Power prediction method, terminal and computer-readable storage medium for electrolytic aluminum system

By evaluating and correcting the theoretical power time model of the electrolytic aluminum system, considering the operating status of the electrolytic cell, the accuracy of the power prediction of the electrolytic aluminum system is improved, and the problem of low prediction accuracy in the existing technology is solved, and the use of electrolytic aluminum systems is realized. Precise management of electricity.

CN113723005BActive Publication Date: 2024-11-26国网河北省电力有限公司营销服务中心 +2
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202111045385.X
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-09-07
Publication Date
2024-11-26
Estimated Expiration
2041-09-07

AI Technical Summary

Technical Problem

In the power prediction of electrolytic aluminum systems, the prior art lacks consideration of the operating state of the electrolytic cell, resulting in low prediction accuracy and the precise management of electricity consumption of electrolytic aluminum systems cannot be achieved.

Method used

By obtaining the theoretical power time model of the electrolytic aluminum system and evaluating and correcting it according to the operating state of the electrolytic cell, a predicted power time model is established, and the impact of the operating state of the electrolytic aluminum system is considered.

Benefits of technology

The power prediction accuracy of the electrolytic aluminum system in one production cycle is improved, making the prediction results closer to the actual operating state, and the precise management of electricity consumption of the electrolytic aluminum system is realized.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN113723005B_ABST
    Figure CN113723005B_ABST
Patent Text Reader

Abstract

The present invention provides a power prediction method, terminal and computer-readable storage medium for an electrolytic aluminum system, the method comprising: obtaining a theoretical power time model of the electrolytic aluminum system in a target production cycle, wherein the theoretical power time model is used to represent the theoretical value of the power of the electrolytic aluminum system changing over time under a preset operating state; evaluating the operating state of all electrolytic cells in the electrolytic aluminum system according to a preset strategy, and obtaining the operating state of each electrolytic cell in the target production cycle; and correcting the theoretical power time model according to the operating state of each electrolytic cell in the target production cycle, and obtaining a predicted power time model of the electrolytic aluminum system in the target production cycle, wherein the predicted power time model is used to represent the predicted value of the power of the electrolytic aluminum system changing over time in the target production cycle. The present invention can predict the power accuracy of the electrolytic aluminum system in a target production cycle.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention belongs to the technical field of power systems, and in particular, relates to a power prediction method, a terminal and a computer-readable storage medium for an electrolytic aluminum system. Background Art

[0002] High-energy-consuming industries refer to industries in which energy costs account for a relatively high proportion of product output value, such as the electrolytic aluminum industry, where electricity costs account for more than 45% of production costs.

[0003] On the one hand, the energy utilization rate of China's electrolytic aluminum industry is low. With the increase in electricity prices, the industry's production costs have increased significantly. On the other hand, high-energy-consuming industries such as electrolytic aluminum are the main sources of power quality interference in the public power grid. With their rapid development, the load in the power grid is becoming more and more nonlinear and time-varying. A large number of interference sources have caused serious pollution to the power quality of the power grid, which will lead to the deterioration of power quality indicators such as power supply voltage deviation, frequency deviation, harmonics, and voltage three-phase imbalance, and even affect the normal operation of the power system and the normal production and living needs of power users.

[0004] The prior art, when predicting the power of an electrolytic aluminum system in a production cycle, only calculates the working time and rated working power of each device in the electrolytic aluminum system, which deviates greatly from the actual power of the electrolytic aluminum system during actual operation. Therefore, how to improve the power prediction accuracy of the electrolytic aluminum system in a production cycle to achieve accurate management of the electricity consumption of the electrolytic aluminum system is a problem that urgently needs to be solved in the prior art. Summary of the invention

[0005] In view of this, the present invention provides a power prediction method, terminal and computer-readable storage medium for an electrolytic aluminum system. In the process of predicting the power of the electrolytic aluminum system in a production cycle, the influence of the operating state of the electrolytic cell on the operating power of the electrolytic aluminum system is taken into account, which can improve the accuracy of power prediction for the electrolytic aluminum system in a production cycle.

[0006] A first aspect of an embodiment of the present invention provides a power prediction method for an electrolytic aluminum system, comprising:

[0007] In a target production cycle, a theoretical power-time model of the electrolytic aluminum system is obtained, wherein the theoretical power-time model is used to represent a theoretical value of power variation over time of the electrolytic aluminum system under a preset operating state;

[0008] According to a preset strategy, the operating status of all electrolytic cells in the electrolytic aluminum system is evaluated to obtain the operating status of each electrolytic cell in the target production cycle;

[0009] According to the operating status of each electrolytic cell in the target production cycle, the theoretical power-time model is corrected to obtain a predicted power-time model of the electrolytic aluminum system in the target production cycle. The predicted power-time model is used to represent the predicted value of the power change of the electrolytic aluminum system over time in the target production cycle.

[0010] In a possible implementation, obtaining a theoretical power-time model of an electrolytic aluminum system includes:

[0011] Establishing an equipment load model according to the process production flow of the electrolytic aluminum system, wherein the equipment load model includes the connection relationship and operation sequence relationship of all equipment in the electrolytic aluminum system;

[0012] Dividing the target production cycle into a plurality of continuous and non-overlapping time periods, and determining the time period during which each device in the electrolytic aluminum system is in a working state in the target production cycle according to the device load model;

[0013] According to the rated power of each device and the time period that each device is in working state in the target production cycle, the rated power time model of the electrolytic aluminum system in the target production cycle is obtained, and the rated power time model is used as the theoretical time model, wherein the rated power time model is used to represent the rated value of the power of the electrolytic aluminum system changing with time in the target production cycle.

[0014] In a possible implementation, the method further includes:

[0015] Obtaining a rated power time model of the aluminum electrolysis system in multiple historical production cycles, temperature information and humidity information of each production cycle, and an actual power time model of the aluminum electrolysis system in each production cycle, wherein the actual power time model is used to represent the actual value of the power of the aluminum electrolysis system changing with time in the corresponding production cycle, and the aluminum electrolysis system is in a preset operating state in the multiple production cycles;

[0016] Performing data processing to obtain a first training set, with respect to a training sample of the first training set, the input of the training sample is the data of the rated power time model of the electrolytic aluminum system in a production cycle, the temperature information, and the humidity information, and the output is the actual power time model of the electrolytic aluminum system in the same production cycle;

[0017] Training a preset neural network model using the first training set to obtain a predictor;

[0018] The rated power-time model of the electrolytic aluminum system in the target production cycle and the temperature information and humidity information of the target production cycle are processed and input into the predictor, and the output result is used as the theoretical power-time model of the electrolytic aluminum system.

[0019] In one possible implementation, the preset operating state means that the electrolyte temperature of each electrolytic cell of the aluminum electrolysis system is within a preset temperature range, and for any electrolytic cell, the operating voltage of the electrolytic cell is within a preset voltage range corresponding to the electrolytic cell.

[0020] In a possible implementation, the evaluating the operating status of all electrolytic cells in the aluminum electrolysis system according to a preset strategy includes:

[0021] For any electrolytic cell, obtaining a plurality of preset state parameters corresponding to the electrolytic cell before the start of the target cycle;

[0022] A plurality of preset state parameters of the electrolytic cell are input into a preset electrolytic cell operation state grade classifier to obtain the grade corresponding to the operation state of the electrolytic cell in the target period.

[0023] In a possible implementation, the method further includes:

[0024] According to the preset status evaluation index, the operation status of the electrolytic cell is divided into M levels, where M is a positive integer greater than or equal to 2;

[0025] For any electrolytic cell, obtaining a status evaluation index of the electrolytic cell in a historical production cycle;

[0026] According to the status evaluation index of the electrolytic cell, obtaining the level corresponding to the operating status of the electrolytic cell in the historical production cycle;

[0027] Establishing a second training set, the training set comprising N samples, wherein a plurality of preset state parameters of an electrolytic cell in a historical production cycle and a level corresponding to the operating state of the electrolytic cell in the production cycle constitute a sample of the second training set;

[0028] The second training set is trained by a preset deep learning model to obtain the electrolytic cell operation status grade classifier.

[0029] In a possible implementation, the modifying the theoretical power-time model according to the operating state of each electrolytic cell in the target production cycle includes:

[0030] The theoretical power-time model is modified according to the time period in which all electrolytic cells in the electrolytic aluminum system are in working condition during the target production cycle, the level corresponding to the operating status of each electrolytic cell and the preset weighting coefficient corresponding to each level.

[0031] In a possible implementation, the method further includes:

[0032] According to the power time model of the electrolytic aluminum system in the target production cycle, determining whether the power average value of the electrolytic aluminum system in a preset time period of the target production cycle exceeds a preset threshold;

[0033] If so, the energy storage module is called to supply power to the electrolytic aluminum system within the preset time period.

[0034] In a second aspect, an embodiment of the present invention provides a terminal, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the steps of the method described in the first aspect or any possible implementation manner of the first aspect are implemented.

[0035] In a third aspect, an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method described in the first aspect or any possible implementation of the first aspect are implemented.

[0036] The embodiment of the present invention provides a power prediction, terminal and computer-readable storage medium for an electrolytic aluminum system. The operating status of the electrolytic cell is evaluated to obtain the operating status of the electrolytic cell within a target period. The theoretical power-time model of the electrolytic aluminum system in the target production period is corrected according to the operating status of the electrolytic cell to obtain a predicted power-time model. Since the operating status of the electrolytic cell is a direct factor causing the operating power of the electrolytic aluminum system to change, the present invention takes the operating status of the electrolytic cell into consideration when predicting the power of the electrolytic aluminum system, so that the obtained predicted power model is closer to the power-time model of the electrolytic aluminum system under the actual operating status, thereby improving the accuracy of power prediction for the electrolytic aluminum system in a production period. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0038] Figure 1This is a flow chart of an implementation method of a power prediction method for an electrolytic aluminum system provided by an embodiment of the present invention;

[0039] Figure 2 is a flow chart of another power prediction method for an electrolytic aluminum system provided by an embodiment of the present invention;

[0040] Figure 3 is a schematic diagram of an equipment load model of an electrolytic aluminum system provided by an embodiment of the present invention;

[0041] Figure 4 is a flow chart of another power prediction method for an electrolytic aluminum system provided by an embodiment of the present invention;

[0042] Figure 5 is a flow chart of another power prediction method for an electrolytic aluminum system provided by an embodiment of the present invention;

[0043] Figure 6 is a flow chart of another power prediction method for an electrolytic aluminum system provided by an embodiment of the present invention;

[0044] Figure 7 It is a schematic diagram of the structure of a power prediction device for an electrolytic aluminum system provided by an embodiment of the present invention;

[0045] Figure 8 is a schematic diagram of a terminal provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0046] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present invention. However, it should be clear to those skilled in the art that the present invention may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present invention.

[0047] In order to make the purpose, technical solutions and advantages of the present invention more clear, specific embodiments will be described below in conjunction with the accompanying drawings.

[0048] See also Figure 1 , which shows a flow chart of a power prediction method for an electrolytic aluminum system provided by an embodiment of the present invention, which is described in detail as follows:

[0049] S101, in a target production cycle, obtain a theoretical power-time model of the electrolytic aluminum system, wherein the theoretical power-time model is used to represent the theoretical value of the power of the electrolytic aluminum system changing with time under a preset operating state.

[0050] Optionally, the above theoretical power-time model is obtained based on the rated power of each device in the electrolytic aluminum system and the working period of each device in an operating cycle.

[0051] Optionally, the preset operating state means that the electrolyte temperature of each electrolytic cell of the aluminum electrolysis system is within a preset temperature range, and for any electrolytic cell, the operating voltage of the electrolytic cell is within a preset voltage range corresponding to the electrolytic cell.

[0052] Combination Figure 2 The embodiment of the present invention further provides a power prediction method for an electrolytic aluminum system, the method is used to obtain a theoretical power time model of the electrolytic aluminum system, the method comprising:

[0053] S1011, establishing an equipment load model according to the process production flow of the electrolytic aluminum system, wherein the equipment load model includes the connection relationship and operation sequence relationship of all equipment in the electrolytic aluminum system.

[0054] Combination Figure 3 , an embodiment of the present invention exemplarily provides an equipment load model for an electrolytic aluminum system.

[0055] According to the equipment analysis of the process production process of the electrolytic aluminum system, it can be known that the equipment for electrolytic aluminum includes but is not limited to: stone crusher, electrolytic cell, silver ingot casting machine, electric melting furnace, etc. Figure 3 As shown, the arrows indicate the operating sequence relationship between the devices.

[0056] That is, after the stone breaker is completed, the electrolytic cell working stage begins. After the electrolytic cell is completed, the silver ingot casting machine starts working. After the silver ingot casting machine is completed, the electric melting furnace starts working.

[0057] It should be noted that Figure 3 The equipment load model of the electrolytic aluminum system shown is only an exemplary description. The actual electrolytic aluminum system is more complicated. Figure 3 The equipment shown also includes a variety of other equipment, such as a steam press, a dust removal reactor, etc.

[0058] On the other hand, in the electrolytic aluminum system, the operating time of one or more equipment overlaps with each other, for example, the silver ingot casting machine and the steam press, whose working periods in the entire production cycle basically overlap.

[0059] therefore, Figure 3 This is only an exemplary equipment load model provided for the embodiment of the present invention. The actual equipment load model needs to be created according to the actual operation conditions of different electrolytic aluminum systems. Any equipment load model created based on the concept of the present invention is within the protection scope of the present invention, and the embodiment of the present invention will not be described in detail.

[0060] S1012, dividing the target production cycle into multiple continuous and non-overlapping time periods, and determining the time period in which each device in the electrolytic aluminum system is in working condition during the target production cycle according to the equipment load model.

[0061] Optionally, the time of each time period is the same. For example, a production cycle is 24 hours, and each time period is 15 minutes, so the 24 hours are divided into 96 time periods.

[0062] The time period in which each device in the electrolytic aluminum system is in working state in a production cycle is determined in sequence. For example, the time periods are numbered, and the 96 time periods are numbered from 1 to 96 in sequence. According to the process production flow of the electrolytic aluminum system, the time period number corresponding to each device in working state is determined, for example, the time period in which the stone crusher is in working state is numbered from 1 to 8; the time period in which the electrolytic cell is in working state is numbered from 9 to 60; the time period in which the silver ingot casting machine is in working state is numbered from 61 to 80; and the time period in which the electric melting furnace is in working state is numbered from 81 to 96.

[0063] S1013, based on the rated power of each device and the time period that each device is in working state in the target production cycle, obtain the rated power time model of the electrolytic aluminum system in the target production cycle, and use the rated power time model as the theoretical time model, wherein the rated power time model is used to represent the rated value of the power of the electrolytic aluminum system in the target production cycle that changes with time.

[0064] It can be seen from step S1011 and step S1012 that the smaller the time period of a production cycle is divided into, the more accurate the rated power time model of the system is. Specifically, the number of time periods of a production cycle is divided into depends on the specific system operation conditions, and the embodiment of the present invention does not limit this.

[0065] When the rated power of each device in the electrolytic aluminum system is known and the corresponding time period in operation is determined, the rated operating power of the system at each moment is the sum of the rated powers of all devices in operation at the current moment.

[0066] S102, according to the preset strategy, the operating status of all electrolytic cells in the electrolytic aluminum system is evaluated to obtain the operating status of each electrolytic cell in the target production cycle.

[0067] The production of modern aluminum electrolysis industry generally adopts cryolite-alumina molten salt electrolysis method, and the main equipment is aluminum electrolysis cell. The electrolysis cell consists of anode and cathode, and its production adopts direct current, which is connected to the busbar through the rectifier and introduced into the electrolysis cell in series. The whole process of aluminum electrolysis is controlled by constant current. An aluminum electrolysis production enterprise usually has dozens to hundreds of electrolysis cells connected in series.

[0068] During the normal production process of electrolytic aluminum, the current of the production line is basically kept at a certain constant value. However, when the operation state of the electrolytic cell is not good, such as when an anode reaction occurs, the voltage of the electrolytic cell will rise sharply, causing the power of the electrolytic cell to rise sharply. Therefore, the operation state of the electrolytic cell is the main factor that causes the change in the operating power of the electrolytic aluminum system.

[0069] Based on this, by predicting and evaluating the operating status of the electrolytic cells in the electrolytic aluminum system, the difference between the theoretical power-time model of the electrolytic aluminum system in the target production cycle and the power-time model under the actual operating status can be predicted.

[0070] S103, according to the operating status of each electrolytic cell in the target production cycle, the theoretical power-time model is corrected to obtain the predicted power-time model of the electrolytic aluminum system in the target production cycle. The predicted power-time model is used to represent the predicted value of the power change of the electrolytic aluminum system in the target production cycle over time.

[0071] The theoretical power-time model is corrected by the operating status of the electrolytic cell in the target production cycle, so that the obtained predicted power-time model is closer to the power-time model under the actual operating status of electrolytic aluminum, thereby improving the accuracy of power prediction of the electrolytic aluminum system in a production cycle.

[0072] From the above, it can be seen that the embodiment of the present invention obtains the theoretical power-time model of the electrolytic aluminum system in the target production cycle and the evaluation results of the operating status of each electrolytic cell in the electrolytic aluminum system, and corrects the theoretical power-time model according to the operating status of the electrolytic cell in the target production cycle, so that the obtained predicted power-time model is closer to the power-time model under the actual operating status of the electrolytic aluminum, thereby improving the accuracy of power prediction of the electrolytic aluminum system in a production cycle.

[0073] Figure 4 A flowchart of a power prediction method for an electrolytic aluminum system provided by an embodiment of the present invention is shown, and the details are as follows:

[0074] S401, obtaining the rated power time model of the electrolytic aluminum system in multiple historical production cycles, the temperature information and humidity information of each production cycle, and the actual power time model of the electrolytic aluminum system in each production cycle, wherein the actual power time model is used to represent the actual value of the power of the electrolytic aluminum system changing with time in the corresponding production cycle, and the electrolytic aluminum system is in a preset operating state in multiple production cycles.

[0075] Optionally, the preset state in the embodiment of the present invention refers to the operating state of the electrolytic cell being under preset conditions, for example, the electrolyte temperature of each electrolytic cell of the aluminum electrolysis system is within a preset temperature range, and for any electrolytic cell, the operating voltage of the electrolytic cell is within a preset voltage range corresponding to the electrolytic cell. At this time, the operating state of the electrolytic cell is in a normal state, and no anode reaction occurs.

[0076] The data of multiple historical production cycles of the electrolytic cell system are obtained, and in multiple selected historical production cycles, the operating status of each electrolytic cell in the electrolytic aluminum system is in a preset operating state.

[0077] S402, perform data processing to obtain a first training set. For a training sample of the first training set, the input of the training sample is the data of the rated power-time model of the electrolytic aluminum system in a production cycle, temperature information, and humidity information, and the output is the actual power-time model of the electrolytic aluminum system in the same production cycle.

[0078] Optionally, the input of the model can be based on the rated power time model of the electrolytic aluminum system in a production cycle to obtain the load value of the electrolytic aluminum system in the first time period, the average load value from the first to the second time period, the average load value of the production cycle, the maximum load value, the minimum load value and the average temperature and average humidity value of the production cycle.

[0079] S403: Train the preset neural network model using the first training set to obtain a predictor.

[0080] S404, performing data processing on the rated power time model of the electrolytic aluminum system in the target production cycle and the temperature information and humidity information of the target production cycle, inputting the data into a predictor, and using the output result as a theoretical power time model of the electrolytic aluminum system.

[0081] Optionally, based on the rated power-time model of the electrolytic aluminum system in the target production cycle, the load value of the electrolytic aluminum system in the first time period, the average load value from the first to the second time period, the average load value of the target production cycle, the maximum load value, the minimum load value and the average temperature and average humidity value of the target production cycle are obtained as inputs to the predictor, and the output results are used as the theoretical power-time model of the electrolytic aluminum system.

[0082] From the above, it can be seen that the method provided by the embodiment of the present invention makes the theoretical power-time model of electrolytic aluminum closer to the actual power-time model of the electrolytic aluminum system when all electrolytic cells are in a preset operating state. On this basis, the theoretical power-time model is corrected according to the evaluation results of the operating state of each electrolytic cell of the electrolytic aluminum system in the target production cycle, and the resulting predicted power-time model is more accurate.

[0083] Figure 5The following is a flowchart of a power prediction method for an electrolytic aluminum system according to an embodiment of the present invention. The method is used to evaluate the operating status of all electrolytic cells in the electrolytic aluminum system. The details are as follows:

[0084] S501, for any electrolytic cell, obtaining a plurality of preset state parameters corresponding to the electrolytic cell before the start of a target cycle.

[0085] S502, inputting a plurality of preset state parameters of the electrolytic cell into a preset electrolytic cell operation state grade classifier to obtain the grade corresponding to the operation state of the electrolytic cell in the target period.

[0086] Optional, combined Figure 6 The embodiment of the present invention further provides a power prediction method for an electrolytic aluminum system, which is used to obtain the electrolytic cell operation status level classifier in step S502, as described in detail as follows:

[0087] S5021, according to the preset status evaluation index, the operating status of the electrolytic cell is divided into M levels, where M is a positive integer greater than or equal to 2.

[0088] Optionally, the operating status of an electrolyzer is graded using the following status evaluation indicators:

[0089] The cumulative duration of the anode reaction in an electrolytic cell during a production cycle;

[0090] The average voltage of the electrolytic cell during the production cycle, or the cumulative duration of the operating voltage of the electrolytic cell exceeding a preset threshold during the production cycle;

[0091] Current efficiency of the electrolyzer.

[0092] In an embodiment of the present invention, a standard electrolytic cell is defined, in which the cumulative duration of the anode reaction in a production cycle of the standard electrolytic cell is 0, the average voltage in the production cycle is a preset value, or within the standard preset voltage range, the cumulative duration of the operating voltage exceeding the preset threshold in the cycle is 0, and the current efficiency is 1.

[0093] According to the actual operating status of the electrolytic cell, the corresponding value of the rating index is obtained and compared with the standard cell defined above:

[0094] The electrolytic cell whose Euclidean distance is within the first preset range [0, x1] is a first-level electrolytic cell, and its corresponding operating state is excellent, and the first preset range includes 0 and x1;

[0095] The electrolytic cell whose Euclidean distance is within the second preset range [x1, x2] is a second-stage electrolytic cell, and its corresponding operating state is good. The second preset range includes x2 but does not include x1.

[0096] The electrolytic cell with a Euclidean distance greater than x2 is a third-level electrolytic cell, and its corresponding operating status is poor.

[0097] Optionally, the above is only a specific implementation method. According to the process production characteristics of the electrolytic aluminum system, other status evaluation indicators can also be selected, and the grading results are not limited to the above three levels. The electrolytic cell operating status grading method based on the concept of the present invention is within the protection scope of the embodiments of the present invention.

[0098] S5022, for any electrolytic cell, obtain a status evaluation index of the electrolytic cell in a historical production cycle.

[0099] S5023, according to the status evaluation index of the electrolytic cell, obtain the level corresponding to the operating status of the electrolytic cell in the historical production cycle.

[0100] The specific implementation of step S5022 and step S5023 can refer to the above step S5021, and the embodiment of the present invention will not be described in detail.

[0101] S5024, establishing a second training set, the training set includes N samples, wherein a plurality of preset state parameters of an electrolytic cell in a historical production cycle and the level corresponding to the operating state of the electrolytic cell in the production cycle constitute a sample of the second training set.

[0102] There are many process parameters that affect the operation of the electrolytic cell, the main ones include:

[0103] The electrolysis temperature is an important parameter of the electrolytic cell's operating state and is usually controlled within a preset temperature range. Too high or too low an electrolytic cell temperature will cause the electrolytic cell's operating state to deteriorate.

[0104] Molecular ratio refers to the ratio of sodium fluoride to aluminum fluoride. A lower molecular ratio is beneficial to improving current efficiency.

[0105] Aluminum output;

[0106] Excess aluminum fluoride, etc.

[0107] And some of the parameters set for the electrolyzer at the beginning of the production cycle, including:

[0108] Slot voltage setting value;

[0109] Aluminum fluoride set point;

[0110] Alumina feeding reference interval, etc.

[0111] The above-mentioned process parameters and setting parameters can both be preset state parameters of the electrolytic cell, which are the input of the deep learning model, and its output is the level corresponding to the operating state of the electrolytic cell in the production cycle.

[0112] S5025, training the second training set through a preset deep learning model to obtain an electrolytic cell operation status grade classifier.

[0113] By learning the second training set, an electrolytic cell operation status grade classifier is obtained.

[0114] Optionally, after obtaining the level corresponding to the operating state of the electrolytic cell in the target cycle, the theoretical power-time model of the electrolytic aluminum system in the target production cycle can be corrected by the following method:

[0115] The theoretical power-time model is modified according to the time period during which all electrolytic cells in the electrolytic aluminum system are in working condition in the target production cycle, the level corresponding to the operating status of each electrolytic cell and the preset weighting coefficient corresponding to each level.

[0116] Optionally, in combination with steps S5021 to S5025, if the electrolytic cell is a first-stage electrolytic cell, it means that its operating state is excellent, and the weighted coefficient corresponding to the electrolytic cell is 1. The possibility of an anodic reaction occurring in the target period is small, and the actual operating voltage is closer to the theoretical voltage; if the electrolytic cell is a second-stage electrolytic cell, it means that its operating state in the target production period is good, and there is a certain possibility of an anodic reaction occurring, and the weighted coefficient corresponding to the electrolytic cell is S1; if the electrolytic cell is a third-stage electrolytic cell, it means that its operating state in the target production period is poor, and there is a relatively high possibility of an anodic reaction occurring in the target period, and the weighted coefficient corresponding to the electrolytic cell is S2, 1<S1 is less than S2.

[0117] Optionally, the method further includes: judging whether the average power value of the electrolytic aluminum system in a preset time period of the target production cycle exceeds a preset threshold value according to the power time model of the electrolytic aluminum system in the target production cycle; if so, calling the energy storage module, and the energy storage module supplies power to the electrolytic aluminum system in the preset time period. Through this method, the electrolytic aluminum enterprise can reduce the power consumption during the period with higher electricity charges and reduce the production cost of the enterprise.

[0118] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.

[0119] The following is an embodiment of the device of the present invention. For details not described in detail therein, reference may be made to the corresponding method embodiment described above.

[0120] Figure 7 The following is a schematic diagram showing the structure of a power prediction device for an electrolytic aluminum system provided by an embodiment of the present invention. For the sake of convenience, only the parts related to the embodiment of the present invention are shown, which are described in detail as follows:

[0121] like Figure 7 As shown, the power prediction device 7 of the electrolytic aluminum system includes: a theoretical power time model acquisition module 71, an electrolytic cell operation status evaluation module 72 and a predicted power time model acquisition module 73.

[0122] The theoretical power time model acquisition module 71 is used to acquire the theoretical power time model of the electrolytic aluminum system in a target production cycle, wherein the theoretical power time model is used to represent the theoretical value of the power of the electrolytic aluminum system changing with time under a preset operating state;

[0123] The electrolytic cell operation status evaluation module 72 is used to evaluate the operation status of all electrolytic cells in the electrolytic aluminum system according to a preset strategy to obtain the operation status of each electrolytic cell in the target production cycle;

[0124] The predicted power time model acquisition module 73 is used to correct the theoretical power time model according to the operating status of each electrolytic cell in the target production cycle to obtain the predicted power time model of the electrolytic aluminum system in the target production cycle. The predicted power time model is used to represent the predicted value of the power change of the electrolytic aluminum system over time in the target production cycle.

[0125] Optionally, the theoretical power time model acquisition module 71 is used to:

[0126] Establishing an equipment load model according to the process production flow of the electrolytic aluminum system, wherein the equipment load model includes the connection relationship and operation sequence relationship of all equipment in the electrolytic aluminum system;

[0127] Dividing the target production cycle into a plurality of continuous and non-overlapping time periods, and determining the time period during which each device in the electrolytic aluminum system is in a working state in the target production cycle according to the device load model;

[0128] According to the rated power of each device and the time period that each device is in working state in the target production cycle, the rated power time model of the electrolytic aluminum system in the target production cycle is obtained, and the rated power time model is used as the theoretical time model, wherein the rated power time model is used to represent the rated value of the power of the electrolytic aluminum system changing with time in the target production cycle.

[0129] Optionally, the theoretical power time model acquisition module 71 is further used for:

[0130] Obtaining a rated power time model of the aluminum electrolysis system in multiple historical production cycles, temperature information and humidity information of each production cycle, and an actual power time model of the aluminum electrolysis system in each production cycle, wherein the actual power time model is used to represent the actual value of the power of the aluminum electrolysis system changing with time in the corresponding production cycle, and the aluminum electrolysis system is in a preset operating state in the multiple production cycles;

[0131] Performing data processing to obtain a first training set, with respect to a training sample of the first training set, the input of the training sample is the data of the rated power time model of the electrolytic aluminum system in a production cycle, the temperature information, and the humidity information, and the output is the actual power time model of the electrolytic aluminum system in the same production cycle;

[0132] Training a preset neural network model using the first training set to obtain a predictor;

[0133] The rated power-time model of the electrolytic aluminum system in the target production cycle and the temperature information and humidity information of the target production cycle are processed and input into the predictor, and the output result is used as the theoretical power-time model of the electrolytic aluminum system.

[0134] Optionally, the preset operating state means that the electrolyte temperature of each electrolytic cell of the aluminum electrolysis system is within a preset temperature range, and for any electrolytic cell, the operating voltage of the electrolytic cell is within a preset voltage range corresponding to the electrolytic cell.

[0135] Optionally, the electrolyzer operation status assessment module 72 is used to:

[0136] For any electrolytic cell, obtaining a plurality of preset state parameters corresponding to the electrolytic cell before the start of the target cycle;

[0137] A plurality of preset state parameters of the electrolytic cell are input into a preset electrolytic cell operation state grade classifier to obtain the grade corresponding to the operation state of the electrolytic cell in the target period.

[0138] Optionally, the electrolyzer operation status assessment module 72 is further used for:

[0139] According to the preset status evaluation index, the operation status of the electrolytic cell is divided into M levels, where M is a positive integer greater than or equal to 2;

[0140] For any electrolytic cell, obtaining a status evaluation index of the electrolytic cell in a historical production cycle;

[0141] According to the status evaluation index of the electrolytic cell, obtaining the level corresponding to the operating status of the electrolytic cell in the historical production cycle;

[0142] Establishing a second training set, the training set comprising N samples, wherein a plurality of preset state parameters of an electrolytic cell in a historical production cycle and a level corresponding to the operating state of the electrolytic cell in the production cycle constitute a sample of the second training set;

[0143] The second training set is trained by a preset deep learning model to obtain the electrolytic cell operation status grade classifier.

[0144] Optionally, the predicted power time model acquisition module 73:

[0145] The theoretical power-time model is modified according to the time period during which all the electrolytic cells in the electrolytic aluminum system are in working condition in the target production cycle, the level corresponding to the operating status of each electrolytic cell and the preset weighting coefficient corresponding to each level.

[0146] Optionally, the device further includes an energy storage calling module 74, which is used to:

[0147] According to the power-time model of the electrolytic aluminum system in the target production cycle, it is determined whether the power average value of the electrolytic aluminum system within the preset time period of the target production cycle exceeds the preset threshold value; if so, the energy storage module is called to supply power to the electrolytic aluminum system within the preset time period.

[0148] From the above, it can be seen that the embodiment of the present invention obtains the theoretical power-time model of the electrolytic aluminum system in the target production cycle and the evaluation results of the operating status of each electrolytic cell in the electrolytic aluminum system, and corrects the theoretical power-time model according to the operating status of the electrolytic cell in the target production cycle, so that the obtained predicted power-time model is closer to the power-time model under the actual operating status of the electrolytic aluminum, thereby improving the accuracy of power prediction of the electrolytic aluminum system in a production cycle.

[0149] Figure 8 is a schematic diagram of a terminal provided by an embodiment of the present invention. Figure 8 As shown, the terminal 8 of this embodiment includes: a processor 80, a memory 81, and a computer program 82 stored in the memory 81 and executable on the processor 80. When the processor 80 executes the computer program 82, the steps in the above-mentioned power prediction method embodiments of the aluminum electrolytic system are implemented, for example Figure 1 Alternatively, when the processor 80 executes the computer program 82, the functions of each module / unit in the above-mentioned device embodiments are realized, for example, Figure 7 Functions of modules / units 71 to 73 are shown.

[0150] Exemplarily, the computer program 82 may be divided into one or more modules / units, which are stored in the memory 81 and executed by the processor 80 to implement the present invention. The one or more modules / units may be a series of computer program instruction segments capable of implementing specific functions, which are used to describe the execution process of the computer program 82 in the terminal 8. For example, the computer program 82 may be divided into Figure 7 Modules / units 71 to 73 are shown.

[0151] The terminal 8 may be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server. The terminal 8 may include, but is not limited to, a processor 80 and a memory 81. Those skilled in the art will appreciate that Figure 8 It is only an example of terminal 8 and does not constitute a limitation on terminal 8. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the terminal may also include input and output devices, network access devices, buses, etc.

[0152] The processor 80 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0153] The memory 81 may be an internal storage unit of the terminal 8, such as a hard disk or memory of the terminal 8. The memory 81 may also be an external storage device of the terminal 8, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the terminal 8. Further, the memory 81 may also include both an internal storage unit of the terminal 8 and an external storage device. The memory 81 is used to store the computer program and other programs and data required by the terminal. The memory 81 may also be used to temporarily store data that has been output or is to be output.

[0154] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0155] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0156] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0157] In the embodiments provided by the present invention, it should be understood that the disclosed devices / terminals and methods can be implemented in other ways. For example, the device / terminal embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0158] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0159] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0160] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the power prediction method embodiments of the above-mentioned electrolytic aluminum system can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device that can carry the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practices in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practices, computer-readable media does not include electrical carrier signals and telecommunication signals.

[0161] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A power prediction method for an electrolytic aluminum system, characterized in that: include: In a target production cycle, a theoretical power-time model of the electrolytic aluminum system is obtained, wherein the theoretical power-time model is used to represent a theoretical value of power variation over time of the electrolytic aluminum system under a preset operating state; According to a preset strategy, the operating status of all electrolytic cells in the electrolytic aluminum system is evaluated to obtain the operating status of each electrolytic cell in the target production cycle; According to the operating state of each electrolytic cell in the target production cycle, the theoretical power-time model is corrected to obtain a predicted power-time model of the electrolytic aluminum system in the target production cycle, wherein the predicted power-time model is used to represent the predicted value of the power of the electrolytic aluminum system changing with time in the target production cycle; Wherein, the evaluating the operating status of all electrolytic cells in the electrolytic aluminum system according to the preset strategy includes: For any electrolytic cell, obtaining a plurality of preset state parameters corresponding to the electrolytic cell before the start of the target production cycle; Inputting a plurality of preset state parameters of the electrolytic cell into a preset electrolytic cell operation state grade classifier to obtain the grade corresponding to the operation state of the electrolytic cell in the target production cycle; The method further includes: According to the preset status evaluation index, the operation status of the electrolytic cell is divided into M levels, where M is a positive integer greater than or equal to 2; For any electrolytic cell, obtaining a status evaluation index of the electrolytic cell in a historical production cycle; According to the status evaluation index of the electrolytic cell, obtaining the level corresponding to the operating status of the electrolytic cell in the historical production cycle; Establishing a second training set, the training set comprising N samples, wherein a plurality of preset state parameters of an electrolytic cell in a historical production cycle and a level corresponding to the operating state of the electrolytic cell in the production cycle constitute a sample of the second training set; The second training set is trained by a preset deep learning model to obtain the electrolytic cell operation status grade classifier; The modifying of the theoretical power-time model according to the operating state of each electrolytic cell in the target production cycle includes: The theoretical power-time model is modified according to the time period during which all the electrolytic cells in the electrolytic aluminum system are in working condition in the target production cycle, the level corresponding to the operating status of each electrolytic cell and the preset weighting coefficient corresponding to each level.

2. The method according to claim 1, characterized in that The theoretical power time model for obtaining the electrolytic aluminum system includes: Establishing an equipment load model according to the process production flow of the electrolytic aluminum system, wherein the equipment load model includes the connection relationship and operation sequence relationship of all equipment in the electrolytic aluminum system; Dividing the target production cycle into a plurality of continuous and non-overlapping time periods, and determining the time period during which each device in the electrolytic aluminum system is in a working state in the target production cycle according to the device load model; According to the rated power of each device and the time period that each device is in working state in the target production cycle, the rated power time model of the electrolytic aluminum system in the target production cycle is obtained, and the rated power time model is used as the theoretical power time model, wherein the rated power time model is used to represent the rated value of the power of the electrolytic aluminum system changing with time in the target production cycle.

3. The method according to claim 2, characterized in that The method further includes: Acquire the rated power time model of the aluminum electrolysis system in multiple historical production cycles, the temperature information and humidity information of each production cycle, and the actual power time model of the aluminum electrolysis system in each production cycle, wherein the actual power time model is used to represent the actual value of the power of the aluminum electrolysis system changing with time in the corresponding production cycle, and the aluminum electrolysis system is in a preset operating state in multiple production cycles; Performing data processing to obtain a first training set, with respect to a training sample of the first training set, the input of the training sample is the data of the rated power time model of the electrolytic aluminum system in a production cycle, the temperature information, and the humidity information, and the output is the actual power time model of the electrolytic aluminum system in the same production cycle; Training a preset neural network model using the first training set to obtain a predictor; The rated power-time model of the electrolytic aluminum system in the target production cycle and the temperature information and humidity information of the target production cycle are processed and input into the predictor, and the output result is used as the theoretical power-time model of the electrolytic aluminum system.

4. The method according to any one of claims 1 to 3, characterized in that: The preset operating state means that the electrolyte temperature of each electrolytic cell of the aluminum electrolysis system is within a preset temperature range, and for any electrolytic cell, the operating voltage of the electrolytic cell is within a preset voltage range corresponding to the electrolytic cell.

5. The method according to claim 1, characterized in that The method further includes: According to the power time model of the electrolytic aluminum system in the target production cycle, determining whether the power average value of the electrolytic aluminum system in a preset time period of the target production cycle exceeds a preset threshold; If so, the energy storage module is called to supply power to the electrolytic aluminum system within the preset time period.

6. A terminal comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 5 are implemented.

7. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.