Anode carbon block consumption prediction method, device, equipment and medium

Abstract

The application discloses an anode carbon block consumption prediction method and device, equipment and medium, and relates to the field of industrial production. According to the scheme, an anode consumption prediction model is generated in advance by collecting data of process parameters in an electrolytic cell and recording net anode consumption in each use cycle, so as to mine the relationship between various process parameters of electrolytic aluminum and anode consumption by means of a mathematical prediction model and the computing power of a computer. Based on the prediction model, the consumption of anode carbon blocks is predicted according to the actual process parameter values of the electrolytic cell every day, so that the prediction of the consumption of anode carbon blocks is more accurate and intelligent, and accurate anode replacement is realized. Meanwhile, the scheme has high feasibility because it does not affect actual production.

Description

Technical Field

[0001] This application relates to the field of industrial production, and in particular to a method, apparatus, equipment and medium for predicting the consumption of anode carbon blocks. Background Technology

[0002] In electrolytic aluminum production, anode consumption is a crucial cost indicator. With the development of modern electrolytic aluminum industry and intelligent technologies, higher demands are being placed on cost control in electrolytic aluminum production.

[0003] In large-scale production in the current aluminum electrolysis industry, hundreds of electrolytic cells may operate simultaneously. The lifespan of anodes in each cell is typically set uniformly based on industry averages and the average consumption rate of aluminum carbon blocks from sampled anode consumption experiments. This method, based on overall averages, is very crude. In actual production, the actual consumption rate of each anode varies significantly due to differences in the actual furnace shape, process parameters, and carbon block quality. This results in some anodes being overused during actual anode replacement, affecting aluminum production, while others are underused, leading to material waste.

[0004] Given the above problems, how to accurately predict the daily anode consumption during the aluminum electrolysis process, so as to achieve precise anode switching, is an urgent problem to be solved by technicians in this field. Summary of the Invention

[0005] The purpose of this application is to provide a method, apparatus, equipment and medium for predicting the consumption of anode carbon blocks, so as to accurately predict the daily anode consumption during the electrolytic aluminum process, thereby achieving precise anode switching.

[0006] To address the aforementioned technical problems, this application provides a method for predicting anode carbon block consumption, comprising:

[0007] Obtain the process parameters of the cell control machine for the day; wherein, the process parameters include at least current density, cell temperature, current efficiency and aluminum output;

[0008] Obtain the specification and usage information of the anode carbon block in the electrolytic cell corresponding to the cell control machine;

[0009] The process parameters, specification information, and usage information are input into the anode consumption prediction model to obtain the daily net consumption of the anode carbon block; wherein, the anode consumption prediction model is generated based on the net consumption of the anode carbon block under different process parameters, different specification information, and different usage information.

[0010] The daily consumption height value of the anode carbon block is obtained based on the daily net consumption and the specification information.

[0011] Preferably, the generation process of the anode consumption prediction model includes:

[0012] The process parameter daily report of the cell control machine is collected, and the specification information and usage information of the anode carbon block are obtained; wherein, the process parameter daily report contains the process parameters for multiple days; the specification information includes density, ash content, bottom area and original height, and the usage information includes residual anode height and usage cycle;

[0013] The process parameters and specification information in the daily process parameter report are preprocessed.

[0014] The total net consumption of the anode carbon block during the service life is obtained based on the specifications and usage information.

[0015] Based on the process parameters, specification information, and total net consumption in the daily process parameter report, the excess anode consumption coefficient is obtained through linear regression.

[0016] The anode consumption prediction model is generated based on the process parameters and the excess anode consumption coefficient.

[0017] Preferably, the preprocessing of the process parameters and specification information in the daily process parameter report includes:

[0018] Delete any missing information from the specification information;

[0019] In the daily process parameter report, process parameters are selected in chronological order to fill in the blank values ​​in the process parameters.

[0020] Combine the specification information and process parameters within the usage period.

[0021] Preferably, after preprocessing the process parameters and specification information in the daily process parameter report, and before obtaining the total net consumption of the anode carbon block during the usage cycle based on the specification information and the usage information, the method further includes:

[0022] The daily change value of current efficiency is generated according to the current efficiency corresponding to each current efficiency in the daily process parameter report;

[0023] The process parameters corresponding to the daily variation values ​​of current efficiency that meet the preset requirements are used as sample data to participate in the generation of the anode consumption prediction model.

[0024] Preferably, after obtaining the daily consumption height value of the anode carbon block based on the daily net consumption and the specification information, the method further includes:

[0025] Generate a cumulative height consumption value based on the height consumption value for the day;

[0026] Determine whether the cumulative consumption height value has reached the first threshold;

[0027] If so, a prompt message will be output indicating that the anode carbon block needs to be replaced.

[0028] Preferably, after obtaining the daily consumption height value of the anode carbon block based on the daily net consumption and the specification information, the method further includes:

[0029] Determine whether the daily consumption height value has reached the second threshold;

[0030] If so, the abnormal consumption of the anode carbon block is confirmed, and a prompt message indicating abnormal consumption of the anode carbon block is output.

[0031] Preferably, it further includes:

[0032] After replacing the anode carbon block, update the residual electrode height of the anode carbon block;

[0033] When the preset cycle is met, the anode consumption prediction model is updated.

[0034] To address the aforementioned technical problems, this application also provides an anode carbon block consumption prediction device, comprising:

[0035] The first acquisition module is used to acquire the process parameters of the cell control machine for the day; wherein, the process parameters include at least current density, cell temperature, current efficiency and aluminum output.

[0036] The second acquisition module is used to acquire the specification information and usage information of the anode carbon block in the electrolytic cell corresponding to the cell control machine;

[0037] The prediction module is used to input the process parameters, the specification information, and the usage information into the anode consumption prediction model, so as to obtain the daily net consumption of the anode carbon block through the anode consumption prediction model; wherein, the anode consumption prediction model is a model generated based on the net consumption of the anode carbon block under different process parameters, different specification information, and different usage information.

[0038] The third acquisition module is used to acquire the daily consumption height value of the anode carbon block based on the daily net consumption and the specification information.

[0039] To address the aforementioned technical problems, this application also provides an anode carbon block consumption prediction device, comprising:

[0040] Memory, used to store computer programs;

[0041] A processor is used to implement the steps of the above-described method for predicting the consumption of anode carbon blocks when executing the computer program.

[0042] To address the aforementioned technical problems, this application also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the above-described method for predicting anode carbon block consumption.

[0043] The anode carbon block consumption prediction method provided in this application obtains the process parameters of the cell control machine for the day; wherein the process parameters include at least current density, cell temperature, current efficiency, and aluminum output; obtains the specification information and usage information of the anode carbon blocks in the electrolytic cell corresponding to the cell control machine; inputs the process parameters, specification information, and usage information into the anode consumption prediction model to obtain the net consumption of anode carbon blocks for the day; wherein the anode consumption prediction model is a model generated based on the net consumption of anode carbon blocks under different process parameters, different specification information, and different usage information; and obtains the daily consumption height value of the anode carbon blocks based on the daily net consumption and specification information. Therefore, the above scheme generates an anode consumption prediction model in advance by collecting data on process parameters in the electrolytic cell and recording the net anode consumption in each usage cycle. This model uses mathematical prediction and computing power to explore the relationship between various process parameters of aluminum electrolysis and anode consumption. Based on the prediction model, the daily consumption of anode carbon blocks is predicted according to the actual process parameter values ​​of the electrolytic cell each day, making the anode carbon block consumption prediction more accurate and intelligent, thereby achieving precise anode switching. At the same time, since it does not affect actual production, the scheme has high feasibility.

[0044] In addition, this application also provides an anode carbon block consumption prediction device, equipment and medium, with the same effect as above. Attached Figure Description

[0045] To more clearly illustrate the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0046] Figure 1 A flowchart illustrating a method for predicting anode carbon block consumption is provided in this application embodiment;

[0047] Figure 2 A schematic diagram illustrating the principle of aluminum electrolysis provided in this application embodiment;

[0048] Figure 3 A schematic diagram of an anode carbon block consumption prediction device provided in an embodiment of this application;

[0049] Figure 4 This is a schematic diagram of an anode carbon block consumption prediction device provided in an embodiment of this application. Detailed Implementation

[0050] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the protection scope of this application.

[0051] The core of this application is to provide a method, apparatus, equipment, and medium for predicting the consumption of anode carbon blocks.

[0052] To enable those skilled in the art to better understand the present application, the present application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0053] Currently, the measurement of anode consumption in electrolytic aluminum production mainly relies on daily real-time measurements of the remaining anode height to estimate the actual daily consumption. While this method solves the accuracy problem, its practical feasibility is poor. The anode carbon block is typically submerged in a high-temperature molten electrolyte approaching 1000 degrees Celsius, and measurement can only be achieved by lifting the anode using an overhead crane. However, the additional daily lifting operations increase the overhead crane's operating load and significantly impact the current efficiency of electrolytic aluminum production, leading to greater losses in actual production and making it highly impractical. Therefore, this application provides an anode carbon block consumption prediction method to address the difficulty in predicting anode consumption during the traditional electrolytic aluminum production process. It should be noted that the anode carbon block consumption prediction method proposed in this application is applicable to anode carbon block consumption prediction in a single electrolytic cell, as well as in large-scale production with numerous electrolytic cells. Its specific application scenario depends on the specific implementation situation and is not limited in this embodiment.

[0054] Figure 1 A flowchart illustrating a method for predicting anode carbon block consumption, provided in an embodiment of this application. Figure 1 As shown, the method includes:

[0055] S10: Obtain the process parameters of the cell control machine for the day. These parameters must include at least the current density, cell temperature, current efficiency, and aluminum output.

[0056] Specifically, to predict the consumption of anode carbon blocks, it is first necessary to obtain the process parameters set by the cell control machine for the day. The cell control machine corresponds to its electrolytic cell and is used to adjust various process parameters of the electrolytic cell during aluminum electrolysis. Different settings of these process parameters ultimately affect resource consumption and aluminum output. In this embodiment, the process parameters should at least include current density, cell temperature, current efficiency, and aluminum output.

[0057] S11: Obtain the specification and usage information of the anode carbon block in the electrolytic cell corresponding to the cell control machine.

[0058] Furthermore, the specifications and usage information of the anode carbon blocks within the electrolytic cell corresponding to the cell control machine are obtained. The specifications of the anode carbon blocks are determined at the factory, generally including density, ash content, bottom area, and initial height. The usage information of the anode carbon blocks includes the residual electrode height after use and the service life.

[0059] S12: Input process parameters, specification information and usage information into the anode consumption prediction model to obtain the daily net consumption of anode carbon blocks through the anode consumption prediction model.

[0060] The anode consumption prediction model is generated based on the net consumption of anode carbon blocks under different process parameters, different specifications, and different usage information.

[0061] In practice, after obtaining the process parameters of the tank control machine, the specification information and usage information of the anode carbon blocks, these are input into the anode consumption prediction model, and the net consumption of the anode carbon blocks for the day is obtained through the anode consumption prediction model.

[0062] It is important to note that the anode consumption prediction model is a pre-generated model. It is created by collecting daily data from the electrolytic cell and recording the anode residual electrode height for each usage cycle. Specifically, it involves collecting data on different electrolytic cell process parameters, anode carbon block specifications, and usage information. Using mathematical prediction models and computer computing power, the model is developed to understand the relationship between various electrolytic aluminum process parameters and anode carbon block consumption. This model can predict the daily net consumption of anode carbon blocks based on the actual daily process parameter values, anode specification information, and usage information of the electrolytic cell. This embodiment does not impose restrictions on the generation process of the anode consumption prediction model; it depends on the specific implementation situation.

[0063] S13: Obtain the daily consumption height value of the anode carbon block based on the daily net consumption and specification information.

[0064] Finally, after obtaining the daily net consumption of the anode carbon block, the daily consumption height value is obtained based on the daily net consumption and its specification information, thereby realizing the real-time estimation of the daily consumption height of the anode without the need to measure the daily consumption height through electrode lifting operations, thus avoiding affecting the production of electrolytic aluminum.

[0065] In this embodiment, the process parameters of the cell control machine for the day are obtained; wherein the process parameters include at least current density, cell temperature, current efficiency, and aluminum output; the specification information and usage information of the anode carbon block in the electrolytic cell corresponding to the cell control machine are obtained; the process parameters, specification information, and usage information are input into the anode consumption prediction model to obtain the net consumption of the anode carbon block for the day; wherein the anode consumption prediction model is a model generated based on the net consumption of the anode carbon block under different process parameters, different specification information, and different usage information; the daily consumption height value of the anode carbon block is obtained based on the daily net consumption and specification information. Therefore, the above scheme generates an anode consumption prediction model in advance by collecting data on process parameters in the electrolytic cell and recording the net anode consumption in each usage cycle. This model uses mathematical prediction and computing power to explore the relationship between various process parameters of aluminum electrolysis and anode consumption. Based on the prediction model, the daily consumption of anode carbon blocks is predicted according to the actual process parameter values ​​of the electrolytic cell each day, making the anode carbon block consumption prediction more accurate and intelligent, thereby achieving precise anode switching. At the same time, since it does not affect actual production, the scheme has high feasibility.

[0066] Based on the above embodiments, as a preferred embodiment, the generation process of the anode consumption prediction model includes:

[0067] Collect daily process parameter reports from the cell control machine and obtain specification and usage information for the anode carbon blocks. The daily process parameter reports contain process parameters for multiple days. Specification information includes density, ash content, bottom area, and initial height. Usage information includes residual anode height and usage cycle.

[0068] Preprocess the process parameters and specifications in the daily process parameter report;

[0069] The total net consumption of the anode carbon block during its service life is obtained based on specification and usage information.

[0070] The excess anode consumption coefficient is obtained by linear regression based on the process parameters, specification information and total net consumption in the daily process parameter report.

[0071] An anode consumption prediction model is generated based on process parameters and the excess anode consumption coefficient.

[0072] In practical implementation, to generate the anode consumption prediction model, it is first necessary to collect process parameters and the specification and usage information of the anode carbon blocks. Specifically, this involves collecting the daily process parameter reports of the cell control machine and obtaining the specification and usage information of the anode carbon blocks. It is important to note that the daily process parameter reports record the process parameters of the corresponding cell control machine on a daily basis; therefore, the daily process parameter reports contain process parameters from multiple days of the cell control machine.

[0073] Furthermore, the process parameters and specifications in the daily process parameter report are preprocessed. The purpose of preprocessing is to remove useless information from the data and fill in missing information to facilitate subsequent model generation. This embodiment does not limit the specific preprocessing steps; it depends on the specific implementation.

[0074] Figure 2 This is a schematic diagram illustrating the principle of aluminum electrolysis provided in an embodiment of this application. Figure 2 As shown, anode consumption in the aluminum electrolysis process can be divided into four parts:

[0075] 1) Theoretical consumption, which is the mass of carbon required to produce 1 ton of aluminum under ideal conditions according to the electrochemical formula, is theoretically 334 kg.

[0076] 2) Electrolysis consumption, which is the consumption of aluminum produced by the secondary reaction of aluminum generated by electrolysis in actual production, resulting in the actual consumption value of the anode being greater than the theoretical consumption value. This part of the consumption value is the theoretical carbon consumption value / current efficiency.

[0077] 3) Net consumption, also known as excess consumption, occurs on top of the electrolysis consumption. Further consumption occurs due to secondary chemical reactions of the anode carbon block itself (e.g., reacting again with CO2 obtained from electrolysis to produce CO and carbon oxides) and the physical consumption of the carbon block. This excess consumption is called excessive consumption. The sum of electrolysis consumption and excessive consumption is the net consumption.

[0078] 4) Total consumption, also known as gross consumption, is the net consumption plus the remaining residue.

[0079] Therefore, the total net consumption can be obtained based on the specifications and usage information of the anode carbon block during its service life:

[0080] W N =ρ×S×(Hh);

[0081] Among them, W N ρ represents the total net consumption, S represents the bottom palm area, H represents the initial height, and h represents the residual pole height.

[0082] Furthermore, based on the aforementioned electrolytic aluminum reaction principle, the total net consumption of the anode within one usage cycle can also be expressed as the sum of daily net consumption:

[0083]

[0084] Among them, W N For total net consumption, t0 and t T These represent the start and end times of the usage cycle, 334 represents the theoretical carbon consumption required to produce one ton of aluminum, and TAP. iLet η be the aluminum output on day i. i Let δ be the current efficiency on day i. i Let be the excess anode consumption coefficient for day i, where i is at t0 and t1. T Between these. It is understandable that daily net consumption equals the product of daily electrolysis consumption and the excess anode consumption coefficient.

[0085] Therefore, in order to obtain the daily net consumption, it is necessary to further obtain the excess anode consumption coefficient through linear regression based on the process parameters, specification information, and total net consumption in the daily process parameter report. In specific implementation, the excess anode consumption coefficient is generated based on the ash content of the anode carbon block and the current process parameters of the electrolytic cell.

[0086]

[0087] Where, ω i Let Temp be the average current density on day i. i Let be the average bath temperature on day i, E be the ash content of the anode carbon block, and b0,...,b5 be the characteristic coefficients.

[0088] It is important to note that the characteristic coefficients are obtained through linear regression using the least squares method, combining process parameters and specification information. Understandably, to avoid impacting electrolytic aluminum production, anode usage data is determined based on the usage cycle, not on a daily basis. However, since the variable affecting the excess anode consumption coefficient is the average of the corresponding process parameters over a certain period, without loss of generality, the fitting estimation of b0,...,b5 can use the excess anode consumption coefficient over the entire measurement cycle as the target variable, while using the average values ​​of current density, cell temperature, and current efficiency over the entire cycle as explanatory variables to establish and solve equations, ultimately achieving the acquisition of the excess anode consumption coefficient.

[0089] Finally, an anode consumption prediction model is generated based on process parameters and the excess anode consumption coefficient. Specifically, the fitted characteristic coefficients b0,...,b5 are recorded. In daily applications, the values ​​of each characteristic coefficient are called, and the excess anode consumption coefficient δ for the day is obtained according to the above expression for the excess anode consumption coefficient. i By combining the actual values ​​of process parameters and the specifications of the anodes, the net consumption for the day is finally obtained. The anode consumption prediction model is as follows:

[0090]

[0091] Furthermore, in order to display the consumption height and remaining height of the anode carbon block, after obtaining the net consumption for the day, the daily consumption height value of the anode can be predicted using the following formula:

[0092]

[0093] In this embodiment, the accuracy of the mapping relationship between the current tank condition process parameters, anode quality and anode carbon block consumption is ensured during the construction of the anode consumption prediction model, thereby realizing the prediction of daily net anode consumption.

[0094] Based on the above embodiments, as a preferred embodiment, preprocessing the process parameters and specifications information in the daily process parameter report includes:

[0095] Remove missing information from the specification information;

[0096] Select process parameters in chronological order in the daily process parameter report to fill in the blank values ​​in the process parameters;

[0097] Combine and use specifications and process parameters within the same cycle.

[0098] To achieve the preprocessing of process parameters and specification information during model construction, as a preferred embodiment, in specific implementation, missing information in the specification information of the anode carbon block is first deleted, and then empty values ​​in the electrolytic aluminum process parameter values ​​in the daily process parameter report are filled in.

[0099] Specifically, the filling method adopts a time sequence, and the null values ​​of a certain process parameter are filled by taking values ​​forward or backward according to the time order. For example, for a null value of a certain parameter on a certain day, the nearest non-null value of the parameter is first traced backward according to the time sequence as the filling value; if all the backward traces are null values, the nearest non-null value of the parameter is traced backward according to the time sequence as the filling value.

[0100] Furthermore, the specification information and process parameters within the usage period are combined, and the anode information data table and the electrolytic aluminum process data table are spliced ​​together. Table 1 shows the combined data table.

[0101]

[0102]

[0103] Table 1

[0104] In this embodiment, by preprocessing the process parameters and specifications, and combining the specifications and process parameters within the cycle, the data is integrated, which facilitates subsequent model generation.

[0105] To obtain more representative training data for the model, based on the above embodiments, as a preferred embodiment, after preprocessing the process parameters and specification information in the daily process parameter report, and before obtaining the total net consumption of the anode carbon block during its service life based on the specification information and usage information, the following steps are also included:

[0106] The daily change value of current efficiency is generated based on the corresponding current efficiency in the daily process parameter report.

[0107] The process parameters corresponding to the daily variation values ​​of current efficiency that meet the preset requirements are used as sample data to participate in the generation of the anode consumption prediction model.

[0108] Specifically, daily current efficiency variation values ​​are generated based on the current efficiency data from multiple days in the daily process parameter report. These daily current efficiency variation values ​​are used as tags to label the corresponding process parameters for each day. Further filtering based on these tags identifies process parameters whose daily current efficiency variation values ​​meet preset requirements. These parameters serve as training data for the subsequent anode consumption prediction model, thus better enabling the generation of the anode consumption prediction model. In this embodiment, the preset requirements are not limited; however, as a preferred embodiment, the preset requirement can be set to a daily current efficiency variation value greater than -0.5%.

[0109] To provide a switching indication, as a preferred embodiment, after obtaining the daily consumption height value of the anode carbon block based on the daily net consumption and specification information, the method further includes:

[0110] Generate a cumulative height consumption value based on the height consumption value for the day;

[0111] Determine whether the cumulative consumption height value has reached the first threshold;

[0112] If so, a prompt message will be output indicating that the anode carbon block needs to be replaced.

[0113] Specifically, after obtaining the daily consumption height value of the anode carbon block, it is added to the previous daily consumption height values ​​to generate a cumulative consumption height value. When the cumulative consumption height value reaches a first threshold, a prompt message to replace the anode carbon block is output to notify the user to perform electrode replacement. In this embodiment, the first threshold is not limited and depends on the specific implementation.

[0114] Furthermore, to prevent excessive and abnormal consumption of anode carbon blocks during the electrolytic aluminum production process, in specific implementations, it can be determined whether the daily consumption height value has reached a second threshold. If so, the abnormal consumption of anode carbon blocks is confirmed, and an abnormal anode carbon block consumption prompt message is output to notify the user that the anode consumption is abnormal and the electrolytic cell needs immediate maintenance. In this embodiment, the second threshold is not limited and depends on the specific implementation situation.

[0115] Finally, to maintain the prediction accuracy of the anode consumption prediction model, the following also includes:

[0116] After replacing the anode carbon block, update the residual electrode height of the anode carbon block;

[0117] When the preset cycle is met, update the anode consumption prediction model.

[0118] In practical implementation, after the anode carbon block is used up and the electrode is replaced, the measured value of the remaining residual electrode height is stored in the corresponding database. Simultaneously, a scheduled task program is set up on the server. When a preset period is met, the model is updated through the generation process of the anode consumption prediction model in the above embodiment to maintain the prediction accuracy of the anode consumption prediction model. This embodiment does not limit the preset period; it depends on the specific implementation. Preferably, the preset period can be set to one month.

[0119] In the above embodiments, the method for predicting the consumption of anode carbon blocks has been described in detail. This application also provides embodiments of the anode carbon block consumption prediction device.

[0120] Figure 3 This is a schematic diagram of an anode carbon block consumption prediction device provided in an embodiment of this application. Figure 3 As shown, the anode carbon block consumption prediction device includes:

[0121] The first acquisition module 10 is used to acquire the process parameters of the cell control machine for the day. The process parameters include at least the current density, cell temperature, current efficiency, and aluminum output.

[0122] The second acquisition module 11 is used to acquire the specification information and usage information of the anode carbon block in the electrolytic cell corresponding to the cell control machine.

[0123] The prediction module 12 is used to input process parameters, specification information, and usage information into the anode consumption prediction model, so as to obtain the daily net consumption of anode carbon blocks through the anode consumption prediction model. The anode consumption prediction model is generated based on the net consumption of anode carbon blocks under different process parameters, different specification information, and different usage information.

[0124] The third acquisition module 13 is used to acquire the daily consumption height value of the anode carbon block based on the daily net consumption and specification information.

[0125] In this embodiment, the anode carbon block consumption prediction device includes a first acquisition module, a second acquisition module, a prediction module, and a third acquisition module. It acquires the process parameters of the cell control machine for the day; wherein the process parameters include at least current density, cell temperature, current efficiency, and aluminum output; it acquires the specification and usage information of the anode carbon blocks in the electrolytic cell corresponding to the cell control machine; it inputs the process parameters, specification information, and usage information into the anode consumption prediction model to obtain the net daily consumption of anode carbon blocks; wherein the anode consumption prediction model is generated based on the net consumption of anode carbon blocks under different process parameters, different specification information, and different usage information; and it obtains the daily consumption height value of the anode carbon blocks based on the daily net consumption and specification information. Therefore, the above scheme generates an anode consumption prediction model in advance by collecting data on process parameters in the electrolytic cell and recording the net anode consumption in each usage cycle. This model uses mathematical prediction and computing power to explore the relationship between various process parameters of aluminum electrolysis and anode consumption. Based on the prediction model, the daily consumption of anode carbon blocks is predicted according to the actual process parameter values ​​of the electrolytic cell each day, making the anode carbon block consumption prediction more accurate and intelligent, thereby achieving precise anode switching. At the same time, since it does not affect actual production, the scheme has high feasibility.

[0126] Figure 4 This is a schematic diagram of an anode carbon block consumption prediction device provided in an embodiment of this application. Figure 4 As shown, the anode carbon block consumption prediction device includes:

[0127] Memory 20 is used to store computer programs.

[0128] Processor 21 is configured to execute a computer program to implement the steps of the method for predicting anode carbon block consumption as described in the above embodiments.

[0129] The anode carbon block consumption prediction device provided in this embodiment may include, but is not limited to, smartphones, tablets, laptops, or desktop computers.

[0130] The processor 21 may include one or more processing cores, such as a quad-core processor or an octa-core processor. The processor 21 may be implemented using at least one of the following hardware forms: Digital Signal Processor (DSP), Field-Programmable Gate Array (FPGA), or Programmable Logic Array (PLA). The processor 21 may also include a main processor and a coprocessor. The main processor, also known as the Central Processing Unit (CPU), is used to process data in the wake-up state; the coprocessor is a low-power processor used to process data in the standby state. In some embodiments, the processor 21 may integrate a Graphics Processing Unit (GPU), which is responsible for rendering and drawing the content to be displayed on the screen. In some embodiments, the processor 21 may also include an Artificial Intelligence (AI) processor, which handles computational operations related to machine learning.

[0131] The memory 20 may include one or more computer-readable storage media, which may be non-transitory. The memory 20 may also include high-speed random access memory and non-volatile memory, such as one or more disk storage devices or flash memory devices. In this embodiment, the memory 20 is used to store at least the following computer program 201, which, after being loaded and executed by the processor 21, is capable of implementing the relevant steps of the anode carbon block consumption prediction method disclosed in any of the foregoing embodiments. In addition, the resources stored in the memory 20 may also include an operating system 202 and data 203, and the storage method may be temporary or permanent storage. The operating system 202 may include Windows, Unix, Linux, etc. The data 203 may include, but is not limited to, the data involved in the anode carbon block consumption prediction method.

[0132] In some embodiments, the anode carbon block consumption prediction device may further include a display screen 22, an input / output interface 23, a communication interface 24, a power supply 25, and a communication bus 26.

[0133] Those skilled in the art will understand that Figure 4 The structure shown does not constitute a limitation on the anode carbon block consumption prediction device and may include more or fewer components than shown.

[0134] In this embodiment, the anode carbon block consumption prediction device includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the steps of the anode carbon block consumption prediction method mentioned in the above embodiment. The process parameters of the cell control machine for the day are obtained; wherein the process parameters include at least current density, cell temperature, current efficiency, and aluminum output; the specification information and usage information of the anode carbon blocks in the electrolytic cell corresponding to the cell control machine are obtained; the process parameters, specification information, and usage information are input into the anode consumption prediction model to obtain the net daily consumption of anode carbon blocks; wherein the anode consumption prediction model is a model generated based on the net consumption of anode carbon blocks under different process parameters, different specification information, and different usage information; the daily consumption height value of the anode carbon blocks is obtained based on the daily net consumption and specification information. Therefore, the above scheme generates an anode consumption prediction model in advance by collecting data on process parameters in the electrolytic cell and recording the net anode consumption in each usage cycle. This model uses mathematical prediction and computing power to explore the relationship between various process parameters of aluminum electrolysis and anode consumption. Based on the prediction model, the daily consumption of anode carbon blocks is predicted according to the actual process parameter values ​​of the electrolytic cell each day, making the anode carbon block consumption prediction more accurate and intelligent, thereby achieving precise anode switching. At the same time, since it does not affect actual production, the scheme has high feasibility.

[0135] Finally, this application also provides an embodiment corresponding to a computer-readable storage medium. The computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps described in the above method embodiments.

[0136] It is understood that if the methods in the above embodiments are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and executes all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0137] In this embodiment, a computer program is stored on a computer-readable storage medium. When the computer program is executed by a processor, it implements the steps described in the above method embodiments. The process parameters of the cell control machine for the day are obtained; wherein the process parameters include at least current density, cell temperature, current efficiency, and aluminum output; the specification and usage information of the anode carbon block in the electrolytic cell corresponding to the cell control machine are obtained; the process parameters, specification information, and usage information are input into the anode consumption prediction model to obtain the daily net consumption of the anode carbon block; wherein the anode consumption prediction model is a model generated based on the net consumption of the anode carbon block under different process parameters, different specification information, and different usage information; the daily consumption height value of the anode carbon block is obtained based on the daily net consumption and specification information. Therefore, the above scheme generates an anode consumption prediction model in advance by collecting data on process parameters in the electrolytic cell and recording the net anode consumption in each usage cycle. This model uses mathematical prediction and computing power to explore the relationship between various process parameters of aluminum electrolysis and anode consumption. Based on the prediction model, the daily consumption of anode carbon blocks is predicted according to the actual process parameter values ​​of the electrolytic cell each day, making the anode carbon block consumption prediction more accurate and intelligent, thereby achieving precise anode switching. At the same time, since it does not affect actual production, the scheme has high feasibility.

[0138] The foregoing provides a detailed description of the method, apparatus, device, and medium for predicting the consumption of anode carbon blocks provided in this application. The various embodiments in the specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the apparatus disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple; relevant parts can be referred to in the method section. It should be noted that those skilled in the art can make several improvements and modifications to this application without departing from the principles of this application, and these improvements and modifications also fall within the protection scope of the claims of this application.

[0139] It should also be noted that, in this specification, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

Claims

1. A method for predicting the consumption of anode carbon blocks, characterized in that, include: Obtain the process parameters of the cell control machine for the day; wherein, the process parameters include at least current density, cell temperature, current efficiency and aluminum output; Obtain the specification and usage information of the anode carbon block in the electrolytic cell corresponding to the cell control machine; The process parameters, specification information, and usage information are input into the anode consumption prediction model to obtain the daily net consumption of the anode carbon block; wherein, the anode consumption prediction model is generated based on the net consumption of the anode carbon block under different process parameters, different specification information, and different usage information. The daily consumption height value of the anode carbon block is obtained based on the daily net consumption and the specification information; The generation process of the anode consumption prediction model includes: The process parameter daily report of the cell control machine is collected, and the specification information and usage information of the anode carbon block are obtained; wherein, the process parameter daily report contains the process parameters for multiple days; the specification information includes density, ash content, bottom area and original height, and the usage information includes residual anode height and usage cycle; The process parameters and specification information in the daily process parameter report are preprocessed. The total net consumption of the anode carbon block during the service life is obtained based on the specifications and usage information, using the following formula: ； ； in, Total net consumption, For density, The area of ​​the base palm. Original height Residual pole height; and These represent the start and end times of the usage cycle, and 334 represents the theoretical carbon consumption required to produce one ton of aluminum. Let i be the amount of aluminum produced on day i. Let be the current efficiency on day i. Let be the anode consumption coefficient on day i, where i is... and between; Based on the process parameters, specifications, and total net consumption in the daily process parameter report, the anode consumption coefficient is obtained through linear regression, as shown in the following formula: ； in, Let be the anode consumption coefficient for day i. Let be the average current density on day i. Let be the average tank temperature on day i. This refers to the ash content of the anode carbon block. The characteristic coefficient is obtained by solving an equation using the anode consumption coefficient over the entire measurement cycle as the target variable and the average current density, cell temperature, and current efficiency over the entire cycle as explanatory variables. The anode consumption prediction model is generated based on the process parameters and the anode consumption coefficient, as shown in the following formula: ； Correspondingly, the formula for obtaining the daily consumption height value of the anode carbon block based on the daily net consumption and the specification information is as follows: ； in, This represents the daily consumption height of the anode carbon block on day i.

2. The method for predicting anode carbon block consumption according to claim 1, characterized in that, The preprocessing of the process parameters and specification information in the daily process parameter report includes: Delete any missing information from the specification information; In the daily process parameter report, process parameters are selected in chronological order to fill in the blank values ​​in the process parameters. Combine the specification information and process parameters within the usage period.

3. The method for predicting anode carbon block consumption according to claim 1, characterized in that, After preprocessing the process parameters and specification information in the daily process parameter report, and before obtaining the total net consumption of the anode carbon block during the usage cycle based on the specification information and usage information, the method further includes: The daily change value of current efficiency is generated according to the current efficiency corresponding to each current efficiency in the daily process parameter report; The process parameters corresponding to the daily variation values ​​of current efficiency that meet the preset requirements are used as sample data to participate in the generation of the anode consumption prediction model.

4. The method for predicting anode carbon block consumption according to claim 1, characterized in that, After obtaining the daily consumption height value of the anode carbon block based on the daily net consumption and the specification information, the method further includes: Generate a cumulative height consumption value based on the height consumption value for the day; Determine whether the cumulative consumption height value has reached the first threshold; If so, a prompt message will be output indicating that the anode carbon block needs to be replaced.

5. The method for predicting anode carbon block consumption according to claim 1, characterized in that, After obtaining the daily consumption height value of the anode carbon block based on the daily net consumption and the specification information, the method further includes: Determine whether the daily consumption height value has reached the second threshold; If so, the abnormal consumption of the anode carbon block is confirmed, and a prompt message indicating abnormal consumption of the anode carbon block is output.

6. The method for predicting anode carbon block consumption according to any one of claims 1 to 5, characterized in that, Also includes: After replacing the anode carbon block, update the residual electrode height of the anode carbon block; When the preset cycle is met, the anode consumption prediction model is updated.

7. A device for predicting the consumption of anode carbon blocks, characterized in that, include: The first acquisition module is used to acquire the process parameters of the cell control machine for the day; wherein, the process parameters include at least current density, cell temperature, current efficiency and aluminum output. The second acquisition module is used to acquire the specification information and usage information of the anode carbon block in the electrolytic cell corresponding to the cell control machine; The prediction module is used to input the process parameters, the specification information, and the usage information into the anode consumption prediction model, so as to obtain the daily net consumption of the anode carbon block through the anode consumption prediction model; wherein, the anode consumption prediction model is a model generated based on the net consumption of the anode carbon block under different process parameters, different specification information, and different usage information. The third acquisition module is used to acquire the daily consumption height value of the anode carbon block based on the daily net consumption and the specification information. The generation process of the anode consumption prediction model includes: The process parameter daily report of the cell control machine is collected, and the specification information and usage information of the anode carbon block are obtained; wherein, the process parameter daily report contains the process parameters for multiple days; the specification information includes density, ash content, bottom area and original height, and the usage information includes residual anode height and usage cycle; The process parameters and specification information in the daily process parameter report are preprocessed. The total net consumption of the anode carbon block during the service life is obtained based on the specifications and usage information, using the following formula: ； ； in, Total net consumption, For density, The area of ​​the base palm. Original height Residual pole height; and These represent the start and end times of the usage cycle, and 334 represents the theoretical carbon consumption required to produce one ton of aluminum. Let i be the amount of aluminum produced on day i. Let be the current efficiency on day i. Let be the anode consumption coefficient on day i, where i is... and between; Based on the process parameters, specifications, and total net consumption in the daily process parameter report, the anode consumption coefficient is obtained through linear regression, as shown in the following formula: ； in, Let be the anode consumption coefficient for day i. Let be the average current density on day i. Let be the average tank temperature on day i. This refers to the ash content of the anode carbon block. The characteristic coefficient is obtained by solving an equation using the anode consumption coefficient over the entire measurement cycle as the target variable and the average current density, cell temperature, and current efficiency over the entire cycle as explanatory variables. The anode consumption prediction model is generated based on the process parameters and the anode consumption coefficient, as shown in the following formula: ； Correspondingly, the formula for obtaining the daily consumption height value of the anode carbon block based on the daily net consumption and the specification information is as follows: ； in, This represents the daily consumption height of the anode carbon block on day i.

8. A device for predicting the consumption of anode carbon blocks, characterized in that, include: Memory, used to store computer programs; A processor, configured to execute the computer program to implement the steps of the anode carbon block consumption prediction method as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the anode carbon block consumption prediction method as described in any one of claims 1 to 6.

Images