Method for establishing coke thermal performance nonlinear regression model based on multiple parameters of coal quality

Abstract

The invention provides a method for establishing a coke thermal performance nonlinear regression model based on multiple coal quality parameters. The method comprises the following steps: acquiring coking coal property parameters; calculating the correlation between each coking coal property parameter and the thermal performance parameter of the coke; screening out coking coal property parameters of which the correlation is within a preset range; constructing a coal coke thermal performance regression model by using minitab data processing software based on the coking coal property parameters and the thermal performance parameters of the coke; and finishing the prediction of the target coke thermal performance by using the coal coke thermal performance regression model. According to the method, the coking coal property parameters with the correlation within the preset range are screened out, the influence of different coal quality indexes on the coke thermal performance is comprehensively considered, a more accurate prediction model can be established, the prediction capacity of the coke thermal performance is comprehensively improved, and powerful support is provided for efficient and green development of the coking industry.

Description

Technical Field

[0001] The present invention relates to the technical field of coke quality prediction, in particular to a method for establishing a nonlinear regression model of coke thermal performance based on multiple coal quality parameters. Background Art

[0002] With the increasing popularity and development of large-scale blast furnaces and oxygen-enriched injection technology, coke, as a key fundamental material in modern blast furnace ironmaking, plays a crucial role. While its reducing properties, heat source, and carburizing effects have been replaced to varying degrees by pulverized coal injection, its structural support remains irreplaceable, further exacerbating the burden on the material. Consequently, steelmakers are urgently seeking to improve coke quality.

[0003] Traditional industrial coke oven coal blending and coking production relies entirely on testing and analyzing test coke ovens to obtain data on coke cold and hot strengths. Only when the coke quality test results are generally within the required range can the specific coal blending scheme for each individual type be applied to actual industrial coke oven production. This entire process is time-consuming and requires significant human, material, and financial resources, hindering timely production guidance. Especially given the current shortage of high-quality coal, the large fluctuations in coal quality among suppliers, and the complex nature of coal types, the lag in the method of using test coke ovens to blend and then test various coke quality parameters is particularly pronounced. Therefore, there is an urgent need to develop a regression model that accurately predicts coke quality, in order to provide timely, accurate, and efficient guidance for coal blending and coking production. Summary of the Invention

[0004] To solve the above problems, the purpose of the present invention is to provide a method for establishing a nonlinear regression model of coke thermal properties based on multiple coal quality parameters.

[0005] To achieve the above object, the present invention provides the following solutions:

[0006] The method for establishing a nonlinear regression model of coke thermal properties based on multiple coal quality parameters includes:

[0007] Step 1: Obtain coking coal property parameters;

[0008] Step 2: Calculate the correlation between each coking coal property parameter and the thermal performance parameters of coke;

[0009] Step 3: Screen out the coking coal property parameters whose correlation is within the preset range;

[0010] Step 4: Based on the coking coal property parameters and the thermal performance parameters of coke, a coal coke thermal performance regression model was constructed using Minitab data processing software;

[0011] Step 5: Use the coal coke thermal property regression model to complete the prediction of the target coke thermal property.

[0012] Preferably, the thermal performance parameters of the coke include: coke reactivity and coke post-reaction strength.

[0013] Preferably, in step 4, the coal char thermal performance regression model is:

[0014]

[0015] Among them, CRI represents coke reactivity, CSR represents coke strength after reaction, Vdaf represents ash-free volatile matter of coking coal, and Rmax represents the average maximum reflectance of vitrinite of coking coal.

[0016] The present invention also provides 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 in the method for establishing a nonlinear regression model of coke thermal properties based on multiple coal quality parameters are implemented.

[0017] The present invention also provides an electronic device, comprising a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and runnable on the processor, wherein the transceiver, the memory, and the processor are connected via the bus, and wherein the computer program, when executed by the processor, implements the steps in the method for establishing a nonlinear regression model of coke thermal properties based on multiple coal quality parameters.

[0018] According to the specific embodiments provided by the present invention, the present invention discloses the following technical effects:

[0019] The present invention provides a method for establishing a nonlinear regression model of coke thermal properties based on multiple coal quality parameters. Compared with the existing technology, the present invention screens out coking coal property parameters with correlation within a preset range, comprehensively considers the impact of different coal quality indicators on the thermal properties of coke, and can establish a more accurate prediction model, comprehensively improve the prediction ability of coke thermal properties, and provide strong support for the efficient and green development of the coking industry. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0021] Figure 1 A flow chart of the method for establishing a nonlinear regression model of coke thermal properties based on multiple coal quality parameters provided by the present invention;

[0022] Figure 2 The residual graph of the strength value of coke after reaction after square root provided by the present invention;

[0023] Figure 3 This is a fitted line diagram of the coke reactivity and post-reaction strength provided by the present invention. DETAILED DESCRIPTION

[0024] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0025] In order to make the technical problems, technical solutions and beneficial effects to be solved by the present invention more clearly understood, the present invention is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0026] To achieve the above object, the technical solution adopted by the present invention is:

[0027] See also Figure 1 The method of establishing a nonlinear regression model of coke thermal properties based on multiple coal quality parameters includes:

[0028] Step 1: Obtaining coking coal property parameters; coking coal property parameters include: ash-based volatile matter, average maximum reflectance of vitrinite, coking coal, caking property, ash content, sulfur content, and phosphorus content;

[0029] Step 2: Calculate the correlation between each coking coal property parameter and the thermal performance parameters of coke;

[0030] Step 3: Screen out the coking coal property parameters whose correlation is within the preset range;

[0031] Step 4: Based on the coking coal property parameters and the thermal performance parameters of coke, a coal coke thermal performance regression model was constructed using Minitab data processing software;

[0032] In practical applications, the first technical problem that the present invention solves is the selection of various parameters in the relationship model between coal and coke. This is closely related to the fit and prediction accuracy of the coke quality prediction model. The coke quality prediction model is not unfamiliar. Through the review of previous materials and the reference of experience, the coke quality prediction methods in recent years are mostly based on prediction equations, and many new prediction indicators have been proposed. Some use Vdaf and G values ​​to predict coke strength, and some use maximum fluidity and coal ash alkalinity index AI to predict CSR and CRI. Among them, the indicators involved in some prediction models themselves are not very clear in meaning, the calculations are cumbersome, and the prediction accuracy is not high, which limits their promotion and application. In addition, the main problem with the existing models is that the scope of application is unclear. Therefore, determining the main related parameters between coal and coke and the specific expression equations of the regression model is the technical difficulty and technical innovation of the present invention.

[0033] The correlation coefficient r is often used in statistics to measure the strength of the linear correlation between two variables. When xi is not all zero and yi is not all zero, the calculation formula for the correlation coefficient of the two variables is:

[0034]

[0035] In the embodiment of the present invention, the above formula may be used to calculate the correlation between each coking coal property parameter and the thermal performance parameter of coke.

[0036] The thermal properties of coke (coke reactivity CRI and coke post-reaction strength CSR) depend on three main factors: the quality of coking coal, the process conditions of coking and coal preparation, and the ash composition of coke or coal. Each of these three factors is composed of many secondary factors. Therefore, the determination and screening of key influencing parameters are crucial. There are dozens of parameters that characterize the properties of coking coal, and each parameter characterizes a characteristic of coking coal. In addition to ash and sulfur content, coalification indexes and coking indexes are often used to characterize the process properties of coking coal. Coalification indexes are often used as dry ash-free volatile matter Vdaf and the average maximum reflectance of the vitrinite group of coal. To characterize, these two parameters have a good correlation:

[0037]

[0038] Therefore, the present invention combines the calculation results of the above correlation formula and selects a nonlinear model with the maximum reflectance of the vitrinite (Rmax) and the volatile matter (Vdaf) as independent variables. The coal coke thermal performance regression model was established using Minitab data processing software. The details are as follows:

[0039]

[0040] Among them, CRI represents coke reactivity, CSR represents coke strength after reaction, Vdaf represents ash-free volatile matter of coking coal, and Rmax represents the average maximum reflectance of vitrinite of coking coal.

[0041] Step 5: Use the coal coke thermal property regression model to complete the prediction of the target coke thermal property.

[0042] The present invention screens out coking coal property parameters with correlations within a preset range, comprehensively considers the impact of different coal quality indicators on the thermal properties of coke, and can establish a more accurate prediction model, comprehensively improving the prediction ability of coke thermal properties, and providing strong support for the efficient and green development of the coking industry.

[0043] The method for establishing a nonlinear regression model of coke thermal properties based on multiple coal quality parameters of the present invention is further described below with reference to specific embodiments:

[0044] like Figure 2 As shown in Table 1, the four-in-one residual plot of post-reaction intensity more clearly demonstrates the strong correlation between the dependent variable (represented by the square root of the CSR) and the independent variables (maximum reflectance of the vitrinite and volatile matter). In the regression analysis, the P-values ​​for both the independent variables Rmax and Vdaf were zero, indicating a significant correlation between these two variables. S = 0.220994 < 1, indicating high prediction accuracy and low error. The P-value of the established regression equation was also zero, further demonstrating the validity and feasibility of this regression model.

[0045] Table 1

[0046]

[0047] Whether there is a linear relationship between the reactivity of coke and its strength after reaction has always been a controversial issue. Through Minitab data processing, the relationship between CRI and CER is given, and the two are linearly correlated. Figure 3 and Table 2.

[0048] Table 2

[0049]

[0050]

[0051] There is a linear correlation between CRI and CER, but from the linear fitting Figure 3As can be seen from the data, the numerical distribution is relatively discrete, and the correlation is average. S = 0.904030 < 1, R-Sq = 75.5% is very close to the adjusted R-Sq (adjusted) = 74.2%, and both are greater than 70%, indicating a correlation between the two. The regression model is reliable, but it is recommended only as a reference for trend parameters of coke cold strength. It is not recommended to draw conclusive judgments based on the predicted values.

[0052] By using Minitab data processing software, the coke performance prediction model was further revised and improved, which greatly improved the prediction accuracy. The correlation coefficient r reached 0.8904, indicating that its prediction accuracy is high and can serve as a powerful basis for guiding actual production.

[0053] Therefore, the prediction model was further verified using the measured thermal strength data of industrial coke ovens. The specific data of coal and coke measured in ovens 1-4#, 7-8#, and 9-10# were randomly sampled, and the prediction model was used to predict the thermal properties of coke, as shown in Table 3.

[0054] Table 3 Comparison of coke prediction values ​​with measured values

[0055] serial number Measured Rmax Measured Vdaf Measured CRI Predicting CRI Measured CSR Predicting CSR 1-4#-1 1.402 24.67 24.8 27.4 64.4 61.7 1-4#-2 1.391 25.84 25.4 25.8 65.6 63.6 7-8#-1 1.476 26.14 25.2 23.2 65.7 68.8 7-8#-2 1.276 26.26 26.0 30.2 63.8 58.5 9-10#-1 1.387 26.7 27.1 24.4 62.8 65.2 9-10#-2 1.259 26.14 29.8 31.2 60.3 57.5

[0056] The average error between the predicted value of coke thermal reactivity and the measured value is 2.22, the minimum difference is 0.4, and the range is 4.2. The average error between the predicted value of coke post-reaction strength and the measured value is 2.97, the minimum difference is 2.0, and the range is 4.8.

[0057] The present invention classifies and identifies coal quality by analyzing the properties of coal species, and establishes a powerful coal rock and coal species analysis database based on actual analysis data. On this basis, the difference analysis of coal blending and coking of single-type coal produced by coke ovens in coking plants is carried out, and the influence of the actual coal composition of coal blending and the coal rock characteristics of coal blending on the quality of coke is explored. With coal rock and coal quality parameters as independent variables, through the theoretical analysis method of the Six Sigma management system and the powerful Minitab data processing software, a coke quality prediction model with coke thermal properties as variables suitable for coke ovens in coking plants is established. In particular, the study of the mechanism of change of coke properties and the internal microstructural properties lays a solid foundation for simulating coal blending and coking. Through the organic combination of the coal rock and coal species characteristic database, the lithologic coal blending prediction system, and the coke quality prediction model, a model of the mutual influence relationship between coal and coke is established, and the fitting prediction of coke quality using digital information parameters is realized. At the same time, it has the powerful functions of adjusting the coal blending ratio, optimizing the proportion, saving high-quality coal, and achieving cost reduction and efficiency improvement.

[0058] The present invention also provides 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 in the method for establishing a nonlinear regression model of coke thermal properties based on multiple coal quality parameters are implemented.

[0059] The present invention also provides an electronic device, comprising a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor. The transceiver, the memory, and the processor are connected via the bus. When the computer program is executed by the processor, the steps in the method for establishing a nonlinear regression model of coke thermal properties based on multiple coal quality parameters are implemented.

[0060] This document uses specific examples to illustrate the principles and implementation methods of the present invention. The above examples are only intended to help understand the method and core concept of the present invention. At the same time, those skilled in the art will find that the specific implementation methods and application scopes may vary based on the concept of the present invention. In summary, the contents of this specification should not be construed as limiting the present invention.

Claims

1. A method for establishing a nonlinear regression model of coke thermal properties based on coal quality multi-parameters, characterized in that: include: Step 1: Obtaining coking coal property parameters; Step 2: Calculate the correlation between each coking coal property parameter and the thermal performance parameter of coke; Step 3: Screen out the coking coal property parameters whose correlation is within a preset range; Step 4: Based on the coking coal property parameters and the thermal performance parameters of coke, a regression model of coal coke thermal performance was constructed using Minitab data processing software; Step 5: Use the coal coke thermal performance regression model to complete the prediction of the target coke thermal performance.

2. The method for establishing a nonlinear regression model of coke thermal properties based on coal quality multi-parameters according to claim 1, characterized in that: The thermal performance parameters of the coke include: coke reactivity and coke post-reaction strength.

3. The method for establishing a nonlinear regression model of coke thermal properties based on coal quality multi-parameters according to claim 2, characterized in that: In step 4, the regression model of coal char thermal properties is: Among them, CRI represents coke reactivity, CSR represents coke post-reaction strength, Vdaf represents ash-free volatile matter of coking coal, and Rmax represents the average maximum reflectance of the vitrinite group of coking coal.

4. 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 in the method for establishing a nonlinear regression model of coke thermal properties based on coal quality multi-parameters as described in any one of claims 1 to 3 are implemented.

5. An electronic device, comprising a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the transceiver, the memory, and the processor are connected via the bus, wherein: When the computer program is executed by the processor, the steps in the method for establishing a nonlinear regression model of coke thermal properties based on coal quality multi-parameters as described in any one of claims 1 to 3 are implemented.

Images