Method, device, equipment and medium for determining sintering ingredients

Through particle swarm algorithm and fuel batching relationship network model, combined with genetic algorithms and other optimization algorithms, the problem of insufficient accuracy and practicality of sintered ore batching solutions is solved, and higher reliability and accuracy of batching solutions are achieved, which is suitable for practical purposes. Business scenario.

CN118504428BActive Publication Date: 2024-11-05CERI DIGITAL TECHNOLOGY (BEIJING) CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410957372.7
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-07-17
Publication Date
2024-11-05
Estimated Expiration
2044-07-17

AI Technical Summary

Technical Problem

The accuracy and practicality of the existing sintered ore batching methods are not good, and cannot be effectively applied to actual business scenarios, resulting in insufficient reliability and accuracy of the batching solutions.

Method used

The particle swarm algorithm and pre-trained fuel batching relationship network model are used, combined with genetic algorithms and other optimization algorithms, and the sintered ore batching scheme is determined through iterative optimization processing. The optimization algorithm is based on warehousing costs, capital occupation costs and raw fuel consumption costs to ensure the batching scheme. accuracy and reliability.

Benefits of technology

Through the combination of multiple optimization algorithms, the reference information of the ingredients scheme is enriched, the reliability and accuracy of the sintered ore ingredients scheme is improved, it is suitable for actual business scenarios, and the comprehensive ingredients cost is reduced.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118504428B_ABST
    Figure CN118504428B_ABST
Patent Text Reader

Abstract

The present application discloses a method, device, equipment and medium for determining the proportion of sintered ore, and belongs to the field of computer technology. The method includes: initializing the iron-containing material ratio and flux ratio of the proportioning scheme of the sintered ore; based on the iron-containing material ratio and flux ratio, using a particle swarm algorithm to determine the particle population of the iron-containing material ratio and flux ratio; based on the particle population of the iron-containing material ratio and flux ratio, using a fuel proportioning relationship network model, obtaining the component constraint of the fuel proportion; based on the preset sintered ore target component constraint, the component constraint of the fuel proportion, and the particle population of the iron-containing material ratio and flux ratio, optimizing the fuel proportion to obtain the fuel proportion corresponding to the individual in each population; based on the objective function of the particle swarm algorithm, the particle population of the iron-containing material ratio and flux ratio, iteratively optimizing the proportioning scheme to obtain the target proportioning scheme, thereby obtaining the optimal sintered ore proportioning scheme.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the fields of metallurgical production technology and computer technology, and in particular to a method, device, equipment and medium for determining sintered ore batching. Background Art

[0002] Sintered ore is a block material made by mixing various powdered iron-containing raw materials with appropriate amounts of fuel and flux, adding appropriate amounts of water, mixing and pelletizing, and then subjecting the materials to a series of physical and chemical changes on sintering equipment, so that the ore powder particles are bonded into blocks.

[0003] At present, the method of sintering ore is mostly to select iron-containing raw materials and flux such as mixed ore, return ore, steelmaking dust, dolomite powder, limestone powder, etc. and flux based on experience, and select fuels such as coal and coke powder based on experience, adjust the raw material ratio through experience, and calculate the target composition of the sintered ore. Alternatively, a sintering secondary system or batching system is used to reversely calculate the raw materials and their ratios by inputting the target composition range of the main components of the sintered ore. Summary of the invention

[0004] The present application provides a method, device, equipment and medium for determining the batching of sintered ore, which can solve the problem of poor accuracy and practicality of the batching scheme of sintered ore. The technical scheme is as follows:

[0005] In a first aspect, a method for determining sintering ingredients is provided, the method comprising:

[0006] Initialize the iron-containing material ratio and flux ratio of the sintering ore batching plan;

[0007] Based on the iron-containing material ratio and the flux ratio, using a particle swarm algorithm to determine the particle population of the iron-containing material ratio and the flux ratio;

[0008] Based on the particle population of the iron-containing material ratio and the flux ratio, a pre-trained fuel proportioning relationship network model is used to obtain the component constraint conditions of the fuel proportion corresponding to the particle population of the iron-containing material ratio and the flux ratio;

[0009] Based on the preset target composition constraint condition, the composition constraint condition of the fuel proportion, and the particle population of the iron-containing material proportion and the flux proportion, the fuel proportion is iteratively optimized to obtain a fuel proportion set corresponding to the particle population of the iron-containing material proportion and the flux proportion;

[0010] Based on the objective function of the particle swarm algorithm, the particle population of the iron-containing material ratio and the flux ratio, and the raw material and fuel ratio relationship network model, the batching scheme is iteratively optimized to obtain a target batching scheme, wherein the objective function is determined based on the relationship between storage cost and the batching scheme, the relationship between capital occupation cost and the batching scheme, and the relationship between raw material and fuel consumption cost and the batching scheme.

[0011] In a possible implementation, the fuel ratio is iteratively optimized based on the preset target composition constraint, the composition constraint of the fuel ratio, and the particle population of the iron-containing material ratio and the flux ratio to obtain a set of fuel ratios corresponding to the particle population of the iron-containing material ratio and the flux ratio, including:

[0012] Initialize the fuel ratio to obtain a fuel ratio population;

[0013] Based on the preset target composition constraints of the sintered ore, the composition constraints corresponding to the fuel ratio output from the raw-fuel ratio relationship network, and the particle population of the iron-containing material ratio and the flux ratio, the fuel ratio set is iteratively optimized using a preset optimization algorithm to obtain a set of fuel ratios corresponding to the particle population of the iron-containing material ratio and the flux ratio.

[0014] In a possible implementation, the preset optimization algorithm includes a target optimization algorithm such as a genetic algorithm, a particle swarm algorithm, a fireworks algorithm, a marine predator algorithm, an ant colony algorithm, etc., and the preset target component constraint condition, the component constraint condition corresponding to the fuel ratio, and the particle population of the iron-containing material ratio and the flux ratio are used to iteratively optimize the fuel ratio set using the preset optimization algorithm to obtain a set of fuel ratios corresponding to the particle population of the iron-containing material ratio and the flux ratio, including:

[0015] Based on the fuel ratio set, determining an initial fuel ratio population;

[0016] Based on the objective function of the genetic algorithm, the preset target composition constraint, the composition constraint corresponding to the fuel proportion, the particle population of the iron-containing material proportion and the flux proportion, the fitness corresponding to each fuel proportion in the initial fuel proportion population is calculated;

[0017] According to each of the fitnesses, each fuel ratio of the fuel ratio population is subjected to evolutionary processing to determine the next generation fuel ratio population;

[0018] Based on the next generation fuel ratio population, the fuel ratio population is iteratively optimized to iteratively update the fitness corresponding to the fuel ratio population and perform evolutionary processing;

[0019] In response to satisfying a preset first convergence condition, obtaining a target fuel ratio based on a result of the iterative optimization process;

[0020] Based on the target fuel ratio, a set of fuel ratios corresponding to the particle populations of the iron-containing material ratio and the flux ratio is obtained.

[0021] In a possible implementation, the objective function of the particle swarm algorithm, the particle population of the iron-containing material ratio and the flux ratio, and the raw material and fuel ratio relationship network model are used to iteratively optimize the ratio scheme to obtain a target ratio scheme, including:

[0022] Based on the particle population of the iron-containing material ratio and the flux ratio and the raw material and fuel ratio relationship network model, a particle population of the ratio of the batching scheme is obtained;

[0023] Fusing the objective function of the particle swarm algorithm and the preset objective component constraint conditions to obtain a fused objective function;

[0024] Based on the objective function after fusion processing, determine the fitness of the particle population of the batching scheme;

[0025] In response to the preset second convergence condition not being met, based on the fitness of the particle population of the batching scheme, updating the speed and position of the individual particles in the particle population of the batching scheme;

[0026] Based on the result of the updating process, a particle population of the iron-containing material ratio and the flux ratio to be optimized next time corresponding to the particle swarm algorithm is obtained;

[0027] Based on the particle population of the iron-containing material ratio and the flux ratio optimized for the next time, return and iteratively execute, and use the pre-trained fuel proportioning relationship network model to obtain the step and subsequent steps of the component constraints of the fuel proportion corresponding to the particle population of the iron-containing material ratio and the flux ratio, until the preset second convergence condition is met to obtain the target proportioning scheme.

[0028] In a possible implementation, before obtaining the fuel proportion component constraint condition corresponding to the particle population of the iron-containing material proportion and the flux proportion based on the particle population of the iron-containing material proportion and the flux proportion by using the pre-trained fuel proportion relationship network model, the method further includes:

[0029] Acquire training sample data, wherein the training sample data includes sample iron-containing material ratio, sample flux ratio, sample fuel carbon content, sample fuel ash content, and sample sintered ore quality data;

[0030] Input the training sample data into the fuel proportioning relationship network model to be trained to obtain the component constraint conditions of the fuel proportion corresponding to the iron-containing material proportion and the flux proportion;

[0031] Based on the training sample data, the component constraints of the fuel ratio corresponding to the iron-containing material ratio and the flux ratio, the fuel ingredient relationship network model to be trained is updated and trained until the preset training termination condition is met, thereby obtaining a trained fuel ingredient relationship network model.

[0032] In a possible implementation, the component constraint conditions of the fuel ratio include the constraint relationship between the fuel ratio, the fuel carbon content, and the fuel ash content.

[0033] In a second aspect, a device for determining sintered ore batching is provided, the device comprising:

[0034] A first initialization unit is used to initialize the iron-containing material ratio and flux ratio of the sintering ore batching scheme;

[0035] A first determination unit is used to determine the particle population of the iron-containing material ratio and the flux ratio based on the iron-containing material ratio and the flux ratio by using a particle swarm algorithm;

[0036] A first obtaining unit is used to obtain the component constraint conditions of the fuel proportion corresponding to the particle population of the iron-containing material proportion and the flux proportion based on the particle population of the iron-containing material proportion and the flux proportion by using a pre-trained fuel proportion relationship network model;

[0037] A first optimization unit is used to iteratively optimize the fuel ratio based on a preset target composition constraint, a composition constraint of the fuel ratio, and a particle population of the iron-containing material ratio and the flux ratio, so as to obtain a set of fuel ratios corresponding to the particle population of the iron-containing material ratio and the flux ratio;

[0038] The second optimization unit is used to iteratively optimize the batching scheme based on the objective function of the particle swarm algorithm, the particle population of the iron-containing material ratio and the flux ratio, and the raw material and fuel ratio relationship network model to obtain a target batching scheme, wherein the objective function is determined based on the relationship between storage cost and the batching scheme, the relationship between capital occupation cost and the batching scheme, and the relationship between raw material and fuel consumption cost and the batching scheme.

[0039] In a third aspect, a computer-readable storage medium is provided, wherein at least one instruction is stored in the storage medium, and the at least one instruction is loaded and executed by a processor to implement the method of the above-mentioned aspect and any possible implementation manner.

[0040] In a fourth aspect, an electronic device is provided, including:

[0041] at least one processor; and

[0042] a memory communicatively connected to the at least one processor; wherein,

[0043] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method of any possible implementation manner and the aspects described above.

[0044] According to a fifth aspect, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the above-mentioned aspects and any possible implementation method.

[0045] The beneficial effects of the technical solution provided by this application include at least:

[0046] It can be seen from the above technical scheme that the embodiment of the present application can initialize the iron-containing material ratio and the flux ratio of the batching scheme of the sintered ore, and then based on the iron-containing material ratio and the flux ratio, the particle population of the iron-containing material ratio and the flux ratio can be determined by using a particle swarm algorithm, and based on the particle population of the iron-containing material ratio and the flux ratio, the component constraints of the fuel ratio corresponding to the particle population of the iron-containing material ratio and the flux ratio are obtained by using a pre-trained fuel batching relationship network model, and based on the preset target component constraints, the component constraints of the fuel ratio, and the particle population of the iron-containing material ratio and the flux ratio, the fuel ratio is iteratively optimized to obtain a set of fuel ratios corresponding to the particle population of the iron-containing material ratio and the flux ratio, and based on the objective function of the particle swarm algorithm, the particle population of the iron-containing material ratio and the flux ratio, and the original fuel ratio relationship network model, the batching scheme is iteratively optimized. To obtain a target batching scheme, wherein the objective function is determined based on the relationship between storage cost and the batching scheme, the relationship between capital occupation cost and the batching scheme, and the relationship between raw fuel consumption cost and the batching scheme. Since the relationship between the input iron-containing material ratio and flux ratio particle population and the fuel ratio can be analyzed by utilizing the fuel batching relationship network model, the corresponding fuel ratio component constraint conditions can be obtained, and then based on the target component constraint conditions, the fuel ratio component constraint conditions, the iron-containing material ratio and the flux ratio particle population, the optimal fuel ratio set is determined. Finally, based on the iron-containing material ratio and the flux ratio particle population and the optimal fuel ratio set, the batching scheme is optimized to obtain the target batching scheme, which can enrich the reference information used to determine the batching scheme, combine the relationship model with multiple optimization algorithms, and optimize the algorithm for determining the sintered ore batching scheme, thereby ensuring the reliability and accuracy of the target batching scheme of the sintered ore.

[0047] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0049] Figure 1 It is a schematic flow chart of a method for determining sintered ore ingredients provided in one embodiment of the present application;

[0050] Figure 2 is a schematic flow chart of a method for determining sintered ore ingredients provided in another embodiment of the present application;

[0051] Figure 3 is a structural block diagram of a device for determining sintered ore batching provided in yet another embodiment of the present application;

[0052] Figure 4 It is a block diagram of an electronic device used to implement the method for determining the sintered ore ingredients in the embodiment of the present application. DETAILED DESCRIPTION

[0053] The following is a description of exemplary embodiments of the present application in conjunction with the accompanying drawings, including various details of the embodiments of the present application to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present application. Similarly, for the sake of clarity and conciseness, the description of well-known functions and structures is omitted in the following description.

[0054] Obviously, the described embodiments are only part of the embodiments of the present application, but not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.

[0055] It should be noted that the terminal devices involved in the embodiments of the present application may include but are not limited to mobile phones, personal digital assistants (PDAs), wireless handheld devices, tablet computers and other smart devices; display devices may include but are not limited to personal computers, televisions and other devices with display functions.

[0056] In addition, the term "and / or" in this article is only a description of the association relationship between the associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0057] At present, in the sintering ore batching method of the related technology, the comprehensiveness of the influencing factors involved in the sintering batching algorithm model is not good, and the determined sintering batching scheme cannot be well applied to the actual business scenario, and thus cannot better guarantee the reliability and accuracy of the sintering batching scheme.

[0058] Therefore, there is an urgent need to provide a method for determining the sintering proportioning, which can optimize the algorithm for determining the sintering proportioning and ensure the reliability and accuracy of the sintering proportioning scheme.

[0059] Please refer to Figure 1 , which shows a schematic flow chart of a method for determining sintered ore ingredients provided by an embodiment of the present application. The method for determining sintered ore ingredients may specifically include:

[0060] Step 101: Initialize the iron-containing material ratio and flux ratio of the sintering ore batching scheme.

[0061] Step 102: Based on the iron-containing material ratio and the flux ratio, a particle swarm algorithm is used to determine the particle population of the iron-containing material ratio and the flux ratio.

[0062] Step 103: Based on the particle populations of the iron-containing material ratio and the flux ratio, a pre-trained fuel proportioning relationship network model is used to obtain the component constraints of the fuel proportion corresponding to the particle populations of the iron-containing material ratio and the flux ratio.

[0063] Step 104, based on the preset target composition constraints, the composition constraints of the fuel ratio, and the particle populations of the iron-containing material ratio and the flux ratio, the fuel ratio is iteratively optimized to obtain a set of fuel ratios corresponding to the particle populations of the iron-containing material ratio and the flux ratio.

[0064] Step 105, based on the objective function of the particle swarm algorithm, the particle population of the iron-containing material ratio and the flux ratio, and the set of the fuel ratio, the batching scheme is iteratively optimized to obtain a target batching scheme, wherein the objective function is determined based on the relationship between storage cost and the batching scheme, the relationship between capital occupation cost and the batching scheme, and the relationship between raw fuel consumption cost and the batching scheme.

[0065] It should be noted that the proportion of the sintering ore batching scheme may include the proportion of iron-containing materials, the proportion of flux, and the proportion of fuel. The iron-containing materials may include mixed ore, return ore, concentrate, domestic processed powder ore, steelmaking dust, etc. The flux may include dolomite powder, limestone powder, etc. The fuel may include coal, coke powder, etc. The proportion of the sintering ore batching scheme may be determined by the proportion of the historical batching scheme and the proportion of the randomly generated batching scheme.

[0066] It should be noted that the batching scheme may be the batching scheme information of the sintered ore to be optimized. Here, the batching scheme may also include but is not limited to the basic information of the sintered ore batching scheme and the proportion of the sintered ore batching scheme. The basic information of the sintered ore batching scheme may include but is not limited to the type of raw materials, component information, burn loss, inventory information, raw material price, unit inventory maintenance cost, etc.

[0067] It should be noted that when constructing a particle swarm algorithm, basic information such as raw material type, component information, burnout, inventory information, raw material price, unit inventory maintenance cost, etc. can be obtained. Specifically, the quality data of each raw material and fuel corresponding to the batching scheme information can be obtained from the inspection and testing system. The quality data of raw materials and fuels include information such as the composition, moisture, and burnout of raw materials and fuels. The inventory data of raw materials and fuels can be obtained from the production information management system. The raw material price data, inventory maintenance cost data, and capital interest rate information can be obtained from the resource management system.

[0068] It should be noted that the target batching scheme may include basic information, target ratio, and corresponding cost information. The target ratio of the target batching scheme may include a target iron-containing material ratio, a target flux ratio, and a target fuel ratio. The target iron-containing material ratio may be the ratio of each iron-containing raw material.

[0069] It should be noted that part or all of the execution subject of steps 101 to 105 may be an application located in the local terminal, or may also be a functional unit such as a plug-in or software development kit (SDK) set in the application located in the local terminal, or may also be a processing engine located in a network-side server, or may also be a distributed system located on the network side, for example, a processing engine or distributed system in a sintered ore batching processing platform on the network side, etc. This embodiment does not specifically limit this.

[0070] It is understandable that the application may be a local program (nativeApp) installed on the local terminal, or may also be a webpage program (webApp) of a browser on the local terminal, which is not limited in this embodiment.

[0071] In this way, the relationship between the input iron-containing material ratio and flux ratio particle population and the fuel ratio can be analyzed by using the fuel-bearing relationship network model to obtain the corresponding fuel ratio component constraints, and then the optimal fuel ratio set can be determined based on the target component constraints, the fuel ratio component constraints, and the iron-containing material ratio and flux ratio particle populations. Finally, based on the iron-containing material ratio and flux ratio particle population and the optimal fuel ratio set, the batching scheme is optimized to obtain the target batching scheme, which can enrich the reference information used to determine the batching scheme, combine the relationship model with multiple optimization algorithms, and optimize the algorithm for determining the sintered ore batching scheme, thereby ensuring the reliability and accuracy of the target batching scheme for the sintered ore.

[0072] Moreover, by combining the various cost information involved in actual business scenarios to construct a combined optimization algorithm, it can be ensured that the determined target batching scheme of sintered ore can be better applied to actual business scenarios, thereby ensuring the reliability and practicality of the target batching scheme of sintered ore.

[0073] Optionally, in a possible implementation of this embodiment, in step 104, first, the fuel ratio may be initialized to obtain an initialized fuel ratio population. Secondly, based on preset target component constraints, component constraints corresponding to the fuel ratio, and particle populations of the iron-containing material ratio and flux ratio, the fuel ratio population is iteratively optimized using a preset optimization algorithm to obtain a fuel ratio set corresponding to the particle population of the iron-containing material ratio and flux ratio.

[0074] In this implementation, the preset optimization algorithm may include, but is not limited to, genetic algorithm, fireworks algorithm, simulated annealing algorithm, ant colony algorithm, marine predator algorithm, machine learning algorithm and other target optimization algorithms.

[0075] In a specific implementation process of this implementation method, the preset optimization algorithm can be a genetic algorithm. Further, first, based on the objective function of the genetic algorithm, the preset target sintered ore composition constraint, the composition constraint corresponding to the fuel ratio, and the particle population of the iron-containing material ratio and the flux ratio, the fitness corresponding to each fuel ratio in the fuel ratio population is calculated. Secondly, according to each fitness, each fuel ratio of the fuel ratio population is subjected to evolutionary processing to determine the next generation of fuel ratio population. Thirdly, based on the next generation of fuel ratio population, the fuel ratio population is subjected to iterative optimization processing to iteratively update the fitness corresponding to the fuel ratio population and to perform evolutionary processing. Thirdly, in response to satisfying the preset first convergence condition, the target fuel ratio is obtained based on the result of the iterative optimization processing. Thirdly, based on the target fuel ratio, a fuel ratio set corresponding to the particle population of the iron-containing material ratio and the flux ratio is obtained.

[0076] In this specific implementation process, the objective function of the genetic algorithm can be determined based on the relationship between storage cost and batching scheme, the relationship between capital occupation cost and batching scheme, and the relationship between raw fuel consumption cost and batching scheme.

[0077] In this specific implementation process, the preset first convergence condition may include the number of iterations reaching a preset threshold number.

[0078] In this specific implementation process, the fuel ratio set may include the optimal fuel ratio corresponding to each individual particle in the particle population of iron-containing material ratio and flux ratio obtained by genetic algorithm, that is, the optimal fuel ratio corresponding to each individual particle of iron-containing material ratio and flux ratio.

[0079] In a specific implementation process of this implementation method, the fitness corresponding to each fuel ratio in the fuel ratio population can be calculated based on the objective function of the genetic algorithm, the preset target sinter composition constraint, the composition constraint corresponding to the fuel ratio, and each individual particle in the particle population of the iron-containing material ratio and the flux ratio. Secondly, according to each fitness, each fuel ratio of the fuel ratio population is subjected to evolutionary processing to determine the next generation of fuel ratio population. Thirdly, based on the next generation of fuel ratio population, the fuel ratio population is subjected to iterative optimization processing to iteratively update the fitness corresponding to the fuel ratio population and to perform evolutionary processing. Thirdly, in response to satisfying the preset first convergence condition, the target fuel ratio corresponding to each individual particle in the particle population of the iron-containing material ratio and the flux ratio is obtained respectively based on the result of the iterative optimization processing. Finally, based on the target fuel ratio corresponding to each individual particle in the particle population of the iron-containing material ratio and the flux ratio, the fuel ratio set corresponding to the particle population of the iron-containing material ratio and the flux ratio can be obtained.

[0080] Optionally, in a possible implementation of the present embodiment, in step 105, first, the objective function of the particle swarm algorithm and the preset target component constraint condition may be fused to obtain the fused objective function. Secondly, based on the fused objective function, the objective function of the particle swarm algorithm, the particle population of the iron-containing material ratio and the flux ratio, and the set of the fuel ratio, the fitness of the particle population of the iron-containing material ratio and the flux ratio is determined. Again, in response to not meeting the preset second convergence condition, based on the fitness of the particle population of the iron-containing material ratio and the flux ratio, the speed and position of the individual particles in the particle population of the iron-containing material ratio and the flux ratio are updated. Again, based on the result of the update process, the particle population of the iron-containing material ratio and the flux ratio corresponding to the particle swarm algorithm for the next optimization is obtained. Again, based on the particle population of the iron-containing material ratio and the flux ratio optimized for the next time, return and iterate, and use the pre-trained fuel formulation relationship network model to obtain the step and subsequent steps of the component constraints of the fuel ratio corresponding to the particle population of the iron-containing material ratio and the flux ratio, until the preset second convergence condition is met to obtain the target formulation scheme.

[0081] In this implementation, the objective function of the particle swarm algorithm can be determined based on the relationship between storage cost and batching scheme, the relationship between capital occupation cost and batching scheme, and the relationship between raw fuel consumption cost and batching scheme.

[0082] In this implementation, the preset second convergence condition may include that the number of iterations reaches a preset number threshold.

[0083] Here, the objective function and the objective component constraints can be integrated to simplify the processing of the constraints, facilitate the construction of the particle swarm algorithm, simplify the construction process of the heuristic algorithm, and be independent of the architecture of the specific optimization algorithm, making it more versatile.

[0084] In a specific implementation process of this implementation method, first, the fitness of the particle population of the iron-containing material ratio and the flux ratio can be determined based on the objective function of the particle swarm algorithm. Again, in response to not meeting the preset second convergence condition, the speed and position of the individual particles in the particle population of the iron-containing material ratio and the flux ratio can be updated based on the fitness of the particle population of the iron-containing material ratio and the flux ratio. Again, based on the result of the update process, the particle population of the iron-containing material ratio and the flux ratio corresponding to the next optimization of the particle swarm algorithm is obtained. Again, based on the particle population of the iron-containing material ratio and the flux ratio optimized next time, return and iterate to execute, using the pre-trained fuel batching relationship network model, obtain the step of obtaining the component constraint condition of the fuel batching corresponding to the particle population of the iron-containing material ratio and the flux ratio and the subsequent steps, so as to iteratively optimize the batching scheme until the preset second convergence condition is met to obtain the target batching scheme.

[0085] In another specific implementation process of the implementation method, first, the basic data of the batching scheme can be obtained, and the basic data can include the unit mass of sintered ore, the sulfur content of each iron-containing material and flux, the sulfur content of each fuel, the ash content of each fuel, the carbon content of each fuel, the unit cost corresponding to the iron-containing material and flux, the burnout data corresponding to each iron-containing material and flux, the burnout data of each fuel, the planned output of the current batch of sintered ore, the inventory corresponding to each iron-containing material and flux, the inventory of each fuel, the unit inventory maintenance cost, the unit price of each raw material of the sintered ore, and the capital interest rate. Secondly, based on the unit mass of sintered ore, the planned output of the current batch of sintered ore, the unit cost corresponding to each iron-containing material and flux, the burnout data of each iron-containing material and flux, the unit cost corresponding to each fuel, and the burnout data of each fuel, the relationship between the raw material consumption cost and the dry basis ratio of the iron-containing material and flux, and the dry basis ratio of the fuel, that is, the raw material consumption cost function, can be constructed. Thirdly, based on the unit mass of sintered ore, the burnout data of each iron-containing material and flux, the burnout data of each fuel, the inventory of each iron-containing material and flux, the inventory of each fuel, the unit inventory maintenance cost, the planned output of the current batch of sintered ore, and the unit price of each raw material, the relationship between the storage cost and the dry basis ratio of iron-containing materials and fluxes, and the dry basis ratio of fuels, i.e., the storage cost function, can be constructed. Thirdly, based on the unit mass of sintered ore, the planned output of the current batch of sintered ore, the unit cost corresponding to each iron-containing material and flux, the burnout data of each iron-containing material and flux, the unit cost corresponding to each fuel, the burnout data of each fuel, the inventory of each iron-containing material and flux, the inventory of each fuel, and the capital interest rate, the relationship between the capital occupation cost and the dry basis ratio of iron-containing materials and fluxes, and the dry basis ratio of fuels, i.e., the capital occupation cost function, can be constructed. Thirdly, based on the relationship between the cost of raw fuel consumption and the batching scheme, the relationship between the storage cost and the batching scheme, and the relationship between the capital occupation cost and the batching scheme, a comprehensive objective function, i.e., the objective function of the particle swarm algorithm, is obtained. Thirdly, based on the upper and lower limits of the target composition of the sintered ore, the unit mass of the sintered ore, the ferrous oxide content of each raw material, the total number of quality inspection items with component control requirements for the sintered ore, the burnout data of each raw material, the chemical composition of the quality inspection items of each raw material of the sintered ore, the burnout data of each raw material of the sintered ore, and the corresponding dry basis ratio of each raw material of the sintered ore, the preset target composition constraints can be determined.

[0086] It should be noted that the specific implementation process provided in this implementation can be combined with the various specific implementation processes provided in the aforementioned implementation to implement the method for determining the sintered ore batching of this embodiment. For a detailed description, please refer to the relevant content in the aforementioned implementation, which will not be repeated here.

[0087] Optionally, in a possible implementation of this embodiment, in step 103, first, the particle population of the determined iron-containing material ratio and flux ratio can be input into a pre-trained fuel proportion relationship network model, and the component constraint conditions of the corresponding fuel proportion can be output.

[0088] In this implementation, the pre-trained fuel ingredient relationship network model may be a model based on a BP neural network (Back Propagation Neural Network).

[0089] Optionally, in a possible implementation of this embodiment, before step 103, first, training sample data may also be obtained. Secondly, the training sample data is input into the fuel proportioning relationship network model to be trained to obtain the component constraints of the fuel proportion corresponding to the iron-containing material proportion and the flux proportion. Thirdly, based on the training sample data and the component constraints of the fuel proportion corresponding to the iron-containing material proportion and the flux proportion, the fuel proportioning relationship network model to be trained is updated and trained until the preset training termination condition is met, thereby obtaining a trained fuel proportioning relationship network model.

[0090] In this implementation, the training sample data includes sample iron-containing material ratio, sample flux ratio, sample fuel carbon content, sample fuel ash content, sample sintered ore quality data, sample iron-containing material ferrous oxide (FeO) and sulfur (S) content, sample flux magnesium oxide and calcium oxide content, sample iron-containing material burnout, sample flux burnout, sample fuel carbon content, sample sintered ore ferrous oxide content, etc.

[0091] Optionally, in a possible implementation of this embodiment, the component constraint conditions of the fuel ratio include the constraint relationship between the fuel ratio, the fuel carbon content, and the fuel ash content.

[0092] It should be noted that the specific implementation process provided in this implementation can be combined with the various specific implementation processes provided in the aforementioned implementation to implement the method for determining the sintered ore batching of this embodiment. For a detailed description, please refer to the relevant content in the aforementioned implementation, which will not be repeated here.

[0093] In order to better understand the method of the embodiment of the present application, the method of the embodiment of the present application is described below in conjunction with the accompanying drawings and specific application scenarios.

[0094] Figure 2 FIG. 1 is a flow chart of a method for determining sintering ingredients provided by another embodiment of the present application. Figure 2 shown.

[0095] Step 201: Initialize the iron-containing material ratio and flux ratio of the sintering ore batching scheme.

[0096] In this embodiment, the ratio of the initialized sintering ore batching scheme may include the ratio of each iron material and flux, and the ratio of fuel, that is, the dry basis ratio of each iron material and flux of the sintering ore, and the dry basis ratio of each fuel.

[0097] For example, the raw materials may include iron-containing materials, flux, etc. The iron-containing materials may include mixed ore, return ore, concentrate, domestic processed powder ore, steelmaking dust, etc. The flux may include dolomite powder, limestone powder, etc. The fuel may include coal, coke powder, etc.

[0098] In this embodiment, the initialized sintering ore batching scheme may be the batching scheme information of the sintering ore to be optimized. The batching scheme may also include but is not limited to the basic information of the sintering ore batching scheme and the proportion of the sintering ore batching scheme. The basic information of the sintering ore batching scheme may include but is not limited to the type of raw materials, component information, burn loss, inventory information, raw material price, unit inventory maintenance cost, etc. The proportion of the sintering ore batching scheme may include

[0099] In this embodiment, raw fuel quality data, including raw material composition, moisture, and burn loss, is collected by connecting to the inspection and testing system. Raw fuel inventory data is collected by connecting to the MES system, and raw material price data is collected by connecting to the ERP system, and the current inventory maintenance cost coefficient and capital utilization coefficient are maintained according to actual conditions.

[0100] In addition, the batching personnel can also pre-configure the target sinter target composition control constraints, namely, the upper and lower limits of the target chemical composition of total iron (TFe), silicon dioxide (SiO2), calcium oxide (CaO), magnesium oxide (MgO), aluminum oxide (Al2O3), titanium (Ti), zinc (Zn), potassium oxide (K2O), sodium oxide (NaO), and tin (Sn), as well as restrictions on harmful elements such as sulfur (S), phosphorus (P), fluorine (F), and chlorine (Cl), set the target sinter FeO content, set the desulfurization rate, etc.

[0101] Step 202: Based on the iron-containing material ratio and the flux ratio, a particle swarm algorithm is used to determine the particle population of the iron-containing material ratio and the flux ratio.

[0102] In this embodiment, the particle swarm algorithm may be a variable coefficient particle swarm algorithm with a compression factor.

[0103] In this embodiment, the objective function of the particle swarm algorithm is determined based on the relationship between the inventory cost and the batching scheme information, and the relationship between the raw fuel consumption cost and the batching scheme information.

[0104] Preferably, before using the particle swarm algorithm to determine the particle population of the iron-containing material ratio and the flux ratio, the objective function of the particle swarm algorithm and the preset target component constraint conditions can be determined to construct the particle swarm algorithm.

[0105] Here, first, the basic data of the batching scheme can be obtained, and the basic data may include the unit mass of sintered ore, the sulfur content of each iron-containing material and flux, the sulfur content of each fuel, the ash content of each fuel, the carbon content of each fuel, the unit cost corresponding to the iron-containing material and flux, the burnout data corresponding to each iron-containing material and flux, the burnout data of each fuel, the planned output of the current batch of sintered ore, the inventory corresponding to each iron-containing material and flux, the inventory of each fuel, the unit inventory maintenance cost, the unit price of each iron-containing material, flux, and fuel of the sintered ore, and the capital interest rate. Secondly, based on the unit mass of sintered ore, the planned output of the current batch of sintered ore, the unit cost corresponding to each iron-containing material and flux, the burnout data of each iron-containing material and flux, the unit cost corresponding to each fuel, and the burnout data of each fuel, the relationship between the raw material consumption cost and the batching scheme can be constructed, that is, the relationship between the raw material consumption cost and the dry basis ratio of the iron-containing material and flux, and the dry basis ratio of the fuel can be constructed.

[0106] Here, the relationship between the raw material consumption cost and the batching scheme information can be expressed as a raw material consumption cost function, as shown in the following formula (1):

[0107] (1)

[0108] in, can be the raw material consumption cost function, It can be the unit mass of sintered ore, The planned output of the current batch of sintered ore can be express The unit cost of each type of iron-containing material and flux is: can be the burning loss data of the i-th iron-containing material and flux, Can be expressed The unit cost of each fuel is represents the burning data of the i-th fuel, represents the dry basis ratio of the ith iron-containing material and flux, Represents the dry basis ratio of the ith fuel.

[0109] Thirdly, based on the unit mass of sintered ore, the burnout data of each iron-containing material and flux, the burnout data of each fuel, the inventory of each iron-containing material and flux, the inventory of each fuel, the unit inventory maintenance cost, the planned output of the current batch of sintered ore, and the unit price of each raw material, the relationship between storage cost and the batching scheme can be constructed, that is, the relationship between storage cost and the dry basis ratio of iron-containing material and flux, and the dry basis ratio of fuel can be constructed.

[0110] Here, the relationship between storage cost and batching scheme information can be expressed as a storage cost function, as shown in the following formula (2):

[0111] (2)

[0112] in, can be the storage cost function, Cost can be maintained for each unit of inventory, It can be the unit mass of sintered ore, The planned output of the current batch of sintered ore can be represents the inventory of the ith type of iron-containing material and flux, It can be the burning loss data of the i-th type of iron-containing material and flux, can be the inventory of the i-th fuel, represents the burning of the i-th fuel, represents the dry basis ratio of the ith iron-containing material and flux, represents the dry basis ratio of the i-th fuel, is the Relu function, that is .

[0113] Thirdly, based on the unit mass of sintered ore, the planned output of the current batch of sintered ore, the unit cost of each iron-containing material and flux, the burn-off data of each iron-containing material and flux, the unit cost of each fuel, the burn-off data of each fuel, the inventory of each iron-containing material and flux, the inventory of each fuel, and the capital interest rate, the relationship between the capital occupation cost and the batching plan information can be constructed, that is, the relationship between the capital occupation cost and the dry basis ratio of iron-containing materials and flux, and the dry basis ratio of fuel can be constructed.

[0114] Here, the relationship between the capital occupation cost and the batching scheme information can be expressed as a capital occupation cost function, as shown in the following formula (3):

[0115] (3)

[0116] in, It can be the capital occupation cost function, It can be the funding rate, It can be the unit mass of sintered ore, The planned output of the current batch of sintered ore can be express The unit cost of each type of iron-containing material and flux is: It can be the burning loss data of the i-th type of iron-containing material and flux, Can be expressed The unit cost of each fuel is represents the burning of the i-th fuel, represents the inventory of the ith type of iron-containing material and flux, can be the inventory of the i-th fuel, represents the dry basis ratio of the ith iron-containing material and flux, represents the dry basis ratio of the i-th fuel, is the Relu function, that is .

[0117] Thirdly, based on the relationship between the raw fuel consumption cost and the batching scheme, the relationship between the storage cost and the batching scheme, and the relationship between the capital occupation cost and the batching scheme, a comprehensive objective function, namely the objective function of the particle swarm algorithm, is obtained.

[0118] Here, the comprehensive objective function It can be expressed as the following formula (4):

[0119] (4)

[0120] Thirdly, the target component constraint conditions can be determined based on the upper and lower limits of the target component of the sintered ore, the unit mass of the sintered ore, the ferrous oxide content of each raw material, the total number of quality inspection items with component control requirements for the sintered ore, the burnout data of each raw material, the chemical composition of the quality inspection items of each raw material of the sintered ore, the burnout data of each raw material of the sintered ore, and the dry basis ratio of each raw material of the sintered ore. Then, the comprehensive objective function and the target component constraint conditions can be fused to obtain the objective function of the fused particle swarm algorithm. Thirdly, based on the objective function and target component constraint conditions of the particle swarm algorithm, a particle swarm algorithm for optimizing the batching scheme of the sintered ore is constructed, or, based on the objective function of the fused particle swarm algorithm, a particle swarm algorithm for optimizing the batching scheme of the sintered ore can be constructed.

[0121] Here, the target composition constraint condition may be a target chemical composition constraint condition of the target sintered ore, and the target composition constraint condition may be expressed as the following formula (5):

[0122] ;

[0123] 100% (5)

[0124] in, Can represent any , can be the lower limit of the target chemical composition of the jth sinter, can be the upper limit of the target chemical composition of the j-th sintered ore, M can be the unit mass of the sintered ore, It can be the number of types of sintered ore raw materials, The total number of quality inspection items for sintered ore with composition control requirements. is the chemical composition of the jth quality inspection item of the i-th sintered ore raw material, can be the burning loss data of the i-th sintered ore raw material, It can be the dry basis ratio corresponding to the i-th sintered ore raw material.

[0125] It is understandable that control constraints on the target chemical composition of the target sintered ore can be set in advance. For example, the upper and lower limits of the target chemical composition of total iron (TFe), silicon dioxide (SiO2), calcium oxide (CaO), magnesium oxide (MgO), aluminum oxide (Al2O3), titanium (Ti), zinc (Zn), potassium oxide (K2O), sodium oxide (NaO), and tin (Sn) can be set in advance, as well as restrictions on harmful elements such as sulfur (S), phosphorus (P), fluorine (F), and chlorine (Cl).

[0126] In addition, the target ferrous oxide (FeO) content of the sintered ore can be pre-set. This is because the desulfurization process and the reaction chemical formula of iron oxide in the sintering production process are: ; Therefore, each time 144 mass is restored The mass will be reduced by 16, that is, the mass of the reduced FeO will be reduced by 1 / 9. The unit mass M of the finished sintered ore is as shown in the following formula (6):

[0127] (6)

[0128] in, It can be the burning loss data of the i-th type of iron-containing material and flux, represents the burning of the i-th fuel, It can be the S content of the i-th iron-containing material or flux, can be the S content of the i-th fuel, The dry basis ratio of the i-th iron-containing material and flux is: The dry basis ratio corresponding to the i-th fuel can be: is the FeO content of the i-th raw material, is the target FeO content of the finished sintered ore, n is the number of raw material types of the sintered ore, It can be the desulfurization rate.

[0129] Here, the comprehensive objective function and the objective component constraints are fused to obtain the objective function of the fused particle swarm algorithm: It can be expressed as the following formula (7):

[0130] (7)

[0131] in, We can take a constant that is 2 orders of magnitude greater than the normal cost, can be the lower limit of the jth target chemical composition, can be the upper limit of the target chemical composition of the jth species, It can be the funding rate, The planned output of the current batch of sintered ore can be M can be the unit inventory maintenance cost, M can be the quality data of the sintered ore, that is, the unit mass of the finished sintered ore, It can be the number of raw material types, The total number of quality inspection items for sintered ore with composition control requirements. express The unit cost of each type of iron-containing material and flux is: The unit cost of each fuel is represents the inventory of the ith type of iron-containing material and flux, can be the inventory of the i-th fuel, It can be the burning loss data of the i-th type of iron-containing material and flux, It can be the dry basis ratio of the i-th iron-containing material and flux, can be the dry basis ratio of the i-th fuel, can be the burning data of the i-th fuel, The dry basis ratio corresponding to the i-th fuel can be: is the FeO content of the i-th raw material, It is the FeO content of the finished sintered ore.

[0132] The unit mass M of the finished sintered ore after fusion can be expressed as follows:

[0133] (8)

[0134] in, It can be the burning loss data of the i-th type of iron-containing material and flux, represents the burning of the i-th fuel, It can be the S content of the i-th iron-containing material or flux, can be the S content of the i-th fuel, It can be the dry basis ratio of the i-th iron-containing material and flux, The dry basis ratio corresponding to the i-th fuel can be: can be the FeO content of the i-th raw material, can be the target FeO content of the finished sintered ore, n can be the number of raw material types of the sintered ore, It can be the desulfurization rate.

[0135] It can be understood that both conditions in the target composition constraint conditions shown in formula (5) can be used for integration with the objective function, and the second condition in the target composition constraint conditions shown in formula (5) can be used for integration with the unit mass M of the finished sintered ore.

[0136] Step 203: input the particle population containing the iron material ratio and the flux ratio into the pre-trained fuel ratio relationship network model to obtain the component constraint conditions of the fuel ratio corresponding to the particle population containing the iron material ratio and the flux ratio.

[0137] In an embodiment, the pre-trained fuel ingredient relationship network model may be a model based on a BP neural network (Back Propagation Neural Network).

[0138] In an embodiment, first, training sample data may also be obtained. Secondly, the training sample data is input into the fuel ingredient relationship network model to be trained to obtain the component constraints of the fuel ratio corresponding to the iron-containing material ratio and the flux ratio. Thirdly, based on the training sample data and the component constraints of the fuel ratio corresponding to the iron-containing material ratio and the flux ratio, the fuel ingredient relationship network model to be trained is updated and trained until the preset training termination condition is met, thereby obtaining a trained fuel ingredient relationship network model.

[0139] Here, the training sample data includes historical iron-containing material ratio, flux ratio, fuel carbon content, fuel ash content, sinter quality data, FeO and sulfur content of iron-containing materials, magnesium oxide and calcium oxide content of flux, iron-containing material burnout, flux burnout, fuel carbon content, ferrous oxide content of sinter, etc.

[0140] For example, nearly 200 sets of sintering production data can be selected as training sample data to train the BP network and obtain the output y=g( ).

[0141] In the forward propagation process of the BP network, the input of the fuel ingredient relationship network model to be trained is the iron material ratio, FeO and S content of the iron material, flux ratio, MgO and CaO content of the flux, iron material burnout, flux burnout, fuel C content, fuel ash content, sintered ore FeO content and other data. As shown in formula (9):

[0142] x M ⃗ =[ ∑ i∈ I ore x A,i , ∑ i∈ I ore x A,i * 1- b A,i * a i,FeO , ∑ i∈ I ore x A,i * 1- b A,i * a i,S , ∑ i∈ I agent x A,i , ∑ i∈ I agent x A,i * 1- b A,i * a i,FeO , ∑ i∈ I agent x A,i * 1- b A,i * a i,S , ∑ i∈ I ore x A,i * 1- b A,i , ∑ i∈ I agent x A,i * 1- b A,i , a FeO ] (9)

[0143] in, for Iron-containing material corner mark collection, for Medium flux corner mark collection, represents the dry basis ratio of the ith iron-containing material and flux, It can be the burning loss data of the i-th type of iron-containing material and flux, It can be the FeO content of the i-th iron-containing material or flux, Indicates the S content of the i-th iron-containing material and flux, It is the FeO content of the finished sintered ore.

[0144] The output y of the fuel ingredient relationship network model to be trained is shown in formula (10):

[0145] y=[ ∑ i=1 n R x R,i , a C , a Ad ] (10)

[0146] in, represents the dry basis ratio of the i-th fuel, is the carbon content of the fuel, is the ash content of the fuel.

[0147] In addition, it can be understood that, through the heat balance relationship, the relationship between the fuel ratio and the iron-containing material and flux ratio is as shown in formula (11):

[0148] (11)

[0149] in, For the fuel ratio, It can be the carbon content of coal powder, is the fuel heat coefficient, which is related to the carbon content of the fuel. X and Y are the proportions of iron-containing material and flux, respectively. is the heat coefficient of iron-containing material kJ / kg, which is related to the FeO and S content of the iron-containing material. is the flux heat coefficient kJ / kg, which is related to the MgO and CaO content of the flux. is the thermal coefficient of sintered ore FeO, ,in, For ore burn loss data, is the flux burnout data, is the ash content of the fuel, Other heat not included in the above items can be considered as When the ratio of iron-containing materials and flux and the FeO of sintered ore are given, the fuel ratio can be calculated. Based on this, the fuel ratio relationship network model based on the BP network model can be constructed to identify the relationship between the fuel ratio and the ratio of iron-containing materials and flux.

[0150] In this embodiment, by collecting the iron-containing material ratio, FeO and S content of the iron-containing material, flux ratio, MgO and CaO content of the flux, iron-containing material burnout, flux burnout, and FeO content of the sintered ore in sintering production as network input, collecting fuel ratio and carbon content, ash content constraints as network output, training the BP fuel ingredient relationship network model, verifying it with a test set, and repeatedly tuning it to form a fuel and raw material ratio relationship with accuracy that meets the requirements, and updating the training to obtain a trained fuel ingredient relationship network model.

[0151] Step 204: Initialize the fuel ratio to obtain an initialized fuel ratio population.

[0152] Step 205: Based on the preset target composition constraints, the composition constraints corresponding to the fuel ratio, and the particle populations of the iron-containing material ratio and the flux ratio, the fuel ratio population is iteratively optimized using a genetic algorithm to obtain a fuel ratio set corresponding to the particle populations of the iron-containing material ratio and the flux ratio.

[0153] In this embodiment, the objective function and the preset target component constraint of the genetic algorithm can be consistent with those of the particle swarm algorithm. Here, the genetic algorithm can be constructed based on the aforementioned comprehensive objective function and target component constraint.

[0154] It is understandable that the genetic algorithm with enhanced elite retention can include operations such as encoding, decoding, initial population generation, fitness calculation, selection, crossover, mutation, etc. Here, a real-valued coded population can be used, and the elite selection method can be used to select individuals in the population, and a small number of optimal candidate solutions can be selected and retained to the next generation, ensuring that the genetic algorithm avoids repeated calculations of some inferior solutions, thereby accelerating the convergence of the algorithm.

[0155] Step 206 , based on the objective function of the particle swarm algorithm, the particle population of the iron material ratio and the flux ratio, and the set of fuel ratios, the fitness of the particle population of the iron material ratio and the flux ratio is calculated.

[0156] In this embodiment, the set of fuel ratios may be used to calculate the fitness of the objective function of the particle swarm algorithm.

[0157] Step 207: Determine whether a preset convergence condition is met.

[0158] In this embodiment, the preset convergence condition may include the number of iterations reaching a preset number threshold.

[0159] If not, execute step 208, and if so, execute step 209 to output the target batching scheme.

[0160] Step 208, in response to the preset convergence condition not being met, based on the fitness of the particle population of the iron-containing material ratio and the flux ratio, the speed and position of the individual particles in the particle population of the iron-containing material ratio and the flux ratio are updated, and based on the result of the update processing, return to and iteratively execute step 203 until the preset convergence condition is met to obtain the target batching scheme.

[0161] In this embodiment, in response to satisfying the preset convergence conditions, the optimal iron-containing material ratio and flux ratio can be obtained. Based on the optimal iron-containing material ratio and flux ratio, the fuel ratio corresponding to the optimal iron-containing material ratio and flux ratio, and the optimal cost can be obtained. Furthermore, based on the optimal iron-containing material ratio and flux ratio, the fuel ratio corresponding to the optimal iron-containing material ratio and flux ratio, and the optimal cost, the target batching scheme can be obtained.

[0162] In this embodiment, for example, based on the particle population of the iron-containing material ratio and the flux ratio, Individuals make up the particle population of iron-containing material ratio and flux ratio. For the entire population, each individual iron-containing material ratio and flux ratio, that is, each individual particle position .here, In the range of [0,1]. During the k-th step of iterative optimization, by calculating the objective function , the optimal position of particle individual i can be determined , the best position of the population .here, It can be the optimal historical position of the particle i that best satisfies the objective function, that is, the fitness function, that has been experienced in this iteration. It can be iterated for all individuals in the population to the historical position that best satisfies the objective function in this step. When the number of iterative optimizations reaches a preset threshold, the position of the individual with the optimal iron-containing material ratio and flux ratio and the position of the population with the optimal iron-containing material ratio and flux ratio can be decoded to obtain the optimal iron-containing material ratio and flux ratio. The optimal batching scheme may include the optimal iron-containing material ratio and flux ratio, the fuel ratio corresponding to the optimal iron-containing material ratio and flux ratio, and the optimal cost. When the number of iterative optimizations does not reach the preset threshold, the speed information and position information of the individuals in the particle population of the iron-containing material ratio and flux ratio can be updated, and the iterative optimization process of the k+1th step can be performed.

[0163] here, It can characterize the individual proportions of a formulation. It can characterize n iron-containing materials, flux types and their proportions respectively.

[0164] By adopting the solution in this embodiment, the performance of the combined optimization algorithm model is improved by comprehensively considering the raw material consumption cost, storage cost, capital occupation cost and the impact of sintering sintering amount. The important components such as Tfe, SiO2, CaO, MgO, Al2O3, S, P, binary basicity (R2) are used as constraints, and the optimal comprehensive cost is taken as the goal. It is more in line with the actual business scenario's requirements for industry cost control, and can effectively and significantly reduce the comprehensive sintering ingredient cost.

[0165] In addition, the scheme in this embodiment is adopted, and the overall algorithm uses the particle swarm algorithm as the outer algorithm, takes iron-containing materials and flux as the characteristics of the particle swarm, and uses the BP neural network to fit the relationship between the ratio of iron-containing materials and flux and the constraints of the fuel ratio. The trained fuel proportioning relationship network model is used to calculate the fuel ratio and the fuel C content and fuel ash content constraints under the conditions of iron-containing materials and flux ratios. After screening under the target component constraints, the genetic algorithm is used to calculate the fuel ratio for the particle swarm that passes the screening, and the result is used as the individual fitness of the current number of iterations of the particle swarm, and the group is selected to be optimal, the position is updated, and it is iterated to finally obtain the ratio of the optimal proportioning scheme that achieves the cost.

[0166] In addition, by adopting the scheme in this embodiment, the relationship between the raw fuel inventory and the sintering ingredients is established, and the relationship between the sintering fuel ingredients and the raw material ingredients is established, so as to establish a fine sintering ingredient comprehensive optimization model. This combined optimization algorithm combines the particle swarm algorithm, neural network, and genetic algorithm to form a comprehensive ingredient optimization for sintering production, assist the steel plant in determining the sintering ingredients, and provide decision-making and guidance for the raw material procurement of sintering production, effectively enriching the sintering intelligent ingredient theory and bringing intuitive economic benefits.

[0167] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0168] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0169] Figure 3 FIG. 1 shows a structural block diagram of a device for determining sintering ingredients provided by an embodiment of the present application. Figure 3As shown. The device 300 for determining the sintered ore proportioning of this embodiment may include a first information initialization unit 301, a first determination unit 302, a first acquisition unit 303, a first optimization unit 304, and a second optimization unit 305. Among them, the first initialization unit 301 is used to initialize the iron-containing material ratio and the flux ratio of the sintered ore proportioning scheme; the first determination unit 302 is used to determine the particle population of the iron-containing material ratio and the flux ratio based on the iron-containing material ratio and the flux ratio by using a particle swarm algorithm; the first acquisition unit 303 is used to obtain the component constraints of the fuel proportion corresponding to the particle population of the iron-containing material ratio and the flux ratio based on the particle population of the iron-containing material ratio and the flux ratio by using a pre-trained fuel proportioning relationship network model; the first optimization unit 304 is used to obtain the component constraints of the fuel proportion corresponding to the particle population of the iron-containing material ratio and the flux ratio based on the preset target component constraints, the composition constraints of the fuel proportion The fuel ratio is iteratively optimized based on the constraint conditions, the particle population of the iron-containing material ratio and the flux ratio, so as to obtain a set of fuel ratios corresponding to the particle population of the iron-containing material ratio and the flux ratio; the second optimization unit 305 is used to iteratively optimize the batching scheme based on the objective function of the particle swarm algorithm, the particle population of the iron-containing material ratio and the flux ratio, and the set of fuel ratios to obtain a target batching scheme, wherein the objective function is determined based on the relationship between the storage cost and the batching scheme, the relationship between the capital occupation cost and the batching scheme, and the relationship between the raw fuel consumption cost and the batching scheme.

[0170] It should be noted that part or all of the device for determining the sintered ore batching of the present embodiment may be an application located in the local terminal, or may also be a functional unit such as a plug-in or software development kit (SDK) arranged in the application located in the local terminal, or may also be a processing engine located in a network-side server, or may also be a distributed system located on the network side, for example, a processing engine or distributed system in a sintered ore batching processing platform on the network side, etc. This embodiment does not specifically limit this.

[0171] It is understandable that the application may be a local program (nativeApp) installed on the local terminal, or may also be a webpage program (webApp) of a browser on the local terminal, which is not limited in this embodiment.

[0172] Optionally, in a possible implementation of this embodiment, the first optimization unit 304 can be specifically used to initialize the fuel ratio to obtain an initialized fuel ratio population; based on preset target component constraints, component constraints corresponding to the fuel ratio, and particle populations of the iron-containing material ratio and flux ratio, a preset optimization algorithm is used to iteratively optimize the fuel ratio population to obtain a fuel ratio set corresponding to the particle population of the iron-containing material ratio and flux ratio.

[0173] Optionally, in a possible implementation of this embodiment, the first optimization unit 304 can be specifically used to calculate the fitness corresponding to each fuel ratio in the fuel ratio population based on the objective function of the genetic algorithm, the preset target sintered ore composition constraint, the composition constraint corresponding to the fuel ratio, and the particle population of the iron-containing material ratio and the flux ratio; according to each of the fitness, each fuel ratio of the fuel ratio population is subjected to evolutionary processing to determine the next generation of fuel ratio population; based on the next generation of fuel ratio population, the fuel ratio population is subjected to iterative optimization processing to iteratively update the fitness corresponding to the fuel ratio population and perform evolutionary processing; in response to satisfying the preset first convergence condition, based on the result of the iterative optimization processing, the target fuel ratio is obtained; based on the target fuel ratio, a fuel ratio set corresponding to the particle population of the iron-containing material ratio and the flux ratio is obtained.

[0174] Optionally, in a possible implementation of this embodiment, the second optimization unit 305 can be specifically used to fuse the objective function of the particle swarm algorithm and the preset target component constraint condition to obtain the fused objective function; determine the fitness of the particle population of the iron-containing material ratio and the flux ratio based on the fused objective function, the objective function of the particle swarm algorithm, the particle population of the iron-containing material ratio and the flux ratio, and the set of the fuel ratio; in response to not meeting the preset second convergence condition, based on the fitness of the particle population of the iron-containing material ratio and the flux ratio, The speed and position of individual particles in the particle population of the iron-containing material ratio and the flux ratio are updated; based on the result of the updating process, the particle population of the iron-containing material ratio and the flux ratio corresponding to the particle swarm algorithm for the next optimization is obtained; based on the particle population of the iron-containing material ratio and the flux ratio for the next optimization, the step of returning and iteratively executing, using the pre-trained fuel batching relationship network model, obtaining the step of component constraints of the fuel batching corresponding to the particle population of the iron-containing material ratio and the flux ratio and subsequent steps, until the preset second convergence condition is met, so as to obtain the target batching scheme.

[0175] Optionally, in a possible implementation of this embodiment, the first acquisition unit 303 can be specifically used to obtain training sample data, wherein the training sample data includes sample iron-containing material ratio, sample flux ratio, sample fuel carbon content, sample fuel ash content, and sample sintered ore quality data; the training sample data is input into the fuel ingredient relationship network model to be trained to obtain component constraints of the fuel ratio corresponding to the iron-containing material ratio and the flux ratio; based on the training sample data and the component constraints of the fuel ratio corresponding to the iron-containing material ratio and the flux ratio, the fuel ingredient relationship network model to be trained is updated and trained until a preset training termination condition is met, thereby obtaining a trained fuel ingredient relationship network model.

[0176] Optionally, in a possible implementation of this embodiment, the component constraint conditions of the fuel ratio include the constraint relationship between the fuel ratio, the fuel carbon content, and the fuel ash content.

[0177] In this embodiment, the iron-containing material ratio and flux ratio of the sintering ore batching scheme are initialized by a first initialization unit. The first determination unit is used to determine the particle population of the iron-containing material ratio and the flux ratio based on the iron-containing material ratio and the flux ratio by using a particle swarm algorithm. The first acquisition unit is used to obtain the component constraints of the fuel ratio corresponding to the particle population of the iron-containing material ratio and the flux ratio based on the particle population of the iron-containing material ratio and the flux ratio by using a pre-trained fuel batching relationship network model. The first optimization unit is used to iteratively optimize the fuel ratio based on preset target component constraints, the component constraints of the fuel ratio, and the particle population of the iron-containing material ratio and the flux ratio to obtain a set of fuel ratios corresponding to the particle population of the iron-containing material ratio and the flux ratio, so that the second optimization unit can optimize the fuel ratio based on the objective function of the particle swarm algorithm, the particle population of the iron-containing material ratio and the flux ratio, and the raw-fuel batching relationship network model. The batching scheme is iteratively optimized to obtain a target batching scheme, wherein the objective function is determined based on the relationship between the storage cost and the batching scheme, the relationship between the capital occupation cost and the batching scheme, and the relationship between the raw fuel consumption cost and the batching scheme. Since the relationship between the input iron-containing material ratio and the flux ratio particle population and the fuel ratio can be analyzed by using the fuel batching relationship network model, the corresponding fuel ratio component constraint conditions can be obtained, and then based on the target component constraint conditions, the fuel ratio component constraint conditions, the iron-containing material ratio and the flux ratio particle population, the optimal fuel ratio particle population is determined. Finally, based on the iron-containing material ratio and the flux ratio particle population and the optimal fuel ratio particle population, the batching scheme is optimized to obtain the target batching scheme, which can enrich the reference information used to determine the batching scheme, combine the relationship model with multiple optimization algorithms, and optimize the algorithm for determining the sintered ore batching scheme, thereby ensuring the reliability and accuracy of the target batching scheme of the sintered ore.

[0178] In the technical solution of this application, the user personal information involved, such as the collection, storage, use, processing, transmission, provision and disclosure of user images and attribute data, etc., complies with the provisions of relevant laws and regulations and does not violate public order and good morals.

[0179] According to an embodiment of the present application, the present application also provides an electronic device, a readable storage medium and a computer program product.

[0180] Figure 4A schematic block diagram of an example electronic device 400 that can be used to implement an embodiment of the present application is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present application described and / or required herein.

[0181] like Figure 4 As shown, the electronic device 400 includes a computing unit 401, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 402 or a computer program loaded from a storage unit 408 into a random access memory (RAM) 403. In the RAM 403, various programs and data required for the operation of the electronic device 400 can also be stored. The computing unit 401, the ROM 402, and the RAM 403 are connected to each other via a bus 404. An input / output (I / O) interface 405 is also connected to the bus 404.

[0182] Multiple components in the electronic device 400 are connected to the I / O interface 405, including: an input unit 406, such as a keyboard, a mouse, etc.; an output unit 407, such as various types of displays, speakers, etc.; a storage unit 408, such as a disk, an optical disk, etc.; and a communication unit 409, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 409 allows the electronic device 400 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0183] The computing unit 401 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 401 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 401 performs the various methods and processes described above, such as a method for determining the sintering batching. For example, in some embodiments, the method for determining the sintering batching may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 408. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 400 via the ROM 402 and / or the communication unit 409. When the computer program is loaded into the RAM 403 and executed by the computing unit 401, one or more steps of the method for determining the sintering batching described above may be performed. Alternatively, in other embodiments, the computing unit 401 may be configured to execute the method for determining the sintering ore batching in any other appropriate manner (for example, by means of firmware).

[0184] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0185] The program code for implementing the method of the present application can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, implements the functions / operations specified in the flow chart and / or block diagram. The program code can be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0186] In the context of the present application, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0187] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0188] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0189] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0190] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution disclosed in this application can be achieved, and this document is not limited here.

[0191] The above specific implementations do not constitute a limitation on the protection scope of this application. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of this application should be included in the protection scope of this application.

Claims

1. A method for determining sintered ore ingredients, characterized in that: The method comprises: Initialize the iron-containing material ratio and flux ratio of the sintering ore batching plan; Based on the iron-containing material ratio and the flux ratio, using a particle swarm algorithm to determine the particle population of the iron-containing material ratio and the flux ratio; Based on the particle population of the iron-containing material ratio and the flux ratio, a pre-trained fuel proportioning relationship network model is used to obtain the component constraints of the fuel proportion corresponding to the particle population of the iron-containing material ratio and the flux ratio; wherein the fuel proportioning relationship network model is a model based on a BP neural network, and the component constraints of the fuel proportion include the constraint relationship between the fuel proportion, the fuel carbon content, and the fuel ash content; Based on the preset target composition constraint conditions, the composition constraint conditions of the fuel proportion, and the particle populations of the iron-containing material proportion and the flux proportion, the fuel proportion is iteratively optimized using a genetic algorithm to obtain a set of fuel proportions corresponding to the particle populations of the iron-containing material proportion and the flux proportion; Based on the objective function of the particle swarm algorithm, the particle population of the iron-containing material ratio and the flux ratio, and the set of the fuel ratio, the batching scheme is iteratively optimized to obtain a target batching scheme, wherein the objective function is determined based on the relationship between storage cost and the batching scheme, the relationship between capital occupation cost and the batching scheme, and the relationship between raw fuel consumption cost and the batching scheme.

2. The method according to claim 1, characterized in that: The method of iteratively optimizing the fuel ratio based on the preset target component constraint condition, the component constraint condition of the fuel ratio, and the particle population of the iron-containing material ratio and the flux ratio by using a genetic algorithm to obtain a set of fuel ratios corresponding to the particle population of the iron-containing material ratio and the flux ratio includes: Initialize the fuel ratio to obtain an initialized fuel ratio population; Based on the preset target composition constraints, the composition constraints corresponding to the fuel ratio, and the particle population of the iron-containing material ratio and the flux ratio, the fuel ratio population is iteratively optimized using a genetic algorithm to obtain a fuel ratio set corresponding to the particle population of the iron-containing material ratio and the flux ratio.

3. The method according to claim 2, characterized in that The method of iteratively optimizing the fuel ratio population based on the preset target component constraint condition, the component constraint condition corresponding to the fuel ratio, and the particle population of the iron-containing material ratio and the flux ratio by using a genetic algorithm to obtain a fuel ratio set corresponding to the particle population of the iron-containing material ratio and the flux ratio includes: Based on the objective function of the genetic algorithm, the preset target sinter composition constraint, the composition constraint corresponding to the fuel ratio, and the particle population of the iron-containing material ratio and the flux ratio, the fitness corresponding to each fuel ratio in the fuel ratio population is calculated; According to each of the fitnesses, performing evolution processing on each fuel ratio of the fuel ratio population to determine the next generation fuel ratio population; Based on the next generation fuel ratio population, the fuel ratio population is iteratively optimized to iteratively update the fitness corresponding to the fuel ratio population and perform evolutionary processing; In response to satisfying a preset first convergence condition, obtaining a target fuel ratio based on a result of the iterative optimization process; Based on the target fuel ratio, a fuel ratio set corresponding to the particle population of the iron-containing material ratio and the flux ratio is obtained.

4. The method according to claim 1, characterized in that: The objective function of the particle swarm algorithm, the particle population of the iron-containing material ratio and the flux ratio, and the set of the fuel ratio are used to iteratively optimize the batching scheme to obtain a target batching scheme, including: Fusing the objective function of the particle swarm algorithm and the preset objective component constraint conditions to obtain a fused objective function; Determine the fitness of the particle population of the iron-containing material ratio and the flux ratio based on the objective function after the fusion processing, the objective function of the particle swarm algorithm, the particle population of the iron-containing material ratio and the flux ratio, and the set of the fuel ratio; In response to not meeting the preset second convergence condition, based on the fitness of the particle population of the iron-containing material ratio and the flux ratio, updating the speed and position of the individual particles in the particle population of the iron-containing material ratio and the flux ratio; Based on the result of the updating process, a particle population of the iron-containing material ratio and the flux ratio to be optimized next time corresponding to the particle swarm algorithm is obtained; Based on the particle population of the iron-containing material ratio and the flux ratio optimized for the next time, return and iteratively execute, and use the pre-trained fuel proportioning relationship network model to obtain the step and subsequent steps of the component constraints of the fuel proportion corresponding to the particle population of the iron-containing material ratio and the flux ratio, until the preset second convergence condition is met to obtain the target proportioning scheme.

5. The method according to claim 1, characterized in that Before obtaining the fuel proportion component constraint condition corresponding to the particle population of the iron-containing material proportion and the flux proportion based on the particle population of the iron-containing material proportion and the flux proportion by using the pre-trained fuel proportion relationship network model, the method further includes: Acquire training sample data, wherein the training sample data includes sample iron-containing material ratio, sample flux ratio, sample fuel carbon content, sample fuel ash content, and sample sintered ore quality data; Input the training sample data into the fuel proportioning relationship network model to be trained to obtain the component constraint conditions of the fuel proportion corresponding to the iron-containing material proportion and the flux proportion; Based on the training sample data, the component constraints of the fuel ratio corresponding to the iron-containing material ratio and the flux ratio, the fuel ingredient relationship network model to be trained is updated and trained until the preset training termination condition is met, thereby obtaining a trained fuel ingredient relationship network model.

6. A device for determining sintered ore ingredients, characterized in that: The device comprises: A first initialization unit is used to initialize the iron-containing material ratio and flux ratio of the sintering ore batching scheme; A first determination unit is used to determine the particle population of the iron-containing material ratio and the flux ratio based on the iron-containing material ratio and the flux ratio by using a particle swarm algorithm; A first obtaining unit is used to obtain the component constraints of the fuel ratio corresponding to the particle population of the iron-containing material ratio and the flux ratio based on the particle population of the iron-containing material ratio and the flux ratio by using a pre-trained fuel ratio relationship network model; wherein the fuel ratio relationship network model is a model based on a BP neural network trained by using training sample data, the training sample data includes sample iron-containing material ratio, sample flux ratio, sample fuel carbon content, sample fuel ash content, and sample sinter quality data, and the component constraints of the fuel ratio include the constraint relationship between the fuel ratio, the fuel carbon content, and the fuel ash content; The first optimization unit is used to iteratively optimize the fuel ratio based on the preset target composition constraint condition, the composition constraint condition of the fuel ratio, and the particle population of the iron-containing material ratio and the flux ratio by using a genetic algorithm to obtain a fuel ratio set corresponding to each individual of the particle population of the iron-containing material ratio and the flux ratio; The second optimization unit is used to iteratively optimize the batching scheme based on the objective function of the particle swarm algorithm, the particle population of the iron-containing material ratio and the flux ratio, and the set of the fuel ratio to obtain a target batching scheme, wherein the objective function is determined based on the relationship between storage cost and the batching scheme, the relationship between capital occupation cost and the batching scheme, and the relationship between raw fuel consumption cost and the batching scheme.

7. An electronic device comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor so that the at least one processor can execute the method according to any one of claims 1-5.

8. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-5.

9. A computer program product, comprising a computer program, which, when executed by a processor, implements the method according to any one of claims 1 to 5.