Method and device for predicting combustion rate of pulverized coal injected into blast furnace

Abstract

The invention discloses a method and a device for predicting the combustion rate of pulverized coal injected by a blast furnace. The method comprises the following steps: acquiring a combustion rate characterization parameter of a coal sample of the pulverized coal injected by the blast furnace; if the correlativity among the multiple combustion rate characterization parameters meets a first preset condition and / or the correlativity between the combustion rate characterization parameters and the corresponding historical combustion rates meets a second preset condition, screening the multiple combustion rate characterization parameters; and generating a combustion rate prediction model according to the plurality of screened combustion rate characterization parameters and the corresponding historical combustion rate, and predicting the combustion rate of the target blast furnace injection pulverized coal by using the combustion rate prediction model. According to the method, the combustion rates of different pulverized coal can be accurately calculated, so that the pulverized coal suitable for being injected by a blast furnace is determined, a steel mill can obtain higher production capacity and product quality under a safer operation condition, and the method has relatively strong practical significance.

Description

Technical Field

[0001] The present invention relates to the technical field of blast furnace ironmaking, and particularly relates to a method and device for predicting the combustion rate of pulverized coal injected into a blast furnace. Background Art

[0002] Although the existing methods for predicting the combustion rate of pulverized coal have certain scientificity and guiding significance in theory, they rely on multiple measurement data and model calculations, so there are certain systematic errors and measurement errors. At the same time, the prediction of the combustion rate of pulverized coal is affected by changes in blast furnace operating conditions. This method does not comprehensively cover all possible variables, resulting in certain limitations in the application effect. Summary of the Invention

[0003] An object of the present invention is to provide a method for predicting the combustion rate of pulverized coal injected into a blast furnace, so that the method can effectively calculate the combustion rates of different pulverized coals, thereby determining the pulverized coal suitable for injection into the blast furnace, enabling the steel plant to obtain higher production capacity and product quality under safer operating conditions.

[0004] Another object of the present invention is to provide a device for predicting the combustion rate of pulverized coal injected into a blast furnace. Still another object of the present invention is to provide an electronic device, which includes a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the steps of the above-mentioned method for predicting the combustion rate of pulverized coal injected into a blast furnace are implemented. Still another object of the present invention is to provide a readable medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the above-mentioned method for predicting the combustion rate of pulverized coal injected into a blast furnace are implemented.

[0005] To solve the technical problems in the background art of the present application, the present invention provides the following technical solutions:

[0006] In a first aspect, the present invention provides a method for predicting the combustion rate of pulverized coal injected into a blast furnace, including:

[0007] Obtaining the combustion rate characterization parameters of the coal sample of the pulverized coal injected into the blast furnace;

[0008] When the correlation relationship between multiple combustion rate characterization parameters meets a first preset condition and / or the correlation relationship between the combustion rate characterization parameter and its corresponding historical combustion rate meets a second preset condition, screening the multiple combustion rate characterization parameters;

[0009] Generating a combustion rate prediction model based on the screened multiple combustion rate characterization parameters and the corresponding historical combustion rates, and using the combustion rate prediction model to predict the combustion rate of the pulverized coal injected into the target blast furnace.

[0010] In some embodiments of the present invention, when the correlation relationship between multiple combustion rate characterization parameters satisfies the first preset condition and / or the correlation relationship between the combustion rate characterization parameter and its corresponding historical combustion rate satisfies the second preset condition, screening the multiple combustion rate characterization parameters includes:

[0011] When the correlation relationship between the multiple combustion rate characterization parameters is greater than 0.3 and / or the correlation relationship between the combustion rate characterization parameter and its corresponding historical combustion rate is greater than 0.3, perform principal component analysis on the multiple combustion rate characterization parameters to screen the multiple combustion rate characterization parameters.

[0012] In some embodiments of the present invention, performing principal component analysis on the multiple combustion rate characterization parameters includes:

[0013] Centralize the multiple combustion rate characterization parameters;

[0014] Calculate the covariance matrix of the multiple combustion rate characterization parameters according to the centralized result;

[0015] Perform eigenvalue decomposition on the covariance matrix;

[0016] Screen the multiple combustion rate characterization parameters according to the eigenvalue decomposition result.

[0017] In some embodiments of the present invention, the combustion rate characterization parameters include: ash content, volatile matter, fixed carbon content, carbon content, hydrogen content, oxygen content, basicity index, ignition point, explosibility, reactivity at 1000 °C, ash fusion temperature ST value, and effective calorific value.

[0018] In some embodiments of the present invention, generating a combustion rate prediction model according to the screened multiple combustion rate characterization parameters and the corresponding historical combustion rates includes:

[0019] Select at least one combustion rate characterization parameter from the screened multiple combustion rate characterization parameters;

[0020] Fit the selected at least one combustion rate characterization parameter and the corresponding historical combustion rate to generate multiple initial combustion rate prediction models;

[0021] Determine the combustion rate prediction model according to the fitting rate of each of the multiple initial combustion rate prediction models.

[0022] In a second aspect, the present invention provides a device for predicting the combustion rate of pulverized coal injected into a blast furnace. The device includes:

[0023] A combustion rate characterization parameter acquisition module, configured to acquire the combustion rate characterization parameters of a coal sample of pulverized coal injected into a blast furnace;

[0024] A combustion rate characterization parameter screening module, configured to screen the multiple combustion rate characterization parameters when the correlation relationship between the multiple combustion rate characterization parameters satisfies a first preset condition and / or the correlation relationship between the combustion rate characterization parameter and its corresponding historical combustion rate satisfies a second preset condition;

[0025] A combustion rate prediction module, configured to generate a combustion rate prediction model according to the screened multiple combustion rate characterization parameters and the corresponding historical combustion rates, and use the combustion rate prediction model to predict the combustion rate of pulverized coal injected into a target blast furnace.

[0026] In some embodiments of the present invention, the combustion rate characterization parameter screening module includes:

[0027] A combustion rate characterization parameter screening unit, configured to perform principal component analysis on the multiple combustion rate characterization parameters when the correlation relationship between the multiple combustion rate characterization parameters is greater than 0.3 and / or the correlation relationship between the combustion rate characterization parameter and its corresponding historical combustion rate is greater than 0.3, so as to screen the multiple combustion rate characterization parameters.

[0028] In some embodiments of the present invention, the combustion rate characterization parameter screening unit includes:

[0029] A combustion rate characterization parameter centering unit, configured to center the multiple combustion rate characterization parameters;

[0030] A covariance matrix calculation unit, configured to calculate the covariance matrix of the multiple combustion rate characterization parameters according to the centering result;

[0031] An eigenvalue decomposition unit, configured to perform eigenvalue decomposition on the covariance matrix;

[0032] A combustion rate characterization parameter screening subunit, configured to screen the multiple combustion rate characterization parameters according to the eigenvalue decomposition result.

[0033] In some embodiments of the present invention, the combustion rate characterization parameters include: ash content, volatile matter, fixed carbon content, carbon content, hydrogen content, oxygen content, basicity index, ignition point, explosibility, reactivity at 1000 °C, ST value of ash melting point, and effective calorific value.

[0034] In some embodiments of the present invention, the combustion rate prediction module includes:

[0035] A combustion rate characterization parameter selection unit, configured to select at least one combustion rate characterization parameter from the screened multiple combustion rate characterization parameters;

[0036] An initial model generation unit, configured to fit the selected at least one combustion rate characterization parameter and the corresponding historical combustion rates to generate multiple initial combustion rate prediction models;

[0037] A combustion rate prediction model determination unit is configured to determine the combustion rate prediction model according to the fitting rate of each of multiple initial combustion rate prediction models.

[0038] In a third aspect, the present invention provides a computer program product, including a computer program / instructions, and when the computer program / instructions are executed by a processor, the steps of a method for predicting the combustion rate of pulverized coal injected into a blast furnace are implemented.

[0039] In a fourth aspect, the present invention provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, and when the processor executes the program, the steps of a method for predicting the combustion rate of pulverized coal injected into a blast furnace are implemented.

[0040] In a fifth aspect, the present invention provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of a method for predicting the combustion rate of pulverized coal injected into a blast furnace are implemented.

[0041] As can be seen from the above description, the embodiments of the present invention provide a method and device for predicting the combustion rate of pulverized coal injected into a blast furnace. The corresponding method includes: First, obtain the combustion rate characterization parameters of the coal samples of the pulverized coal injected into the blast furnace; Then, screen multiple combustion rate characterization parameters according to the correlation between multiple combustion rate characterization parameters and / or the correlation between the combustion rate characterization parameters and their corresponding historical combustion rates; Finally, generate a combustion rate prediction model according to the screened multiple combustion rate characterization parameters and the corresponding historical combustion rates, and use the combustion rate prediction model to predict the combustion rate of the pulverized coal injected into the target blast furnace.

[0042] The present invention can accurately calculate the combustion rates of different pulverized coals, thereby determining the pulverized coal suitable for injection into the blast furnace, enabling the steel plant to obtain higher production capacity and product quality under safer operating conditions, and having strong practical significance. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the following drawings are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0044] Figure 1 It is a schematic flowchart of a method for predicting the combustion rate of pulverized coal injected into a blast furnace in an embodiment of the present invention;

[0045] Figure 2 It is a schematic flowchart of performing principal component analysis on combustion rate characterization parameters in an embodiment of the present invention;

[0046] Figure 3 Schematic flow chart of step 300 of a method for predicting the combustion rate of pulverized coal injected into a blast furnace in an embodiment of the present invention;

[0047] Figure 4 Schematic flow chart of a method for predicting the combustion rate of pulverized coal injected into a blast furnace in a specific embodiment of the present invention;

[0048] Figure 5 Technical flow chart of a method for predicting the combustion rate of pulverized coal injected into a blast furnace in a specific embodiment of the present invention;

[0049] Figure 6 Comparison chart between the predicted value and the experimental value of the combustion rate prediction model in a specific embodiment of the present invention;

[0050] Figure 7 Block diagram of a device for predicting the combustion rate of pulverized coal injected into a blast furnace in an embodiment of the present invention;

[0051] Figure 8 Block diagram of a combustion rate characterization parameter screening unit in an embodiment of the present invention;

[0052] Figure 9 Block diagram of a combustion rate prediction module 30 in an embodiment of the present invention;

[0053] Figure 10 Schematic structural diagram of an electronic device in an embodiment of the present invention. Specific embodiments

[0054] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0055] Those skilled in the art should understand that the embodiments of the present invention may be provided as a method, a system, or a computer program product. Therefore, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention may take the form of a computer program product implemented 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.

[0056] It should be noted that the terms "including" and "having" and any variations thereof in the description, claims and the above-mentioned drawings of this application are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices. Without conflict, the embodiments in this application and the features in the embodiments can be combined with each other. The following will detail this application with reference to the drawings and in combination with the embodiments.

[0057] The technology of injecting pulverized coal into blast furnaces is a major technological breakthrough in the field of modern blast furnace smelting. It is of great significance for alleviating the shortage of coking coal resources in iron and steel enterprises, reducing coke ratio and production costs, and has become the mainstream direction of the progress of global ironmaking technology. As an efficient auxiliary fuel, injecting pulverized coal into blast furnaces can replace up to 30% or even more of coke consumption. This not only significantly reduces the production cost per ton of iron, but also increases the gas output, optimizes the energy configuration of integrated iron and steel enterprises, greatly improves economic benefits, and also plays a positive role in environmental protection. The technology of injecting pulverized coal into blast furnaces has been widely applied, and its advantages are mainly reflected in: First, using affordable pulverized coal to replace high-price coke not only reduces the cost of hot metal smelting, but also alleviates the environmental burden of coking production; Second, the endothermic pyrolysis of high-volatile pulverized coal in the tuyere raceway paves the way for the implementation of high-temperature air and oxygen-enriched operations in blast furnaces, helping to improve the smelting efficiency of blast furnaces; Third, the hydrogen element rich in pulverized coal shows strong penetration in the reduction reaction. The heat and reducing gases generated by the combustion of pulverized coal help to accelerate the reduction process of iron ore, improve the production efficiency of blast furnaces, and stabilize the operation state of blast furnaces.

[0058] However, the combustibility of pulverized coal determines the utilization rate of pulverized coal in blast furnaces. If the combustion rate of pulverized coal is low during the process of increasing the coal injection ratio, a large amount of unburned pulverized coal will remain in the softening-melting zone and dripping zone of the blast furnace, which not only reduces the permeability of the burden, but also leads to deteriorated combustion conditions, uneven distribution of coal gas flow, increased pressure difference, increased heat loss of the furnace wall, and a decrease in the utilization rate of pulverized coal. Therefore, the combustibility of pulverized coal is one of the key indicators for evaluating the coal used in blast furnace injection.

[0059] The patent application with the publication number CN114724640A discloses a calculation method for the combustion rate of pulverized coal injected into the blast furnace tuyere. This method first analyzes the physical and chemical properties of the pulverized coal injected into the blast furnace to obtain data such as the fixed carbon content, volatile matter content, hydrogen element content, oxygen element content, and average particle size value of the pulverized coal. Subsequently, the smelting technical parameters related to blast furnace production are obtained, including the injection volume of hydrogen-rich gas, the composition of hydrogen-rich gas, the coal injection ratio, the blast volume per ton of iron, the oxygen content in the blast, and the theoretical combustion temperature of the tuyere. Through these data, the remaining oxygen content and the gas residence time after the combustion of hydrogen-rich gas in the tuyere are calculated. Combining with the gas-solid combustion kinetics model, the combustion rate of the pulverized coal injected into the blast furnace is finally calculated through parameters such as the coal injection ratio, the remaining oxygen content after the combustion of hydrogen-rich gas, the particle size of the pulverized coal, and the theoretical combustion temperature of the tuyere. This method provides important guidance for optimizing the selection of pulverized coal and the co-injection scheme of hydrogen-rich gas. Specifically, it includes: 1. Optimizing the selection of pulverized coal types according to the combustion rate of the pulverized coal injected into the blast furnace, and selecting pulverized coal with a higher combustion rate for injection; 2. Determining the influence of the coal injection ratio and the oxygen content in the blast on the combustion rate, and formulating a reasonable injection and oxygen enrichment strategy; 3. Evaluating the influence of hydrogen-rich gas on the combustion rate, so as to select the best hydrogen-rich gas injection scheme.

[0060] Although the above method has certain scientificity and guiding significance in theory, it relies on multiple measurement data and model calculations, so there are certain systematic errors and measurement errors. At the same time, the prediction of the pulverized coal combustion rate is affected by the changes in the blast furnace operating conditions. This method does not comprehensively cover all possible variables, resulting in certain limitations in the application effect.

[0061] The patent application with the publication number CN114724640A discloses a calculation method for the combustion rate of pulverized coal injected into the blast furnace tuyere, including: analyzing the physical and chemical properties of the pulverized coal injected into the blast furnace; obtaining the smelting technical data of the production blast furnace; calculating the remaining oxygen content and the gas residence time after the combustion of hydrogen-rich gas in the tuyere, and the remaining oxygen content after the combustion of hydrogen-rich gas is calculated through the oxygen content in the blast, the injection volume of hydrogen-rich gas, the blast volume per ton of iron, and the composition of hydrogen-rich gas; the combustion rate of the pulverized coal is calculated through the remaining oxygen content after the combustion of hydrogen-rich gas, the average particle size value, and the theoretical combustion temperature of the tuyere; the combustion rate of the pulverized coal injected into the blast furnace is calculated according to the gas-solid combustion kinetics model under turbulent conditions through the coal injection ratio, the remaining oxygen content after the combustion of hydrogen-rich gas, the average particle size value, the theoretical combustion temperature of the tuyere, and the gas residence time. The present invention provides important guidance for the optimized selection of pulverized coal injected into the blast furnace and the co-injection of hydrogen-rich gas. Specifically, the patent application discloses the following technical features:

[0062] (1) Analyze the physical and chemical properties of the pulverized coal injected into the blast furnace to obtain the fixed carbon content, volatile content, hydrogen element content, oxygen element content, and average particle size value. The composition of the pulverized coal injected into the blast furnace uses dry basis data, and the fixed carbon content and the volatile content are denoted as w(FC) and w(V) respectively; the hydrogen element content and the oxygen element content are denoted as w(H) and w(O) respectively; and the average particle size value is analyzed using a laser particle size analyzer, and the D50 value is used as the average particle size value of the pulverized coal injected into the blast furnace, denoted as d50.

[0063] (2) Obtain the blast furnace smelting technology data, including the injection amount of hydrogen-rich gas, the composition of hydrogen-rich gas, the coal injection ratio, the blast volume per ton of iron, the oxygen content in the blast, and the theoretical combustion temperature at the tuyere.

[0064] (3) According to the characteristics of gas-gas combustion reaction, calculate the remaining oxygen content and the gas residence time after the combustion of hydrogen-rich gas in the tuyere. The remaining oxygen content after the combustion of hydrogen-rich gas is calculated from the oxygen content in the blast, the injection amount of hydrogen-rich gas, the blast volume per ton of iron, and the composition of hydrogen-rich gas:

[0065] According to the characteristics of gas-solid combustion reaction, calculate the combustion rate of pulverized coal in the tuyere. The combustion rate of pulverized coal is calculated from the remaining oxygen content after the combustion of hydrogen-rich gas, the average particle size value, and the theoretical combustion temperature at the tuyere: Combustion rate of pulverized coal and the activation energy E of the basic characteristics of the pulverized coal combustion reaction coal 、reaction rate constant k coal and the combustion rate x of the pulverized coal injected into the blast furnace at time t conform to the following relationship:

[0066]

[0067] where R is 8.314 J / K, E coal =a - b·w(V), k_coal = m - n·(w(H)+

[0068] w(O)) / w(FC).

[0069] where the value ranges of a, b, m, and n are 154000 < a < 170000, 50000 < b < 70000, 40 < m < 60, and 0.4 < n < 0.6 respectively.

[0070] where the gas residence time t gas is calculated based on the volume V of the tuyere raceway raceway and the gas production volume V per unit time at the tuyere gas obtained:

[0071]

[0072] (4) Based on the physical and chemical characteristics of pulverized coal injected into the blast furnace and the blast furnace smelting technical data, the combustion rate of pulverized coal injected into the blast furnace is calculated according to the gas-solid combustion kinetics model under turbulent conditions. The combustion rate of pulverized coal injected into the blast furnace is calculated through the coal injection ratio, the remaining oxygen content after the combustion of the hydrogen-rich gas, the average particle size value, the theoretical combustion temperature at the tuyere, and the gas residence time.

[0073]

[0074] The above method is based on gas-gas and gas-solid combustion kinetics models. Although it can reflect the general laws of pulverized coal combustion, it does not fully consider the dynamic factors in the actual operation of the blast furnace (such as equipment wear and air flow distribution fluctuations), which may lead to deviations in the calculation results.

[0075] Secondly, this method only selects several core physical and chemical parameters such as fixed carbon content, volatile matter, and hydrogen content. The combustion rate of a single blast furnace may also be affected by factors such as ash composition, which will lead to inaccurate calculation results. Although this method mentions that it can be used for the calculation of various fuels (such as anthracite, biomass carbonized fuel, etc.), it does not specifically describe the applicability and reliability for mixed fuels (such as the synergistic effect of biomass and bituminous coal). This method highly depends on the accuracy of the input parameters. For example, there may be errors in the measurement of the composition of hydrogen-rich gas and the gas residence time, which will directly affect the reliability of the calculation results.

[0076] Next, the patent application with the publication number CN 117451916 A provides a method for simulating and testing the combustion rate of pulverized coal at the tuyere of a hydrogen-rich blast furnace. The amount of hydrogen-rich gas injected per single tuyere, the amount of pulverized coal injected, the amount of oxygen-rich gas injected, and the amount of carrier gas are determined from the process parameters of the hydrogen-rich blast furnace, and the molar amount of carbon atoms, the molar amount of oxygen atoms, the oxygen-carbon atom ratio, and the volume ratio of oxygen and hydrogen-rich gas are calculated; combined with the pipeline of the new type of blast furnace composite injection simulation experimental device, the experimental oxygen volume and the hot air volume are obtained, so as to calculate the amount of pulverized coal injected, the amount of hydrogen-rich gas, the volume fraction of oxygen in the carrier gas, and the volume fraction of nitrogen under the experimental conditions; finally, experiments are carried out according to the obtained experimental parameters, and the combustion rate is calculated in cooperation with the experimental results. The present invention scientifically calculates the actual working conditions of the hydrogen-rich blast furnace, obtains the simulation parameters under the experimental conditions, and conducts a combustion rate experiment, simulating the behavior of pulverized coal injection into the furnace and its combustion process in the hydrogen-rich blast furnace, accurately reflecting the actual combustion rate of pulverized coal at the tuyere, and having guiding significance for the actual production of the hydrogen-rich blast furnace. Specifically, the patent application discloses the following technical features:

[0077] (1) Determine the amount of hydrogen-rich gas injected per single tuyere of the blast furnace, the amount of pulverized coal injected per single tuyere, the amount of oxygen-rich gas injected per single tuyere, and the amount of carrier gas injected per single tuyere from the process parameters of the actual blast furnace;

[0078] (2) Determine the molar amount of carbon atoms in a single tuyere from the amount of pulverized coal injected through a single tuyere described in step (1), and determine the molar amount of oxygen atoms in a single tuyere from the amount of oxygen-enriched gas injected through a single tuyere, thereby obtaining the oxygen-to-carbon atom ratio; obtain the volume ratio of oxygen gas and oxygen-enriched gas from the amount of oxygen-enriched gas injected through a single tuyere and the amount of hydrogen-rich gas injected through a single tuyere;

[0079] (3) Obtain the experimental oxygen gas volume and experimental hot air volume based on the pipelines of the new type of blast furnace combined injection simulation experimental device, and calculate the experimental pulverized coal injection amount, experimental hydrogen-rich gas injection amount, experimental oxygen volume fraction and nitrogen volume fraction in the carrier gas under the experimental conditions according to the oxygen-to-carbon atom ratio and the volume ratio of oxygen gas and hydrogen-rich gas;

[0080] (4) Conduct experiments in the new type of blast furnace combined injection simulation experimental device according to the experimental pulverized coal injection amount, experimental hydrogen-rich gas injection amount, experimental oxygen volume fraction and nitrogen volume fraction obtained in step 3, and calculate the combustion rate according to the results of the gas analyzer; the calculation formula of the combustion rate is as follows:

[0081]

[0082] In the formula: X CO Are respectively the molar fractions of CO2 and CO generated by burning 0.1 g of pulverized coal material measured by the gas analyzer; Is the molar fraction of CO2 generated by complete combustion of carbon in pulverized coal and hydrogen-rich gas theoretically.

[0083] This method uses multiple mathematical models to calculate experimental parameters such as the oxygen-to-carbon atom ratio and the volume ratio of oxygen gas and hydrogen-rich gas. These models are theoretically reasonable, but in practical applications, due to the complexity inside the blast furnace, the matching degree of the models may be affected to a certain extent. In addition, this method relies on a series of precise calculation processes and model construction to achieve an in-depth simulation of the pulverized coal combustion process at the blast furnace tuyere. It should be noted that the acquisition of blast furnace data needs to cover many different physical and chemical parameters, which not only have significant differences in dimensions, but also have a very wide numerical range.

[0084] The mixing effect of hydrogen-rich gas and pulverized coal may be difficult to fully simulate the actual situation in the blast furnace in the laboratory. In the blast furnace, hydrogen-rich gas and pulverized coal are mixed and burned under the action of high-speed airflow, while it may be difficult to achieve this high-speed mixing effect in the laboratory. If the mixing effect is not good, it will directly affect the combustion efficiency and combustion rate of pulverized coal. In addition, the mixing effect may also be affected by the experimental device and operation process, further increasing the uncertainty of the experimental results.

[0085] For the above-mentioned various reasons, the embodiments of the present invention provide a specific implementation manner of a prediction method for the combustion rate of pulverized coal injected into a blast furnace. SeeFigure 1 , the method specifically includes the following contents:

[0086] Step 100: Obtain the combustion rate characterization parameters of the coal samples for pulverized coal injection in the blast furnace.

[0087] Step 200: When the correlation relationships between multiple combustion rate characterization parameters satisfy the first preset condition and / or the correlation relationship between the combustion rate characterization parameter and its corresponding historical combustion rate satisfies the second preset condition, screen the multiple combustion rate characterization parameters.

[0088] Step 300: Generate a combustion rate prediction model based on the screened multiple combustion rate characterization parameters and the corresponding historical combustion rates, and use the combustion rate prediction model to predict the combustion rate of the target pulverized coal injection in the blast furnace.

[0089] In some embodiments of the present invention, the combustion rate characterization parameters in Step 100 include: ash content, volatile matter, fixed carbon content, carbon content, hydrogen content, oxygen content, basicity index (AI), ignition point, explosibility, reactivity at 1000°C, ST value of ash melting point, and effective calorific value.

[0090] For Step 100, a new type of simulated combustion test device for pulverized coal injection in the blast furnace is used to conduct combustion tests on 50 coal samples under high temperature and high pressure. Then, unburned pulverized coal is prepared, and the co-gasification reaction of unburned pulverized coal and columnar coke is studied in combination with the actual production of the blast furnace, and the influence mechanism of unburned pulverized coal on coke strength is analyzed emphatically. Thus, technical data generated during the pulverized coal combustion process are obtained, including data of 12 pulverized coal parameter indexes such as ash content, volatile matter, fixed carbon content, carbon content, hydrogen content, oxygen content, basicity index (AI), ignition point, explosibility, reactivity at 1000°C, ST value of ash melting point, and effective calorific value (ECV) as input variables for the subsequent combustion rate prediction model.

[0091] The applicable ranges of the above 12 pulverized coal parameter indexes are: ash content Aad: 2.5 - 14%, volatile matter Vad: 8 - 32%, fixed carbon content FCad: 52 - 81%, carbon content Cad: 64.5 - 80%, hydrogen content Had: 3.5 - 5%, oxygen content Oad: 2.5 - 20%, AI: 1.5 - 9.5%, ignition point: 273 - 410°C, explosibility: 0 - 800mm, reactivity (1000°C): 13 - 100%, ST value of ash melting point: 1010 - 1400°C, and effective calorific value: 5397 - 7025 kJ / kg.

[0092] For the above basicity index (basic catalytic index of coal char combustion (AI)), it is used to characterize the catalytic effect of minerals in ash on the combustion reactivity, and is calculated by the following formula:

[0093]

[0094] Where: Ash represents the ash content in coal, %; wt CaO 、wt MgO 、 and are the percentage contents of various substances in the ash, % respectively.

[0095] For step 200, it is necessary to further determine whether there is a linear correlation between the 12 input variable parameters of the coal and the combustion rate of the prediction variable parameter, and diagnose whether there is a collinearity problem among the variables. When the correlation between multiple combustion rate characterization parameters and / or the correlation between the combustion rate characterization parameter and its corresponding historical combustion rate is too high, it means that there is a high correlation among the input variables. Therefore, it is necessary to screen multiple combustion rate characterization parameters.

[0096] For step 300, 12 parameter indicators of 50 kinds of pulverized coal are used as input variables, and the combustion rate of the pulverized coal is used as the prediction variable for multiple linear regression analysis. First, the principal component dimensionality reduction is performed according to n = 1 - 12 dimensions to generate a principal component transformation coefficient report. Then, a regression model is built under each dimension, and the corresponding main report and the performance reports of 3 evaluation indicators (mean squared error (MSE), root mean squared error (RMSE), goodness of fit (R Squared)) are generated. Based on the performance reports, a judgment can be made on the model. By the method of excluding high-ash coal types and special-property coal types one by one, the accuracy and fitting optimization degree of the prediction model are optimized. Compare the model performances under different principal component dimensions and select the optimal principal component dimension.

[0097] In some embodiments of the present invention, step 200 includes:

[0098] If the correlation between the multiple combustion rate characterization parameters is greater than 0.3 and / or the correlation between the combustion rate characterization parameter and its corresponding historical combustion rate is greater than 0.3, perform principal component analysis on the multiple combustion rate characterization parameters to screen the multiple combustion rate characterization parameters.

[0099] It can be understood that the above steps include the following three situations:

[0100] (1) The correlation between multiple combustion rate characterization parameters is greater than 0.3, but the correlation between the combustion rate characterization parameter and its corresponding historical combustion rate is not greater than 0.3;

[0101] (2) The correlation between multiple combustion rate characterization parameters is not greater than 0.3, but the correlation between the combustion rate characterization parameter and its corresponding historical combustion rate is greater than 0.3;

[0102] (3) The correlation between multiple combustion rate characterization parameters and the correlation between a combustion rate characterization parameter and its corresponding historical combustion rate are both greater than 0.3;

[0103] All of the above three cases are in the action of triggering the screening of multiple combustion rate characterization parameters, that is, as long as one (any one) of the correlation between multiple combustion rate characterization parameters and the correlation between a combustion rate characterization parameter and its corresponding historical combustion rate is greater than 0.3, it is necessary to screen multiple combustion rate characterization parameters.

[0104] Specifically, through linear correlation analysis, the correlation coefficients of multiple combustion rate characterization parameters are between 0.37 and 0.85, and the absolute values of the correlation coefficients between 12 input variables are greater than 0.3, indicating a high degree of correlation between the input variables. Therefore, it is necessary to perform a dimensionality reduction operation on the 12 input variables.

[0105] In some embodiments of the present invention, referring to Figure 2 , the principal component analysis of the multiple combustion rate characterization parameters in step 201 includes:

[0106] Step 2011: Centralize the multiple combustion rate characterization parameters;

[0107] Step 2012: Calculate the covariance matrix of the multiple combustion rate characterization parameters according to the centralized result;

[0108] Step 2013: Perform eigenvalue decomposition on the covariance matrix;

[0109] Step 2014: Screen the multiple combustion rate characterization parameters according to the eigenvalue decomposition result.

[0110] In steps 2011 to 2014, principal component dimensionality reduction is performed on 12 input variable indicators of 50 kinds of pulverized coal through Python language combined with the Scikit-learn (sklearn) code library. Taking 12 parameter indicators of 50 kinds of pulverized coal as input variables, principal component dimensionality reduction is performed according to n = 1 - 12 dimensions and a principal component transformation coefficient report is generated. The algorithm description of the principal component analysis is as follows:

[0111] Table 1 Algorithm description of principal component analysis in steps 2011 to 2014

[0112]

[0113]

[0114] Divide the sample data sets corresponding to multiple burning rate characterization parameters into a training set and a test set (preferably, use the PCA algorithm to perform dimensionality reduction processing on the data samples to obtain sample data sets of the transformed variables and parameters under different dimensions), and import them into a multiple linear regression model for training and verification (divide the sample data sets into a training set and a test set in the leave-one-out method, and import them into multiple linear regression for training and verification), obtain a regression equation based on the data sets after dimensionality reduction according to different schemes, determine the optimal dimensionality reduction dimension through evaluation indicators, and obtain a burning rate prediction equation.

[0115] In some embodiments of the present invention, refer to Figure 3 , generating a burning rate prediction model according to the selected multiple burning rate characterization parameters and the corresponding historical burning rates in step 300 includes:

[0116] Step 301: Select at least one burning rate characterization parameter from the selected multiple burning rate characterization parameters;

[0117] Step 302: Fit the selected at least one burning rate characterization parameter and the corresponding historical burning rates to generate multiple initial burning rate prediction models;

[0118] Step 303: Determine the burning rate prediction model according to the fitting rate of each of the multiple initial burning rate prediction models.

[0119] In steps 301 to 303, the 12 parameter indicators of 50 kinds of pulverized coal are reduced to different dimensions, and a multiple linear regression (MLR) model is established based on the data after dimensionality reduction to predict the burning rate of pulverized coal, and the most suitable dimension is determined according to the model prediction accuracy and prediction range.

[0120] To further illustrate the solution, the present invention also provides a specific implementation manner of a method for predicting the burning rate of pulverized coal injected into a blast furnace, which specifically includes the following content:

[0121] In the blast furnace ironmaking process, to maximize efficiency and minimize costs, the combustion efficiency of the pulverized coal injection technology in blast furnaces has become the core issue of industry research and attention. The combustion condition of pulverized coal in the blast furnace directly determines its impact on blast furnace production, and the working conditions experienced by the injected pulverized coal when entering the blast furnace interior are extremely harsh. In the direct injection pipe - tuyere - raceway system, the residence time of coal particles is only about 20 milliseconds. Even in an oxygen - enriched environment, complete gasification of pulverized coal cannot be achieved, and there will always be a certain amount of unburned pulverized coal remaining. The pulverized coal combustion rate is not only an important indicator for evaluating the combustion performance of pulverized coal but also a key parameter for blast furnace operation efficiency and the coal - coke replacement ratio. A low combustion rate will lead to the accumulation of unburned pulverized coal, affecting the gas flow distribution, burden permeability, and overall smelting stability in the blast furnace, thus significantly increasing production costs. Therefore, improving the pulverized coal combustion rate has become the core goal of current optimization of the pulverized coal injection technology in blast furnaces. Currently, the industry mainly improves the combustion rate through the following technical means: selecting pulverized coal with high combustion performance, increasing the oxygen - enrichment rate, raising the blast temperature, reducing the pulverized coal particle size, and using new injection devices, etc. However, although these technical measures are helpful for improving the combustion rate, there is still a lack of a systematic and effective solution for accurately predicting the combustion rates of different coal types, which has become a key technical problem to be urgently solved.

[0122] Among them, machine - learning algorithms, due to their powerful data - processing capabilities and pattern - recognition capabilities, have shown great potential in predicting the pulverized coal combustion rate. By collecting a large amount of historical data, including the combustion performance of different coal types under various operating conditions, accurate prediction models can be trained. These models can not only learn the complex relationship between pulverized coal characteristics and the combustion rate but also capture the subtle impact of fine - tuning of blast furnace operating parameters on combustion efficiency.

[0123] Based on the combustion rate test results of 50 kinds of pulverized coal (including bituminous coal, anthracite, and blended coal) and the corresponding physical and chemical indexes as basic data, this invention uses the Python programming language combined with the principal component analysis (PCA) data - mining technology to conduct a correlation analysis between multiple indexes of pulverized coal and the combustion rate and establish a regression model, proposes a prediction formula for the combustion rate of pulverized coal injected into blast furnaces, as well as the prediction accuracy and range, aiming to accurately predict the pulverized coal combustion rate and provide guidance for pre - judging the pulverized coal combustion condition at the production site of pulverized coal injection into blast furnaces.

[0124] First, refer to Figure 4 and Figure 5 , the above - mentioned specific implementation method includes the following steps:

[0125] S1: Select the combustion rate characterization parameters.

[0126] S2: Conduct a correlation analysis between the combustion rate characterization parameters.

[0127] S3: Conduct Python - principal component analysis / dimensionality reduction on the combustion rate characterization parameters.

[0128] S4: Optimization and analysis of the combustion rate prediction model.

[0129] Specifically, the following six schemes are optimized according to the methods shown in steps S1 to S4:

[0130] Scheme 1: The 12 parameter indicators of 50 kinds of pulverized coal are reduced to different dimensions, and a multiple linear regression (MLR) model is established based on the reduced data to predict the combustion rate of pulverized coal. The results show that when reduced to 6 dimensions, the prediction accuracy of the model is the highest, but the prediction range is relatively wide, and the prediction effect for high-ash coal types is not good.

[0131] Scheme 2: On the basis of Scheme 1, after excluding high-ash blended coal 1 (the ash content of this pulverized coal is too high and not suitable for blast furnace injection), principal component analysis (PCA) dimensionality reduction and multiple linear regression (MLR) modeling are carried out again. The results show that the accuracy and precision of the 7-dimensional model for predicting the combustion rate of pulverized coal are improved compared with Scheme 1.

[0132] Scheme 3: On the basis of Scheme 2, by further excluding special coal types (in the comparison chart of the predicted value and experimental value of Scheme 2, the predicted value of the combustion rate of this pulverized coal is almost very close to the experimental value, but its ash content is relatively high and usually not within the range of blast furnace injection procurement coal types), principal component analysis (PCA) dimensionality reduction and multiple linear regression (MLR) modeling are carried out again. The results show that although the prediction accuracy is slightly improved, the overall model performance optimization is not obvious, and the model prediction range is further narrowed. The MSE and RMSE are increased by 0.08% and 0.02% respectively compared with Scheme 2.

[0133] Scheme 4: On the basis of Scheme 3, an attempt is made to remove more high-ash coal types, and it is found that the model performance is not significantly improved, and the dimensionality reduction dimension increases, failing to achieve the purpose of principal component dimensionality reduction.

[0134] Scheme 5: On the basis of Scheme 4, specific high basicity index coal types are removed, and the model accuracy and precision are slightly decreased.

[0135] Scheme 6: On the basis of Scheme 5, the explosive index is removed, and the model performance is not significantly optimized, proving that this index has no negative impact on the model.

[0136] From the analysis results of principal component dimensionality reduction of 12 parameter indicators of 50 kinds of pulverized coal and the establishment of a multiple regression model, it can be seen that high-ash coal types are likely to reduce the accuracy and precision of the prediction model; the basicity index and explosive index have no negative impact on the performance of the prediction model. Therefore, considering comprehensively, Scheme 3 (n = 7 dimensions) is selected as the final prediction model. The variables and parameters after the principal component dimensionality reduction of the 12 parameter indicators of the 48 kinds of pulverized coal corresponding to Scheme 3 to n = 7 are shown in Table 2.

[0137] Table 2 Transformed Variables and Parameters When the Principal Components of Scheme III are Reduced to n = 7

[0138] Parameter <![CDATA[A ad > <![CDATA[V ad > <![CDATA[FC ad > <![CDATA[C ad > <![CDATA[H ad > <![CDATA[O ad > <![CDATA[X 0 > -0.00035 -0.013714 -0.01754 0.00963 -0.000335 -0.005253 <![CDATA[X 1 > -0.00591 0.00889 0.005973 -0.000918 0.00074 0.00545 <![CDATA[X 2 > 0.0041 -0.023745 -0.02626 0.01372 -0.00057 -0.0121 <![CDATA[X 3 > 0.01006 -0.046046 -0.05009 0.02603 -0.00317 -0.036 <![CDATA[X 4 > -0.00748 0.067146 -0.10188 -0.08818 -0.00122 0.0654 <![CDATA[X 5 > 0.00644 -0.66803 0.68945 0.217212 -0.00612 -0.0309 <![CDATA[X 6 > 0.6556 -0.39221 -0.22881 -0.52253 -0.0670 -0.2901 Parameter AI Fire Explosion React ST ECV <![CDATA[X 0 > -0.0009 0.0591 -0.4524 -0.0461 0.2247 0.8594 <![CDATA[X 1 > 0.00005 -0.0342 0.8617 0.03376 -0.1223 0.4900 <![CDATA[X 2 > 0.00036 0.0334 0.2233 -0.1320 0.9668 -0.1423 <![CDATA[X 3 > -0.0128 -0.9392 0.05402 -0.3129 -0.0967 -0.02996 <![CDATA[X 4 > 0.0687 0.3332 -0.00513 0.9177 0.1225 -0.00382 <![CDATA[X 5 > -0.0474 -0.0255 0.006894 0.1638 -0.01846 -0.00842 <![CDATA[X 6 > 0.0413 -0.0167 0.004116 -0.0174 -0.00436 0.00629

[0139] Multiple Linear Regression (MLR) The formula for multiple linear regression is:

[0140] y i = β 0 + β 1 x i1 + β 1 x i2 +... + β p x p + ∈

[0141] Where: i = n observations;

[0142] y i —— Dependent variable;

[0143] x i —— Explanatory variables;

[0144] β 0 —— y - intercept / constant term;

[0145] β p —— Slope coefficients of each explanatory variable;

[0146] ∈ —— The model's error term / residual.

[0147] The above multiple linear regression model has the following basic assumptions:

[0148] (1) There is a linear relationship between the dependent variable and the explanatory variables;

[0149] (2) The explanatory variables are uncorrelated with each other (no multicollinearity);

[0150] (3) y i The overall observed values are independent and random;

[0151] (4) The residuals should be normally distributed, with a mean of 0 and a variance of σ.

[0152] In this paper, three evaluation indicators, namely mean squared error (MSE), root mean squared error (RMSE), and coefficient of determination (R Squared), are selected to optimize the pulverized coal combustion rate prediction model. The introduction of the three evaluation indicators is as follows.

[0153] Mean Squared Error (MSE): The range is [0, +∞). When the predicted value is exactly the same as the experimental value, its value is 0, which means the model can fully predict the experimental value; the larger this value is, the greater the error.

[0154] Root Mean Squared Error (RMSE): Taking the square root of the mean squared error gives the root mean squared error. The error result is at the same level as the original data and is more intuitive in terms of magnitude. Also, the larger this value is, the greater the error.

[0155] Coefficient of Determination (R Squared): It represents the goodness of fit of the regression model to the experimental values. The normal range of values is [0, 1]. The larger the R 2 the better the fitting effect, that is, the stronger the explanatory ability of the variables in the model equation for the predicted variable; the optimal value of R is 1; if R 2 appears as a negative number, it indicates that the model is incorrect and there is a non - linear relationship in the data. 2

[0156] Prediction formula for pulverized coal combustion rate: Through the above - mentioned principal component dimensionality reduction analysis, 12 original variables are transformed into 7 new variables X0 - X6. Then, using the Python language and the Scikit - learn code library, a multiple linear regression prediction model for the pulverized coal combustion rate in blast furnace injection is established based on 50 groups of data of the saved pulverized coal samples. The obtained combustion rate prediction regression equation is shown as follows.

[0157] y = - 0.00664637X 0 + 0.00573765X 1 - 0.02141882X 2 - 0.02493836X 3

[0158] + 0.12165323X 4 - 0.27268767X 5 - 0.32409567X 6 + 75.388

[0159] Since the training set is different each time, there are 50 value cases for variables X0 - X6. Therefore, on the premise of determining that Scheme 3 with n = 7 is the optimal model, adding the original 1 - group data that was used as the test set to the training set and using 50 groups of data for the regression model will not seriously affect the prediction accuracy. The final form of the prediction model for the pulverized coal combustion rate in blast furnace injection after arrangement is shown as follows.

[0160] y = - 0.2155×A ad + 0.3188×V ad - 0.1282×FC ad + 0.0984×C ad + 0.0233×H​ad

[0161] +0.1116×O ad +0.0083×AI + 0.0282×Fire - 0.0020×Explosion

[0162] +0.0839×React + 0.0012×ST + 0.0007×ECV + 48.442

[0163] In the formula: y—the pulverized coal combustion rate, %;

[0164] A ad —the ash content in air-dried coal, %;

[0165] V ad —the volatile content in air-dried coal, %;

[0166] FC ad —the fixed carbon content in air-dried coal, %;

[0167] C ad —the carbon element content in air-dried coal, %;

[0168] H ad —the hydrogen element content in air-dried coal, %;

[0169] O ad —the oxygen element content in air-dried coal, %;

[0170] AI—the basicity index of coal, %;

[0171] Fire—the ignition point of coal, °C;

[0172] Explosion—the explosibility of coal, mm;

[0173] React—the reactivity of coal at 1000°C, %;

[0174] T—the ST value of the ash fusion temperature of coal, °C;

[0175] ECV—the effective calorific value of coal, kJ / kg.

[0176] Applicable range of pulverized coal parameters: The applicable range of coal type parameters for this pulverized coal combustion rate prediction model is shown in Table 3 below:

[0177] Table 3 Applicable range of coal type parameters for the pulverized coal combustion rate prediction model

[0178]

[0179] See Figure 6, when this model predicts the combustion rate of pulverized coal injected into the blast furnace, the error range of the prediction accuracy is ±2.02%, the upper boundary of the prediction accuracy is +5%, and the lower boundary is -7%. The goodness of fit R 2 is 0.747.

[0180] Select the blast furnaces injecting pulverized coal for analysis. The measured values of the pulverized coal quality for blast furnace injection are shown in Table 4 as follows:

[0181] Table 4 Composition Indexes of Pulverized Coal for Blast Furnace Injection

[0182]

[0183] According to the two sets of pulverized coal data provided in Table 4 and substituting them into the combustion rate prediction formula, the predicted combustion rates of the two kinds of pulverized coal can be obtained. At the same time, the true combustion rates of these two kinds of pulverized coal are measured through experiments for comparison, as shown in Table 5 below.

[0184] Table 5 Measured Combustion Rate and Predicted Combustion Rate

[0185] Combustion rate, % Predicted combustion rate, % Coal type - 1 72.058 72.97 Coal type - 2 66.80 65.49

[0186] As can be seen from the above table, the error ranges between the combustion rates calculated according to the regression model using the basic data and the combustion rates obtained from the actual experiments are all within ±2.02%. It can be seen that the combustion rate of pulverized coal - 1 is better than that of pulverized coal - 2 as the pulverized coal for blast furnace injection.

[0187] From the above description, the specific implementation mode of the present invention provides a method for predicting the combustion rate of pulverized coal injected into the blast furnace, including: collecting 12 pulverized coal parameter indexes such as ash content, volatile matter, fixed carbon content, carbon content, hydrogen content, oxygen content, basicity index (AI), ignition point, explosibility, reactivity at 1000°C, ash softening temperature ST value, and effective calorific value (ECV) of 50 kinds of pulverized coal to obtain a sample data set; performing dimensionality reduction processing on the collected data in different sample data schemes in sequence to obtain a sample data set; dividing the sample data set into a training set and a test set, and importing them into a multiple linear regression model for training and verification, obtaining a regression equation according to the data set after dimensionality reduction in different schemes, judging the optimal dimensionality reduction dimension through evaluation indexes, and obtaining a combustion rate prediction equation; converting the obtained prediction equation related to the dimensionality reduction data into a prediction equation related to the combustion rate and 12 pulverized coal indexes.

[0188] The present invention proposes a high - precision method that applies big data model training to the prediction of the combustion rate of pulverized coal injected into the blast furnace, which can effectively help calculate the combustion rates of different pulverized coals, thereby determining the pulverized coal suitable for blast furnace injection, enabling the steel plant to obtain higher production capacity and product quality under safer operating conditions, and having strong practical significance. Specifically, the present invention has the following beneficial effects:

[0189] 1. Through comprehensive analysis of the combustion rate test data and multiple physical and chemical indexes of 50 kinds of pulverized coal (including bituminous coal, anthracite, and blended coal), an accurate multiple regression prediction model was established. The model can accurately reflect the combustion performance of different pulverized coal under various working conditions, with a prediction error range of ±2.02%, significantly improving the prediction accuracy and reliability.

[0190] 2. Using the principal component analysis (PCA) technique to reduce the dimensionality of the multi-dimensional data of pulverized coal simplifies the analysis process of the influencing factors of the combustion rate. Compressing 12 initial indexes into 7 principal component variables not only reduces the computational complexity of the model but also retains the key information, providing concise support for subsequent analysis and decision-making.

[0191] 3. By collecting and analyzing a large amount of historical data and making full use of the operation data of the industrial site for model training, compared with the traditional calculation method based on physical models, this invention significantly reduces the dependence on manual experience and complex measurements.

[0192] 4. The model is applicable to different proportion contents of pulverized coal, providing reliable support for iron and steel enterprises to flexibly adjust the injection parameters and improve the utilization rate of pulverized coal.

[0193] 5. By scientifically predicting the combustion rate of pulverized coal, this invention helps enterprises reasonably adjust the injection volume and types of pulverized coal on the premise of ensuring the stable operation of the blast furnace, thereby effectively reducing the proportion of unburned pulverized coal, increasing the coal-coke replacement ratio, and optimizing the production cost.

[0194] 6. For the first time, the principal component analysis (PCA) is deeply combined with the prediction of the combustion rate of pulverized coal injection in the blast furnace, breaking through the limitations of traditional indirect measurement methods, introducing innovative big data analysis technology into the iron and steel industry, and improving the technical barrier.

[0195] Based on the same inventive concept, the embodiment of this application also provides a prediction device for the combustion rate of pulverized coal injection in the blast furnace, which can be used to implement the method described in the above embodiment, as in the following embodiment. Since the principle of solving problems by the prediction device for the combustion rate of pulverized coal injection in the blast furnace is similar to that of the prediction method for the combustion rate of pulverized coal injection in the blast furnace, the implementation of the prediction device for the combustion rate of pulverized coal injection in the blast furnace can refer to the implementation of the prediction method for the combustion rate of pulverized coal injection in the blast furnace, and the repeated parts will not be described again. Hereinafter, the term "unit" or "module" can be a combination of software and / or hardware that can achieve a predetermined function. Although the systems described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware is also possible and contemplated.

[0196] The embodiment of the present invention provides a specific implementation manner of a prediction device for the combustion rate of pulverized coal injection in the blast furnace that can implement the prediction method for the combustion rate of pulverized coal injection in the blast furnace, see Figure 7, A prediction device for the combustion rate of pulverized coal injected into a blast furnace specifically includes the following:

[0197] A combustion rate characterization parameter acquisition module 10 for acquiring combustion rate characterization parameters of a coal sample of pulverized coal injected into a blast furnace;

[0198] A combustion rate characterization parameter screening module 20 for screening the multiple combustion rate characterization parameters when the correlation relationship between the multiple combustion rate characterization parameters meets the first preset condition and / or the correlation relationship between the combustion rate characterization parameter and its corresponding historical combustion rate meets the second preset condition;

[0199] A combustion rate prediction module 30 for generating a combustion rate prediction model based on the screened multiple combustion rate characterization parameters and the corresponding historical combustion rates, and using the combustion rate prediction model to predict the combustion rate of the pulverized coal injected into the target blast furnace.

[0200] In some embodiments of the present invention, the combustion rate characterization parameter screening module 20 includes:

[0201] A combustion rate characterization parameter screening unit for performing principal component analysis on the multiple combustion rate characterization parameters when the correlation relationship between the multiple combustion rate characterization parameters is greater than 0.3 and / or the correlation relationship between the combustion rate characterization parameter and its corresponding historical combustion rate is greater than 0.3, so as to screen the multiple combustion rate characterization parameters.

[0202] In some embodiments of the present invention, see Figure 8 , the combustion rate characterization parameter screening unit includes:

[0203] A combustion rate characterization parameter centering unit 20a1 for centering the multiple combustion rate characterization parameters;

[0204] A covariance matrix calculation unit 20a2 for calculating the covariance matrix of the multiple combustion rate characterization parameters according to the centering result;

[0205] An eigenvalue decomposition unit 20a3 for performing eigenvalue decomposition on the covariance matrix;

[0206] A combustion rate characterization parameter screening subunit 20a4 for screening the multiple combustion rate characterization parameters according to the eigenvalue decomposition result.

[0207] In some embodiments of the present invention, the combustion rate characterization parameters include: ash content, volatile matter, fixed carbon content, carbon content, hydrogen content, oxygen content, basicity index, ignition point, explosiveness, reactivity at 1000 °C, ST value of ash melting point, and effective calorific value.

[0208] In some embodiments of the present invention, see Figure 9, the combustion rate prediction module 30 includes:

[0209] A combustion rate characterization parameter selection unit 30a, configured to select at least one combustion rate characterization parameter from among a plurality of screened combustion rate characterization parameters;

[0210] An initial model generation unit 30b, configured to fit at least one selected combustion rate characterization parameter and the corresponding historical combustion rate to generate a plurality of initial combustion rate prediction models;

[0211] A combustion rate prediction model determination unit 30c, configured to determine the combustion rate prediction model according to the fitting rate of each of the plurality of initial combustion rate prediction models.

[0212] As can be seen from the above description, an embodiment of the present invention provides a prediction device for the combustion rate of pulverized coal injected into a blast furnace, including: a combustion rate characterization parameter acquisition module, configured to acquire combustion rate characterization parameters of a coal sample of pulverized coal injected into a blast furnace; a combustion rate characterization parameter screening module, configured to screen a plurality of combustion rate characterization parameters according to the correlation between the plurality of combustion rate characterization parameters and / or the correlation between the combustion rate characterization parameter and its corresponding historical combustion rate; a combustion rate prediction module, configured to generate a combustion rate prediction model according to the plurality of screened combustion rate characterization parameters and the corresponding historical combustion rate, and use the combustion rate prediction model to predict the combustion rate of pulverized coal injected into a target blast furnace.

[0213] The present invention can effectively calculate the combustion rates of different pulverized coals, so as to determine the pulverized coal suitable for injection into a blast furnace, enabling a steel plant to obtain higher production capacity and product quality under safer operating conditions, and having strong practical significance.

[0214] An embodiment of the present application further provides a specific implementation manner of an electronic device capable of implementing all steps in the prediction method for the combustion rate of pulverized coal injected into a blast furnace in the above embodiment. Refer to Figure 10 , the electronic device specifically includes the following:

[0215] A processor 1201, a memory 1202, a communication interface 1203, and a bus 1204;

[0216] Wherein, the processor 1201, the memory 1202, and the communication interface 1203 complete mutual communication through the bus 1204; the communication interface 1203 is used to implement information transmission between related devices such as a server-side device and a user-side device;

[0217] The processor 1201 is used to call the computer program in the memory 1202. When the processor executes the computer program, all steps in the prediction method of the pulverized coal injection combustion rate in the blast furnace in the above embodiments are implemented. For example, when the processor executes the computer program, the following steps are implemented:

[0218] Step 100: Obtain the combustion rate characterization parameters of the coal sample of the pulverized coal injected into the blast furnace;

[0219] Step 200: When the correlation relationship between multiple combustion rate characterization parameters satisfies the first preset condition and / or the correlation relationship between the combustion rate characterization parameter and its corresponding historical combustion rate satisfies the second preset condition, screen the multiple combustion rate characterization parameters;

[0220] Step 300: Generate a combustion rate prediction model according to the screened multiple combustion rate characterization parameters and the corresponding historical combustion rates, and use the combustion rate prediction model to predict the combustion rate of the target pulverized coal injected into the blast furnace.

[0221] An embodiment of the present application also provides a computer-readable storage medium capable of implementing all steps in the prediction method of the pulverized coal injection combustion rate in the blast furnace in the above embodiments. A computer program is stored on the computer-readable storage medium. When the computer program is executed by a processor, all steps in the prediction method of the pulverized coal injection combustion rate in the above embodiments are implemented. For example, when the processor executes the computer program, the following steps are implemented:

[0222] Step 100: Obtain the combustion rate characterization parameters of the coal sample of the pulverized coal injected into the blast furnace;

[0223] Step 200: When the correlation relationship between multiple combustion rate characterization parameters satisfies the first preset condition and / or the correlation relationship between the combustion rate characterization parameter and its corresponding historical combustion rate satisfies the second preset condition, screen the multiple combustion rate characterization parameters;

[0224] Step 300: Generate a combustion rate prediction model according to the screened multiple combustion rate characterization parameters and the corresponding historical combustion rates, and use the combustion rate prediction model to predict the combustion rate of the target pulverized coal injected into the blast furnace.

[0225] Each embodiment in this specification is described in a progressive manner. The same or similar parts between each embodiment can be referred to each other. The key point of each embodiment is to illustrate the differences from other embodiments. In particular, for the hardware + program type embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can refer to the partial description of the method embodiments.

[0226] The above description relates to specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the acts or steps recited in the claims may be performed in a different order than in the embodiments and still achieve the desired result. Additionally, the processes depicted in the figures do not necessarily require the particular order or sequential order shown to achieve the desired result. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0227] Although this application provides method operation steps such as in the embodiments or flowcharts, based on routine or non-creative labor, there may be more or fewer operation steps. The order of steps listed in the embodiments is only one way among many possible execution orders and does not represent the only execution order. When the actual device or client product is executing, it can be executed in the order shown in the embodiments or the figures, or in parallel (e.g., in an environment with parallel processors or multi-threaded processing).

[0228] For convenience of description, when describing the above device, it is divided into various modules according to functions for separate description. Of course, when implementing the embodiments of this specification, the functions of each module can be realized in the same or multiple software and / or hardware, or the modules implementing the same function can be realized by a combination of multiple sub-modules or sub-units, etc. The device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of the devices or units can be in electrical, mechanical or other forms.

[0229] Those skilled in the art also know that in addition to implementing the controller in the form of pure computer-readable program code, the method steps can be logically programmed to enable the controller to be implemented in the form of logic gates, switches, application-specific integrated circuits, programmable logic controllers, embedded microcontrollers, etc. to achieve the same function. Therefore, such a controller can be considered a hardware component, and the devices included therein for implementing various functions can also be regarded as the structures within the hardware component. Or even, the devices for implementing various functions can be regarded as both software modules for implementing the method and structures within the hardware component.

[0230] In a typical configuration, a computing device includes one or more processors (CPUs), an input / output interface, a network interface, and a memory.

[0231] The memory may include non-permanent memory in the form of computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM). The memory is an example of computer-readable media.

[0232] Each embodiment in this specification is described in a progressive manner. For the same or similar parts among the embodiments, reference can be made to each other. Each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can refer to the description of the method embodiment. In the description of this specification, the description with reference to terms such as "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the embodiments of this specification. In this specification, the schematic description of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in a suitable manner in any one or more embodiments or examples. In addition, without contradiction, those skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples.

[0233] The above is only the embodiment of the embodiments of this specification and is not used to limit the embodiments of this specification. For those skilled in the art, various changes and modifications can be made to the embodiments of this specification. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the embodiments of this specification shall be included within the scope of the claims of the embodiments of this specification.

Claims

1. A method for predicting the combustion rate of pulverized coal injected into a blast furnace, characterized in that: include: Obtaining combustion rate characterization parameters of coal samples injected with pulverized coal in blast furnaces; If the correlation between the multiple combustion rate characterization parameters satisfies the first preset condition and / or the correlation between the combustion rate characterization parameters and their corresponding historical combustion rates satisfies the second preset condition, screening the multiple combustion rate characterization parameters; A combustion rate prediction model is generated according to the screened multiple combustion rate characterization parameters and the corresponding historical combustion rates, and the combustion rate of the target blast furnace pulverized coal injection is predicted using the combustion rate prediction model.

2. The prediction method according to claim 1, characterized in that: If the correlation between the plurality of combustion rate characterization parameters satisfies the first preset condition and / or the correlation between the combustion rate characterization parameter and its corresponding historical combustion rate satisfies the second preset condition, screening the plurality of combustion rate characterization parameters comprises: If the correlation between the multiple combustion rate characterization parameters is greater than 0.3 and / or the correlation between the combustion rate characterization parameters and their corresponding historical combustion rates is greater than 0.3, principal component analysis is performed on the multiple combustion rate characterization parameters to screen the multiple combustion rate characterization parameters.

3. The prediction method according to claim 2, characterized in that: Performing principal component analysis on the plurality of combustion rate characterization parameters includes: Centralizing the plurality of combustion rate characterization parameters; Calculate the covariance matrix of the plurality of combustion rate characterization parameters according to the centering result; Performing eigenvalue decomposition on the covariance matrix; The plurality of combustion rate characterization parameters are screened according to the eigenvalue decomposition result.

4. The prediction method according to claim 1, characterized in that: The combustion rate characterization parameters include: ash content, volatile matter, fixed carbon content, carbon content, hydrogen content, oxygen content, basicity index, ignition point, explosiveness, reactivity at 1000°C, ash melting point ST value and effective calorific value.

5. The prediction method according to any one of claims 1 to 4, characterized in that: The method of generating a combustion rate prediction model according to the selected multiple combustion rate characterization parameters and the corresponding historical combustion rates includes: selecting at least one combustion rate characterization parameter from the filtered plurality of combustion rate characterization parameters; Fitting the selected at least one combustion rate characterization parameter and the corresponding historical combustion rate to generate a plurality of combustion rate prediction initial models; The combustion rate prediction model is determined according to respective fitting rates of a plurality of combustion rate prediction initial models.

6. A device for predicting the combustion rate of pulverized coal injected into a blast furnace, characterized in that: include: A combustion rate characterization parameter acquisition module, used to acquire combustion rate characterization parameters of a coal sample for blast furnace pulverized coal injection; A combustion rate characterization parameter screening module, configured to screen the plurality of combustion rate characterization parameters if a correlation between the plurality of combustion rate characterization parameters satisfies a first preset condition and / or a correlation between the combustion rate characterization parameter and its corresponding historical combustion rate satisfies a second preset condition; The combustion rate prediction module is used to generate a combustion rate prediction model based on the screened multiple combustion rate characterization parameters and the corresponding historical combustion rates, and use the combustion rate prediction model to predict the combustion rate of the target blast furnace pulverized coal injection.

7. The prediction device according to claim 6, characterized in that The combustion rate characterization parameter screening module includes: The combustion rate characterization parameter screening unit is used to perform principal component analysis on the multiple combustion rate characterization parameters to screen the multiple combustion rate characterization parameters if the correlation between the multiple combustion rate characterization parameters is greater than 0.3 and / or the correlation between the combustion rate characterization parameters and their corresponding historical combustion rates is greater than 0.

3.

8. The prediction device according to claim 7, characterized in that The combustion rate characterization parameter screening unit comprises: A burning rate characterization parameter centralization unit, used for centralizing the plurality of burning rate characterization parameters; A covariance matrix calculation unit, used for calculating the covariance matrix of the plurality of combustion rate characterization parameters according to the centralization result; An eigenvalue decomposition unit, used for performing eigenvalue decomposition on the covariance matrix; The combustion rate characterization parameter screening subunit is used to screen the plurality of combustion rate characterization parameters according to the eigenvalue decomposition result.

9. The prediction device according to claim 6, characterized in that The combustion rate characterization parameters include: ash content, volatile matter, fixed carbon content, carbon content, hydrogen content, oxygen content, basicity index, ignition point, explosiveness, reactivity at 1000°C, ash melting point ST value and effective calorific value.

10. The prediction device according to any one of claims 6 to 9, characterized in that: The combustion rate prediction module includes: A combustion rate characterization parameter selection unit, used to select at least one combustion rate characterization parameter from the filtered plurality of combustion rate characterization parameters; An initial model generating unit, used for fitting the selected at least one combustion rate characterization parameter and the corresponding historical combustion rate to generate a plurality of combustion rate prediction initial models; The combustion rate prediction model determination unit is used to determine the combustion rate prediction model according to the respective fitting rates of a plurality of combustion rate prediction initial models.

11. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instructions are executed by a processor, the steps of the method for predicting the combustion rate of pulverized coal injected into a blast furnace as described in any one of claims 1 to 5 are implemented.

12. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the steps of the method for predicting the combustion rate of pulverized coal injected into a blast furnace as described in any one of claims 1 to 5 are implemented.

13. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for predicting the combustion rate of pulverized coal injected into a blast furnace as described in any one of claims 1 to 5 are implemented.

Images