse movement.

[0187] S4. Through the optimization function module, the adjustment range, impact interval, limit amplitude, data lock, smoothing type, etc. in the process of curve optimization or data optimization are limited and further adjusted; that is, the curve after dragging and data adjustment is limited according to one or a combination of the above optimization functions, and the overall trend or interval curve is smoothly previewed.

[0188] S5. The optimized data can be exported to a standard format file through the material list export module, that is, the curve after smooth adjustment preview can be clicked on the Apply button to complete the confirmation. The optimized new material list can be exported to the default format of the reduction furnace production information management system for direct use in the subsequent furnace start-up.

[0189] In order to better understand the reduction furnace charge table optimization method provided in the embodiments of the present application, it is described below in conjunction with a number of specific implementation methods.

[0190] Implementation 1:

[0191] After a certain material list was put into use in a certain 40-pair-rod polysilicon reduction furnace (i.e., the target reduction furnace), atomization occurred between 10 and 20 hours. The operator eliminated the atomization after performing a hydrogen extraction operation. The current H2:TCS ratio was 2.7. Combined with on-site feedback and production experience, the ratio of H2 and TCS between 10 and 20 hours in the material list (i.e., the initial reduction furnace material list) needed to be adjusted to 3 (i.e., the target optimization value). According to the reduction furnace material list optimization method provided in the embodiment of the present application, the following steps A1 to A5 are included.

[0192] A1. In the batch management module, search for the batch number or furnace number and other information to find the batch (i.e. the target batch), and click to enter the material list intelligent optimization interface.

[0193] A2. Select H2 flow, TCS flow, H2:TCS ratio (i.e., the first parameter) in the parameter selection module, and click OK to display the real-time H2 flow, TCS flow, H2:TCS ratio of the batch operation in the curve optimization module and data optimization module below, as well as the material table used and the corresponding trend and data of the new value. For example, H2 flow (i.e., the actual parameter value of hydrogen flow) is the H2 flow of the actual operation of the batch, H2 flow (material table, i.e., the preset parameter value of hydrogen flow) is the H2 material table value set before the start of the batch, and H2 flow (new value, i.e., the first target parameter value of hydrogen flow) is the new material table value (i.e., the value in the target reduction furnace material table) adjusted by the intelligent optimization system and method for the polysilicon reduction furnace material table provided in the embodiment of the present application (i.e., the reduction furnace material table optimization method), wherein only the new value can drag the trend line and edit the value in the data box. Similarly, TCS and H2:TCS ratio also correspond to the above three data and curves.

[0194] A3. In the optimization function module, select the adjustment mode (i.e., target optimization direction), set the influence interval (i.e., target influence interval) and limit amplitude (i.e., target limit amplitude). For data locking (i.e., target data locking), you can choose to lock any one of TCS, H2, and H2:TCS ratio. In this embodiment, it is planned to increase the ratio of 10 to 20 hours (i.e., the first ratio). You can choose the adjustment mode as the right side (i.e., the second optimization direction), set the influence interval to 5 hours, the limit amplitude to 10%, lock TCS, select the draggable curve as H2:TCS ratio (new value), and drag the H2:TCS ratio trend line of 10 hours to 20 hours upward in the curve optimization module to the position where the cursor displays a value of 3 (i.e., the target optimization value). Since TCS is locked in advance, the corresponding value of the H2 flow rate (new value) can be based on the formula M=nH2:nTCS. It increases with the increase of the ratio M, and the corresponding curve will automatically adjust upward according to the increase in the value. Optionally, you can also directly edit the H2:TCS ratio (new value) in the data frame to 3, then the H2:TCS ratio (new value) curve in the curve optimization module will change synchronously according to the change of the value in the data frame. Since the TCS is locked unchanged, the corresponding value and curve of the H2 flow (new value) will be automatically calculated and adjusted according to the formula M=nH2:nTCS, that is, in the curve optimization module and data optimization module, the trend line and value of the H2 flow (new value) will automatically change with the change of the H2:TCS ratio curve.

[0195] A4. To further make the adjusted material table curve (i.e., the adjusted first target parameter value curve) smooth and have a stable increase value, select interval smoothing in the smoothing type (i.e., target smoothing type) of the optimization function module, set the interval to 10-20h, click the smooth button multiple times, and observe the increase value in the data frame to be stable or observe the smooth curve to achieve the expected effect.

[0196] A5. In this embodiment, the above scenario can also lock the H2 flow rate unchanged according to the technical solution described in the embodiment of the present application, and adjust the H2:TCS ratio. The TCS flow rate will automatically decrease according to the formula M=nH2:nTCS, which can also achieve the effect of improving the ratio. A variety of optimization functions are combined to process the parameters in the material list to the expected effect. Click the export button to form a fixed-format material list file for use in the next furnace start-up.

[0197] Implementation 2:

[0198] In other embodiments, after a certain material list of 40 pairs of rods of polysilicon reduction furnace (i.e., target reduction furnace) is put into use, about 30 hours later, on-site inspection personnel report that the furnace temperature is high and there is a trend of atomization in the furnace. After querying the current material list (i.e., initial reduction furnace material list), the total power reaches a peak of 6700kw in about 30 hours. Combined with the on-site feedback and production experience, it is necessary to peak the total power in the material list (i.e., initial reduction furnace material list) in 30 hours and reduce the peak to 6400kw (i.e., target optimization value). According to the intelligent optimization system and method for polysilicon reduction furnace material list provided by the present invention, the following steps B1 to B5 are included.

[0199] B1. In the batch management module, search for the batch number or furnace number and other information to find the batch (i.e. the target batch), and click to enter the material list intelligent optimization interface.

[0200] B2, select total power, total voltage, and total current in the parameter selection module, and click OK to display the real-time total power (i.e., the real-time parameter value of the total power), total voltage (i.e., the real-time parameter value of the total voltage), total current (i.e., the real-time parameter value of the total current) of the batch operation in the curve optimization module and data optimization module below, and the corresponding trend (i.e., the real-time parameter value curve, the preset parameter value curve, and the first target parameter value curve) and data of the material table used. For example, the total power (i.e., the actual parameter value of the total power) is the sum of the six-phase power of the actual operation of the batch, the total power (material table, i.e., the preset parameter value of the total power) is the total power baseline set according to the voltage baseline and the current material table before the batch starts, and the total power (new value, i.e., the first target parameter value of the total power) is the new material table value (i.e., the value in the target reduction furnace material table) after adjustment using the polysilicon reduction furnace material table intelligent optimization system and method (i.e., the reduction furnace material table optimization method) provided by the embodiment of the present application, wherein only the new value can drag the trend line and edit the value in the data box. Similarly, the total voltage and total current also correspond to the above three data and curves.

[0201] B3. Select the adjustment mode (i.e., target optimization direction) in the optimization function module, set the influence interval (i.e., target influence interval) and limit amplitude (i.e., target limit amplitude). For data locking (i.e., target locking data), you can choose to lock any one of the total power, total voltage, and total current. This embodiment plans to reduce the total power peak value. The adjustment mode can be selected as two-side adjustment (i.e., the first optimization direction and the second optimization direction). The influence interval is set to 10h, the limit amplitude is 10%, the total voltage is locked, and the draggable curve is selected as the total power (new value). In the curve optimization module, drag the total power (new value) trend line downward to the position where the cursor displays a value of 6400kw. Since the total voltage is locked in advance, the corresponding value of the total current (new value) can be based on the formula P=UI. It decreases with the decrease of power P, and the corresponding curve will automatically adjust downward according to the decrease in value. Optionally, you can also directly edit the total power (new value) of the corresponding interval in the data box to 6400kw and below, then the total power (new value) curve of the curve optimization module will change synchronously according to the change of the value in the data box. Since the total voltage is locked and unchanged, the corresponding value and curve of the total current will be automatically calculated and adjusted according to the formula P=UI, that is, in the curve optimization module and the data optimization module, the trend line and value of the total current (new value) will automatically change with the change of the total power curve and value, and the corresponding phase current will be redistributed to each phase according to the proportion of each phase current in the original material table.

[0202] B4. To further make the adjusted material list trend line (i.e., the adjusted first target parameter value curve) smooth and have a stable increase value, select overall smoothing in the smoothing type of the optimization function module, click the smooth button multiple times, and observe that the increase value in the data frame is stable or the curve is smooth to achieve the expected effect.

[0203] B5. In the embodiments of the present application, the above scenario can also lock the current unchanged and adjust the total power according to the technical solution described in the embodiments of the present application. The total voltage will automatically decrease according to the formula P=UI, and the effect of reducing power can also be achieved. A variety of optimization functions are combined to process the parameters in the material list to the expected effect. Click the export button to form a fixed-format material list file for use in the next furnace start-up.

[0204] In the embodiment of the present application, batch information is imported on the basis of the reduction furnace production information management system, and the deviation between the raw material list and the actual operation status of the batch is intuitively displayed in the form of numerical values ​​and curves, which is convenient for the analysis of the optimization direction of the material list; according to the calculation formula M=nH2:nTCS and P=UI between the variables (TCS flow and H2 flow and ratio, power and voltage and current), by pre-setting the relationship between them, it is possible to lock a certain parameter without changing it, and adjust one of the variables by simple mouse dragging or data editing. The remaining variables that affect each other can be automatically adjusted, which simplifies the material list optimization process; the data smoothing, data locking and other functions set by the program are used to greatly reduce the workload of material list optimization, eliminate the problem of subjective errors that may exist in manual optimization, improve work efficiency, and assist process personnel to conduct data analysis and material list optimization in a timely, rapid and effective manner.

[0205] Example 2

[0206] The polysilicon production method provided in the embodiment of the present application can be executed by a polysilicon production device and an electronic device, etc. The following takes the polysilicon production method executed by an electronic device as an example for description.

[0207] The polysilicon production method provided in the embodiment of the present application may include steps S210 to S220.

[0208] S210. According to the reduction charge table optimization method of any one of Embodiment 1, a target reduction charge table for a target reduction furnace under a target batch is generated.

[0209] S220. Control polysilicon production according to the target reduction furnace charge list.

[0210] In an embodiment of the present application, through the reduction charge table optimization method of any one of Example 1, a target reduction charge table of a target reduction furnace under a target batch is produced, that is, part of the first parameter values ​​of multiple first parameter values ​​are optimized using the information to be optimized to obtain a target reduction charge table, and then the polysilicon production is controlled according to the target reduction charge table, which can improve the quality of polysilicon.

[0211] In some embodiments, before controlling the production of polysilicon according to the target reduction charge table, the method further comprises:

[0212] Output the target reduction charge list in a preset format.

[0213] In this embodiment, by outputting the target restored furnace material list in a preset format, the step of manually optimizing the material list and modifying the format is omitted, and the problem of mixing the six-phase currents when manually modifying the material list format can be avoided.

[0214] The preset format may be a system default format. For example, the embodiment of the present application is based on a reduction furnace production information management system, and the default material table format of the system is based on 1 hour, including hydrogen flow, hydrogen flow increase value, TCS flow, TCS flow increase value, current value and current increase value of six-phase current (A1 / B1 / C1 / A2 / B2 / C2), and ratio.

[0215] Example 3

[0216] like Figure 4 As shown, the reduction furnace material table optimization device provided in the embodiment of the present application may include a first acquisition module 410, a first determination module 420 and a first generation module 430.

[0217] A first acquisition module 410 is used to acquire a target batch of a target reduction furnace;

[0218] A first determination module 420, connected to the first acquisition module 410, is used to determine information to be optimized corresponding to the target batch and a plurality of first parameter values ​​corresponding to the target batch, wherein the information to be optimized includes at least one of a target optimization direction, a target influence interval, a target limit amplitude, a target smoothing type, a target locking data, a target following information and a target optimization value;

[0219] The first generating module 430 is connected to the first determining module 420 and is used to generate a target reduction furnace charge table for a target reduction furnace under a target batch according to the information to be optimized and a plurality of first parameter values.

[0220] In some embodiments, the first acquisition module 410 is specifically used to search for a target batch of the target reduction furnace from the reduction furnace production information management system based on at least one of the target furnace number and the batch number of the target reduction furnace.

[0221] In some embodiments, the first determination module 420 is specifically used to: obtain a first parameter value corresponding to a target batch, the first parameter value including an actual parameter value and a preset parameter value of at least one of a material parameter, a voltage parameter, a current parameter, and a power parameter; determine an actual parameter value curve and a preset parameter value curve based on multiple actual parameter values ​​and multiple preset parameter values; determine information to be optimized based on the actual parameter value curve and the preset parameter value curve.

[0222] In some embodiments, the first parameter value includes a first target parameter value of at least one of a material parameter, a voltage parameter, a current parameter, and a power parameter; the first generation module 430 is specifically used to: obtain a first type of information; optimize the first target parameter value curve based on the information to be optimized and the first type of information to obtain a second target parameter value curve, wherein the first target parameter value curve is determined based on multiple first target parameter values; and generate a target reduction furnace material table for a target reduction furnace under a target batch based on the second target parameter value curve.

[0223] The reduction furnace charge table optimization device provided in the embodiment of the present application can be used to execute the reduction furnace charge table optimization method, that is, it has the beneficial effects and implementation methods of the reduction furnace charge table optimization method provided in Example 1 of the present application. For details, please refer to the specific description of the reduction furnace charge table optimization method in the above Example 1, and this embodiment will not be repeated here.

[0224] Example 4

[0225] The polysilicon production system provided in the embodiment of the present application comprises the reduction furnace charge table optimization device of any one of the embodiments 3 and the polysilicon production device. The reduction furnace charge table optimization device is connected to the polysilicon production device.

[0226] A reduction furnace charge table optimization device, used for generating a target reduction furnace charge table under a target batch for a target reduction furnace;

[0227] The polysilicon production device is connected to the reduction furnace charge table production device and is used to control the polysilicon production according to the target reduction furnace charge table.

[0228] The polysilicon production system provided in the embodiment of the present application can be used to execute the polysilicon production method, that is, it has the beneficial effects and implementation methods of the polysilicon production method provided in Example 2 of the present application. For details, please refer to the specific description of the polysilicon production method in the above Example 2, and this embodiment will not be repeated here.

[0229] It is to be understood that the above embodiments are merely exemplary embodiments used to illustrate the principles of the present application, but the present application is not limited thereto. For those skilled in the art, various modifications and improvements can be made without departing from the spirit and substance of the present application, and these modifications and improvements are also considered to be within the scope of protection of the present application.

Claims

1. A method for optimizing a reduction furnace charge table, characterized in that: include: Obtain a target batch of a target reduction furnace; Determine information to be optimized corresponding to the target batch and a plurality of first parameter values ​​corresponding to the target batch, wherein the information to be optimized includes at least one of a target optimization direction, a target influence interval, a target limit amplitude, a target smoothing type, a target locking data, a target following information and a target optimization value; A target reduction furnace material table for the target reduction furnace under the target batch is generated according to the information to be optimized and the plurality of first parameter values.

2. The method according to claim 1, characterized in that The step of obtaining a target batch of target reduction furnaces comprises: Based on at least one of a target furnace number and a batch number of a target reduction furnace, a target batch of the target reduction furnace is searched from a reduction furnace production information management system.

3. The method according to claim 1, characterized in that The determining the information to be optimized corresponding to the target batch and a plurality of first parameter values ​​corresponding to the target batch includes: Obtaining a first parameter value corresponding to the target batch, the first parameter value comprising an actual parameter value and a preset parameter value of at least one of a material parameter, a voltage parameter, a current parameter, and a power parameter; Based on the multiple actual parameter values ​​and the multiple preset parameter values, determining an actual parameter value curve and a preset parameter value curve; The information to be optimized is determined according to the actual parameter value curve and the preset parameter value curve.

4. The method according to claim 3, characterized in that: The obtaining of the first parameter value corresponding to the target batch includes: In response to a first operation of a user, a plurality of first parameter values ​​corresponding to the target batch are determined.

5. The method according to claim 3, characterized in that: The determining the information to be optimized according to the actual parameter value curve and the preset parameter value curve includes: The first parameter value also includes a first target parameter value of at least one of a material parameter, a voltage parameter, a current parameter, and a power parameter; Based on the plurality of first target parameter values, determining a first target parameter value curve; Displaying a plurality of actual parameter values, a plurality of preset parameter values, a plurality of first target parameter values, an actual parameter value curve, a preset parameter value curve, and a first target parameter value curve; In response to a second operation of the user, information to be optimized corresponding to the target batch is determined.

6. The method according to claim 5, characterized in that In a case where the information to be optimized includes a target optimization direction and a target optimization value, the second operation includes a first sub-operation, the target optimization direction includes at least one of a first optimization direction and a second optimization direction, and the first optimization direction is opposite to the second optimization direction; The step of determining the information to be optimized corresponding to the target batch in response to the second operation of the user includes: In response to a first sub-operation of the user, determining a target optimization direction and a target optimization value corresponding to the target batch; And / or, in a case where the information to be optimized includes a target impact interval and a target optimization value, the second operation includes a second sub-operation, the target impact interval being used to characterize an interval in which a moving point on the first target parameter value curve is located; The step of determining the information to be optimized corresponding to the target batch in response to the second operation of the user includes: In response to a second sub-operation of the user, determining a target impact interval and a target optimization value corresponding to the target batch; and / or, in a case where the information to be optimized includes a target limit amplitude and a target optimization value, the second operation includes a third sub-operation; The step of determining the information to be optimized corresponding to the target batch in response to the second operation of the user includes: In response to a third sub-operation of the user, determining a target limit range and a target optimization value corresponding to the target batch; and / or, in a case where the information to be optimized includes target locking data and a target optimization value, the second operation includes a fourth sub-operation; The step of determining the information to be optimized corresponding to the target batch in response to the second operation of the user includes: In response to a fourth sub-operation of the user, determining target locking data and target optimization value corresponding to the target batch; And / or, in the case where the information to be optimized includes a target smoothing type and a target optimization value, the second operation includes a fifth sub-operation; the target smoothing type includes interval smoothing and overall smoothing; The step of determining the information to be optimized corresponding to the target batch in response to the second operation of the user includes: In response to a fifth sub-operation of the user, determining a target smoothing type and a target optimization value corresponding to the target batch; and / or, in a case where the information to be optimized includes target following information and a target optimization value, the second operation includes a sixth sub-operation; The step of determining the information to be optimized corresponding to the target batch in response to the second operation of the user includes: In response to a sixth sub-operation of the user, target following information and a target optimization value corresponding to the target batch are determined.

7. The method according to claim 1, characterized in that The first parameter value includes a first target parameter value of at least one of a material parameter, a voltage parameter, a current parameter, and a power parameter; The step of generating a target reduction furnace material table for the target reduction furnace under the target batch according to the information to be optimized and the plurality of first parameter values ​​includes: Get the first type of information; According to the information to be optimized and the first type of information, a first target parameter value curve is optimized to obtain a second target parameter value curve, wherein the first target parameter value curve is determined according to a plurality of first target parameter values; According to the second target parameter value curve, a target reduction furnace charge table for the target reduction furnace under the target batch is generated.

8. The method according to claim 7, characterized in that The information to be optimized includes a target optimization direction and a target optimization value, the target optimization direction includes at least one of a first optimization direction and a second optimization direction, and the first optimization direction is opposite to the second optimization direction; The first type of information includes a first target point on a first target parameter value curve; The obtaining of the first type of information includes: In response to a third operation of the user, determining a first target point on the first target parameter value curve; The step of optimizing the first target parameter value curve according to the information to be optimized and the first type of information to obtain the second target parameter value curve includes: According to the target optimization direction, the first type of information and the target optimization value, the first target parameter value curve is optimized to obtain a second target parameter value curve.

9. The method according to claim 8, characterized in that The step of optimizing the first target parameter value curve according to the target optimization direction, the first type of information and the target optimization value to obtain a second target parameter value curve includes: The value of the first target point is optimized to the target optimization value, and all second target points in the first target parameter value curve in the target optimization direction of the first target point are optimized to obtain a second target parameter value curve.

10. The method according to claim 7, characterized in that The information to be optimized includes a target impact interval and a target optimization value. The step of optimizing the first target parameter value curve according to the information to be optimized and the first type of information to obtain the second target parameter value curve includes: The value of the first target point is optimized to the target optimization value, and all third target points in the first target parameter value curve that are within the target influence interval are optimized to obtain a second target parameter curve.

11. The method according to claim 7, characterized in that The information to be optimized includes a target limit range and a target optimization value; The step of optimizing the first target parameter value curve according to the information to be optimized and the first type of information to obtain the second target parameter value curve includes: The value of the first target point is optimized to the target optimization value, and within the target limit range, all fourth target points in the first target parameter value curve except the first target point are optimized to obtain a second target parameter curve.

12. The method according to claim 7, characterized in that The information to be optimized includes target locking data and target optimization value; The step of optimizing the first target parameter value curve according to the information to be optimized and the first type of information to obtain the second target parameter value curve includes: When the first target parameter value curve is not the first target parameter value curve corresponding to the target locking data, the value of the first target point is optimized to the target optimization value, and all fourth target points in the first target parameter value curve except the first target point are optimized to obtain a second target parameter curve.

13. The method according to claim 7, characterized in that The information to be optimized includes a target smoothing type and a target optimization value; The step of optimizing the first target parameter value curve according to the information to be optimized and the first type of information to obtain the second target parameter value curve includes: The value of the first target point is optimized to the target optimization value, and a smoothing process corresponding to the target smoothing type is performed to obtain a second target parameter curve.

14. The method according to claim 13, characterized in that After performing the smoothing process corresponding to the target smoothing type to obtain the second target parameter curve, the method further includes: In response to a fourth operation by the user, a second target parameter curve is displayed.

15. The method according to claim 7, characterized in that The information to be optimized includes target following information and target optimization value; The step of optimizing the first target parameter value curve according to the information to be optimized and the first type of information to obtain the second target parameter value curve includes: According to the target following information, a first target point on the first target parameter value curve is optimized to obtain a second target parameter curve.

16. The method according to any one of claims 3 to 15, characterized in that The material parameters include at least one of hydrogen flow rate, trichlorosilane flow rate and the first ratio; And / or, the voltage parameter includes at least one of a phase voltage and a total voltage; And / or, the current parameter includes at least one of a phase current and a total current; And / or, the power parameter includes at least one of phase power and total power.

17. A method for producing polycrystalline silicon, characterized in that: include: According to the reduction furnace charge table optimization method according to any one of claims 1 to 16, a target reduction furnace charge table under a target batch is generated for a target reduction furnace; The polysilicon production is controlled according to the target reduction charge table.

18. The method according to claim 17, characterized in that Before controlling the production of polysilicon according to the target reduction furnace charge table, the method further comprises: The target reduction furnace charge list is output in a preset format.

19. A reduction furnace charge table optimization device, characterized in that: include: A first acquisition module is used to acquire a target batch of a target reduction furnace; a first determination module, connected to the first acquisition module, for determining information to be optimized corresponding to the target batch and a plurality of first parameter values ​​corresponding to the target batch, wherein the information to be optimized includes at least one of a target optimization direction, a target influence interval, a target limit amplitude, a target smoothing type, a target locking data, a target following information and a target optimization value; A first generating module is connected to the first determining module and is used for generating a target reduction furnace material table for the target reduction furnace under the target batch according to the information to be optimized and a plurality of the first parameter values.

20. The device according to claim 19, characterized in that The first acquisition module is specifically used to: Based on at least one of a target furnace number and a batch number of a target reduction furnace, a target batch of the target reduction furnace is searched from a reduction furnace production information management system.

21. The device according to claim 19, characterized in that The first determining module is specifically configured to: Obtaining a first parameter value corresponding to the target batch, the first parameter value comprising an actual parameter value and a preset parameter value of at least one of a material parameter, a voltage parameter, a current parameter, and a power parameter; Based on the multiple actual parameter values ​​and the multiple preset parameter values, determining an actual parameter value curve and a preset parameter value curve; The information to be optimized is determined according to the actual parameter value curve and the preset parameter value curve.

22. The device according to claim 19, characterized in that The first parameter value includes a first target parameter value of at least one of a material parameter, a voltage parameter, a current parameter, and a power parameter; The first generating module is specifically used for: Get the first type of information; According to the information to be optimized and the first type of information, a first target parameter value curve is optimized to obtain a second target parameter value curve, wherein the first target parameter value curve is determined according to a plurality of first target parameter values; According to the second target parameter value curve, a target reduction furnace charge table for the target reduction furnace under the target batch is generated.

23. A polysilicon production system, characterized in that: include: The reduction furnace charge table optimization device according to any one of claims 19 to 22, used to generate a target reduction furnace charge table under a target batch for a target reduction furnace; A polysilicon production device is connected to the reduction furnace charge table production device and is used to control polysilicon production according to the target reduction furnace charge table.

Images