Methods, apparatuses, electronic devices, and media for predicting softening melting drop temperature of iron ore

Abstract

The application discloses a method and device for predicting iron ore softening melting drop temperature, electronic equipment and medium, and belongs to the field of metallurgy. The method comprises the following steps: detecting and analyzing, collecting data and classifying and arranging; determining input data set and response data set, evaluating their correlation complexity based on linear correlation analysis method, and performing data screening; establishing a BP neural network model; optimizing the weight and bias parameters of the BP neural network model; establishing a geometric model, setting the size parameters of the geometric model and performing grid division; establishing an ontology model, simulating iron ore softening melting drop, and obtaining the reduction degree at the softening start and end temperatures; combining the new input data with the input data set to form an observation data set; taking the observation data set as input and the response data set as output, training the BP neural network model, and obtaining an iron ore softening melting drop temperature prediction model. The application has higher efficiency and lower cost in obtaining the iron ore softening melting drop temperature.

Description

Technical Field

[0001] This invention relates to a method, apparatus, electronic device, and medium for predicting the softening droplet temperature of iron ore. Specifically, it relates to a method, apparatus, electronic device, and medium for predicting the softening droplet temperature of iron ore based on the coupling of multiple optimization algorithms and computational fluid dynamics, belonging to the field of metallurgical technology. Background Technology

[0002] Blast furnace ironmaking is a crucial step in steel production. It involves the continuous production of liquid pig iron using coke, iron-bearing ore (natural lump ore, sinter, and pellets), and flux (limestone and dolomite) in a vertical reactor—the blast furnace. Modern blast furnace ironmaking evolved from the ancient vertical furnace method and remains a vital part of modern steel production. Although many new ironmaking methods have emerged, blast furnace ironmaking remains the primary method of modern ironmaking due to its favorable technical and economic indicators, simple process, high production capacity, high labor productivity, and low energy consumption.

[0003] Blast furnace charge is the foundation of blast furnace ironmaking. Blast furnace charge includes sinter, pellets, and lump ore. The quality of blast furnace ironmaking performance is inextricably linked to the quality of the charge. Typically, the softening and dripping temperature of the charge is obtained through testing and analysis using an iron ore softening and dripping temperature tester. The high-temperature load reduction softening and dripping test of iron ore is used to verify the softening and dripping properties of iron ore. It simulates the blast furnace smelting conditions and measures important parameters such as ore expansion, softening range, reducing gas pressure difference, melting range, and dripping temperature. Currently, researchers can only obtain metallurgical performance data of the charge through physical experiments. However, physical experiments are time-consuming and expensive, and cannot meet the requirement of obtaining the softening and dripping temperature of a large number of iron ore samples in a short time.

[0004] To improve the efficiency of obtaining the softening droplet temperature of iron ore, it is necessary to develop a method for intelligent prediction of the softening droplet temperature of iron ore by combining data technology and various simulation techniques. Summary of the Invention

[0005] To address the aforementioned problems, this invention proposes a method, apparatus, electronic device, and medium for predicting the softening droplet temperature of iron ore, which can improve the efficiency of obtaining the softening droplet temperature of iron ore.

[0006] The technical solution adopted by this invention to solve its technical problem is as follows:

[0007] In a first aspect, the present invention provides a method for predicting the softening droplet temperature of iron ore, comprising the following steps:

[0008] Step 1: Conduct tests and analyses on different sintered ores, pellets, lump ores and mixed ores respectively, collect data and classify and organize the data. The collected data includes: the proportion of mineral types, the chemical composition of mineral types, the composition of reducing gases, the particle size of ore, the softening start temperature and the softening end temperature.

[0009] Step 2: The proportion of minerals in the furnace charge, the chemical composition of the minerals, the composition of reducing gases and the particle size of the ore are used as the input dataset, and the softening start temperature and softening end temperature are used as the response dataset. The correlation complexity between the input dataset and the response dataset is evaluated based on the linear correlation analysis method, and the data is filtered based on the correlation complexity.

[0010] Step 3: Establish a BP neural network model based on the neural network algorithm;

[0011] Step 4: Optimize the weights and bias parameters of the BP neural network model based on the particle swarm optimization algorithm to obtain the optimized BP neural network model.

[0012] Step 5: Establish the geometric model of the iron ore softening droplet temperature measuring instrument, set the dimensional parameters of the geometric model, and perform mesh generation on the geometric model;

[0013] Step 6: Based on computational fluid dynamics and coupled with the geometric model of the iron ore softening droplet temperature measuring instrument, establish the main body model of the iron ore softening droplet temperature measuring instrument. Use the softening start temperature and softening end temperature data as input conditions to simulate the iron ore softening droplet experimental process. By analyzing the simulation results of the main body model of the iron ore softening droplet temperature measuring instrument, obtain the degree of reduction of iron ore at the softening start temperature and softening end temperature.

[0014] Step 7: Combine the degree of reduction of iron ore at the softening start temperature and softening end temperature as new input data with the input dataset to form the observation dataset;

[0015] Step 8: Use the observation dataset as the input to the neural network and the response dataset as the output of the neural network to train the optimized BP neural network model and obtain the iron ore softening droplet temperature prediction model.

[0016] As one possible implementation of this embodiment, in step 1, the collected data includes: sinter ratio, pellet ratio, lump ore ratio, TFe content, FeO content, SiO2 content, CaO content, Al2O3 content, MgO content, Ni content, S content, Ti content, CO gas content, N2 gas content, iron ore particle size, iron ore mass, softening start temperature T10, and softening end temperature T40.

[0017] As one possible implementation of this embodiment, in step 2, the input dataset for data filtering by correlation complexity includes: sinter ratio, pellet ratio, lump ore ratio, TFe content, FeO content, SiO2 content, CaO content, Al2O3 content, MgO content, CO gas content, and iron ore particle size. The filtered output dataset includes softening start temperature T10 and softening end temperature T40.

[0018] As one possible implementation of this embodiment, the parameters of the BP neural network model include at least: training data, validation data, test data, number of hidden layers, number of neurons, optimization algorithm, activation function, number of training iterations, and learning rate.

[0019] As one possible implementation of this embodiment, the training data, validation data, and test data are randomly sampled from the prediction dataset, representing 75%, 15%, and 15% respectively; the hidden layer is set to one layer, the number of neurons is set to 10, and the optimization algorithm is set to gradient descent; the activation function between the input layer and the hidden layer is set to... The activation function between the hidden layer and the output layer is set to purelin(x) = x; the number of training iterations is set to 5000, and the learning rate is set to 0.05.

[0020] As one possible implementation of this embodiment, the main body model of the iron ore softening droplet temperature measuring instrument includes at least a chemical reaction model, a heat transfer model, a mass transfer model, and a softening zone model.

[0021] As one possible implementation of this embodiment, the simulated iron ore softening droplet experiment process includes solving the internal temperature field, pressure field, velocity field, and permeability index of the softening zone.

[0022] Secondly, an embodiment of the present invention provides an apparatus for predicting the softening droplet temperature of iron ore, comprising:

[0023] The data acquisition module is used to detect and analyze different sintered ores, pellets, lump ores and mixed ores, collect data and classify and organize the data. The collected data includes: the proportion of minerals contained, the chemical composition of minerals, the composition of reducing gases, the particle size of ore, the softening start temperature and the softening end temperature.

[0024] The dataset generation module is used to take the proportion of minerals in the furnace charge, the chemical composition of the minerals, the composition of reducing gases and the particle size of the ore as the input dataset, and the softening start temperature and softening end temperature as the response dataset. It evaluates the correlation complexity between the input dataset and the response dataset based on the linear correlation analysis method, and performs data filtering based on the correlation complexity.

[0025] The neural network model building module is used to build a BP neural network model based on the neural network algorithm.

[0026] The neural network model optimization module is used to optimize the weights and bias parameters of the BP neural network model based on the particle swarm optimization algorithm to obtain the optimized BP neural network model.

[0027] The geometric model building module is used to build the geometric model of the iron ore softening droplet temperature measuring instrument, set the dimensional parameters of the geometric model, and perform mesh generation on the geometric model;

[0028] The ontological model building module is used to build an ontological model of the iron ore softening droplet temperature measuring instrument based on computational fluid dynamics and coupled with the geometric model of the iron ore softening droplet temperature measuring instrument. The softening start temperature and softening end temperature data are used as input conditions to simulate the iron ore softening droplet experimental process. By analyzing the simulation results of the ontological model of the iron ore softening droplet temperature measuring instrument, the degree of reduction of iron ore at the softening start temperature and softening end temperature is obtained.

[0029] The observation dataset generation module is used to take the degree of reduction of iron ore at the softening start temperature and softening end temperature as new input data and combine them with the input dataset to form the observation dataset;

[0030] The prediction model acquisition module is used to train an optimized BP neural network model by taking the observation dataset as the input of the neural network and the response dataset as the output of the neural network, and obtaining a prediction model for the softening droplet temperature of iron ore.

[0031] Thirdly, an electronic device provided by an embodiment of the present invention includes a processor, a memory, and a program stored in the memory and executable on the processor. When the electronic device is running, the processor executes the program to implement the steps of the method described above for predicting the softening droplet temperature of iron ore.

[0032] Fourthly, embodiments of the present invention provide a storage medium storing a program that, when executed by a processor, performs the steps of any of the methods described above for predicting the softening droplet temperature of iron ore.

[0033] The technical solutions of the embodiments of the present invention can have the following beneficial effects:

[0034] This invention provides intelligent prediction of the softening droplet temperature of iron ore based on the coupling of multiple optimization algorithms and computational fluid dynamics. It obtains the degree of reduction of iron ore at the softening start and end temperatures by simulating the iron ore softening droplet experiment. Using simulation data combined with physical experimental data, a prediction model for the iron ore softening droplet temperature is established based on multiple optimization algorithms. This prediction model can analyze the softening start and end temperatures of iron ores with different compositions. This invention's method for obtaining the iron ore softening droplet temperature has high calculation accuracy, speed, and wide applicability, while reducing the cost of physical experiments. It can obtain the metallurgical performance data of iron ore from its physical and chemical properties. Compared with physical experiments, this invention's method of obtaining the iron ore softening droplet temperature through data technology combined with simulation technology is more efficient and lower in cost.

[0035] This invention uses computational fluid dynamics to simulate the softening and molten droplet process of iron ore, determining the degree of reduction of iron ore at different temperatures. It then uses simulation data combined with physical experimental data and various optimization algorithms coupled with computational fluid dynamics to predict the softening and molten droplet temperature of iron ore. This invention, by combining data technology with simulation technology to predict the softening and molten droplet temperature of iron ore, solves the problem that existing methods for analyzing iron ore softening and molten droplet temperature mainly rely on physical experiments.

[0036] The apparatus for predicting the softening droplet temperature of iron ore according to the technical solution of this invention has the same beneficial effects as the method for predicting the softening droplet temperature of iron ore according to the technical solution of this invention. Attached Figure Description

[0037] Figure 1 This is a flowchart illustrating a method for predicting the softening droplet temperature of iron ore according to an exemplary embodiment;

[0038] Figure 2 This is a block diagram illustrating an apparatus for predicting the softening droplet temperature of iron ore according to an exemplary embodiment. Detailed Implementation

[0039] The present invention will be further described below with reference to the accompanying drawings and embodiments:

[0040] To clearly illustrate the technical features of this solution, the invention will be described in detail below through specific embodiments and in conjunction with the accompanying drawings. The following disclosure provides many different embodiments or examples for implementing different structures of the invention. To simplify the disclosure of the invention, components and arrangements of specific examples are described below. Furthermore, reference numerals and / or letters may be repeated in different examples. This repetition is for simplification and clarity and does not in itself indicate a relationship between the various embodiments and / or arrangements discussed. It should be noted that the components illustrated in the drawings are not necessarily drawn to scale. Descriptions of well-known components, processing techniques, and processes are omitted in this invention to avoid unnecessarily limiting the invention.

[0041] like Figure 1 As shown, this embodiment of the invention provides a method for predicting the softening droplet temperature of iron ore, comprising the following steps:

[0042] Step 1: Conduct tests and analyses on different sintered ores, pellets, lump ores and mixed ores respectively, collect data and classify and organize the data. The collected data includes: the proportion of mineral types, the chemical composition of mineral types, the composition of reducing gases, the particle size of ore, the softening start temperature and the softening end temperature.

[0043] Step 2: The proportion of minerals in the furnace charge, the chemical composition of the minerals, the composition of reducing gases and the particle size of the ore are used as the input dataset, and the softening start temperature and softening end temperature are used as the response dataset. The correlation complexity between the input dataset and the response dataset is evaluated based on the linear correlation analysis method, and the data is filtered based on the correlation complexity.

[0044] Step 3: Establish a BP neural network model based on the neural network algorithm;

[0045] Step 4: Optimize the weights and bias parameters of the BP neural network model based on the particle swarm optimization algorithm to obtain the optimized BP neural network model.

[0046] Step 5: Establish the geometric model of the iron ore softening droplet temperature measuring instrument, set the dimensional parameters of the geometric model, and perform mesh generation on the geometric model;

[0047] Step 6: Based on computational fluid dynamics and coupled with the geometric model of the iron ore softening droplet temperature measuring instrument, establish the main body model of the iron ore softening droplet temperature measuring instrument. Use the softening start temperature and softening end temperature data as input conditions to simulate the iron ore softening droplet experimental process. By analyzing the simulation results of the main body model of the iron ore softening droplet temperature measuring instrument, obtain the degree of reduction of iron ore at the softening start temperature and softening end temperature.

[0048] Step 7: Combine the degree of reduction of iron ore at the softening start temperature and softening end temperature as new input data with the input dataset to form the observation dataset;

[0049] Step 8: Use the observation dataset as the input to the neural network and the response dataset as the output of the neural network to train the optimized BP neural network model and obtain the iron ore softening droplet temperature prediction model.

[0050] This invention provides intelligent prediction of the softening droplet temperature of iron ore based on the coupling of multiple optimization algorithms and computational fluid dynamics. It obtains the degree of reduction of iron ore at the softening start and end temperatures by simulating the iron ore softening droplet experiment. Using simulation data combined with physical experimental data, a prediction model for the iron ore softening droplet temperature is established based on multiple optimization algorithms. This prediction model can analyze the softening start and end temperatures of iron ores with different compositions. This invention's method for obtaining the iron ore softening droplet temperature has high calculation accuracy, speed, and wide applicability, while reducing the cost of physical experiments. It can obtain the metallurgical performance data of iron ore from its physical and chemical properties. Compared with physical experiments, this invention's method of obtaining the iron ore softening droplet temperature through data technology combined with simulation technology is more efficient and lower in cost.

[0051] As one possible implementation of this embodiment, in step 1, the collected data includes: sinter ratio, pellet ratio, lump ore ratio, TFe content, FeO content, SiO2 content, CaO content, Al2O3 content, MgO content, Ni content, S content, Ti content, CO gas content, N2 gas content, iron ore particle size, iron ore mass, softening start temperature T10, and softening end temperature T40.

[0052] As one possible implementation of this embodiment, in step 2, the input dataset for data filtering by correlation complexity includes: sinter ratio, pellet ratio, lump ore ratio, TFe content, FeO content, SiO2 content, CaO content, Al2O3 content, MgO content, CO gas content, and iron ore particle size. The filtered output dataset includes softening start temperature T10 and softening end temperature T40.

[0053] As one possible implementation of this embodiment, the parameters of the BP neural network model include at least: training data, validation data, test data, number of hidden layers, number of neurons, optimization algorithm, activation function, number of training iterations, and learning rate.

[0054] As one possible implementation of this embodiment, the training data, validation data, and test data are randomly sampled from the prediction dataset, representing 75%, 15%, and 15% respectively; the hidden layer is set to one layer, the number of neurons is set to 10, and the optimization algorithm is set to gradient descent; the activation function between the input layer and the hidden layer is set to... The activation function between the hidden layer and the output layer is set to purelin(x) = x; the number of training iterations is set to 5000, and the learning rate is set to 0.05.

[0055] As one possible implementation of this embodiment, the main body model of the iron ore softening droplet temperature measuring instrument includes at least a chemical reaction model, a heat transfer model, a mass transfer model, and a softening zone model.

[0056] As one possible implementation of this embodiment, the simulated iron ore softening droplet experiment process includes solving the internal temperature field, pressure field, velocity field, and permeability index of the softening zone.

[0057] like Figure 2 As shown in the figure, an embodiment of the present invention provides an apparatus for predicting the softening droplet temperature of iron ore, comprising:

[0058] The data acquisition module is used to detect and analyze different sintered ores, pellets, lump ores and mixed ores, collect data and classify and organize the data. The collected data includes: the proportion of minerals contained, the chemical composition of minerals, the composition of reducing gases, the particle size of ore, the softening start temperature and the softening end temperature.

[0059] The dataset generation module is used to take the proportion of minerals in the furnace charge, the chemical composition of the minerals, the composition of reducing gases and the particle size of the ore as the input dataset, and the softening start temperature and softening end temperature as the response dataset. It evaluates the correlation complexity between the input dataset and the response dataset based on the linear correlation analysis method, and performs data filtering based on the correlation complexity.

[0060] The neural network model building module is used to build a BP neural network model based on the neural network algorithm.

[0061] The neural network model optimization module is used to optimize the weights and bias parameters of the BP neural network model based on the particle swarm optimization algorithm to obtain the optimized BP neural network model.

[0062] The geometric model building module is used to build the geometric model of the iron ore softening droplet temperature measuring instrument, set the dimensional parameters of the geometric model, and perform mesh generation on the geometric model;

[0063] The ontological model building module is used to build an ontological model of the iron ore softening droplet temperature measuring instrument based on computational fluid dynamics and coupled with the geometric model of the iron ore softening droplet temperature measuring instrument. The softening start temperature and softening end temperature data are used as input conditions to simulate the iron ore softening droplet experimental process. By analyzing the simulation results of the ontological model of the iron ore softening droplet temperature measuring instrument, the degree of reduction of iron ore at the softening start temperature and softening end temperature is obtained.

[0064] The observation dataset generation module is used to take the degree of reduction of iron ore at the softening start temperature and softening end temperature as new input data and combine them with the input dataset to form the observation dataset;

[0065] The prediction model acquisition module is used to train an optimized BP neural network model by taking the observation dataset as the input of the neural network and the response dataset as the output of the neural network, and obtaining a prediction model for the softening droplet temperature of iron ore.

[0066] The specific process of intelligent prediction of iron ore softening droplet temperature based on the coupling of multiple optimization algorithms and computational fluid dynamics is as follows.

[0067] Step 1: Using an iron ore softening and dripping performance tester, 100 types of sinter, 100 types of pellets, 100 types of lump ore, and 100 types of mixed ore were tested and analyzed. Data were collected, including: sinter ratio, pellet ratio, lump ore ratio, TFe content, FeO content, SiO2 content, CaO content, Al2O3 content, MgO content, Ni content, S content, Ti content, CO gas content, N2 gas content, iron ore particle size, iron ore mass, softening start temperature T10, and softening end temperature T40.

[0068] Step Two: The following parameters are used as the input dataset: sinter ratio, pellet ratio, lump ore ratio, TFe content, FeO content, SiO2 content, CaO content, Al2O3 content, MgO content, Ni content, S content, Ti content, CO gas content, and N2 gas content. The softening start temperature and softening end temperature are used as the response dataset. The linear correlation complexity between the input and response datasets is calculated using linear correlation analysis. The input dataset, filtered by linear correlation complexity, includes: sinter ratio, pellet ratio, lump ore ratio, TFe content, FeO content, SiO2 content, CaO content, Al2O3 content, MgO content, CO gas content, and iron ore particle size.

[0069] Step 3: Use Matlab R2022a software to build a BP neural network model based on the neural network algorithm. Set the model parameters, including: training data, validation data, and test data are randomly sampled from the prediction dataset at 75%, 15%, and 15% respectively; set one hidden layer, 10 neurons, the optimization algorithm to gradient descent, and the activation function between the input layer and the hidden layer to tansig, with the expression: The activation function between the hidden layer and the output layer is set to purlin, with the expression purelin(x) = x. The training iterations are set to 5000, and the learning rate is set to 0.05.

[0070] Step 4: Establish an optimizable BP neural network based on the particle swarm optimization algorithm coupled with the BP neural network model. The optimization objectives are: the weights W1 and bias b1 between the input layer and the hidden layer, and the weights W2 and b2 between the hidden layer and the output layer.

[0071] Step 5: Using an iron ore softening and dripping performance tester as the research object, establish a geometric model and divide it into meshes.

[0072] Step 6: Establish the main body model of the iron ore softening droplet performance tester based on the computational fluid dynamics coupled geometric model, including the chemical reaction model, heat transfer model, mass transfer model, and softening zone model.

[0073] Step 7: Using the softening start temperature and softening end temperature from Step 2 as partial input conditions, the iron ore softening and dripping performance tester's main body model is used to simulate the iron ore softening and dripping experimental process. Input conditions must include at least: iron ore particle size, coke particle size, ore-to-coke ratio, softening and dripping temperature, and reducing gas.

[0074] Step 8: Solve the reduction degrees R10 and R40 of iron ore at the softening start temperature and softening end temperature by analyzing the output results of the main body model of the iron ore softening droplet performance tester.

[0075] Step 9: The iron ore reduction data R10 and R40 are fed back to Step 2 and combined with the filtered input dataset to form the observation dataset.

[0076] Step 10: Use the observation dataset and response dataset as the input and output of an optimizable BP neural network, respectively, to train the model and obtain a prediction model for the softening droplet temperature of iron ore.

[0077] This invention uses computational fluid dynamics to simulate the softening and molten droplet process of iron ore, determining the degree of reduction of iron ore at different temperatures. It then uses simulation data combined with physical experimental data and multiple optimization algorithms coupled with computational fluid dynamics to predict the softening and molten droplet temperature of iron ore. This invention provides a more efficient and lower-cost method for obtaining the softening and molten droplet temperature of iron ore.

[0078] This invention provides an electronic device, including a processor, a memory, and a program stored in the memory and executable on the processor. When the electronic device is running, the processor executes the program to implement the steps of the method described above for predicting the softening droplet temperature of iron ore.

[0079] Specifically, the aforementioned memory and processor can be general-purpose memory and processor, without any specific limitations. When the processor runs the computer program stored in the memory, it can execute the aforementioned method for predicting the softening droplet temperature of iron ore.

[0080] Those skilled in the art will understand that the structure of the electronic device does not constitute a limitation on the electronic device, and may include more or fewer components than shown in the figure, or combine some components, or split some components, or have different component arrangements.

[0081] In some embodiments, the electronic device may further include a touchscreen for displaying a graphical user interface (e.g., an application launch screen) and receiving user actions on the graphical user interface (e.g., launching an application). Specifically, the touchscreen may include a display panel and a touch panel. The display panel may be configured as an LCD (Liquid Crystal Display), OLED (Organic Light-Emitting Diode), or similar type. The touch panel can collect user touch or non-touch operations on or near it and generate pre-set operation commands, such as user actions using fingers, styluses, or any suitable object or accessory on or near the touch panel. Additionally, the touch panel may include a touch detection device and a touch controller. The touch detection device detects the user's touch position and posture, and detects the signals generated by the touch operation, transmitting the signals to the touch controller. The touch controller receives touch information from the touch detection device, converts it into information that the processor can process, sends it to the processor, and can also receive and execute commands from the processor. Furthermore, touch panels can be implemented using various types of sensors, including resistive, capacitive, infrared, and surface acoustic wave sensors, as well as any future technologies. Moreover, the touch panel can cover the display panel. Users can operate on or near the touch panel, which is covered by the graphical user interface displayed on the display panel. After detecting the operation on or near the touch panel, the touch panel transmits it to the processor to determine the user input. The processor then responds to the user input by providing corresponding visual output on the display panel. Additionally, the touch panel and display panel can be implemented as two separate components or integrated together.

[0082] Corresponding to the above application startup method, this embodiment of the invention also provides a storage medium storing a program that, when run by a processor, executes the steps of the above-described method for predicting the softening droplet temperature of iron ore.

[0083] The application launch device provided in this application embodiment can be specific hardware on the device or software or firmware installed on the device. The device provided in this application embodiment has the same implementation principle and technical effects as the foregoing method embodiments. For the sake of brevity, any parts not mentioned in the device embodiment can be referred to the corresponding content in the foregoing method embodiments. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can all be referred to the corresponding processes in the above method embodiments, and will not be repeated here.

[0084] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0085] In the embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. The apparatus embodiments described above are merely illustrative. For example, the division of modules is only a logical functional division, and there may be other division methods in actual implementation. Furthermore, multiple modules or components may be combined or integrated into another system, or some features may be ignored or not executed. Additionally, the coupling or direct coupling or communication connection shown or discussed may be through some communication interface, and the indirect coupling or communication connection of the apparatus or modules may be electrical, mechanical, or other forms.

[0086] The modules described as separate components may or may not be physically separate. Similarly, the components shown as modules may or may not be physical modules; they may be located in one place or distributed across multiple network modules. Some or all of the modules can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0087] In addition, the functional modules in the embodiments provided in this application can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module.

[0088] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0089] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0090] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0091] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the specific implementation of the present invention. Any modifications or equivalent substitutions that do not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A method for predicting the softening droplet temperature of iron ore, characterized in that, Includes the following steps: Step 1: Conduct tests and analyses on different sintered ores, pellets, lump ores and mixed ores respectively, collect data and classify and organize the data. The collected data includes: the proportion of mineral types, the chemical composition of mineral types, the composition of reducing gases, the particle size of ore, the softening start temperature and the softening end temperature. Step 2: The proportion of minerals in the furnace charge, the chemical composition of the minerals, the composition of reducing gases and the particle size of the ore are used as the input dataset, and the softening start temperature and softening end temperature are used as the response dataset. The correlation complexity between the input dataset and the response dataset is evaluated based on the linear correlation analysis method, and the data is filtered based on the correlation complexity. Step 3: Establish a BP neural network model based on the neural network algorithm; Step 4: Optimize the weights and bias parameters of the BP neural network model based on the particle swarm optimization algorithm to obtain the optimized BP neural network model. Step 5: Establish the geometric model of the iron ore softening droplet temperature measuring instrument, set the dimensional parameters of the geometric model, and perform mesh generation on the geometric model; Step 6: Based on computational fluid dynamics and coupled with the geometric model of the iron ore softening droplet temperature measuring instrument, establish the main body model of the iron ore softening droplet temperature measuring instrument. Use the softening start temperature and softening end temperature data as input conditions to simulate the iron ore softening droplet experimental process. By analyzing the simulation results of the main body model of the iron ore softening droplet temperature measuring instrument, obtain the degree of reduction of iron ore at the softening start temperature and softening end temperature. Step 7: Combine the degree of reduction of iron ore at the softening start temperature and softening end temperature as new input data with the input dataset to form the observation dataset; Step 8: Use the observation dataset as the input to the neural network and the response dataset as the output of the neural network to train the optimized BP neural network model and obtain the iron ore softening droplet temperature prediction model.

2. The method for predicting the softening droplet temperature of iron ore according to claim 1, characterized in that, In step 1, the collected data include: sinter ratio, pellet ratio, lump ore ratio, TFe content, FeO content, SiO2 content, CaO content, Al2O3 content, MgO content, Ni content, S content, Ti content, CO gas content, N2 gas content, iron ore particle size, iron ore mass, softening start temperature T10, and softening end temperature T40.

3. The method for predicting the softening droplet temperature of iron ore according to claim 2, characterized in that, In step 2, the input dataset for data filtering by correlation complexity includes: sinter ratio, pellet ratio, lump ore ratio, TFe content, FeO content, SiO2 content, CaO content, Al2O3 content, MgO content, CO gas content, and iron ore particle size. The filtered output dataset includes softening start temperature T10 and softening end temperature T40.

4. The method for predicting the softening droplet temperature of iron ore according to claim 1, characterized in that, The parameters set for the BP neural network model include at least: training data, validation data, test data, number of hidden layers, number of neurons, optimization algorithm, activation function, number of training iterations, and learning rate.

5. The method for predicting the softening droplet temperature of iron ore according to claim 4, characterized in that, The training data, validation data, and test data are 75%, 15%, and 15% of the prediction dataset, respectively, randomly sampled; the hidden layer is set to 1 layer, the number of neurons is set to 10, and the optimization algorithm is set to gradient descent. The activation function between the input layer and the hidden layer is set to The activation function between the hidden layer and the output layer is set to purelin(x) = x; the number of training iterations is set to 5000, and the learning rate is set to 0.

05.

6. The method for predicting the softening droplet temperature of iron ore according to any one of claims 1-5, characterized in that, The main body model of the iron ore softening droplet temperature measuring instrument includes at least a chemical reaction model, a heat transfer model, a mass transfer model, and a softening zone model.

7. The method for predicting the softening droplet temperature of iron ore according to any one of claims 1-5, characterized in that, The simulated iron ore softening and molten droplet experiment process includes solving the internal temperature field, pressure field, velocity field, and permeability index of the softening zone.

8. An apparatus for predicting the softening droplet temperature of iron ore, characterized in that, include: The data acquisition module is used to detect and analyze different sintered ores, pellets, lump ores and mixed ores, collect data and classify and organize the data. The collected data includes: the proportion of minerals contained, the chemical composition of minerals, the composition of reducing gases, the particle size of ore, the softening start temperature and the softening end temperature. The dataset generation module is used to take the proportion of minerals in the furnace charge, the chemical composition of the minerals, the composition of reducing gases and the particle size of the ore as the input dataset, and the softening start temperature and softening end temperature as the response dataset. It evaluates the correlation complexity between the input dataset and the response dataset based on the linear correlation analysis method, and performs data filtering based on the correlation complexity. The neural network model building module is used to build a BP neural network model based on the neural network algorithm. The neural network model optimization module is used to optimize the weights and bias parameters of the BP neural network model based on the particle swarm optimization algorithm to obtain the optimized BP neural network model. The geometric model building module is used to build the geometric model of the iron ore softening droplet temperature measuring instrument, set the dimensional parameters of the geometric model, and perform mesh generation on the geometric model; The ontological model building module is used to build an ontological model of the iron ore softening droplet temperature measuring instrument based on computational fluid dynamics and coupled with the geometric model of the iron ore softening droplet temperature measuring instrument. The softening start temperature and softening end temperature data are used as input conditions to simulate the iron ore softening droplet experimental process. By analyzing the simulation results of the ontological model of the iron ore softening droplet temperature measuring instrument, the degree of reduction of iron ore at the softening start temperature and softening end temperature is obtained. The observation dataset generation module is used to take the degree of reduction of iron ore at the softening start temperature and softening end temperature as new input data and combine them with the input dataset to form the observation dataset; The prediction model acquisition module is used to train an optimized BP neural network model by taking the observation dataset as the input of the neural network and the response dataset as the output of the neural network, and obtaining a prediction model for the softening droplet temperature of iron ore.

9. An electronic device, characterized in that, The device includes a processor, a memory, and a program stored in the memory and executable on the processor. When the electronic device is running, the processor executes the program to implement the steps of the method for predicting the softening droplet temperature of iron ore as described in any one of claims 1-7.

10. A storage medium, characterized in that, The storage medium stores a program that, when executed by a processor, performs the steps of the method for predicting the softening droplet temperature of iron ore as described in any one of claims 1-7.

Images