Blast furnace production process simulation and prediction method, equipment and storage medium

Abstract

The invention provides a blast furnace production process simulation and prediction method and device and a storage medium, and the method comprises the steps: obtaining the geometric and production data of a target blast furnace, building a detailed geometric model, carrying out the grid division, forming a background grid information table, recording the gas-solid two-phase state information, and carrying out the cleaning and fitting of the production data, thereby achieving the simulation and prediction of the blast furnace production process. The method comprises the following steps: setting boundary conditions for a model, calculating furnace charge flow characteristics in a furnace, updating related information in a background grid based on calculation results, initializing basic physical parameters of gas-solid phases, simulating flow, heat transfer and chemical reaction in a smelting process by utilizing a fluid mechanics equation set, and carrying out iterative calculation until convergence; the method further comprises the step of collecting production data in real time and inputting the production data into the simulation model so as to evaluate the current production state and predict the future production trend, and therefore the operation condition of the blast furnace is effectively monitored and optimized. The method is beneficial for improving the production efficiency and stability of the blast furnace.

Description

Technical Field

[0001] The present application relates to the fields of metallurgy and computer application, and specifically to a blast furnace production process simulation and prediction method, equipment and storage medium. Background Art

[0002] The blast furnace is the core equipment of the steel industry and one of the largest single reactors in the world. As a large vertical smelting furnace, the blast furnace plays a vital role in the steel production process. Its volume and capacity are huge, usually measured in cubic meters, with a height of tens of meters and a diameter of several meters. The design and construction of the blast furnace are very complex and need to withstand extreme conditions such as high temperature, high pressure, gas flow and chemical reaction. Due to the characteristics and importance of the blast furnace, the steel industry has been committed to improving the efficiency and stability of the blast furnace. However, there are still many challenges in the operation and maintenance of the blast furnace.

[0003] The blast furnace smelting process involves high temperature and high pressure, and has the characteristics of complex reaction mechanism, difficult measurement, and expensive industrial experiments. Blast furnace simulation technology is an important means to open the "black box" of blast furnace smelting and achieve low-carbon and intelligent ironmaking. Therefore, blast furnace full furnace simulation is hailed as the crown jewel of technology in the field of metallurgical simulation. However, due to the extremely complex reaction mechanism of the blast furnace, it has the disadvantages of extremely difficult model establishment and low computational efficiency. Summary of the invention

[0004] In view of the above-mentioned shortcomings of the prior art, the present invention provides a blast furnace production process simulation and prediction method, equipment and storage medium to solve the above-mentioned technical problems.

[0005] The present invention provides a method for simulating a blast furnace production process, the method comprising: obtaining geometric data and production data of a target blast furnace, the production data at least comprising charge parameters and reducing gas parameters; constructing a blast furnace geometric model based on the geometric data, and meshing the blast furnace geometric model to divide the blast furnace geometric space into a plurality of grids; deriving coordinate information of grids in a gas-solid overlapping region to form a background grid information table, the background grid information table comprising grid coordinate information and charge information and gas-solid two-phase state information associated with each grid; performing data cleaning and data fitting on the production data, and providing the blast furnace with a plurality of grids based on the cleaned and fitted data. The furnace model sets boundary conditions; calculates the charge flow information in the furnace, including charge velocity, charge flow trajectory and charge residence time; updates the charge related information in the background grid information table according to the calculated charge flow information; initializes the gas-solid two-phase temperature, concentration, velocity and pressure in the background grid information table; calculates the mass, momentum and energy source terms according to the gas-solid information in the background grid information table, solves the basic fluid mechanics equations of the gas and solid phases, and simulates the flow, heat transfer and chemical reaction in the blast furnace smelting process; updates the gas-solid two-phase state information in the background grid information table; determines whether the calculation results converge. If not, repeats the above calculation until convergence.

[0006] In one embodiment of the present invention, the production data includes: material distribution matrix, material distribution cycle, ore batch weight, coke batch weight, charge batch, composition, particle size, porosity, soft melting starting temperature and air supply data, wherein the air supply data at least includes coke ratio, coal ratio, oxygen enrichment, blast volume, blast humidity, blast temperature, oxygen enrichment temperature, coal powder carrier gas volume, coal powder carrier gas temperature, coal powder industrial analysis results, coal powder lower calorific value and coal powder combustion rate.

[0007] In one embodiment of the present invention, the fluid mechanics is basically the Navier-Stokes equations, and the finite volume method or the finite element method is used to solve the Navier-Stokes equations, and the turbulence model is combined to describe the gas-solid two-phase flow characteristics.

[0008] In one embodiment of the present invention, the determination of whether the calculation result is converged is performed by comparing the difference between the results of two consecutive iterations, and when the difference is less than a preset threshold, it is considered to be converged.

[0009] In one embodiment of the present invention, the method further includes: establishing a blast furnace simulation model for receiving real-time production data input, so as to predict the production status of the target blast furnace through the blast furnace simulation model and display data in different dimensions.

[0010] The present application provides a method for predicting a blast furnace production process, the method comprising: collecting real-time production data of a target blast furnace, and inputting the real-time production data into a blast furnace simulation model to obtain current smelting parameters of the target blast furnace, the current smelting parameters being used to characterize the current production status of the target blast furnace; calculating the current smelting parameters to obtain a changing trend of the current smelting parameters, so as to obtain a future production status of the target blast furnace based on the current production status and the changing trend, the future production status being used to characterize the prediction result of the production status of the target blast furnace.

[0011] In one embodiment of the present invention, the data under each dimension are displayed separately, including: decomposing the current smelting parameters into multiple single smelting parameters based on the gas-solid sub-model, and determining any single smelting parameter as the target smelting parameter; drawing a target visualization chart based on the target smelting parameters to display the current smelting status of the target smelting process, and the target smelting process is the smelting project corresponding to the target smelting parameters; traversing all parameter categories to visualize the entire smelting process of the target blast furnace.

[0012] In one embodiment of the present invention, after establishing a blast furnace simulation model for characterizing data of different dimensions, it also includes: collecting real-time production data of a target blast furnace and actual smelting parameters of the target blast furnace; inputting the real-time production data into the blast furnace simulation model to obtain predicted smelting parameters of the target blast furnace; comparing the predicted smelting parameters with the actual smelting parameters to obtain a deviation value between the predicted smelting parameters and the actual smelting parameters; if the deviation value is greater than or equal to a preset deviation threshold, the blast furnace simulation model is judged to be unqualified, and the blast furnace simulation model is retrained until the deviation value is less than the preset deviation threshold.

[0013] The present application provides an electronic device, which includes: one or more processors; a storage device for storing one or more programs, and when the one or more programs are executed by the one or more processors, the electronic device implements the blast furnace production process prediction method as described above.

[0014] The present application provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor of a computer, the computer is enabled to execute the blast furnace production process prediction method as described above.

[0015] The beneficial effects of the present invention are as follows: the blast furnace production process prediction method, device, equipment and storage medium of the present invention collect physical data and production data of the target blast furnace and construct a blast furnace geometric model, mesh the blast furnace geometric model and assign production parameters to each grid, set multiple empty areas and characterize the influence of charge on the flow of reducing gas in the furnace by changing the parameters of the porous medium, and calculate the influence of each data on the blast furnace production process respectively by multi-threaded parallel calculation, thereby decoupling the gas-solid production data, and performing phase coupling on the decoupled gas-solid data based on the source term, thereby establishing a blast furnace simulation model based on the grid, the charge flow information in the furnace and the data after phase coupling processing, so as to predict the production process of the blast furnace; by establishing a blast furnace geometric model, gas-solid decoupling, parallel calculation, and source term coupling, the solution complexity of the blast furnace production process prediction system is reduced.

[0016] In addition, the blast furnace production process prediction method proposed in this application models the blast furnace production process by collecting blast furnace parameters and production data, and reduces the computational difficulty in the blast furnace modeling process and improves the computational efficiency through data decoupling, thereby realizing the prediction of the blast furnace production process and improving the safety of the blast furnace production process; it also displays and monitors some important parameters in the blast furnace separately through visual display, so that relevant personnel can understand the blast furnace status more timely and accurately, thereby improving the safety of the blast furnace production process.

[0017] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The drawings herein are incorporated into the specification and constitute a part of the specification, showing embodiments consistent with the present application, and together with the specification, are used to explain the principles of the present application. Obviously, the drawings described below are only some embodiments of the present application, and for those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative work. In the drawings:

[0019] Figure 1 is a schematic diagram of an implementation environment of a blast furnace production process prediction method shown in an exemplary embodiment of the present application;

[0020] Figure 2 is a flow chart of a blast furnace production process prediction method shown in an exemplary embodiment of the present application;

[0021] Figure 3 It is a schematic diagram of the implementation steps of a blast furnace production process prediction method shown in an exemplary embodiment of the present application;

[0022] FIG4( a ) is a schematic diagram showing a visualized display of a material layer structure and a soft melting zone in a blast furnace production process according to an exemplary embodiment of the present application;

[0023] FIG4( b ) is a schematic diagram showing a flow chart visualization of a blast furnace production process according to an exemplary embodiment of the present application;

[0024] FIG4( c ) is a schematic diagram showing a visualization of a pressure cloud diagram in a blast furnace production process, shown in an exemplary embodiment of the present application;

[0025] FIG4( d ) is a schematic diagram showing a visualized display of a cloud diagram of the mass fraction of iron in a blast furnace production process, shown in an exemplary embodiment of the present application;

[0026] FIG4( e) is a schematic diagram showing a visualized display of a carbon dioxide composition cloud diagram in a blast furnace production process, shown in an exemplary embodiment of the present application;

[0027] FIG4( f) is a schematic diagram showing a visualized display of a temperature cloud diagram in a blast furnace production process, shown in an exemplary embodiment of the present application;

[0028] Figure 5 A schematic diagram of the structure of a computer system suitable for implementing an electronic device of an embodiment of the present application is shown. DETAILED DESCRIPTION

[0029] The following will describe the embodiments of the present invention with reference to the accompanying drawings and preferred embodiments. Those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention. It should be understood that the preferred embodiments are only for illustrating the present invention, not for limiting the scope of protection of the present invention.

[0030] It should be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present invention, and thus the drawings only show components related to the present invention rather than being drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component may be changed arbitrarily, and the component layout may also be more complicated.

[0031] In the following description, numerous details are discussed to provide a more thorough explanation of the embodiments of the present invention. However, it is obvious to those skilled in the art that the embodiments of the present invention can be implemented without these specific details. In other embodiments, well-known structures and devices are shown in the form of block diagrams rather than in detail to avoid making the embodiments of the present invention difficult to understand.

[0032] First of all, it should be noted that decoupling is a concept in mathematics that is used to solve the relationship between two or more variables. In specific problems, decoupling means treating two or more tightly coupled variables separately in order to better understand the relationship between them. In control system theory, decoupling is a common control strategy used to reduce the mutual influence between system variables and improve the stability and reliability of the system.

[0033] The Ranz-Marshall equation is used to describe the mass transfer process of gas or liquid in a solid particle bed. This equation is based on the principles of conservation of mass and momentum, takes into account the convection and diffusion effects in the mass transfer process, and can be used to calculate the mass transfer coefficient and the distribution of mass concentration in the particle bed.

[0034] The three-interface unreacted core model is a kinetic model used to describe surface and interface reactions of materials. This model assumes that the controlling step of the reaction on particles, surfaces and interfaces is the surface reaction. It is mainly applicable to heterogeneous catalytic reactions, especially multiphase catalytic reactions.

[0035] Figure 1 It is a schematic diagram of the implementation environment of the blast furnace production process prediction method shown in an exemplary embodiment of the present application.

[0036] like Figure 1 As shown, the implementation environment of the blast furnace production process prediction method includes a data acquisition device 101 and a computer device 102, wherein the parameter acquisition device 101 is used to obtain blast furnace parameters and production parameters in the blast furnace production process, and send the collected data to the computer device 102, and the computer device 102 is used to model the blast furnace based on the obtained blast furnace parameters and production parameters in the blast furnace reaction process, so as to display the blast furnace production process in a visual way. Among them, the computer device 102 can be at least one of a desktop graphics processing unit (Graphic Processing Unit, GPU) computer, a GPU computing cluster, a neural network computer, etc., or it can be an intelligent processor integrated in the current vehicle, and this application does not impose any restrictions on this.

[0037] Figure 2 It is a flow chart of a blast furnace production process prediction method shown as an exemplary embodiment of the present application.

[0038] like Figure 2 As shown, in an exemplary embodiment, the blast furnace production process prediction method includes at least steps S210 to S270, which are described in detail as follows:

[0039] Step S210, obtaining physical data and production data of the target blast furnace, where the production data includes solid parameters and gas parameters in the blast furnace.

[0040] In one embodiment of the present application, first, the physical data of the blast furnace to be predicted (i.e., the target blast furnace) is collected by consulting the design documents, historical records, and communication with the blast furnace operators, and sensors are installed at key parts of the blast furnace to monitor the production data of the blast furnace in real time, such as temperature, pressure, gas composition, etc.; then, the production data is transmitted from the sensor to the data processing center for storage and analysis through the data transmission system, thereby obtaining the physical data and production data of the blast furnace, and sending it to the relevant parties for subsequent use. It should be noted that the physical data of the blast furnace includes the design parameters, raw material properties, operating conditions, etc. of the blast furnace, and the production data includes solid parameters (i.e., charge data) and gas parameters, wherein the solid parameters include but are not limited to charge properties, charge location, batch, type, composition, particle size, porosity, etc., and the gas parameters include pressure fluctuations, gas composition, etc., as well as other indicators calculated based on these data, such as temperature curve, thermal efficiency, fuel consumption, etc. In addition, the above-mentioned sensor should be able to adapt to the harsh environment inside the blast furnace and can accurately and reliably transmit real-time data. The present application does not impose any restrictions on the above-mentioned data categories and sensor categories.

[0041] In a specific embodiment of the present application, the charge properties include: charge batch number, ore composition, ore bulk density, ore diameter, ore sphericity, ore resistance characteristic coefficient, ore start and end soft melting temperatures, coke composition, coke bulk density, coke diameter, coke sphericity, coke resistance characteristic coefficient, charge compression characteristics, charge pulverization characteristics, etc.

[0042] Step S220, constructing a blast furnace geometric model based on solid parameters and physical data, and performing spatial division on the blast furnace geometric model, dividing the geometric space of the blast furnace collective model into a plurality of grids.

[0043] In one embodiment of the present application, a blast furnace geometric model is constructed based on solid parameters and physical data, including: determining a top charging system and a tuyere air supply system of a target blast furnace based on solid parameters, and determining a bed diameter and a dead material column diameter of the target blast furnace based on physical data; calculating a material surface geometry of the target blast furnace based on the top charging system, calculating a tuyere shape and size of the target blast furnace based on the tuyere air supply system, and calculating a dead material column height of the target blast furnace based on the bed diameter and the dead material column diameter; constructing a blast furnace geometric model based on the material surface geometry, tuyere shape and size, and dead material column height.

[0044] In one embodiment of the present application, first, according to the design parameters of the blast furnace, or by measuring and observing the existing blast furnace, the top charging system of the target blast furnace is obtained, which usually includes determining the type, proportion, number of turns and other parameters of the raw materials for charging; next, by measuring and observing the existing blast furnace, or using professional software for simulation, the tuyere air supply system of the target blast furnace and the bed diameter and dead material column diameter of the target blast furnace are obtained, wherein the tuyere air supply system usually includes the number, shape, size, distribution and other parameters of the tuyere, and the bed diameter refers to the material layer in the blast furnace. The diameter of the dead material column refers to the diameter of the dead material area; then, using numerical simulation methods such as finite element analysis or discrete element analysis, the geometry of the material surface of the target blast furnace is calculated based on the furnace top distribution system, the shape and size of the tuyere of the target blast furnace is calculated based on the tuyere air supply system, and the height of the dead material column of the target blast furnace is calculated based on the bed diameter and the dead material column diameter; and then using professional CAD software or other three-dimensional modeling software based on the geometry of the material surface, the shape and size of the tuyere, the height of the dead material column and other parameters, to construct a geometric model of the target blast furnace. It should be noted that the design of the tuyere air supply system needs to consider factors such as the efficiency, fuel consumption, and gas composition of the blast furnace. In addition, the above-mentioned numerical simulation methods such as finite element analysis or discrete element analysis and related information such as CAD software are only used as exemplary explanations. In the specific implementation of this method, corresponding adjustments can be made based on actual needs, and this application does not impose any restrictions on it.

[0045] In a specific embodiment of the present application, the furnace top distribution system includes: ore batch weight, coke batch weight, distribution cycle, coke distribution matrix, ore distribution matrix, etc.; the tuyere air supply system includes: coke ratio, coal ratio, oxygen enrichment, blast volume, blast humidity, blast temperature, oxygen enrichment temperature, coal powder carrier gas volume, coal powder carrier gas temperature, coal powder industrial analysis results, coal powder low calorific value, coal powder combustion rate, etc.

[0046] In addition, after constructing the blast furnace grid, the blast furnace geometric model boundary area is also included in the grid boundary area. The method of setting feature points is used in the identification process. The feature points include: the center point of the furnace top, the center point of the furnace throat, the center point of the furnace body, the center point of the furnace waist, the center point of the furnace belly, and the center point of the furnace bottom. When dividing the grid, structured + unstructured grids are used to realize the blast furnace geometric discretization.

[0047] Step S230, deriving the coordinate information of the grids in the gas-solid overlap region to form a background grid information table, wherein the background grid information table includes grid coordinate information and charge information and gas-solid two-phase state information related to each grid.

[0048] In one embodiment of the present application, after the gas-solid data after the same position assignment is stored in the same grid of the corresponding position in each process, it also includes: obtaining the data category of the grid production data, and determining the data of the same data category as the same family data, the grid production data includes multiple data categories; calculating multiple same family data at the same time to obtain multiple data parameters for characterizing the calculation results of each same family data; combining multiple data parameters to obtain comprehensive data parameters, and determining the comprehensive data parameters as the grid production parameters of the grid.

[0049] In a specific embodiment of the present application, the gas-solid data at the same location is placed in the grid blocks in the same process, taking N categories of data being placed in M ​​grids as an example. The N types of data in the same grid are placed in different processes, and the same type of data in M ​​grids are placed in the same process, so that the data of all grids are obtained based on the parallel calculation of N processes, thereby realizing the single-core interactive CPU parallel partitioning strategy to perform parallel calculations on the grid data, effectively improving the data calculation efficiency.

[0050] Step S240, performing data cleaning and data fitting on the production data, and setting boundary conditions for the blast furnace model based on the cleaned and fitted data.

[0051] In one embodiment of the present application, firstly, a porous area is set on the geometric model according to the demand, and the porous area may include materials such as charge, coke, and the gaps between them, so as to simulate the effect of charge on the flow of reducing gas in the furnace by setting these porous areas; then, porous medium parameters are obtained by experimental measurement or simulation using professional software, and the relevant porous medium parameters may include permeability, porosity, medium density, etc., which are used to characterize the effect of charge on gas flow; then, the porous medium parameters and other known parameters are used to decouple the grid production data to obtain the decoupled gas parameters and solid parameters, and the decoupled parameters may include gas flow rate, mass flow rate of solid materials, etc. It should be noted that the blast furnace can also be optimized according to the decoupled parameters, for example, the air supply volume of the tuyere can be adjusted according to the gas parameters, and the charge mass and stacking method can be adjusted according to the solid parameters. It should be noted that the porosity needs to be obtained through experiments, and the viscous resistance coefficient and the inertial resistance coefficient can be obtained through experiments or theoretical calculations. The present application does not impose any restrictions on the original acquisition method of the data.

[0052] Step S250, calculate the charge flow information in the furnace, including charge velocity, charge flow trajectory and charge residence time, update the charge related information in the background grid information table according to the calculated charge flow information, and initialize the gas-solid two-phase temperature, concentration, velocity and pressure in the background grid information table.

[0053] In one embodiment of the present application, the source terms include a mass source term, a momentum source term and an energy source term. The mass source term is used to characterize the mass exchange between gas and solid caused by chemical reactions in the target blast furnace to achieve mass coupling between gas and solid; the momentum source term is used to characterize the momentum exchange between gas and solid caused by chemical reactions in the target blast furnace to achieve momentum coupling between gas and solid; the energy source term is used to characterize the heat exchange between gas and solid caused by chemical reactions in the target blast furnace to achieve energy coupling between gas and solid.

[0054] Step S260, calculate the mass, momentum and energy source terms according to the gas-solid information in the background grid information table, solve the basic fluid mechanics equations of the gas and solid phases, and simulate the flow, heat transfer and chemical reaction in the blast furnace smelting process.

[0055] In a specific embodiment of the present application, the "source term" includes: a mass source term, a momentum source term and an energy source term; the mass source term is used to consider the mass exchange between gas and solid caused by the chemical reaction in the blast furnace, the momentum source term is used to realize the momentum coupling between gas and solid phases, and the energy source term is used to consider the heat exchange between gas and solid and the heat of chemical reaction in the blast furnace.

[0056] Step S270, updating the state information of the gas-solid two phases in the background grid information table, and judging whether the calculation result is converged, if not, repeating the above calculation until convergence.

[0057] In one embodiment of the present application, after establishing a blast furnace simulation model for characterizing data of different dimensions, it also includes: collecting real-time production data of the target blast furnace and the actual smelting parameters of the target blast furnace; inputting the real-time production data into the blast furnace simulation model to obtain the predicted smelting parameters of the target blast furnace; comparing the predicted smelting parameters with the actual smelting parameters to obtain the deviation value between the predicted smelting parameters and the actual smelting parameters; if the deviation value is greater than or equal to a preset deviation threshold, the blast furnace simulation model will be judged as unqualified, and the blast furnace simulation model will be retrained until the deviation value is less than the preset deviation threshold.

[0058] In one embodiment of the present application, taking the preset deviation threshold of 5% as an example, when it is detected that the deviation value between the predicted smelting parameters obtained by the blast furnace simulation model and the actual smelting parameters obtained based on sensor collection is 6%, it is determined that the error of the blast furnace simulation model is too large and is an unqualified model. Therefore, the model needs to be optimized until its data deviation is less than 5%.

[0059] In one embodiment of the present application, real-time production data is input into a blast furnace simulation model to predict the production status of a target blast furnace, including: collecting real-time production data of the target blast furnace, and inputting the real-time production data into the blast furnace simulation model to obtain current smelting parameters of the target blast furnace, the current smelting parameters are used to characterize the current production status of the target blast furnace; calculating the current smelting parameters to obtain the changing trend of the current smelting parameters, so as to obtain the future production status of the target blast furnace based on the current production status and the changing trend, the future production status is used to characterize the prediction result of the production status of the target blast furnace.

[0060] In one embodiment of the present application, the blast furnace simulation model includes multiple sub-models with different functions, including a silo unloading sub-model, a furnace top distribution sub-model, a furnace body mirror sub-model, a soft melting belt sub-model, an air volume distribution sub-model, a gas-solid sub-model, a chemical reaction sub-model, and a furnace cylinder / iron groove erosion sub-model, and the coupling between the models can be achieved through the gas-solid sub-model.

[0061] In a specific embodiment of the present application, the current smelting parameters are decomposed into multiple single smelting parameters based on the gas-solid sub-model, and any single smelting parameter is determined as the target smelting parameter, the blast furnace simulation model includes the gas-solid sub-model, and the current smelting parameters include single smelting parameters of multiple data categories; based on the target smelting parameters, a target visualization chart is drawn to display the current smelting status of the target smelting process, and the target smelting process is the smelting project corresponding to the target smelting parameters; all parameter categories are traversed to visualize the entire smelting process of the target blast furnace.

[0062] Figure 3 It is a schematic diagram of the implementation steps of a blast furnace production process prediction method shown as an exemplary embodiment of the present application.

[0063] like Figure 3 As shown in the figure, in the prediction process of the blast furnace production process, it is first necessary to obtain the real-time production data on site, and then generate the blast furnace geometric model according to the material surface data and the air supply system, and mesh the several models of the blast furnace and identify the mesh boundaries. Then, the real-time production data is fitted and the boundary matching is assigned, and the blast furnace simulation model is used to calculate the internal smelting state of the blast furnace; finally, the calculation results are compared with the on-site measurement data, the key parameter error is 5%, the model parameters are corrected, and the calculation is recalculated. After the calculation is completed, the key process parameters of the calculation results are extracted and visualized.

[0064] In one embodiment of the present application, firstly, by presetting a set of pre-drawn geometric space grids, the key information required for calculating gas-solid momentum exchange, heat exchange and chemical reaction is recorded. The set space grid contains all geometric spaces from the slag surface to the furnace top, and its key information includes but is not limited to the position information and attribute information of the charge, the temperature information, concentration information, velocity information, pressure information of the gas and solid phases at the corresponding position, and the existence of charge and other related information; then the "viscous flow + background grid" technical solution is adopted to calculate the flow of charge in the furnace; and the corresponding charge attributes are recorded, and the charge attributes are not limited to information such as charge position, batch, type, composition, particle size, porosity, etc., and the corresponding attributes are mapped to the pre-drawn background grid; then the porosity, viscous resistance coefficient and inertial resistance coefficient of the "porous medium" model are used to consider the influence of the charge inside the blast furnace (i.e., the particles inside the blast furnace) on the flow of reducing gas, thereby realizing the momentum coupling between the gas-solid phases after gas-solid decoupling, wherein the porosity in the "porous medium" model must be obtained through experiments, and the viscous resistance coefficient and inertial resistance coefficient can be obtained through experiments or theoretical calculations. Due to the large volume and mass of the charge (ore and coke) in the furnace, the influence of the reducing gas on the flow of the charge in the furnace is ignored, and the coupling between the mass, momentum and energy between the gas and solid phases is realized by adding mass source terms, momentum source terms and energy source terms; among them, the mass source term is used to consider the mass exchange between the gas and solid phases caused by the chemical reaction in the blast furnace, the momentum source term is used to realize the momentum coupling between the gas and solid phases, and the energy source term is used to consider the heat exchange and chemical reaction heat between the gas and solid phases in the blast furnace; then the three-interface unreacted core model is used to describe the chemical reaction in the furnace, and the Ranz-Marsh The all equations describe the convective heat transfer between the gas and solid phases in the furnace, and the heat transfer values ​​calculated for the cases where the charge temperature is higher than 1000℃ and lower than 1000℃ must be corrected according to the actual situation. In addition, in order to reduce the data communication time between the computing cores during parallel computing and improve the parallel efficiency, a CPU parallel partitioning strategy for gas-solid data single-core interaction suitable for large particle size and gas-solid decoupling method is proposed. This strategy follows the principle of putting the gas-solid data at the same position into the same process when dividing the grid, which can greatly reduce the communication time between the computing cores. After testing, within the range of 18 parallel computing cores, the model adopts this grid partitioning strategy, and its parallel acceleration ratio basically increases linearly.

[0065] In addition, based on the above-mentioned gas-solid decoupling processing method suitable for metallurgical dense phase and large-size particles and the corresponding CPU parallel partitioning strategy for gas-solid data single-core interaction, a full-furnace simulation model of the blast furnace was established. And combined with domain knowledge development. The blast furnace simulation model was decoupled into 8 sub-models, including: silo sub-model, furnace top distribution sub-model, furnace body mirror sub-model, soft melting belt sub-model, air volume distribution sub-model, gas-solid sub-model, chemical reaction sub-model, furnace cylinder / iron groove erosion sub-model, and the coupling between the models was realized through the gas-solid sub-model. The blast furnace simulation model uses a three-interface unreacted core model to describe the chemical reaction model in the furnace, and calculates the mass source term between the gas-solid phases through the gas-solid temperature, concentration, velocity, viscosity, charge particle size, porosity, sphericity, etc. in the background grid, and uses a porous medium model to describe the momentum exchange between gas and solid. The Ranz-Marshall equation is used to describe the gas-solid heat exchange in the blast furnace, and the gas-solid temperature, velocity, gas phase thermal conductivity, charge particle size, sphericity, etc. in the background grid are used to calculate the gas-solid heat exchange. The heat exchange values ​​calculated for the cases where the charge temperature is higher than 1000°C and lower than 1000°C need to be corrected according to the actual situation. It should be noted that in the above embodiment, the acquired on-site real-time production data includes: charge attributes, furnace top charge distribution system, tuyere air supply system and other related information, wherein the charge attributes include but are not limited to charge batch number, ore composition, ore bulk density, ore diameter, ore sphericity, ore resistance characteristic coefficient, ore start and end soft melting temperature, coke composition, coke bulk density, coke diameter, coke sphericity, coke resistance characteristic coefficient, charge compression characteristics, charge pulverization characteristics and other information; the furnace top charge distribution system includes but is not limited to ore batch weight, coke batch weight, distribution cycle, coke distribution matrix, ore distribution matrix and other information; the tuyere air supply system includes but is not limited to coke ratio, coal ratio, oxygen enrichment, blast volume, blast humidity, blast temperature, enrichment, etc. Oxygen temperature, pulverized coal carrier gas volume, pulverized coal carrier gas temperature, pulverized coal industrial analysis results, pulverized coal low calorific value, pulverized coal combustion rate and other information; in addition, when generating the blast furnace geometric model according to the real-time production data on site, the blast furnace charge surface geometry is calculated and generated in real time according to the furnace top distribution system, the tuyere shape and size are calculated and generated in real time according to the tuyere air supply system, and the dead material column height is calculated according to the bed diameter and the dead material column diameter; when identifying the boundary of the blast furnace geometric model, the method of setting feature points is adopted, and the feature points include: the center point of the furnace top, the center point of the furnace throat, the center point of the furnace body, the center point of the furnace waist, the center point of the furnace belly, and the center point of the furnace bottom; when dividing the grid, the structure + unstructured grid is used to realize the geometric discretization of the blast furnace.

[0066] Figure 4 is a partial schematic diagram for visual display in an embodiment of the present application, wherein Figure 4(a) is a schematic diagram for visual display of the material layer structure and soft melting zone in the blast furnace production process shown in an exemplary embodiment of the present application; Figure 4(b) is a schematic diagram for visual display of the streamline diagram in the blast furnace production process shown in an exemplary embodiment of the present application; Figure 4(c) is a schematic diagram for visual display of the pressure cloud map in the blast furnace production process shown in an exemplary embodiment of the present application; Figure 4(d) is a schematic diagram for visual display of the mass fraction cloud map of iron in the blast furnace production process shown in an exemplary embodiment of the present application; Figure 4(e) is a schematic diagram for visual display of the carbon dioxide composition cloud map in the blast furnace production process shown in an exemplary embodiment of the present application; Figure 4(f) is a schematic diagram for visual display of the temperature cloud map in the blast furnace production process shown in an exemplary embodiment of the present application.

[0067] In a specific embodiment of the present application, after the blast furnace to be predicted is modeled and the relevant smelting parameters are obtained, a part of the parameters are extracted for visualization. The relevant information such as the top gas composition, top gas utilization rate, top gas temperature, top gas volume, bed resistance, soft melting zone position and shape of the blast furnace is extracted and visualized to obtain the material layer structure and soft melting zone information as shown in Figure 4 (a), the streamline information as shown in Figure 4 (b), the pressure cloud map information as shown in Figure 4 (c), the mass fraction cloud map of iron as shown in Figure 4 (d), the carbon dioxide component cloud map as shown in Figure 4 (e), and the temperature cloud map as shown in Figure 4 (f).

[0068] It should be noted that the blast furnace production process prediction method proposed in this application realizes data transmission, decoupling and phase coupling processing after decoupling between dense phase and large-size particle gas-solid phase through the combination of "background grid + charge tracking + porous medium + source term". It effectively avoids the direct coupling solution between gas and solid, greatly reduces the complexity of solving the blast furnace production process prediction system, and preliminarily solves the technical problems such as complex model, difficult system modeling, and poor program solution robustness in the development process of the blast furnace production process prediction system. It promotes the transformation of blast furnace production and operation from experience to digitalization and intelligence, improves the level of intelligent decision-making and production operation, and contributes to the development of smart blast furnaces.

[0069] An embodiment of the present application also provides an electronic device, comprising: one or more processors; a storage device for storing one or more programs, when the one or more programs are executed by the one or more processors, the electronic device implements the blast furnace production process prediction method provided in the above-mentioned embodiments.

[0070] Figure 5 The structure diagram of the computer system suitable for implementing the electronic device of the embodiment of the present application is shown. It should be noted that: Figure 5 The computer system 500 of the electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0071] like Figure 5 As shown, the computer system 500 includes a central processing unit (CPU) 501, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 502 or the program loaded from the storage part 508 to the random access memory (RAM) 503, such as executing the method described in the above embodiment. In the RAM 503, various programs and data required for system operation are also stored. The CPU 501, the ROM 502 and the RAM 503 are connected to each other through the bus 504. The input / output (I / O) interface 505 is also connected to the bus 504.

[0072] The following components are connected to the I / O interface 505: an input section 506 including a keyboard, a mouse, etc.; an output section 507 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker; a storage section 508 including a hard disk, etc.; and a communication section 509 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section 509 performs communication processing via a network such as the Internet. A drive 510 is also connected to the I / O interface 505 as needed. A removable medium 511, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 510 as needed so that a computer program read therefrom is installed into the storage section 508 as needed.

[0073] In particular, according to an embodiment of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a computer program for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication section 509, and / or installed from a removable medium 511. When the computer program is executed by a central processing unit (CPU) 501, various functions defined in the system of the present application are executed.

[0074] It should be noted that the computer-readable medium shown in the embodiment of the present application can be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium can be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media can include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, wherein a computer-readable computer program is carried. This propagated data signal can take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. A computer program contained on a computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0075] The flowchart and block diagram in the accompanying drawings illustrate the possible architecture, functions and operations of the system, method and computer program product according to various embodiments of the present application. Wherein, each box in the flowchart or block diagram can represent a module, a program segment, or a part of the code, and the above-mentioned module, program segment, or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0076] The units involved in the embodiments described in this application may be implemented by software or hardware, and the units described may also be set in a processor. The names of these units do not, in some cases, constitute limitations on the units themselves.

[0077] Another aspect of the present application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor of a computer, causes the computer to execute the blast furnace production process prediction method as described above. The computer-readable storage medium may be included in the electronic device described in the above embodiment, or may exist independently without being assembled into the electronic device.

[0078] Another aspect of the present application also provides a computer program product or computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the blast furnace production process prediction method provided in each of the above embodiments.

[0079] The above embodiments are merely illustrative of the principles and effects of the present invention, and are not intended to limit the present invention. Anyone familiar with the technology may modify or change the above embodiments without violating the spirit and scope of the present invention. Therefore, all equivalent modifications or changes made by a person of ordinary skill in the art without departing from the spirit and technical ideas disclosed by the present invention shall still be covered by the claims of the present invention.

Claims

1. A blast furnace production process simulation method, characterized in that: The method comprises: Acquiring geometric data and production data of a target blast furnace, wherein the production data at least includes furnace charge parameters and reducing gas parameters; Constructing a blast furnace geometric model based on the geometric data, and meshing the blast furnace geometric model to divide the blast furnace geometric space into a plurality of meshes; Exporting the coordinate information of the grids in the gas-solid overlap region to form a background grid information table, wherein the background grid information table includes grid coordinate information and charge information and gas-solid two-phase state information related to each grid; Performing data cleaning and data fitting on the production data, and setting boundary conditions for the blast furnace model based on the cleaned and fitted data; Calculate the charge flow information in the furnace, including charge velocity, charge flow trajectory and charge residence time; update the charge related information in the background grid information table according to the calculated charge flow information; initialize the gas-solid two-phase temperature, concentration, velocity and pressure in the background grid information table; Calculate the mass, momentum and energy source terms according to the gas-solid information in the background grid information table, solve the basic fluid mechanics equations of gas and solid phases, and simulate the flow, heat transfer and chemical reaction in the blast furnace smelting process; Update the state information of the gas-solid two phases in the background grid information table; determine whether the calculation results converge. If not, repeat the above calculation until convergence.

2. The blast furnace production process simulation method according to claim 1, characterized in that: The production data include: material distribution matrix, material distribution cycle, ore batch weight, coke batch weight, charge batch, composition, particle size, porosity, soft melting starting temperature and air supply data, wherein the air supply data at least includes coke ratio, coal ratio, oxygen enrichment, blast volume, blast humidity, blast temperature, oxygen enrichment temperature, coal powder carrier gas volume, coal powder carrier gas temperature, coal powder industrial analysis results, coal powder lower calorific value and coal powder combustion rate.

3. The blast furnace production process simulation method according to claim 1, characterized in that: The fluid mechanics is basically the Navier-Stokes equations, and the finite volume method or the finite element method is used to solve the Navier-Stokes equations, and the turbulence model is combined to describe the gas-solid two-phase flow characteristics.

4. The blast furnace production process simulation method according to claim 1, characterized in that: The judgment of whether the calculation result is converged is performed by comparing the difference between the results of two consecutive iterations, and when the difference is less than a preset threshold, it is considered to be converged.

5. The blast furnace production process simulation method according to any one of claims 1 to 4, characterized in that: The method further includes: establishing a blast furnace simulation model for receiving real-time production data input, so as to predict the production status of the target blast furnace through the blast furnace simulation model and display data in different dimensions.

6. A method for predicting a blast furnace production process, characterized in that: The method comprises: Collecting real-time production data of a target blast furnace, and inputting the real-time production data into the blast furnace simulation model to obtain current smelting parameters of the target blast furnace, wherein the current smelting parameters are used to characterize the current production status of the target blast furnace; The current smelting parameters are calculated to obtain the changing trend of the current smelting parameters, so as to obtain the future production state of the target blast furnace based on the current production state and the changing trend, and the future production state is used to characterize the prediction result of the production state of the target blast furnace.

7. The method for predicting a blast furnace production process according to claim 6, characterized in that: The data under each dimension are displayed separately, including: Decomposing the current smelting parameters into a plurality of individual smelting parameters based on the gas-solid sub-model, and determining any individual smelting parameter as a target smelting parameter; Drawing a target visualization chart based on the target smelting parameters to display the current smelting state of the target smelting process, the target smelting process being the smelting project corresponding to the target smelting parameters; All parameter categories are traversed to visualize the entire smelting process of the target blast furnace.

8. The blast furnace production process prediction method according to any one of claims 6-7, characterized in that: After establishing a blast furnace simulation model for representing data of different dimensions, it also includes: Collecting real-time production data of a target blast furnace and actual smelting parameters of the target blast furnace; Inputting the real-time production data into the blast furnace simulation model to obtain predicted smelting parameters of the target blast furnace; Comparing the predicted smelting parameters with the actual smelting parameters to obtain a deviation value between the predicted smelting parameters and the actual smelting parameters; If the deviation value is greater than or equal to the preset deviation threshold, the blast furnace simulation model will be judged as unqualified, and the blast furnace simulation model will be retrained until the deviation value is less than the preset deviation threshold.

9. An electronic device, characterized in that: The electronic device comprises: one or more processors; A storage device for storing one or more programs, which, when executed by the one or more processors, enables the electronic device to implement the blast furnace production process prediction method as described in any one of claims 6 to 8.

10. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed by a processor of a computer, the computer is caused to execute the blast furnace production process prediction method according to any one of claims 6 to 8.

Images