Shaft furnace reduction process optimization method and device, storage medium and equipment

Abstract

The invention discloses a shaft furnace reduction process optimization method and device, a storage medium and equipment, and the method comprises the steps: firstly obtaining reduction process parameters of a target shaft furnace and to-be-reduced target iron ore data, and then inputting the reduction process parameters of the target shaft furnace into a pre-constructed shaft furnace reduction process prediction model, predicting the shaft furnace reduction process of the target iron ore data to obtain a prediction result; wherein the shaft furnace reduction process prediction model is a kinetic model obtained by training reduction process parameters of a sample shaft furnace and sample iron ore data on the basis of three-stage reduction reaction kinetics and coupling heat conduction and substance diffusion processes; and then, according to the prediction result, the reduction process parameters of the target shaft furnace are optimized, and the optimized reduction process parameters of the target shaft furnace are obtained and used for carrying out shaft furnace reduction treatment on the target iron ore data. Therefore, the shaft furnace reduction energy consumption in practical application can be reduced, and the stability of the shaft furnace reduction process is improved.

Description

Technical Field

[0001] The present application relates to the field of metallurgical technology, and in particular to a method, device, storage medium, and equipment for optimizing a shaft furnace reduction process. Background Art

[0002] Currently, in direct reduced iron (DRI) production, the reduction process in the shaft furnace is a key indicator for evaluating product quality. This process reflects the extent to which iron ore is reduced to metallic iron, directly impacting the efficiency and product quality of subsequent steelmaking processes. Therefore, accurately predicting the reduction performance in the shaft furnace is crucial for further optimizing the process.

[0003] However, existing methods for predicting the shaft furnace reduction process primarily rely on empirical formulas, statistical analysis models, and simulations, making them incapable of coping with complex and changing process conditions. A lack of systematic research into data anomaly handling, model migration capabilities, and real-time optimization results in poor model adaptability and an inability to meet the actual needs of industrial sites. This in turn prevents accurate predictions of shaft furnace reduction performance and, consequently, effective optimization of the shaft furnace reduction process. Summary of the Invention

[0004] The main purpose of the embodiments of the present application is to provide a method, device, storage medium and equipment for optimizing the shaft furnace reduction process, which can use a pre-built shaft furnace reduction process prediction model to accurately predict the reduction process in the shaft furnace, and use the obtained prediction results to provide effective data support for the shaft furnace reduction operation in actual applications, so as to effectively optimize the shaft furnace reduction process in actual applications, thereby reducing energy consumption and improving the stability of the shaft furnace reduction process.

[0005] The present application provides an optimization method for a shaft furnace reduction process, comprising:

[0006] Obtaining reduction process parameters of a target shaft furnace and data of a target iron ore to be reduced;

[0007] Inputting the reduction process parameters of the target shaft furnace into a pre-built shaft furnace reduction process prediction model, predicting the shaft furnace reduction process for the target iron ore data, and obtaining a prediction result; the shaft furnace reduction process prediction model is a kinetic model trained using the reduction process parameters of a sample shaft furnace and sample iron ore data based on three-stage reduction reaction kinetics coupled with heat conduction and material diffusion processes;

[0008] According to the prediction result, the reduction process parameters of the target shaft furnace are optimized to obtain the optimized reduction process parameters of the target shaft furnace, which are used to perform shaft furnace reduction processing on the target iron ore data.

[0009] In one possible implementation, the shaft furnace reduction process prediction model is constructed as follows:

[0010] Obtaining reduction process parameters of a sample shaft furnace and sample iron ore data;

[0011] Based on the three-stage reduction reaction kinetics and coupling the heat conduction and material diffusion processes, the reduction process parameters of the sample shaft furnace are used to describe the reduction process of the sample iron ore data from Fe2O3 to Fe3O4, Fe3O4 to FeO, and FeO to Fe. The gas-solid reaction kinetic equation is used to model each stage to obtain the shaft furnace reduction process prediction model.

[0012] In a possible implementation, the method further includes:

[0013] A deviation analysis algorithm is used to evaluate the accuracy and applicability of the prediction results output by the shaft furnace reduction process prediction model to obtain an evaluation result, and the evaluation result is used to verify the reliability of the shaft furnace reduction process prediction model to obtain a verified shaft furnace reduction process prediction model.

[0014] In one possible implementation, inputting the reduction process parameters of the target shaft furnace into a pre-built shaft furnace reduction process prediction model, predicting the shaft furnace reduction process for the target iron ore data, and obtaining a prediction result includes:

[0015] The reduction process parameters of the target shaft furnace are input into a pre-built shaft furnace reduction process prediction model to solve the differential equations for the target iron ore data in the shaft furnace reduction process; and the differential equations are used to predict the shaft furnace reduction process of the target iron ore data to obtain a prediction result.

[0016] In one possible implementation, the reduction process parameters of the target shaft furnace include gas flow rate, temperature, and feeding rate; and optimizing the reduction process parameters of the target shaft furnace based on the prediction results to obtain optimized reduction process parameters of the target shaft furnace for performing shaft furnace reduction processing on the target iron ore data includes:

[0017] Based on the prediction results, potential abnormal or metastable operating conditions are identified, and according to the potential abnormal or metastable operating conditions, the gas flow rate, temperature or material discharge rate is optimized to obtain an adjusted gas flow rate, temperature or material discharge rate, which is used to optimize the operating state of the target shaft furnace for shaft furnace reduction of the target iron ore data.

[0018] In a possible implementation, the reduction process parameters of the target shaft furnace include at least one of geometric parameters, operating parameters, gas composition, and reaction kinetic parameters.

[0019] In a possible implementation, the prediction result includes at least one of a metallization rate distribution cloud diagram in the height direction of the shaft furnace, a concentration distribution diagram of different gas components, a temperature distribution curve of the gas-solid phase, and a reaction rate variation diagram of each main reaction.

[0020] The present application also provides an optimization device for a shaft furnace reduction process, comprising:

[0021] A first acquisition unit is used to acquire reduction process parameters of a target shaft furnace and data of a target iron ore to be reduced;

[0022] a prediction unit, configured to input the reduction process parameters of the target shaft furnace into a pre-established shaft furnace reduction process prediction model, predict the shaft furnace reduction process for the target iron ore data, and obtain a prediction result; the shaft furnace reduction process prediction model is a kinetic model trained using the reduction process parameters of a sample shaft furnace and sample iron ore data based on three-stage reduction reaction kinetics coupled with heat conduction and material diffusion processes;

[0023] An optimization unit is used to optimize the reduction process parameters of the target shaft furnace according to the prediction result to obtain the optimized reduction process parameters of the target shaft furnace for performing shaft furnace reduction processing on the target iron ore data.

[0024] In a possible implementation, the apparatus further includes:

[0025] A second acquisition unit is used to acquire reduction process parameters of the sample shaft furnace and sample iron ore data;

[0026] The modeling unit is used to describe the reduction process of the sample iron ore data from Fe2O3 to Fe3O4, Fe3O4 to FeO, and FeO to Fe based on the three-stage reduction reaction kinetics and coupled heat conduction and material diffusion processes, using the reduction process parameters of the sample shaft furnace, and adopting gas-solid reaction kinetic equations to model each stage to obtain a prediction model of the shaft furnace reduction process.

[0027] In a possible implementation, the apparatus further includes:

[0028] The verification unit is used to use a deviation analysis algorithm to evaluate the accuracy and applicability of the prediction results output by the shaft furnace reduction process prediction model to obtain an evaluation result, and use the evaluation result to verify the reliability of the shaft furnace reduction process prediction model to obtain a verified shaft furnace reduction process prediction model.

[0029] In one possible implementation, the prediction unit is specifically configured to:

[0030] The reduction process parameters of the target shaft furnace are input into a pre-built shaft furnace reduction process prediction model to solve the differential equations for the target iron ore data in the shaft furnace reduction process; and the differential equations are used to predict the shaft furnace reduction process of the target iron ore data to obtain a prediction result.

[0031] In one possible implementation, the reduction process parameters of the target shaft furnace include gas flow rate, temperature, and material feeding rate; and the optimization unit is specifically configured to:

[0032] Based on the prediction results, potential abnormal or metastable operating conditions are identified, and according to the potential abnormal or metastable operating conditions, the gas flow rate, temperature or material discharge rate is optimized to obtain an adjusted gas flow rate, temperature or material discharge rate, which is used to optimize the operating state of the target shaft furnace for shaft furnace reduction of the target iron ore data.

[0033] In a possible implementation, the reduction process parameters of the target shaft furnace include at least one of geometric parameters, operating parameters, gas composition, and reaction kinetic parameters.

[0034] In a possible implementation, the prediction result includes at least one of a metallization rate distribution cloud diagram in the height direction of the shaft furnace, a concentration distribution diagram of different gas components, a temperature distribution curve of the gas-solid phase, and a reaction rate variation diagram of each main reaction.

[0035] The embodiment of the present application also provides an optimization device for a shaft furnace reduction process, comprising: a processor, a memory, and a system bus;

[0036] The processor and the memory are connected via the system bus;

[0037] The memory is used to store one or more programs, wherein the one or more programs include instructions, and when the instructions are executed by the processor, the processor executes any one of the implementations of the above-mentioned method for optimizing the shaft furnace reduction process.

[0038] An embodiment of the present application further provides a computer-readable storage medium storing instructions. When the instructions are executed on a terminal device, the terminal device executes any one of the above-mentioned methods for optimizing the shaft furnace reduction process.

[0039] An embodiment of the present application further provides a computer program product, which, when executed on a terminal device, enables the terminal device to execute any one of the implementations of the above-mentioned method for optimizing the shaft furnace reduction process.

[0040] An embodiment of the present application provides a method, device, storage medium, and equipment for optimizing a shaft furnace reduction process. The method first obtains reduction process parameters of a target shaft furnace and target iron ore data to be reduced, then inputs the reduction process parameters of the target shaft furnace into a pre-constructed shaft furnace reduction process prediction model, and predicts the shaft furnace reduction process of the target iron ore data to obtain a prediction result. The shaft furnace reduction process prediction model is a kinetic model trained using the reduction process parameters of a sample shaft furnace and sample iron ore data based on three-stage reduction reaction kinetics and coupled with heat conduction and material diffusion processes. Then, based on the prediction result, the reduction process parameters of the target shaft furnace are optimized to obtain the optimized reduction process parameters of the target shaft furnace, which are used to perform shaft furnace reduction processing on the target iron ore data.

[0041] It can be seen that compared with traditional prediction methods that rely on empirical formulas, statistical analysis models, and simulations, the present application is first based on the three-stage reduction reaction kinetics and coupled with the heat conduction and material diffusion processes, and uses the reduction process parameters of the sample vertical furnace and the sample iron ore data for training to obtain a vertical furnace reduction process prediction model with higher prediction accuracy. Therefore, when using the vertical furnace reduction process prediction model to predict the vertical furnace reduction process of the target iron ore data, the accuracy and efficiency of the prediction results can be effectively improved, and thus effective data support can be provided for the vertical furnace reduction operation in actual applications, the vertical furnace reduction process in actual applications can be optimized, energy consumption can be reduced, and the stability of the vertical furnace reduction process can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0043] Figure 1 A schematic flow chart of a method for optimizing a shaft furnace reduction process provided in an embodiment of the present application;

[0044] Figure 2 This is an example diagram of the changes in volume fractions of several gases at different heights in a shaft furnace in some prediction results of the model provided in an embodiment of the present application;

[0045] Figure 3 An example diagram of the overall prediction process of the shaft furnace reduction process provided in an embodiment of the present application;

[0046] Figure 4 A schematic diagram of the composition of an optimization device for a shaft furnace reduction process provided in an embodiment of the present application. DETAILED DESCRIPTION

[0047] In the production of direct reduced iron in the metallurgical field, the reduction process of the vertical furnace process is the core link, which directly affects production efficiency, resource utilization, product quality and energy consumption, and is the key to determining the overall process economy and sustainability.

[0048] Currently, existing prediction methods for shaft furnace reduction processes rely primarily on three approaches: (1) Empirical formulas: These methods are based on empirical formulas but cannot effectively handle complex process dynamics. (2) Traditional numerical models: These methods, such as those based on statistical analysis, have poor adaptability to nonlinear parameters. (3) Simulation: Although highly accurate, these methods have limited real-time performance and applicability, making them difficult to deploy on industrial sites.

[0049] However, because traditional shaft furnace reduction process prediction methods primarily rely on empirical formulas, statistical analysis models, and simulation, they struggle to cope with complex and changing process conditions. A lack of systematic research into data anomaly handling, model migration capabilities, and real-time optimization results in poor model adaptability and an inability to meet the actual needs of industrial sites. This in turn prevents accurate predictions of shaft furnace reduction performance and, consequently, effective optimization of the shaft furnace reduction process.

[0050] To address the above-mentioned defects, the present application provides a method for optimizing the shaft furnace reduction process. First, the reduction process parameters of the target shaft furnace and the target iron ore data to be reduced are obtained. Then, the reduction process parameters of the target shaft furnace are input into a pre-constructed shaft furnace reduction process prediction model. The shaft furnace reduction process is predicted for the target iron ore data to obtain a prediction result. The shaft furnace reduction process prediction model is a kinetic model obtained by training the reduction process parameters of a sample shaft furnace and the sample iron ore data based on the three-stage reduction reaction kinetics and coupling the heat conduction and material diffusion processes. Then, according to the prediction result, the reduction process parameters of the target shaft furnace are optimized to obtain the optimized reduction process parameters of the target shaft furnace, which are used to perform shaft furnace reduction processing on the target iron ore data.

[0051] It can be seen that compared with traditional prediction methods that rely on empirical formulas, statistical analysis models, and simulations, the present application is first based on the three-stage reduction reaction kinetics and coupled with the heat conduction and material diffusion processes, and uses the reduction process parameters of the sample vertical furnace and the sample iron ore data for training to obtain a vertical furnace reduction process prediction model with higher prediction accuracy. Therefore, when using the vertical furnace reduction process prediction model to predict the vertical furnace reduction process of the target iron ore data, the accuracy and efficiency of the prediction results can be effectively improved, and thus effective data support can be provided for the vertical furnace reduction operation in actual applications, the vertical furnace reduction process in actual applications can be optimized, energy consumption can be reduced, and the stability of the vertical furnace reduction process can be improved.

[0052] To make the purpose, technical solutions, and advantages of the embodiments of this application more clear, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0053] First embodiment

[0054] See also Figure 1 , is a schematic flow chart of a method for optimizing a shaft furnace reduction process provided in this embodiment, the method comprising the following steps:

[0055] S101: Obtain reduction process parameters of a target shaft furnace and target iron ore data to be reduced.

[0056] In this embodiment, any shaft furnace requiring reduction process optimization is defined as a target shaft furnace. The iron ore data requiring reduction using the target shaft furnace is defined as the target iron ore data to be reduced. To improve the reduction efficiency of the target shaft furnace for the target iron ore data in practical applications, the reduction process parameters of the target shaft furnace and the target iron ore data to be reduced are first obtained to execute subsequent steps S102 and S103.

[0057] The present application does not limit the specific content or acquisition method of the target shaft furnace reduction process parameters. In one optional implementation, the target shaft furnace reduction process parameters may include, but are not limited to, at least one of geometric parameters (e.g., reactor diameter, reactor height, particle radius), operating parameters (e.g., gas flow rate, system pressure, gas inlet temperature, solid inlet temperature, iron yield), gas composition (e.g., volume fraction of H₂, CO, H₂O, CO₂, CH₄, N₂), reaction kinetic parameters (e.g., prefactor, activation energy, diffusion coefficient), and other parameters (e.g., particle density, heat transfer coefficient). Another optional implementation, taking the example of integrating the shaft furnace reduction process prediction model into a visualization software interface, allows a user to input the target shaft furnace reduction process parameters into the visualization software interface to obtain the reduction process parameters (e.g., geometric parameters, operating parameters, gas composition, reaction kinetic parameters, and other parameters) required for shaft furnace reduction of the target iron ore data. Furthermore, the user may choose to use the system default parameters or flexibly adjust the input content based on actual operating conditions.

[0058] S102: Input the reduction process parameters of the target shaft furnace into a pre-built shaft furnace reduction process prediction model, predict the shaft furnace reduction process of the target iron ore data, and obtain a prediction result; wherein, the shaft furnace reduction process prediction model is a kinetic model obtained by training using the reduction process parameters of the sample shaft furnace and the sample iron ore data based on the three-stage reduction reaction kinetics and coupling the heat conduction and material diffusion processes.

[0059] In this embodiment, after obtaining the reduction process parameters of the target shaft furnace and the target iron ore data to be reduced in step S101, in order to effectively improve the shaft furnace reduction effect on the target iron ore data, the reduction process parameters of the target shaft furnace can be further input into a pre-established shaft furnace reduction process prediction model to accurately predict the shaft furnace reduction process of the target iron ore data. The prediction results are used to execute the subsequent step S103, optimize the reduction process parameters of the target shaft furnace, and then use the optimized reduction process parameters of the target shaft furnace to perform more efficient shaft furnace reduction processing on the target iron ore data.

[0060] Among them, this application does not limit the specific content of the prediction results. An optional implementation method is that the prediction results may include but are not limited to a metallization rate distribution cloud map in the height direction of the vertical furnace, a concentration distribution map of different gas components, a temperature distribution curve of the gas-solid phase, at least one of the reaction rate change maps of each major reaction, etc.

[0061] It should be noted that in recent years, with the development of kinetic modeling technology, especially the widespread application of multi-physics field coupling models in nonlinear modeling, its advantages in industrial forecasting have gradually become apparent. Some studies have attempted to apply kinetic models to the prediction of metallurgical process parameters. Building on this, to further improve the efficiency and accuracy of predictions for the shaft furnace reduction process, this application pre-collects a large number of sample shaft furnace reduction process parameters and sample iron ore data. Based on the three-stage reduction reaction kinetics and coupled with heat conduction and material diffusion processes, the model is trained, thereby constructing a shaft furnace reduction process prediction model with better prediction results.

[0062] On this basis, an optional implementation method is that the specific implementation process of "inputting the reduction process parameters of the target shaft furnace into a pre-built shaft furnace reduction process prediction model, predicting the shaft furnace reduction process of the target iron ore data, and obtaining a prediction result" in this step S102 may include: inputting the reduction process parameters of the target shaft furnace into a pre-built shaft furnace reduction process prediction model, solving a group of differential equations for the shaft furnace reduction process of the target iron ore data; and using the group of differential equations to predict the shaft furnace reduction process of the target iron ore data to obtain a prediction result.

[0063] In this implementation, the reduction process parameters of the target shaft furnace are input into a pre-built shaft furnace reduction process prediction model. The model then outputs the spatial and temporal evolution of each state variable by solving a set of ordinary differential equations involving reaction, heat transfer, and mass transfer. This allows the model to dynamically characterize the reduction degree, gas composition, temperature, and heat transfer process inside the shaft furnace.

[0064] Next, this embodiment will respectively introduce in detail the training process and verification and update process of the shaft furnace reduction process prediction model. An optional implementation method is that the construction method of the shaft furnace reduction process prediction model includes: first, the reduction process parameters and sample iron ore data of the sample shaft furnace can be obtained; then, based on the three-stage reduction reaction kinetics and coupling the heat conduction and material diffusion processes, the reduction process parameters of the sample shaft furnace are used to describe the reduction process of the sample iron ore data from Fe2O3 to Fe3O4, Fe3O4 to FeO, and FeO to Fe, respectively, and the gas-solid reaction kinetic equation is used to model each stage to obtain the shaft furnace reduction process prediction model.

[0065] In this implementation, the three-stage reduction reaction can be expressed as follows:

[0066] 3Fe2O3+H2→2Fe3O4+H2O (1)

[0067] Fe3O4+H2→3FeO+H2O (2)

[0068] FeO+H2→Fe+H2O (3)

[0069] 3Fe2O3+CO→2Fe3O4+CO2 (4)

[0070] Fe3O4+CO→3FeO+CO2 (5)

[0071] FeO+CO→Fe+CO2 (6)

[0072] Simultaneously coupled with the water-gas shift reaction and methane steam reforming reaction To more fully describe the gas-solid interactions in the shaft furnace.

[0073] Carburizing reactions (such as methane decomposition and CO disproportionation) generate solid carbon on the surface of metallic iron, affecting the composition of the final product.

[0074] Assuming that the volume of the iron oxide particles remains unchanged during the reduction process, and the reaction front advances layer by layer from the outside to the inside, the degree of reduction at each stage can be calculated using the following formula:

[0075]

[0076] In addition, the vertical furnace reduction process prediction model also includes gas and solid mass balance equations, reaction rate constants, etc., which are not listed here one by one.

[0077] Furthermore, this application does not limit the specific network structure of the shaft furnace reduction process prediction model, and it can be selected and set according to actual conditions. In a preferred implementation, the specific components of the pre-built shaft furnace reduction process prediction model may include but are not limited to the following parts:

[0078] 1. Core Physics Coupling Module: A one-dimensional model is established along the shaft height (z-axis), assuming radial uniformity and neglecting lateral flow and mass transfer. This describes the reduction of iron oxide particles and tracks the step-by-step reaction of Fe2O3→Fe3O4→FeO→Fe through three reaction fronts (X1, X2, and X3).

[0079] 2. Key equations and solution methods: including mass balance equation, energy balance equation, momentum balance (Ergun equation), etc.

[0080] 3. Numerical solution method: Convert the partial differential equation (PDE) into a system of ordinary differential equations (ODE) for solution.

[0081] 4. Setting boundary conditions and initial conditions.

[0082] 5. Key sub-models and simplifying assumptions.

[0083] Furthermore, an adaptive optimization mechanism can be employed during model training to iteratively train the model by regularly collecting shaft furnace operating data, thereby improving the model's accuracy in predicting reduction behavior under different operating conditions. Shaft furnace operating data should be regularly collected, such as temperature data at different shaft furnace heights, product FeO residual rate or metallization rate test results, and gas flow and pressure data.

[0084] The model's input data (i.e., reduction process parameters for the sample shaft furnace) can include, but are not limited to, geometric parameters (reactor diameter, reactor height, and pellet radius); operating parameters (gas flow rate, system pressure, gas inlet temperature, solid inlet temperature, and iron yield); gas composition (volume fractions of H₂, CO, H₂O, CO₂, CH₄, and N₂); reaction kinetics (pre-exponential factor, activation energy, and diffusion coefficient); and other parameters (pellet density and heat transfer coefficient). Based on these process parameter inputs, the model can predict key indicators within the sample shaft furnace in real time, including reduction degree, gas composition, and temperature distribution, as output from the model simulation.

[0085] The prediction results output by the model simulation (such as the degree of reduction, gas composition, and temperature distribution at different heights) are then compared with the measured shaft furnace reduction data corresponding to industrial field sample iron ore data. Deviation analysis algorithms (such as maximum relative error and mean absolute error) are used to evaluate the accuracy and applicability of the prediction results output by the shaft furnace reduction process prediction model. The evaluation results are then used to verify the reliability of the shaft furnace reduction process prediction model, resulting in a verified shaft furnace reduction process prediction model. The goal of the evaluation can be to ensure that the model's prediction error under key operating conditions is within an acceptable range (e.g., ±5%), thereby verifying the model's reliability for engineering prediction and process analysis.

[0086] For example: Assume that the input data of the model is as follows:

[0087] The specific geometric parameters are: reactor diameter: 426 cm; reaction zone height: 975 cm; iron ore particle radius: 0.55 cm.

[0088] The specific operating parameters are: Gas flow: 53863Nm 3 / h; system pressure: 1.4atm; gas inlet temperature: 1230K; solid inlet temperature: 300K; iron output: 26.4t / h.

[0089] The gas composition (volume fraction) is specifically H2: 52.58%; CO: 29.97%; H2O: 4.65%; CO2: 4.80%; CH4+N2: 8.10%.

[0090] The specific reaction kinetic parameters are: H2 reduction reaction: pre-exponential factor: 0.114 cm / s; activation energy: 14700 cal / mol; diffusion coefficient: 1.467 cm2 / s.

[0091] The CO reduction reaction is as follows: pre-exponential factor: 0.283 cm / s; activation energy: 28100 cal / mol; diffusion coefficient: 1.276 cm 2 / s.

[0092] Other parameters: Particle density: 0.64pellets / cm 3 ;Heat transfer coefficient: 0.0001cal / (cm 2 ·s·K).

[0093] Then the example diagram of the volume fraction change of several gases at different heights in the vertical furnace in the partial prediction results output by the model can be shown as follows: Figure 2 shown.

[0094] The predicted results of the model simulation output are then compared with the measured vertical furnace reduction data (mainly the comparison of outlet gas composition and metallization rate), as shown in Table 1 below:

[0095] Measured vertical furnace restoration data Model prediction results error(%) Outlet gas composition <![CDATA[H2]]> 37.0 38.5 4.1 CO 18.9 18.2 3.7 <![CDATA[H2O]]> 21.2 20.2 4.7 <![CDATA[CO2]]> 14.3 14.1 1.4 <![CDATA[CH4+N2]]> 8.6 9.0 4.7 Metallization rate 93 95.2 2.4

[0096] Table 1

[0097] Thus, it can be verified from Table 1 above that the errors of the model simulation predictions are all within a reasonable range (such as ±5%), thereby proving the accuracy of the model prediction results.

[0098] S103: Optimizing the reduction process parameters of the target shaft furnace according to the prediction result to obtain the optimized reduction process parameters of the target shaft furnace, which are used to perform shaft furnace reduction processing on the target iron ore data.

[0099] In this embodiment, in step S102, the target shaft furnace reduction process parameters (such as gas flow rate, temperature, and material discharge rate) are input into a pre-built shaft furnace reduction process prediction model. The shaft furnace reduction process is predicted for the target iron ore data. After obtaining prediction results (including key variables such as the degree of reduction within the shaft furnace, gas composition, and temperature distribution), the target shaft furnace reduction process parameters can be optimized based on the prediction results to obtain optimized target shaft furnace reduction process parameters for use in shaft furnace reduction of the target iron ore data. For example, an operator or other machine can identify potential abnormal or metastable operating conditions based on the prediction results. Based on these potential abnormal or metastable operating conditions, the operator can then optimize process parameters such as gas flow rate, temperature, or material discharge rate to obtain adjusted process parameters such as gas flow rate, temperature, or material discharge rate, which are then used to optimize the operating state of the target shaft furnace for shaft furnace reduction of the target iron ore data. This eliminates the need for real-time adaptive control algorithms and improves product consistency and system stability through a closed-loop optimization path of "prediction - comparison - (human or machine) adjustment."

[0100] Alternatively, a rule-based optimization algorithm can be used to optimize the reduction process parameters (such as reducing gas flow rate and feed rate) of the target shaft furnace to improve production stability and quality consistency. For example, if the model predicts that the temperature in a certain section is too low, resulting in a decrease in the Fe2O3→Fe conversion efficiency, the reducing gas flow rate or preheating temperature in that section can be increased; if FeO is still present in large quantities at the middle height, the residence time of the ore in that section can be extended, that is, the overall feed rate can be reduced; if the CO2 concentration in the gas is too high, indicating that the reducing agent is depleted, the gas reforming reaction temperature or concentration ratio can be increased.

[0101] Furthermore, it should be noted that after the pre-built vertical furnace reduction process prediction model is deployed in an actual industrial system, the vertical furnace reduction process of the target iron ore data is predicted using the pre-built vertical furnace reduction process prediction model to obtain prediction results of core indicators such as the degree of reduction, gas composition and temperature distribution in the vertical furnace. The prediction time interval of the model is usually only a few seconds (such as 3 seconds), and the prediction accuracy is not less than 95%. In this way, based on the more accurate prediction results obtained, auxiliary operators or other machinery and equipment can evaluate the current working conditions and propose process parameter adjustment suggestions, such as gas flow, temperature distribution or feeding rate, so as to optimize the reduction process and improve product quality and energy efficiency.

[0102] In addition, it should be noted that the present application does not limit the deployment method of the pre-built vertical furnace reduction process prediction model. For example, it can be integrated into a visual software interface, so that users can input or modify process parameters through the interface to simulate and predict the reduction process of iron ore in the vertical furnace. Taking the simulation of iron ore reduction under a certain working condition as an example, the user can input the following parameters required by the model in the interface, namely geometric parameters, operating parameters, gas composition, reaction kinetic parameters, other parameters, etc. Alternatively, the user can also choose to use the system default parameters, or flexibly adjust the above input content according to the actual working conditions. In this way, after the model is run, the program can automatically solve the differential equations in the reduction process and output prediction results, including but not limited to the metallization rate distribution cloud map in the height direction of the vertical furnace, the concentration distribution map of different gas components, the temperature distribution curve of the gas-solid phase, the reaction rate change map of each major reaction, etc. In addition, the model can complete the calculation within a few seconds to tens of seconds, and the output results can be used to judge the reaction state in the furnace and assist in process analysis and adjustment decisions. Among them, the overall prediction process of the vertical furnace reduction process can be as follows Figure 3 As shown, by using the pre-built shaft furnace reduction process prediction model and collecting data sets to predict the shaft furnace reduction process, the prediction accuracy of the reduction process can be improved and quality fluctuations can be reduced; data support can be provided for shaft furnace operation, reducing energy consumption; and intelligent production management can be achieved to improve process stability.

[0103] It can be understood that the application scenarios of the vertical furnace reduction process prediction model constructed in this application are relatively rich, which may include but are not limited to: (1) Iron and steel smelting industry. Specifically, the vertical furnace reduction process prediction model constructed in this application can be widely used in the vertical furnace reduction process in the iron and steel smelting industry to assist in optimizing process parameters, reducing energy consumption, and improving product quality. (2) Direct reduced iron production. Specifically, in direct reduced iron production, the vertical furnace reduction process prediction model constructed in this application can effectively predict and optimize the reduction process, improve reduction efficiency, and reduce production costs. (3) Intelligent factory. Specifically, the vertical furnace reduction process prediction model constructed in this application can be applied to intelligent factory to realize the automated control and intelligent management of the vertical furnace reduction process, reduce manual intervention, and improve production efficiency.

[0104] Thus, this application uses the three-stage reduction reaction kinetics and coupled heat conduction and material diffusion processes to train a shaft furnace reduction process prediction model using sample shaft furnace reduction process parameters and sample iron ore data. This model then incorporates key factors such as temperature field distribution, gas composition changes, and ore reduction degree. Using kinetic parameters and heat transfer characteristics, a mathematical model is established to dynamically simulate and analyze the reduction process within the shaft furnace. The simulation results can assist in evaluating the impact of process parameters on the smelting process, providing theoretical support for optimizing shaft furnace operation strategies and improving process stability and production efficiency.

[0105] In summary, the present embodiment provides a method for optimizing a shaft furnace reduction process. The method first obtains the reduction process parameters of a target shaft furnace and the target iron ore data to be reduced. The reduction process parameters of the target shaft furnace are then input into a pre-constructed shaft furnace reduction process prediction model. The shaft furnace reduction process is predicted for the target iron ore data to obtain a prediction result. The shaft furnace reduction process prediction model is a kinetic model trained using the reduction process parameters of a sample shaft furnace and the sample iron ore data based on the three-stage reduction reaction kinetics and coupled heat conduction and material diffusion processes. The model is then optimized based on the prediction result to obtain the optimized reduction process parameters of the target shaft furnace, which are used to perform shaft furnace reduction on the target iron ore data.

[0106] It can be seen that compared with traditional prediction methods that rely on empirical formulas, statistical analysis models, and simulations, the present application is first based on the three-stage reduction reaction kinetics and coupled with the heat conduction and material diffusion processes, and uses the reduction process parameters of the sample vertical furnace and the sample iron ore data for training to obtain a vertical furnace reduction process prediction model with higher prediction accuracy. Therefore, when using the vertical furnace reduction process prediction model to predict the vertical furnace reduction process of the target iron ore data, the accuracy and efficiency of the prediction results can be effectively improved, and thus effective data support can be provided for the vertical furnace reduction operation in actual applications, the vertical furnace reduction process in actual applications can be optimized, energy consumption can be reduced, and the stability of the vertical furnace reduction process can be improved.

[0107] Second embodiment

[0108] This embodiment will introduce an optimization device for a shaft furnace reduction process. For related content, please refer to the above method embodiment.

[0109] See also Figure 4 , is a schematic diagram of the composition of an optimization device for a shaft furnace reduction process provided in this embodiment, the device 400 includes:

[0110] The first acquisition unit 401 is used to acquire the reduction process parameters of the target shaft furnace and the target iron ore data to be reduced;

[0111] Prediction unit 402 is configured to input the reduction process parameters of the target shaft furnace into a pre-established shaft furnace reduction process prediction model, predict the shaft furnace reduction process for the target iron ore data, and obtain a prediction result; the shaft furnace reduction process prediction model is a kinetic model trained using the reduction process parameters of a sample shaft furnace and sample iron ore data based on three-stage reduction reaction kinetics coupled with heat conduction and material diffusion processes;

[0112] The optimization unit 403 is configured to optimize the reduction process parameters of the target shaft furnace according to the prediction result to obtain the optimized reduction process parameters of the target shaft furnace for performing shaft furnace reduction processing on the target iron ore data.

[0113] In one implementation of this embodiment, the apparatus further includes:

[0114] A second acquisition unit is used to acquire reduction process parameters of the sample shaft furnace and sample iron ore data;

[0115] The modeling unit is used to describe the reduction process of the sample iron ore data from Fe2O3 to Fe3O4, Fe3O4 to FeO, and FeO to Fe based on the three-stage reduction reaction kinetics and coupled heat conduction and material diffusion processes, using the reduction process parameters of the sample shaft furnace, and adopting gas-solid reaction kinetic equations to model each stage to obtain a prediction model of the shaft furnace reduction process.

[0116] In one implementation of this embodiment, the apparatus further includes:

[0117] The verification unit is used to use a deviation analysis algorithm to evaluate the accuracy and applicability of the prediction results output by the shaft furnace reduction process prediction model to obtain an evaluation result, and use the evaluation result to verify the reliability of the shaft furnace reduction process prediction model to obtain a verified shaft furnace reduction process prediction model.

[0118] In one implementation of this embodiment, the prediction unit 402 is specifically configured to:

[0119] The reduction process parameters of the target shaft furnace are input into a pre-built shaft furnace reduction process prediction model to solve the differential equations for the target iron ore data in the shaft furnace reduction process; and the differential equations are used to predict the shaft furnace reduction process of the target iron ore data to obtain a prediction result.

[0120] In one implementation of this embodiment, the reduction process parameters of the target shaft furnace include gas flow rate, temperature, and material feeding rate; the optimization unit 403 is specifically configured to:

[0121] Based on the prediction results, potential abnormal or metastable operating conditions are identified, and according to the potential abnormal or metastable operating conditions, the gas flow rate, temperature or material discharge rate is optimized to obtain an adjusted gas flow rate, temperature or material discharge rate, which is used to optimize the operating state of the target shaft furnace for shaft furnace reduction of the target iron ore data.

[0122] In an implementation of this embodiment, the reduction process parameters of the target shaft furnace include at least one of geometric parameters, operating parameters, gas composition, and reaction kinetic parameters.

[0123] In one implementation of this embodiment, the prediction results include at least one of a metallization rate distribution cloud diagram in the height direction of the shaft furnace, a concentration distribution diagram of different gas components, a temperature distribution curve of the gas-solid phase, and a reaction rate change diagram of each main reaction.

[0124] Furthermore, an embodiment of the present application also provides an optimization device for a shaft furnace reduction process, comprising: a processor, a memory, and a system bus;

[0125] The processor and the memory are connected via the system bus;

[0126] The memory is used to store one or more programs, wherein the one or more programs include instructions, and when the instructions are executed by the processor, the processor executes any one of the implementation methods of the above-mentioned method for optimizing the shaft furnace reduction process.

[0127] Furthermore, an embodiment of the present application also provides a computer-readable storage medium, which stores instructions. When the instructions are executed on a terminal device, the terminal device executes any implementation method of the above-mentioned method for optimizing the shaft furnace reduction process.

[0128] Furthermore, an embodiment of the present application also provides a computer program product, which, when executed on a terminal device, enables the terminal device to execute any one of the implementation methods of the above-mentioned method for optimizing the shaft furnace reduction process.

[0129] Through the description of the above embodiments, it can be seen that those skilled in the art can clearly understand that all or part of the steps in the above-mentioned embodiment methods can be implemented by means of software plus the necessary general hardware platform. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which can be stored in a storage medium such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network communication device such as a media gateway, etc.) to execute the methods described in each embodiment of the present application or certain parts of the embodiments.

[0130] It should be noted that the various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. Reference can be made to the common and similar parts between the various embodiments. For the devices disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the description is relatively simple, and the relevant parts can be referred to the description of the methods.

[0131] It should also be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of additional identical elements in the process, method, article, or device comprising the element.

[0132] The above description of the disclosed embodiments is intended to enable one skilled in the art to implement or use the present application. Various modifications to these embodiments will be readily apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application is not limited to the embodiments shown herein, but is intended to conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for optimizing a shaft furnace reduction process, characterized in that: include: Obtaining reduction process parameters of a target shaft furnace and data of a target iron ore to be reduced; Inputting the reduction process parameters of the target shaft furnace into a pre-built shaft furnace reduction process prediction model, predicting the shaft furnace reduction process for the target iron ore data, and obtaining a prediction result; The shaft furnace reduction process prediction model is a kinetic model obtained by training based on the three-stage reduction reaction kinetics and coupling the heat conduction and material diffusion processes using the reduction process parameters of the sample shaft furnace and the sample iron ore data; According to the prediction result, the reduction process parameters of the target shaft furnace are optimized to obtain the optimized reduction process parameters of the target shaft furnace, which are used to perform shaft furnace reduction processing on the target iron ore data.

2. The method according to claim 1, characterized in that The shaft furnace reduction process prediction model is constructed as follows: Obtaining reduction process parameters of a sample shaft furnace and sample iron ore data; Based on the three-stage reduction reaction kinetics and coupling the heat conduction and material diffusion processes, the reduction process parameters of the sample shaft furnace are used to describe the reduction process of the sample iron ore data from Fe2O3 to Fe3O4, Fe3O4 to FeO, and FeO to Fe. The gas-solid reaction kinetic equation is used to model each stage to obtain the shaft furnace reduction process prediction model.

3. The method according to claim 2, characterized in that The method further comprises: A deviation analysis algorithm is used to evaluate the accuracy and applicability of the prediction results output by the shaft furnace reduction process prediction model to obtain an evaluation result, and the evaluation result is used to verify the reliability of the shaft furnace reduction process prediction model to obtain a verified shaft furnace reduction process prediction model.

4. The method according to claim 1, wherein The step of inputting the reduction process parameters of the target shaft furnace into a pre-built shaft furnace reduction process prediction model, predicting the shaft furnace reduction process for the target iron ore data, and obtaining a prediction result includes: The reduction process parameters of the target shaft furnace are input into a pre-built shaft furnace reduction process prediction model to solve the differential equations for the target iron ore data in the shaft furnace reduction process; and the differential equations are used to predict the shaft furnace reduction process of the target iron ore data to obtain a prediction result.

5. The method according to claims 1-4, characterized in that The reduction process parameters of the target shaft furnace include gas flow rate, temperature, and feeding rate; optimizing the reduction process parameters of the target shaft furnace based on the prediction results to obtain optimized reduction process parameters of the target shaft furnace for performing shaft furnace reduction processing on the target iron ore data, including: Based on the prediction results, potential abnormal or metastable operating conditions are identified, and according to the potential abnormal or metastable operating conditions, the gas flow rate, temperature or material discharge rate is optimized to obtain an adjusted gas flow rate, temperature or material discharge rate, which is used to optimize the operating state of the target shaft furnace for shaft furnace reduction of the target iron ore data.

6. The method according to claim 1, wherein The reduction process parameters of the target shaft furnace include at least one of geometric parameters, operating parameters, gas composition, and reaction kinetic parameters.

7. The method according to any one of claims 1 to 6, characterized in that The prediction results include at least one of a metallization rate distribution cloud diagram in the height direction of the shaft furnace, a concentration distribution diagram of different gas components, a temperature distribution curve of the gas-solid phase, and a reaction rate variation diagram of each main reaction.

8. An optimization device for a shaft furnace reduction process, characterized in that: include: A first acquisition unit is used to acquire reduction process parameters of a target shaft furnace and data of a target iron ore to be reduced; a prediction unit, configured to input the reduction process parameters of the target shaft furnace into a pre-established shaft furnace reduction process prediction model, predict the shaft furnace reduction process for the target iron ore data, and obtain a prediction result; the shaft furnace reduction process prediction model is a kinetic model trained using the reduction process parameters of a sample shaft furnace and sample iron ore data based on three-stage reduction reaction kinetics coupled with heat conduction and material diffusion processes; An optimization unit is used to optimize the reduction process parameters of the target shaft furnace according to the prediction result to obtain the optimized reduction process parameters of the target shaft furnace for performing shaft furnace reduction processing on the target iron ore data.

9. An optimization device for a shaft furnace reduction process, characterized in that: include: Processor, memory, system bus; The processor and the memory are connected via the system bus; The memory is configured to store one or more programs, wherein the one or more programs include instructions, and when the instructions are executed by the processor, the processor is enabled to perform the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores instructions, and when the instructions are executed on a terminal device, the terminal device executes the method according to any one of claims 1 to 7.

Images