Aluminum electrolysis process parameter optimization method based on multi-target badger optimization algorithm

Abstract

The invention discloses an aluminum electrolysis process parameter optimization method based on a multi-target badger optimization algorithm, and belongs to the technical field of industrial process parameter optimization, the method comprises the following steps: selecting parameters capable of representing production power consumption, carbon emission and impurity content from aluminum electrolysis process parameters as output variables; selecting an aluminum electrolysis process parameter which has the greatest influence on the output variable as a decision variable; constructing a multi-objective optimization model based on the output variable and the decision variable; integrating a plurality of strategies in the badger algorithm to obtain a multi-target badger optimization algorithm; wherein the multiple strategies comprise a non-dominated sorting strategy, a crowding distance strategy and an external file dynamic updating strategy; and carrying out iterative operation by using the multi-target badger optimization algorithm, and outputting an optimal scheme set after iteration is finished so as to realize aluminum electrolysis process parameter optimization. By adopting the scheme of the invention, the accuracy of a process parameter optimization result can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of process parameter optimization in industry, and in particular to an aluminum electrolysis process parameter optimization method based on a multi-objective honey badger optimization algorithm. Background Art

[0002] At present, the low carbonization and greening of the aluminum electrolysis industry have become an urgent need within the industry. In aluminum electrolysis, the ultimate goal of parameter optimization is to find the optimal process parameters and reduce production power consumption, carbon emissions and impurity content. However, when solving the optimal process parameters, the variables are coupled and conflicting with each other, and it is impossible to find a unique process parameter so that the production power consumption, carbon emissions and impurity content all meet the minimum requirements. Therefore, it is necessary to use a multi-objective optimization algorithm to solve the Pareto optimal solution set of process parameters. Chinese patent literature (Intelligent decision-making and multi-objective optimization method for aluminum electrolysis production process) discloses an adaptive dynamic programming method. However, due to the strong dependence of this method on the model and the problem of being easily trapped in local optimality, it is easy to cause the problem of difficulty in solving and low solution accuracy when facing complex aluminum electrolysis process models. Chinese patent literature (Differential evolution aluminum electrolysis multi-objective optimization method based on AR preference information) discloses the AR-PMDE method. However, due to the excessive reliance of the search strategy of this method on random factors, it is easy to cause slow convergence and low solution accuracy. Summary of the invention

[0003] The present invention provides an aluminum electrolysis process parameter optimization method based on a multi-objective honey badger optimization algorithm to solve the technical problems of high solution difficulty and low solution accuracy in the existing meta-heuristic optimization algorithm in the aluminum electrolysis process parameter optimization problem.

[0004] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0005] On the one hand, the present invention provides an aluminum electrolysis process parameter optimization method based on a multi-objective honey badger optimization algorithm, and the aluminum electrolysis process parameter optimization method based on a multi-objective honey badger optimization algorithm comprises:

[0006] Selecting parameters that can characterize production power consumption, carbon emissions and impurity content from aluminum electrolysis process parameters as output variables; selecting aluminum electrolysis process parameters that have the greatest impact on the output variables as decision variables;

[0007] Based on the output variables and the decision variables, construct a multi-objective optimization model;

[0008] Integrate multiple strategies into the honey badger algorithm to obtain a multi-objective honey badger optimization algorithm; wherein the multiple strategies include: non-dominated sorting strategy, crowding distance strategy and external archive dynamic update strategy;

[0009] For the multi-objective optimization model, the multi-objective honey badger optimization algorithm is used to perform iterative operations, and after the iteration is completed, an optimal solution set is output to achieve optimization of aluminum electrolysis process parameters.

[0010] Furthermore, the output variables include: energy consumption per ton of aluminum, carbon emissions per ton of aluminum, and quality of raw aluminum.

[0011] Furthermore, the decision variables include: cell voltage, electrolysis temperature, electrolyte level, aluminum level and aluminum fluoride feed rate.

[0012] Furthermore, based on the output variables and the decision variables, a multi-objective optimization model is constructed, including:

[0013] Based on the output variables and the decision variables, a multi-objective optimization model is established using a recurrent neural network.

[0014] Furthermore, based on the output variables and the decision variables, a multi-objective optimization model is established using a recurrent neural network, including:

[0015] In the aluminum electrolysis site database, output variables and decision variables of consecutive dates are selected as original process parameter data, and the original process parameter data are preprocessed to obtain preprocessed process parameter data; wherein the preprocessing includes: removing outliers, completing data, and normalizing data;

[0016] Build a recurrent neural network;

[0017] Using the preprocessed process parameter data, a five-input and three-output model was trained based on a recurrent neural network as a multi-objective optimization model for optimizing production power consumption, carbon emissions, and impurity content.

[0018] Furthermore, the structure of the recurrent neural network is set as follows: the input layer contains 5 nodes, the hidden layer uses a node structure containing 20 LSTM units, and the output layer is a linear node; the LSTM unit uses sigmoid and tanh functions as activation functions, and the output layer uses a linear activation function to predict continuous values; the number of iterations is set to 200 times, the learning rate is set to 0.001, the Adam optimizer is used, and a batch size of 32 is used for training; to prevent overfitting, Dropout is used as a regularization method.

[0019] Furthermore, the non-dominated sorting strategy is expressed as follows: when performing non-dominated sorting, the solution set is first classified according to the non-dominated relationship, and the non-dominated solutions are marked as the first-level Pareto optimal; then, the solutions dominated by the first level are classified to the next level until all solutions are classified, and each level of the Pareto optimal front contains solutions with different degrees of domination.

[0020] Furthermore, the crowding distance strategy is expressed as follows: the crowding distance evaluates the distribution density of the solution by summing the distances between adjacent solutions; the larger the crowding distance, the more dispersed the distribution is and the greater the advantage of the solution is.

[0021] Further, the external archive dynamic update strategy is expressed as follows: the archive stores the Pareto optimal solutions obtained by non-dominated sorting and crowding distance; the archive is dynamically updated during the optimization process to maintain representative and effective solutions; after each iteration, the offspring are compared with the existing individuals in the archive: if all offspring are dominated by any individual in the archive, then they will be discarded; if the new offspring are in the same dominance level as all individuals stored in the archive, the new offspring should be added to the archive; if any offspring in the archive dominates an individual, the dominated individual is deleted and the dominant offspring is added; if the offspring added to the archive exceeds the capacity of the archive, the crowding distance of all individuals is calculated; in order to enhance diversity and avoid local optimality, individuals are stored in descending order according to crowding distance until the archive is full, and any remaining individuals are discarded; from this archive, the individuals with the top 10% of crowding distance are selected as potential leader candidates; then a roulette wheel selection method is used to determine the final leader from these candidates, and the selection probability of each individual is proportional to its crowding distance, and the individual with a larger crowding distance has a greater chance of being selected.

[0022] Furthermore, the multi-objective honey badger optimization algorithm is used to perform iterative operations, and after the iteration, an optimal solution set is output to achieve the optimization of aluminum electrolysis process parameters, including:

[0023] Step 1: Initialize the population P and population size N; define the position of the i-th honey badger as x i ;

[0024] Step 2: Initialize the optimization algorithm parameters, including: define β = 6, C = 2, and iter max =200;

[0025] Step 3, sorting the population P using the non-dominated sorting strategy and the crowding distance strategy, including: first, calculating the target value of each individual in the population; then, non-dominated sorting the individuals in ascending order of their target values; finally, sorting the individuals in each non-dominated level in descending order of crowding distance;

[0026] Step 4, the sorted population is used as the initial external archive and the iteration begins;

[0027] Step 5, selecting the leader individual, including: sorting the individuals in the external archives by non-dominance, sorting the individuals in ascending order; finally, sorting the individuals in each non-dominance level by descending order of crowding distance; selecting the top 10% of the individuals in the crowding distance in the first Pareto level, and then using the roulette wheel selection method to determine the final leader individual;

[0028] Step 6, update the adaptive reduction factor α, the formula is:

[0029]

[0030] Where t is the number of iterations;

[0031] Step 7: Update the density factor I, where the density factor I of the i-th individual is i Defined as:

[0032]

[0033] Where S = (x i -x i+1 ) 2 ,d i =x prey -x i , where S represents the concentration intensity, di represents the position x of the prey and the i+1th honey badger i+1 The distance between prey Indicates the location of the best prey; r2 indicates a random value in the range [0,1];

[0034] Step 8, updating the positions of individuals in the population, including: determining the formula for generating new offspring based on the random value r, if r < 0.5, entering the exploration phase and updating the positions using the following equation:

[0035] x new =x prey +F×β×I×x prey +F×r3×α×d i ×|cos(2πr4)×[1-cos(2πr5)]|

[0036]

[0037] Otherwise, proceed to the development phase and update the position using the following equation:

[0038] x new =x prey +F×r7×α×d i

[0039] Among them, x newUpdate the position of the individual; r3, r4, r5, r6, and r7 are all random values ​​in the range [0,1];

[0040] Step 9, dynamic updating of archives, includes: first, merging the generated new offspring and parent generations to generate a new population; then, using an external archive dynamic updating strategy to save the optimal solution set to the archive;

[0041] Step 10, check whether the maximum number of iterations has been reached. If not, return to step 5 and continue iterating; otherwise, exit the iterative operation and use the individuals in the archive as the final Pareto optimal solution, that is, the optimal process parameters, so as to obtain the optimal solution set and output it to achieve the optimization of aluminum electrolysis process parameters.

[0042] On the other hand, the present invention further provides an electronic device, comprising a processor and a memory; wherein the memory stores at least one instruction, and the instruction is loaded and executed by the processor to implement the above method.

[0043] In yet another aspect, the present invention further provides a computer-readable storage medium, wherein at least one instruction is stored in the storage medium, and the instruction is loaded and executed by a processor to implement the above method.

[0044] The beneficial effects brought about by the technical solution provided by the present invention include at least:

[0045] The present invention proposes a multi-objective honey badger optimization method, which introduces and integrates external archive dynamic update, non-dominated sorting, crowding distance and HBA search strategy. The multi-objective honey badger optimization method is used to optimize the aluminum electrolysis process parameters, which can effectively overcome the existing meta-heuristic optimization algorithm in the aluminum electrolysis process parameter optimization problem. The problem of high difficulty in solving and low solution accuracy can improve the accuracy of the process parameter optimization results. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. 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 creative work.

[0047] Figure 1 It is a schematic diagram of the execution flow of the aluminum electrolysis process parameter optimization method based on the multi-objective honey badger optimization algorithm provided by an embodiment of the present invention;

[0048] Figure 2 is a schematic diagram of non-dominated sorting and crowding distance provided by an embodiment of the present invention;

[0049] Figure 3It is a flow chart of a multi-objective honey badger optimization algorithm provided by an embodiment of the present invention;

[0050] Figure 4 It is a system block diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0051] In order to make the objectives, technical solutions and advantages of the present invention more clear, the embodiments of the present invention will be further described in detail below with reference to the accompanying drawings.

[0052] First of all, it should be noted that in the embodiments of the present invention, words such as "exemplarily" and "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "exemplary" in the present invention should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of the word "exemplarily" is intended to present the concept in a concrete way. In addition, in the embodiments of the present invention, the meaning expressed by "and / or" can be both, or it can be either of the two.

[0053] First embodiment

[0054] This embodiment provides an aluminum electrolysis process parameter optimization method based on a multi-objective honey badger optimization algorithm. The method can be implemented by an electronic device. The execution flow of the method is as follows: Figure 1 As shown, the following steps are included:

[0055] S1, selecting parameters that can characterize production power consumption, carbon emissions and impurity content from aluminum electrolysis process parameters as output variables; selecting the aluminum electrolysis process parameters that have the greatest impact on the output variables as decision variables;

[0056] Specifically, in this embodiment, the implementation process of the above S1 is as follows:

[0057] S11, obtaining on-site process parameter data, and then selecting a parameter Y that can characterize production power consumption, carbon emissions and impurity content from the on-site process parameter data as an output variable;

[0058] Specifically, this embodiment selects energy consumption per ton of aluminum W, carbon emissions per ton of aluminum E and raw aluminum quality Q in the process parameters to respectively characterize production power consumption, carbon emissions and impurity content, as the output Y = [W, Q, E] of the multi-objective optimization model.

[0059] S12, select the controllable process parameters that have the greatest impact on Y to form the decision variable X;

[0060] Specifically, in this embodiment, after theoretical process analysis, the process parameters that will affect the optimization target are selected; then, by calculating the covariance, the five process parameters with the strongest correlation are selected as the input variables X=[x1,x2,x3,x4,x5] of the multi-objective optimization model, specifically including: cell voltage x1, electrolysis temperature x2, electrolyte level x3, aluminum level x4, and aluminum fluoride feed amount x5.

[0061] S2, constructing a multi-objective optimization model based on the output variables and the decision variables;

[0062] Specifically, this embodiment uses a recurrent neural network to establish models of three optimization objectives based on the output variables and the decision variables. The specific implementation process is as follows:

[0063] S21, input and output training data preprocessing;

[0064] In the aluminum electrolysis site database, process parameter data of consecutive dates are selected as original process parameter data, and the original process parameter data are preprocessed to obtain preprocessed process parameter data; wherein the preprocessing includes: removing outliers, completing data, and normalizing data.

[0065] S22, build a recurrent neural network; the network structure is set as follows: the input layer contains 5 nodes, the hidden layer uses a node structure containing 20 LSTM units, and the output layer is a linear node; the LSTM unit uses sigmoid and tanh functions as activation functions, and the output layer uses a linear activation function to predict continuous values; the number of iterations is set to 200 times, the learning rate is set to 0.001, the Adam optimizer is used, and the batch size of 32 is used for training; to prevent overfitting, Dropout (0.2) is used as a regularization method. This model structure can effectively process time series data and capture the temporal dependencies in the data.

[0066] S23, training model;

[0067] Utilizing the preprocessed process parameter data and the above-mentioned recurrent neural network structure, a five-input and three-output model is trained as a multi-objective optimization model for optimizing production power consumption, carbon emissions, and impurity content.

[0068] S3, integrating multiple strategies into the honey badger algorithm to obtain a multi-objective honey badger optimization algorithm; wherein the multiple strategies include: a non-dominated sorting strategy, a crowding distance strategy, and an external archive dynamic update strategy;

[0069] It should be noted that the Honey Badger Algorithm (HBA), as a newly proposed new type of swarm intelligence optimization algorithm, is widely used in the engineering field due to its strong convergence performance, especially its fast convergence speed. However, HBA cannot be used to solve the multi-objective whale optimization algorithm, so it is necessary to integrate other strategies to expand HBA to solve the multi-objective optimization problem. To this end, this embodiment designs a multi-objective honey badger optimization algorithm that integrates multiple strategies, including: non-dominated sorting, crowding distance, and dynamic update of external archives; the specific implementation process is as follows:

[0070] S31, introduces non-dominant relations;

[0071] A Pareto optimal solution is better than other solutions in at least one objective and not inferior to other solutions in other objectives. Essentially, a Pareto optimal solution is a set of solutions that cannot be improved on all objectives simultaneously. Non-dominated relations describe the superiority or inferiority relationship between solution sets. Solution 1 is superior to solution 2 if the following two conditions are met: (a) Solution 2 is not significantly better than solution 1 in all objectives. (b) Solution 1 is definitely better than solution 2 in at least one objective. Non-dominated relations can be expressed as Figure 2 As shown: individuals A, B and C are on the first Pareto frontier F1, while individuals D and E are dominated by F1 and therefore belong to the second Pareto frontier F2.

[0072] S32, sort the solution set using a non-dominated sorting strategy;

[0073] When performing non-dominated sorting, the solution set is first classified according to the non-dominated relationship, and the non-dominated solutions are marked as the first-level Pareto optimal. Then the solutions dominated by the first level are classified to the next level until all solutions are classified, and each level of the Pareto optimal front contains solutions with different degrees of domination.

[0074] S33, using crowding distance to sort the solution sets of the same dominance level;

[0075] The crowding distance evaluates the distribution density of solutions by summing the distances between adjacent solutions. The larger the crowding distance, the more dispersed the distribution is and the greater the advantage of the solution. Figure 2 As shown. In the crowding distance calculation, the population is first sorted according to the value of each objective function. Infinite crowding distance is assigned to the boundary solution. For non-boundary solutions, the crowding distance of individual j is defined as:

[0076] S34, dynamic update of external archive. The archive stores Pareto optimal solutions obtained by non-dominated sorting and crowding distance, with the goal of maintaining the diversity of the population and providing high-quality candidate solutions. The archive is dynamically updated during the optimization process to maintain representative and effective solutions. After each iteration, the offspring are compared with the existing individuals in the archive: if all offspring are dominated by any individual in the archive, they will be discarded; if the new offspring are at the same dominance level as all individuals stored in the archive, the new offspring should be added to the archive; if any offspring in the archive dominates an individual, the dominated individual is deleted and the dominant offspring is added. If the offspring added to the archive exceeds the capacity of the archive, the crowding distance of all individuals is calculated. In order to enhance diversity and avoid local optimality, individuals are stored in descending order according to the crowding distance until the archive is full and any remaining individuals are discarded.

[0077] S35, select leader individuals for updating offspring;

[0078] Due to the introduction of external archives, the best non-dominated solutions are stored in the archive. From this archive, the individuals with the top 10% of crowding distance are selected as potential leader candidates. The roulette wheel selection method is then used to determine the final leader from these candidates, and the selection probability of each individual is proportional to its crowding distance, and individuals with larger crowding distances have a greater chance of being selected.

[0079] S4, using the multi-objective honey badger optimization algorithm to perform iterative calculations, and outputting an optimal solution set after the iteration is completed to achieve optimization of aluminum electrolysis process parameters;

[0080] Specifically, Figure 3 As shown in the figure, the specific process of using the multi-objective honey badger optimization algorithm for iterative calculation and outputting the optimal solution set to achieve the optimization of aluminum electrolysis process parameters is as follows:

[0081] S41, initialize the population P and population size N; define the position of the i-th honey badger as: The population consists of N = 100 honey badgers individuals.

[0082] S42, initializing optimization algorithm parameters;

[0083] Define HBA parameters: β = 6, C = 2, and the maximum number of iterations iter max =200.

[0084] S43, sorting the group P using the non-dominated sorting strategy and the crowding distance strategy;

[0085] First, the target value of each individual in the population is calculated; then, non-dominated sorting is performed based on these values ​​to sort the individuals in ascending order; finally, within each non-dominated level, the individuals are sorted in descending order of crowding distance.

[0086] S44, the sorted population is used as the initial external archive and the iteration begins;

[0087] S45, select leader individual x prey ;

[0088] Perform non-dominated sorting on the individuals in the external archives and sort the individuals in ascending order; finally, within each non-dominated level, sort the individuals in descending order of crowding distance; select the top 10% of the individuals in the crowding distance in the first Pareto level, and then use the roulette wheel selection method to determine the final leader individual x prey ;

[0089] S46, updating the adaptive decrement factor α of the HBA, the formula is:

[0090]

[0091] Where t is the number of iterations; the adaptive reduction factor is used to ensure a smooth transition between the exploration and exploitation phases and varies with the number of iterations.

[0092] S47, update density factor I;

[0093] Among them, the odor intensity I i Characterizes the concentration and distance between prey and honey badgers; the density factor I of the i-th individual i Defined as:

[0094]

[0095] Where S = (x i -x i+1 ) 2 ,d i =x prey -x i , where S represents the concentration intensity, di represents the position x of the prey and the i+1th honey badger i+1 The distance between prey Indicates the location of the best prey; r2 indicates a random value in the range [0,1];

[0096] S48, update the position of individuals in the population;

[0097] The formula for generating new offspring is determined based on the random value r. If r < 0.5, the exploration phase is entered and the position is updated using the following equation:

[0098] xnew =x prey +F×β×I×x prey +F×r3×α×d i ×|cos(2πr4)×[1-cos(2πr5)]

[0099]

[0100] Otherwise, proceed to the development phase and update the position using the following equation:

[0101] x new =x prey +F×r7×α×d i

[0102] Among them, x new Update the position of the individual; r3, r4, r5, r6, and r7 are all random values ​​in the range [0,1];

[0103] S49, dynamic updating of archives;

[0104] First, the generated new offspring and parent generations are merged to generate a new population; then, the external archive dynamic update strategy is used to save the optimal solution set to the archive;

[0105] S410, check whether the maximum number of iterations has been reached. If not, return to S45 and continue iterating; otherwise, exit the iterative operation and use the individuals in the archive as the final Pareto optimal solution, that is, the optimal process parameters, so as to obtain the optimal solution set and output it to achieve the optimization of aluminum electrolysis process parameters.

[0106] In summary, this embodiment provides an aluminum electrolysis process parameter optimization method based on a multi-objective honey badger optimization algorithm, wherein the proposed multi-objective honey badger optimization method introduces and integrates external archive dynamic update, non-dominated sorting, crowding distance and HBA search strategy. The use of the multi-objective honey badger optimization method for aluminum electrolysis process parameter optimization can effectively overcome the existing meta-heuristic optimization algorithm in the aluminum electrolysis process parameter optimization problem. The problem of high difficulty in solving and low solution accuracy can improve the accuracy of the process parameter optimization results.

[0107] Second embodiment

[0108] This embodiment provides an electronic device, such as Figure 4As shown, the electronic device includes: a processor and a memory; wherein the processor and the memory can be connected via a communication bus; the memory stores at least one instruction, and the instruction is loaded and executed by the processor to implement the method of the first embodiment. In addition, the electronic device may also include a transceiver, the processor and the transceiver can be connected via a communication bus, and the transceiver is used to communicate with other devices.

[0109] Next, combine Figure 4 The following is a detailed introduction to the various components of the electronic device:

[0110] Among them, the processor is the control center of the electronic device, and the electronic device may include multiple processors, each of which may be a single-core processor (single-CPU) or a multi-core processor (multi-CPU). The processor here may be a processor or a general term for multiple processing elements. For example, the processor is one or more central processing units (CPUs), or other general-purpose processors, application specific integrated circuits (ASICs), or one or more integrated circuits configured to implement an embodiment of the present invention, such as one or more microprocessors (digital signal processors, DSPs), or one or more field programmable gate arrays (field programmable gate arrays, FPGAs), or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor may execute various functions of the electronic device by running or executing software programs stored in the memory and calling data stored in the memory.

[0111] In a specific implementation, as an embodiment, the processor may include one or more CPUs, such as Figure 4 The CPU0 and CPU1 shown in the figure are, of course, only exemplary.

[0112] The memory is used to store the software program for executing the solution of the present invention, and the execution is controlled by the processor. The specific implementation method can refer to the above method embodiment and will not be repeated here.

[0113] Optionally, the memory may be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory may be integrated with the processor or exist independently and accessed through the interface circuit ( Figure 4 (not shown) is coupled to the processor, which is not specifically limited in this embodiment of the present invention.

[0114] The transceiver may include a receiver and a transmitter ( Figure 4 The receiver is used to implement the receiving function, and the transmitter is used to implement the sending function. The transceiver can be integrated with the processor or exist independently and communicate with the electronic device through the interface circuit ( Figure 4 (not shown) is coupled to the processor, which is not specifically limited in this embodiment of the present invention.

[0115] In addition, it should be noted that Figure 4 The structure of the electronic device shown in the figure does not constitute a limitation on the device, and the actual device may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently. In addition, the technical effects achieved by the electronic device when executing the method of the first embodiment above can refer to the technical effects described in the first embodiment above, so they are not repeated here.

[0116] Third embodiment

[0117] This embodiment provides a computer-readable storage medium, which stores at least one instruction, and the instruction is loaded and executed by a processor to implement the method of the first embodiment. The computer-readable storage medium may be a ROM, a random access memory, a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc. The instructions stored therein may be loaded by a processor in a terminal to execute the method.

[0118] In addition, it should be noted that the present invention can be provided as a method, an apparatus or a computer program product. Therefore, the embodiment of the present invention can be in the form of a full or partial hardware embodiment, a full or partial software embodiment or an embodiment combining software and hardware. Moreover, when implemented using software, the embodiment of the present invention can be in the form of a computer program product implemented on one or more computer-usable storage media containing computer-usable program codes. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center containing one or more available media sets. The available medium may be a magnetic medium (eg, a floppy disk, a hard disk, a magnetic tape), an optical medium (eg, a DVD), or a semiconductor medium. The semiconductor medium may be a solid state hard disk.

[0119] The embodiments of the present invention are described with reference to the flowcharts and / or block diagrams of the methods, terminal devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, an embedded processor, or other programmable data processing terminal device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing terminal device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0120] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing terminal device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device, so that a series of operation steps are executed on the computer or other programmable terminal device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable terminal device provide for implementing the process in the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0121] It should also be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. The terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that the process, method, article or terminal device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or terminal device. In the absence of more restrictions, the elements defined by the sentence "including one..." do not exclude the existence of other identical elements in the process, method, article or terminal device including the elements. In addition, the term "and / or" is only an association relationship describing the associated objects, indicating that there can be three relationships, for example, A and / or B, which can represent: A exists alone, A and B exist at the same time, and B exists alone, wherein A and B can be singular or plural. In addition, the character " / " in this article generally indicates that the objects before and after are in an "or" relationship, but it may also indicate an "and / or" relationship. Please refer to the context for specific understanding. "At least one" means one or more, and "plurality" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can be represented by: a, b, c, ab, ac, bc or abc, where a, b, c can be single or plural.

[0122] In addition, it can be understood that in various embodiments of the present invention, the size of the serial numbers of the above-mentioned processes does not 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 embodiments of the present invention.

[0123] 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.

[0124] In several embodiments provided by the present invention, it should be understood that the disclosed equipment, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of functional modules / units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point, the coupling or direct coupling or communication connection between each other 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. The unit described as a separate component may or may not be physically separated, and the component displayed as a unit may or may not be a physical unit, that is, it may be located in one place, or it may be distributed on multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, each functional unit in each embodiment of the present invention can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit.

[0125] If the method 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 technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0126] Finally, it should be noted that the above is only a preferred embodiment of the present invention. It should be pointed out that although the preferred embodiment of the present invention has been described, for ordinary technicians in this technical field, once the basic creative concept of the present invention is known, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as the protection scope of the present invention. Therefore, the attached claims are intended to be interpreted as including the preferred embodiment and all changes and modifications that fall within the scope of the embodiments of the present invention.

Claims

1. A method for optimizing aluminum electrolysis process parameters based on a multi-objective honey badger optimization algorithm, characterized in that: The aluminum electrolysis process parameter optimization method based on the multi-objective honey badger optimization algorithm includes: Selecting parameters that can characterize production power consumption, carbon emissions and impurity content from aluminum electrolysis process parameters as output variables; selecting aluminum electrolysis process parameters that have the greatest impact on the output variables as decision variables; Based on the output variables and the decision variables, construct a multi-objective optimization model; Integrate multiple strategies into the honey badger algorithm to obtain a multi-objective honey badger optimization algorithm; wherein the multiple strategies include: non-dominated sorting strategy, crowding distance strategy and external archive dynamic update strategy; For the multi-objective optimization model, the multi-objective honey badger optimization algorithm is used to perform iterative operations, and after the iteration is completed, an optimal solution set is output to achieve optimization of aluminum electrolysis process parameters.

2. The aluminum electrolysis process parameter optimization method based on the multi-objective honey badger optimization algorithm according to claim 1 is characterized in that: The output variables include: energy consumption per ton of aluminum, carbon emissions per ton of aluminum, and quality of raw aluminum.

3. The aluminum electrolysis process parameter optimization method based on the multi-objective honey badger optimization algorithm according to claim 2 is characterized in that: The decision variables include: cell voltage, electrolysis temperature, electrolyte level, aluminum level and aluminum fluoride feed rate.

4. The aluminum electrolysis process parameter optimization method based on the multi-objective honey badger optimization algorithm according to claim 1 is characterized in that: Based on the output variables and the decision variables, a multi-objective optimization model is constructed, including: Based on the output variables and the decision variables, a multi-objective optimization model is established using a recurrent neural network.

5. The aluminum electrolysis process parameter optimization method based on the multi-objective honey badger optimization algorithm according to claim 4 is characterized in that: Based on the output variables and the decision variables, a multi-objective optimization model is established using a recurrent neural network, including: In the aluminum electrolysis site database, output variables and decision variables of consecutive dates are selected as original process parameter data, and the original process parameter data are preprocessed to obtain preprocessed process parameter data; wherein the preprocessing includes: removing outliers, completing data, and normalizing data; Build a recurrent neural network; Using the preprocessed process parameter data, a five-input and three-output model was trained based on a recurrent neural network as a multi-objective optimization model for optimizing production power consumption, carbon emissions, and impurity content.

6. The aluminum electrolysis process parameter optimization method based on the multi-objective honey badger optimization algorithm according to claim 5 is characterized in that: The structure of the recurrent neural network is set as follows: the input layer contains 5 nodes, the hidden layer uses a node structure containing 20 LSTM units, and the output layer is a linear node; the LSTM unit uses sigmoid and tanh functions as activation functions, and the output layer uses a linear activation function to predict continuous values; the number of iterations is set to 200 times, the learning rate is set to 0.001, the Adam optimizer is used, and a batch size of 32 is used for training; to prevent overfitting, Dropout is used as a regularization method.

7. The aluminum electrolysis process parameter optimization method based on the multi-objective honey badger optimization algorithm according to claim 1 is characterized in that: The non-dominated sorting strategy is expressed as follows: when performing non-dominated sorting, the solution set is first classified according to the non-dominated relationship, and the non-dominated solutions are marked as the first-level Pareto optimal; then, the solutions dominated by the first level are classified to the next level until all solutions are classified, and each level of the Pareto optimal front contains solutions with different degrees of domination.

8. The aluminum electrolysis process parameter optimization method based on the multi-objective honey badger optimization algorithm according to claim 7 is characterized in that: The crowding distance strategy is expressed as follows: the crowding distance evaluates the distribution density of the solution by summing the distances between adjacent solutions; the larger the crowding distance, the more dispersed the distribution is and the greater the advantage of the solution is.

9. The aluminum electrolysis process parameter optimization method based on the multi-objective honey badger optimization algorithm according to claim 8, characterized in that: The external archive dynamic update strategy is expressed as follows: the archive stores the Pareto optimal solutions obtained by non-dominated sorting and crowding distance; the archive is dynamically updated during the optimization process to maintain representative and effective solutions; after each iteration, the offspring are compared with the existing individuals in the archive: if all offspring are dominated by any individual in the archive, then they will be discarded; if the new offspring are in the same dominance level as all individuals stored in the archive, the new offspring should be added to the archive; if any offspring in the archive dominates an individual, the dominated individual is deleted and the dominant offspring is added; if the offspring added to the archive exceeds the capacity of the archive, the crowding distance of all individuals is calculated; in order to enhance diversity and avoid local optimality, individuals are stored in descending order according to crowding distance until the archive is full, and any remaining individuals are discarded; from this archive, the individuals with the top 10% of crowding distance are selected as potential leader candidates; then a roulette wheel selection method is used to determine the final leader from these candidates, and the selection probability of each individual is proportional to its crowding distance, and the individual with a larger crowding distance has a greater chance of being selected.

10. The aluminum electrolysis process parameter optimization method based on the multi-objective honey badger optimization algorithm according to claim 9, characterized in that: The multi-objective honey badger optimization algorithm is used to perform iterative operations, and after the iteration is completed, an optimal solution set is output to achieve the optimization of aluminum electrolysis process parameters, including: Step 1: Initialize the population P and population size N; define the position of the i-th honey badger as x i ; Step 2: Initialize the optimization algorithm parameters, including: define β = 6, C = 2, and iter max =200; Step 3, sorting the population P using the non-dominated sorting strategy and the crowding distance strategy, including: first, calculating the target value of each individual in the population; then, non-dominated sorting the individuals in ascending order of their target values; finally, sorting the individuals in each non-dominated level in descending order of crowding distance; Step 4, the sorted population is used as the initial external archive and the iteration begins; Step 5, selecting the leader individual, including: sorting the individuals in the external archives by non-dominance, sorting the individuals in ascending order; finally, sorting the individuals in each non-dominance level by descending order of crowding distance; selecting the top 10% of the individuals in the crowding distance in the first Pareto level, and then using the roulette wheel selection method to determine the final leader individual; Step 6, update the adaptive reduction factor α, the formula is: Where t is the number of iterations; Step 7: Update the density factor I, where the density factor I of the i-th individual is i Defined as: Where S = (x i -x i+1 ) 2 ,d i =x prey -x i , where S represents the concentration intensity, di represents the position x of the prey and the i+1th honey badger i+1 The distance between prey Indicates the location of the best prey; r2 indicates a random value in the range [0,1]; Step 8, updating the positions of individuals in the population, including: determining the formula for generating new offspring based on the random value r, if r < 0.5, entering the exploration phase and updating the positions using the following equation: x new =x prey +F×β×I×x prey +F×r3×α×d i ×|cos(2πr4)×[1-cos(2πr5)]| Otherwise, proceed to the development phase and update the position using the following equation: x new =x prey +F×r7×α×d i Among them, x new Update the position of the individual; r3, r4, r5, r6, and r7 are all random values ​​in the range [0,1]; Step 9, dynamic updating of archives, includes: first, merging the generated new offspring and parent generations to generate a new population; then, using an external archive dynamic updating strategy to save the optimal solution set to the archive; Step 10, check whether the maximum number of iterations has been reached. If not, return to step 5 and continue iterating; otherwise, exit the iterative operation and use the individuals in the archive as the final Pareto optimal solution, that is, the optimal process parameters, so as to obtain the optimal solution set and output it to achieve the optimization of aluminum electrolysis process parameters.

Images