Hydrogen-based dri-scraps electric arc furnace intelligent dynamic dosing method, device and equipment

Abstract

This application provides a hydrogen-based DRI-scrap electric arc furnace intelligent dynamic batching method, apparatus, and equipment, belonging to the field of iron and steel smelting. The method includes: before the start of each smelting stage, detecting the steel composition, steel temperature, and furnace state parameters of the previous smelting stage, obtaining the detection results; inputting the detection results and the material characteristic information parameters into the stage material conservation model of the current smelting stage, predicting the element content at the end of the current smelting stage, and calculating element deviation data based on the element content and the corresponding stage-specific target component constraint interval; dynamically optimizing the material addition amount and power supply parameters of the current stage based on the multi-objective optimization model, the element deviation data, and the energy deviation data, obtaining the optimization result, and executing the smelting operation of the current stage according to the optimization result.

Description

Technical Field

[0001] This application relates to the field of iron and steel smelting, and in particular to a method, apparatus and equipment for intelligent dynamic batching of hydrogen-based DRI-scrap electric arc furnace. Background Technology

[0002] Against the backdrop of the "dual carbon" goals and the green transformation of the steel industry, electric arc furnace short-process steelmaking has been widely used due to its high scrap utilization rate and relatively low carbon emission intensity. With the development of hydrogen-based direct reduced iron (DRI) technology, hydrogen-based DRI, as a low-carbon, high-quality ferrite raw material, has broad application prospects in electric arc furnace steelmaking.

[0003] However, hydrogen-based DRI differs significantly from traditional scrap steel in terms of chemical composition, physical properties, melting behavior, energy requirements, and cost structure. Existing electric arc furnace batching methods mostly rely on empirical batching or static batching based on endpoint composition, resulting in poor product quality and smelting cost control, and weak engineering adaptability. Summary of the Invention

[0004] To address the aforementioned technical problems, this application provides a method, apparatus, and equipment for intelligent dynamic batching of hydrogen-based DRI-scrap electric arc furnace.

[0005] In a first aspect, embodiments of this application provide a method for intelligent dynamic batching of hydrogen-based DRI-scrap electric arc furnaces, the method comprising: Obtain material characteristic information parameters of smelting materials, wherein the smelting materials include smelting raw materials and auxiliary raw materials, wherein the smelting raw materials include hydrogen-based DRI and mixed scrap steel; The final chemical composition requirements of the target steel grade are mapped to the phased target composition constraint ranges corresponding to each element in each smelting stage. Before each smelting stage begins, the composition, temperature, and internal state parameters of the molten steel from the previous smelting stage in the electric arc furnace are measured, and the results are obtained. The detection results and the material characteristic information parameters are input into the stage material conservation model of the current smelting stage to predict the element content at the end of the current smelting stage, and the element deviation data is calculated based on the element content and the stage target component constraint interval corresponding to the element. The detection results and the material characteristic information parameters are input into the stage energy balance model of the current smelting stage to calculate the energy deviation data; A multi-objective optimization model is obtained by weighting the stage steel composition deviation model, stage smelting cost model, stage carbon emission model, and stage smelting duration model. Based on the multi-objective optimization model, the element deviation data, and the energy deviation data, the material addition amount and power supply parameters of the current stage are dynamically optimized to obtain the optimization results, and the smelting operation of the current stage is executed according to the optimization results.

[0006] Secondly, embodiments of this application provide a hydrogen-based DRI-scrap electric arc furnace intelligent dynamic batching device, the hydrogen-based DRI-scrap electric arc furnace intelligent dynamic batching device comprising: The acquisition module is used to acquire material characteristic information parameters of smelting materials, which include smelting raw materials and auxiliary raw materials, and the smelting raw materials include hydrogen-based DRI and mixed scrap steel. The mapping module is used to map the final chemical composition requirements of the target steel grade to the staged target composition constraint ranges corresponding to each element in each smelting stage. The detection module is used to detect the composition, temperature and internal parameters of the molten steel in the previous smelting stage of the electric arc furnace before the start of each smelting stage, and obtain the detection results. The first calculation module is used to input the detection results and the material characteristic information parameters into the stage material conservation model of the current smelting stage, predict the element content at the end of the current smelting stage, and calculate the element deviation data based on the element content and the stage target component constraint interval corresponding to the element. The second calculation module is used to input the detection results and the material characteristic information parameters into the stage energy balance model of the current smelting stage to calculate the energy deviation data. The characterization module is used to perform weighted characterization of the stage steel composition deviation model, the stage smelting cost model, the stage carbon emission model, and the stage smelting duration model to obtain a multi-objective optimization model. The optimization module is used to dynamically optimize the material addition amount and power supply parameters of the current stage based on the multi-objective optimization model, the element deviation data and the energy deviation data, obtain the optimization result, and execute the smelting operation of the current stage according to the optimization result.

[0007] Thirdly, embodiments of this application provide an electronic device, including a memory and a processor. The memory is used to store a computer program, and the computer program executes the hydrogen-based DRI-scrap electric arc furnace intelligent dynamic batching method provided in the first aspect when the processor is running.

[0008] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program that, when run on a processor, executes the hydrogen-based DRI-scrap electric arc furnace intelligent dynamic batching method provided in the first aspect.

[0009] The intelligent dynamic batching method for hydrogen-based DRI-scrap electric arc furnace provided in this application obtains material characteristic information parameters of the smelting materials, which include smelting raw materials and auxiliary raw materials. The smelting raw materials include hydrogen-based DRI and mixed scrap steel. The method maps the final chemical composition requirements of the target steel grade to the stage-specific target composition constraint intervals corresponding to each element in each smelting stage. Before the start of each smelting stage, the steel composition, steel temperature, and furnace state parameters of the previous smelting stage are detected, and the detection results are obtained. The detection results and the material characteristic information parameters are input into the stage-specific material conservation model of the current smelting stage to predict the element content at the end of the current smelting stage. The elemental deviation data is calculated based on the element content and the corresponding phased target component constraint range. The detection results and material characteristic information parameters are input into the phased energy balance model of the current smelting phase to calculate the energy deviation data. The phased steel composition deviation model, phased smelting cost model, phased carbon emission model, and phased smelting duration model are weighted to obtain a multi-objective optimization model. Based on the multi-objective optimization model, the elemental deviation data, and the energy deviation data, the material addition amount and power supply parameters of the current phase are dynamically optimized to obtain the optimization results. The smelting operation of the current phase is then executed according to the optimization results. Attached Figure Description

[0010] To more clearly illustrate the technical solutions of this application, the accompanying drawings used in the embodiments will be briefly described below. It should be understood that the following drawings only show some embodiments of this application and should not be considered as a limitation on the scope of protection of this application. In the various drawings, similar components are numbered similarly.

[0011] Figure 1 This paper illustrates a flowchart of the intelligent dynamic batching method for hydrogen-based DRI-scrap electric arc furnace provided in an embodiment of this application. Figure 2 This paper presents another schematic diagram of the intelligent dynamic batching method for hydrogen-based DRI-scrap electric arc furnace provided in an embodiment of this application. Figure 3 A schematic diagram of the structure of the intelligent dynamic batching device for hydrogen-based DRI-scrap electric arc furnace provided in an embodiment of this application is shown.

[0012] Icons: 300-Hydrogen-based DRI-Intelligent Dynamic Batching Device for Scrap Steel Electric Arc Furnace, 301-Acquisition Module, 302-Mapping Module, 303-Detection Module, 304-First Calculation Module, 305-Second Calculation Module, 306-Characteristic Module, 307-Optimization Module. Detailed Implementation

[0013] The technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments.

[0014] The components of the embodiments of this application described and illustrated in the accompanying drawings can be arranged and designed in a variety of different configurations. Therefore, the following detailed description of the embodiments of this application provided in the drawings is not intended to limit the scope of the claimed application, but merely to illustrate selected embodiments of the application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0015] In the following, the terms “comprising,” “having,” and their cognates, which may be used in various embodiments of this application, are intended only to indicate a particular feature, number, step, operation, element, component, or combination thereof, and should not be construed as excluding, firstly, the presence of one or more other features, numbers, steps, operations, elements, components, or combinations thereof, or adding the possibility of one or more features, numbers, steps, operations, elements, components, or combinations thereof.

[0016] Furthermore, the terms "first," "second," and "third" are used only to distinguish descriptions and should not be interpreted as indicating or implying relative importance.

[0017] Unless otherwise specified, all terms used herein (including technical and scientific terms) shall have the same meaning as commonly understood by one of ordinary skill in the art to which the various embodiments of this application pertain. Terms (such as those defined in commonly used dictionaries) shall be interpreted as having the same meaning as in their contextual meaning in the relevant technical field and shall not be construed as having an idealized or overly formal meaning, unless clearly defined in the various embodiments of this application.

[0018] Example 1 This application provides a method for intelligent dynamic batching of hydrogen-based DRI-scrap electric arc furnace.

[0019] See Figure 1 A hydrogen-based DRI-scrap electric arc furnace intelligent dynamic batching method includes S101-S107: S101: Obtain material characteristic information parameters of smelting materials, wherein the smelting materials include smelting raw materials and auxiliary raw materials, and the smelting raw materials include hydrogen-based DRI and mixed scrap steel.

[0020] In this embodiment, the material characteristic information parameters include at least the elemental content of various raw materials, carbon emission factor per unit mass, unit melting energy consumption, and market price. Furthermore, the material characteristic information for hydrogen-based DRIs includes pore structure parameters (porosity) and gangue content.

[0021] S102: Map the final chemical composition requirements of the target steel grade to the phased target composition constraint range corresponding to each element in each smelting stage.

[0022] In this embodiment, based on the obtained final chemical composition requirements of the target steel grade, the final composition requirements are decomposed into stage-specific quality constraint intervals for each stage of the smelting process. The smelting process is divided into... N The first smelting stage, then the second k Phase 1 j The phased component constraint interval of the element is: ,in, Indicates the first During the smelting process, according to the composition requirements, the raw material C is added... The composition value of an element.

[0023] In one embodiment, S102 includes: the phased target component constraint range changes dynamically according to different smelting stages, and the phased target component constraint range of the early smelting stage is wider than the phased target component constraint range of the later smelting stage.

[0024] In this embodiment, the smelting stage of the electric arc furnace includes at least several stages, such as the melting start-up stage, the main melting stage, the enhanced melting stage, the composition adjustment stage, and the refining preparation stage. The target composition constraint range of each smelting stage changes dynamically according to the different smelting stages. The early stage focuses on rapid melting and preliminary impurity removal, while the later stage focuses on precise composition control and quality optimization. Therefore, the target composition constraint range of the early smelting stage is wider than that of the later smelting stage.

[0025] Furthermore, as the smelting process progresses, the composition range gradually converges, allowing for better control of the final composition deviation and preventing excessive deviation from the target steel's final chemical composition requirements, thus satisfying: This means that the composition constraint range in subsequent stages is gradually tightened in order to ensure the accuracy of the final chemical composition of the molten steel.

[0026] S103: Before each smelting stage begins, the composition, temperature, and internal parameters of the molten steel from the previous smelting stage in the electric arc furnace are measured, and the results are obtained.

[0027] In this embodiment, before the start of each smelting stage, the steel composition, steel temperature, and furnace state parameters of the current smelting stage are detected in real time. The furnace state parameters include at least the furnace power input, electrode working status, and slag state parameters. The slag state parameters are used to predict the decarburization amount of the current smelting stage to obtain elemental deviation data; the furnace power input and electrode working status are used to obtain energy deviation data.

[0028] S104: Input the detection results and the material characteristic information parameters into the stage material conservation model of the current smelting stage, predict the element content at the end of the current smelting stage, and obtain element deviation data based on the element content and the stage target component constraint interval corresponding to the element.

[0029] In this embodiment, the acquired detection results (e.g., carbon content in the molten steel from the previous smelting stage) and the carbon input from the hydrogen-based DRI in the smelting raw materials are input into the stage material conservation model of the current smelting stage to obtain the carbon content of the current smelting stage. Based on the oxygen supply of the oxygen lance, furnace state parameters (slag basicity), and historical statistical models, the decarburization amount of the current smelting stage is predicted, and finally, the carbon content at the end of the current smelting stage is predicted. ,Compare By comparing the carbon control target parameters with those of the current smelting stage, the elemental deviation data can be obtained.

[0030] Specifically, the phased material conservation model can be expressed as: ; in, For the first The amount of each raw material added at this stage; Indicates material middle The content of elements; Indicates material middle Effective yield of elemental components; express During the phase Elemental composition content; express During the phase Elemental composition content; For the quality of molten steel.

[0031] S105: Input the detection results and the material characteristic information parameters into the stage energy balance model of the current smelting stage to obtain energy deviation data.

[0032] In this embodiment, the detection results (molten steel temperature) and material characteristic information parameters (hydrogen-based DRI unit melting energy consumption and mixed scrap steel unit melting energy consumption) are input into the stage energy balance model of the current smelting stage to obtain energy deviation data. Based on the energy deviation data and furnace state parameters (current power supply and operating status of the electrodes), the required electrical energy and power supply time for the current stage are predicted.

[0033] Specifically, the stage energy balance model can be expressed as: ; in, For the first The amount of each raw material added at this stage; The heat consumption for melting a unit mass of raw material (unit melting energy consumption). For the quality of molten steel; For electrical energy input; The chemical reaction is exothermic; Specific heat of molten steel; This is a phased temperature rise; This is the heat loss term.

[0034] In one embodiment, prior to S106, the method further includes: constructing a phased smelting cost model based on the amount of smelting materials added and the current electricity price. ; in, For the first Unit quantity of stage smelting cost; For the first Phase 1 Amount of each raw material added; For materials The price; For the first The electrical energy required for this stage; This represents the electricity price for the current period.

[0035] See Figure 2 In one embodiment, before constructing the stage smelting cost model based on the amount of smelting materials added and the current electricity price, the method further includes S201-S202: S201: Generate the initial batching scheme for each stage based on the material characteristic information parameters and the staged target component constraint range.

[0036] S202: Determine the initial amount of smelting materials to be added in the current stage based on the initial batching plan for each stage.

[0037] In this embodiment, the initial batching scheme for each stage is a static batching scheme that meets the final chemical composition requirements of the target steel grade and the smelting cost constraints. It is used as the initial solution of the multi-objective optimization model, that is, the initial addition amount of smelting materials in the current smelting stage can be determined based on the initial batching scheme.

[0038] In one embodiment, prior to S106, the method further includes: constructing a stage carbon emission model based on the carbon emissions of smelting materials and the carbon emissions of electricity consumption.

[0039] ; in, For the first Phase-specific carbon emissions per unit; For the first Phase 1 Amount of each raw material added; It is the first Carbon emissions per unit of raw material; For the first The electrical energy required for this stage; The carbon emission factor of electricity is related to the electricity consumption period.

[0040] S106: The stage steel composition deviation model, stage smelting cost model, stage carbon emission model, and stage smelting duration model are weighted and characterized to obtain a multi-objective optimization model.

[0041] In this embodiment, under the constraints of material conservation and energy conservation in each stage, and with the optimization objectives of minimizing the steel composition deviation, smelting cost, carbon emissions, and stage duration within the smelting stage, a stage steel composition deviation model was constructed. Stage smelting cost model Stage carbon emission model and stage smelting duration model .

[0042] Furthermore, based on the weighted characterization of the steel composition deviation model, the stage smelting cost model, the stage carbon emission model, and the stage smelting duration model, we obtain: ; in, For the stage steel composition deviation model, This is a staged smelting cost model. This is a phased carbon emission model. For the stage smelting duration model, For the first The weighting coefficients corresponding to each stage.

[0043] In one embodiment, the method described in S106 further includes: using different weighting coefficients to weight the stage steel composition deviation model, stage smelting cost model, stage carbon emission model, and stage smelting duration model for different smelting stages.

[0044] In this embodiment, the weighting coefficient needs to be dynamically adjusted according to external conditions and smelting objectives. This can be achieved by adjusting the weighting coefficient based on external conditions and smelting objectives, such as when the current electricity price is detected. Below the set threshold At the same time, increase the weight of electricity-related targets. When there are significant changes in hydrogen-based DRI or scrap steel market prices, the weight of the raw material cost target should be increased accordingly, and the weight should be met. It is positively correlated with material prices. When production plans impose strict limits on carbon emissions, increase the weight of carbon emission targets. In the later stages of smelting, increase the weighting of composition deviation. Reduce the weight of smelting duration The aforementioned weight adjustment mechanism enables the optimization model to possess good engineering adaptability and dynamic response capability.

[0045] S107: Based on the multi-objective optimization model, the element deviation data, and the energy deviation data, dynamically optimize the material addition amount and power supply parameters for the current stage to obtain the optimization results, and execute the smelting operation for the current stage according to the optimization results.

[0046] In this embodiment, the material addition amount and power supply parameters are dynamically optimized based on the multi-objective optimization model, element deviation data and energy deviation data. The addition amount of hydrogen-based DRI, mixed scrap steel and auxiliary raw materials is dynamically adjusted, and the power supply parameters are adjusted simultaneously. The power supply parameters include the electric arc furnace power supply level, electrode power distribution and power supply duration. After the current stage is completed, the next smelting stage is entered, and the above steps S103-S107 are repeated until the smelting is completed.

[0047] In one embodiment, the multi-objective optimization model is solved using a Pareto optimal strategy.

[0048] In this embodiment, the Pareto optimal strategy is similar to linear programming. Based on the conditions, it gradually narrows the range to a point (small interval) through comprehensive weighting and then makes a rounding selection. Its recursive process is influenced by a part of the experience database, which is mainly used to control the recursive direction and make it proceed in the direction with more historical ingredient combinations.

[0049] Specifically, the smelting process is divided into five stages: melting start-up stage, main melting stage, intensified melting stage, composition adjustment stage, and refining preparation stage. This embodiment focuses on the dynamic batching calculation process of the intensified melting stage; the other stages use the same calculation logic. Taking the smelting of medium carbon structural steel in a 120 t AC electric arc furnace as an example, the final chemical composition requirements of the target steel grade are shown in Table 1: Table 1: Final Chemical Composition of Molten Steel for the Target Steel Grade

[0050] Specifically, before smelting begins, the composition and physical properties of all raw materials involved in the smelting process are analyzed. The collected data are obtained through the following methods: the chemical composition data of the raw materials comes from rapid pre-furnace analysis and historical batch statistical averages; the physical properties and energy consumption parameters come from production statistics and empirical model corrections; and the carbon emission factor and electricity price parameters come from the company's internal database or publicly available industry statistics. The parameters of the smelting raw materials are shown in Table 2, the parameters of the auxiliary materials are shown in Table 3, and the electricity and energy consumption parameters are shown in Table 4.

[0051] Table 2 Smelting Raw Material Parameters

[0052] Table 3 Auxiliary raw material parameter table

[0053] Table 4 Electricity and Energy Consumption Parameters

[0054] Before entering the intensified melting stage, the current smelting status parameters, including molten steel quality, are acquired in real time through the furnace front detection system and the electric arc furnace control system. M k The capacity is 118.0 t, and the temperature of the molten steel is... T k The temperature is 1545 °C, and the furnace status parameters include the current power supply. P k The capacity is 75 MW, the slag basicity is 2.4, and the electrode is in a stable operating state.

[0055] Because unreduced iron oxide is present in hydrogen-based DRIs, the effective iron content needs to be determined based on the metal yield. correction, Defined as the proportion of metallic iron, that is, the percentage of the mass of metallic iron in the material relative to the total mass of iron. Assuming the mass of hydrogen-based DRI input is... Based on the total iron content (TFe) and metal yield of hydrogen-based DRIs, Calculate its effective metallic iron mass for: ; Effective metallic iron mass of mixed scrap steel for: ; During the enhanced melting stage, the amount of auxiliary materials such as lime, dolomite, and carbon raisers added is mainly determined by the target slag alkalinity, degree of oxidation, and fine-tuning requirements of the final composition. The range of variation in their dosage is relatively small, and they are not used as free variables for stage dynamic optimization.

[0056] Given that the cost and carbon emission contribution of the aforementioned auxiliary materials in the enhanced melting stage are significantly lower than those of hydrogen-based DRI, scrap steel, and electricity consumption, they are treated as fixed parameters or constraints in this embodiment and are not included in the explicit calculation terms of the multi-objective optimization function.

[0057] Specifically, taking the conservation of carbon as an example, if the carbon content in the molten steel is found to be 0.34% during pre-furnace testing in the intensified melting stage, then: ; The carbon input of the hydrogen-based DRI is calculated based on the mass, carbon content, and effective carbon recovery rate (the carbon recovery rate of the hydrogen-based DRI is 0.85) during this smelting stage. for: ; The carbon input of the mixed scrap steel is calculated based on the mass of the mixed scrap steel, the carbon content of the mixed scrap steel, and the effective carbon recovery rate of the mixed scrap steel (the carbon recovery rate of the mixed scrap steel is 0.9) during this smelting stage. for: ; Based on the oxygen supply of the oxygen lance, slag alkalinity, and historical statistical models, the decarbonization amount in this stage is predicted. for: ; At the end of the stage, based on the carbon quality of the molten steel With the quality of molten steel Carbon content prediction for: ; ; ; Meanwhile, the target for controlling carbon content during the enhanced melting stage is: ; Therefore, we can conclude that: ; Specifically, regarding the energy balance during the intensified melting stage, assuming the target molten steel temperature is 1620℃ and the current molten steel temperature is 1545℃, then: ; Sensible heat requirements of molten steel for: ; The unit melting energy consumption of hydrogen-based DRI is 380 kWh / t, and the unit melting energy consumption of mixed scrap steel is 350 kWh / t. Therefore, the total unit melting energy consumption of raw materials is... for: ; Calculate heat loss correction based on heat loss ratio. for: ; During the intensified melting stage, the net contribution of chemical reactions to the furnace energy balance is relatively small and negligible compared to electrical energy input. Therefore, a separate heat term for chemical reactions is not introduced into the energy model for this stage. Based on the electrical-to-thermal conversion efficiency in Table 4, the total electrical energy demand in the calculation stage is... for: ; Based on the power supply in front of the electrodes P k Phase power supply time prediction for: ; In the enhanced melting stage, in addition to carbon as the main control variable, elements such as silicon, manganese, phosphorus, and sulfur are simultaneously included in the constraints and verification scope of the stage dynamic batching model.

[0058] Among them, silicon and manganese are mainly affected by oxidation reaction and slag conditions during the enhanced melting stage. Their changing trends are predicted by historical statistical models and precisely controlled by alloy addition in the subsequent composition adjustment stage. Phosphorus element is predicted using a model of slag basicity, oxygen potential, and reaction efficiency, with the stage control target being no higher than the upper limit of the final component. Sulfur is mainly controlled during the refining preparation and refining stages through slag treatment and desulfurization processes, while it is only used as a constraint monitoring parameter during the intensified melting stage.

[0059] When the predicted value of any alloying element exceeds the preset constraint range, the system will adjust the raw material ratio, oxygen supply intensity or stage target parameters in a coordinated manner to correct the batching strategy for the current or subsequent stages.

[0060] Furthermore, under the premise of satisfying the multi-element composition constraints, a multi-objective optimization model is constructed, with the optimization objectives of minimizing the steel composition deviation, the lowest smelting cost, the lowest carbon emissions, and the shortest stage duration, to solve for the amount of hydrogen-based DRI and mixed scrap steel added during the enhanced melting stage.

[0061] Optionally, the cost and carbon emissions of the auxiliary materials can be incorporated into the comprehensive objective function for unified optimization as needed.

[0062] Parameters were constructed based on the deviation of carbon content in molten steel. : ; Based on the lowest smelting cost, the construction parameters are... : ; Based on minimum carbon emission building parameters : ; Build based on the shortest duration : ; Construct comprehensive optimization target parameters : ; In the enhanced melting stage, the main focus is on melting efficiency and composition stability, with the following weighting coefficients set: ; Under constraints (elemental deviation data) , The solution is obtained by using the weighted objective function or Pareto optimal strategy mentioned in step S106, and the optimal solution is: ; The calculation results were then verified, thus the carbon content was calculated. for: ; ; The test results show that the phased control objectives have been met.

[0063] After verifying each element, the system outputs the batching list and control parameters for the enhanced melting stage as follows:

[0064] After completing the enhanced melting stage, the system reacquires the steel composition, steel temperature, and furnace state parameters, and then enters the next stage of dynamic batching calculation.

[0065] This embodiment provides an intelligent dynamic batching method for hydrogen-based DRI-scrap electric arc furnaces. It acquires material characteristic information parameters of the smelting materials, including raw materials and auxiliary materials. The raw materials include hydrogen-based DRI and mixed scrap steel. The method maps the target steel grade's final chemical composition requirements to the stage-specific target composition constraint intervals corresponding to each element in each smelting stage. Before the start of each smelting stage, the steel composition, temperature, and furnace state parameters from the previous smelting stage are detected, and the detection results are obtained. The detection results and the material characteristic information parameters are input into the stage-specific material conservation model for the current smelting stage to predict the element content at the end of the current smelting stage. The elemental deviation data is calculated based on the element content and the corresponding phased target component constraint range. The detection results and material characteristic information parameters are input into the phased energy balance model of the current smelting phase to calculate the energy deviation data. The phased steel composition deviation model, phased smelting cost model, phased carbon emission model, and phased smelting duration model are weighted to obtain a multi-objective optimization model. Based on the multi-objective optimization model, the elemental deviation data, and the energy deviation data, the material addition amount and power supply parameters of the current phase are dynamically optimized to obtain the optimization results. The smelting operation of the current phase is then executed according to the optimization results.

[0066] Example 2 In addition, this application provides a hydrogen-based DRI-scrap electric arc furnace intelligent dynamic batching device, which is applied to electronic equipment.

[0067] like Figure 3 As shown, the hydrogen-based DRI-scrap electric arc furnace intelligent dynamic batching device 300 includes: The acquisition module 301 is used to acquire material characteristic information parameters of smelting materials, the smelting materials including smelting raw materials and auxiliary raw materials, the smelting raw materials including hydrogen-based DRI and mixed scrap steel; The mapping module 302 is used to map the final chemical composition requirements of the target steel grade to the phased target composition constraint ranges corresponding to each element in each smelting stage. The detection module 303 is used to detect the composition, temperature and internal state parameters of the molten steel in the previous smelting stage of the electric arc furnace before the start of each smelting stage, and obtain the detection results. The first calculation module 304 is used to input the detection results and the material characteristic information parameters into the stage material conservation model of the current smelting stage, predict the element content at the end of the current smelting stage, and calculate the element deviation data based on the element content and the stage target component constraint interval corresponding to the element. The second calculation module 305 is used to input the detection results and the material characteristic information parameters into the stage energy balance model of the current smelting stage to calculate the energy deviation data. Characterization module 306 is used to perform weighted characterization of the stage steel composition deviation model, stage smelting cost model, stage carbon emission model and stage smelting duration model to obtain a multi-objective optimization model. The optimization module 307 is used to dynamically optimize the material addition amount and power supply parameters of the current stage based on the multi-objective optimization model, the element deviation data and the energy deviation data, obtain the optimization result, and execute the smelting operation of the current stage according to the optimization result.

[0068] Optionally, the mapping module 302 is further configured to dynamically change the phased target component constraint range according to different smelting stages, and the phased target component constraint range of the early smelting stage is wider than the phased target component constraint range of the later smelting stage.

[0069] Optionally, the characterization module 306 is also used to construct a stage smelting cost model based on the amount of smelting materials added and the current electricity price. ; in, For the first Unit quantity of stage smelting cost; For the first Phase 1 Amount of each raw material added; For materials The price; For the first The electrical energy required for this stage; This represents the electricity price for the current period.

[0070] Optionally, the characterization module 306 is also used to generate initial batching schemes for each stage based on the material characteristic information parameters and the staged target component constraint range; The initial amount of smelting materials to be added in the current stage is determined based on the initial batching plan for each stage.

[0071] Optionally, the characterization module 306 is also used to construct a stage carbon emission model based on the carbon emissions of smelting materials and the carbon emissions of electricity consumption. ; in, For the first Phase-specific carbon emissions per unit; For the first Phase 1 Amount of each raw material added; It is the first Carbon emissions per unit of raw material; For the first The electrical energy required for this stage; The carbon emission factor of electricity is related to the electricity consumption period.

[0072] Optionally, the characterization module 306 is also used to perform weighted characterization of the stage steel composition deviation model, stage smelting cost model, stage carbon emission model and stage smelting duration model using different weighting coefficients for different smelting stages.

[0073] Optionally, the optimization module 307 is further configured to solve the multi-objective optimization model using a Pareto optimal strategy.

[0074] The intelligent dynamic batching device 300 for hydrogen-based DRI-scrap electric arc furnace provided in this embodiment can realize the intelligent dynamic batching method for hydrogen-based DRI-scrap electric arc furnace provided in Embodiment 1. To avoid repetition, it will not be described again here.

[0075] The intelligent dynamic batching device for hydrogen-based DRI-scrap electric arc furnace provided in this embodiment acquires material characteristic information parameters of the smelting materials, which include smelting raw materials and auxiliary raw materials. The smelting raw materials include hydrogen-based DRI and mixed scrap steel. The device maps the final chemical composition requirements of the target steel grade to the stage-specific target composition constraint intervals corresponding to each element in each smelting stage. Before the start of each smelting stage, the device detects the steel composition, steel temperature, and furnace state parameters of the previous smelting stage in the electric arc furnace, obtaining the detection results. The detection results and the material characteristic information parameters are input into the stage-specific material conservation model of the current smelting stage to predict the element content at the end of the current smelting stage. The elemental deviation data is calculated based on the element content and the corresponding phased target component constraint range. The detection results and material characteristic information parameters are input into the phased energy balance model of the current smelting phase to calculate the energy deviation data. The phased steel composition deviation model, phased smelting cost model, phased carbon emission model, and phased smelting duration model are weighted to obtain a multi-objective optimization model. Based on the multi-objective optimization model, the elemental deviation data, and the energy deviation data, the material addition amount and power supply parameters of the current phase are dynamically optimized to obtain the optimization results. The smelting operation of the current phase is then executed according to the optimization results.

[0076] Example 3 Furthermore, this application provides an electronic device, including a memory and a processor. The memory stores a computer program, which, when run on the processor, executes the hydrogen-based DRI-scrap electric arc furnace intelligent dynamic batching method provided in Embodiment 1.

[0077] The electronic device provided in this embodiment of the invention can execute the steps of the intelligent dynamic batching method for hydrogen-based DRI-scrap electric arc furnace provided in the above method embodiment 1. To avoid repetition, it will not be described again here.

[0078] Example 4 This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the hydrogen-based DRI-scrap electric arc furnace intelligent dynamic batching method provided in Embodiment 1.

[0079] In this embodiment, the computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, etc.

[0080] The computer-readable storage medium provided in this embodiment can realize the intelligent dynamic batching method for hydrogen-based DRI-scrap electric arc furnace provided in Embodiment 1. To avoid repetition, it will not be described again here.

[0081] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or terminal that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or terminal. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or terminal that includes that element.

[0082] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0083] The embodiments of this application have been described above with reference to the accompanying drawings. However, this application is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of this application without departing from the spirit and scope of the claims, and all of these forms are within the protection scope of this application.

Claims

1. A method for intelligent dynamic batching of hydrogen-based DRI-scrap electric arc furnace, characterized in that, The method includes: Obtain material characteristic information parameters of smelting materials, wherein the smelting materials include smelting raw materials and auxiliary raw materials, wherein the smelting raw materials include hydrogen-based DRI and mixed scrap steel; The final chemical composition requirements of the target steel grade are mapped to the phased target composition constraint ranges corresponding to each element in each smelting stage. Before each smelting stage begins, the composition, temperature, and internal state parameters of the molten steel from the previous smelting stage in the electric arc furnace are measured, and the results are obtained. The detection results and the material characteristic information parameters are input into the stage material conservation model of the current smelting stage to predict the element content at the end of the current smelting stage, and the element deviation data is calculated based on the element content and the stage target component constraint interval corresponding to the element. The detection results and the material characteristic information parameters are input into the stage energy balance model of the current smelting stage to calculate the energy deviation data; A multi-objective optimization model is obtained by weighting the stage steel composition deviation model, stage smelting cost model, stage carbon emission model, and stage smelting duration model. Based on the multi-objective optimization model, the element deviation data, and the energy deviation data, the material addition amount and power supply parameters of the current stage are dynamically optimized to obtain the optimization results, and the smelting operation of the current stage is executed according to the optimization results.

2. The method according to claim 1, characterized in that, The mapping of the final chemical composition requirement of the target steel grade to the phased target composition constraint range of each smelting stage of the electric arc furnace includes: The phased target component constraint range changes dynamically according to different smelting stages, and the phased target component constraint range of the early smelting stage is wider than that of the later smelting stage.

3. The method according to claim 1, characterized in that, Before obtaining the multi-objective optimization model by weighting and characterizing the stage steel composition deviation model, stage smelting cost model, stage carbon emission model, and stage smelting duration model, the method further includes: A phased smelting cost model is constructed based on the amount of smelting materials added and the current electricity price. in, For the first Unit quantity of stage smelting cost; For the first Phase 1 Amount of each raw material added; For materials The price; For the first The electrical energy required for this stage; This represents the electricity price for the current period.

4. The method according to claim 3, characterized in that, Before constructing the stage smelting cost model based on the amount of smelting materials added and the current electricity price, the method further includes: The initial batching scheme for each stage is generated based on the material characteristic information parameters and the staged target component constraint range; The initial amount of smelting materials to be added in the current stage is determined based on the initial batching plan for each stage.

5. The method according to claim 1, characterized in that, Before obtaining the multi-objective optimization model by weighting and characterizing the stage steel composition deviation model, stage smelting cost model, stage carbon emission model, and stage smelting duration model, the method further includes: A phased carbon emission model is constructed based on the carbon emissions from smelting materials and the carbon emissions from electricity consumption. in, For the first Phase-specific carbon emissions per unit; For the first Phase 1 Amount of each raw material added; It is the first Carbon emissions per unit of raw material; For the first The electrical energy required for this stage; The carbon emission factor of electricity is related to the electricity consumption period.

6. The method according to claim 1, characterized in that, The method further includes weighted characterization of the stage steel composition deviation model, stage smelting cost model, stage carbon emission model, and stage smelting duration model. Different weighting coefficients are used to weight and characterize the stage steel composition deviation model, stage smelting cost model, stage carbon emission model, and stage smelting duration model for different smelting stages.

7. The method according to claim 1, characterized in that, The multi-objective optimization model is solved using a Pareto optimal strategy.

8. A hydrogen-based DRI-scrap electric arc furnace intelligent dynamic batching device, characterized in that, The device includes: The acquisition module is used to acquire material characteristic information parameters of smelting materials, which include smelting raw materials and auxiliary raw materials, and the smelting raw materials include hydrogen-based DRI and mixed scrap steel. The mapping module is used to map the final chemical composition requirements of the target steel grade to the staged target composition constraint ranges corresponding to each element in each smelting stage. The detection module is used to detect the composition, temperature and internal parameters of the molten steel in the previous smelting stage of the electric arc furnace before the start of each smelting stage, and obtain the detection results. The first calculation module is used to input the detection results and the material characteristic information parameters into the stage material conservation model of the current smelting stage, predict the element content at the end of the current smelting stage, and calculate the element deviation data based on the element content and the stage target component constraint interval corresponding to the element. The second calculation module is used to input the detection results and the material characteristic information parameters into the stage energy balance model of the current smelting stage to calculate the energy deviation data. The characterization module is used to perform weighted characterization of the stage steel composition deviation model, the stage smelting cost model, the stage carbon emission model, and the stage smelting duration model to obtain a multi-objective optimization model. The optimization module is used to dynamically optimize the material addition amount and power supply parameters of the current stage based on the multi-objective optimization model, the element deviation data and the energy deviation data, obtain the optimization result, and execute the smelting operation of the current stage according to the optimization result.

9. An electronic device, characterized in that, The device includes a memory and a processor, wherein the memory stores a computer program that executes the hydrogen-based DRI-scrap electric arc furnace intelligent dynamic batching method as described in any one of claims 1 to 7 when the processor is running.

10. A computer-readable storage medium, characterized in that, It stores a computer program that, when run on a processor, executes the hydrogen-based DRI-scrap electric arc furnace intelligent dynamic batching method as described in any one of claims 1 to 7.

Images