A method for constructing a coke quality prediction model and related equipment

Abstract

The application discloses a construction method of a coke quality prediction model and related equipment, relates to the technical field of coal blending and coking, and comprises the following steps: acquiring actual coke quality and coking coal, wherein the coking coal comprises gas coal, 1 / 3 coking coal, fat coal, lean coal and coking coal; pretreating the coking coal to obtain influence factors, wherein the influence factors comprise coal coking microstructure, first high-flow coal fluidity, second high-flow coal fluidity and expansion degree; and constructing a prediction model by using the actual coke quality, the influence factors and a random forest algorithm.

Description

Technical Field

[0001] This application relates to the field of coal blending and coking technology, and in particular to a method for constructing a coke quality prediction model and related equipment. Background Technology

[0002] Currently, many domestic enterprises have established coke quality prediction systems, from coal source to coke quality prediction and blending optimization, to achieve coke quality control and coal blending cost control. However, due to differences in coal sources, coking coal blending control mechanisms, and parameter selection among different units, the prediction results vary considerably. Furthermore, many enterprises have not yet achieved intelligent coke quality prediction, and their blending adjustments remain conservative, relying on manual experience and coal quality testing indicators. If there are significant changes in the blending structure or the use of new coal types, numerous coking experiments are required, which is time-consuming. This limits the efficiency of tasks such as adjusting blending ratios and determining coal mine resource quantities, failing to meet the current demands for efficient, rapid, and intelligent manufacturing. With the development of coal blending and coking technology, the microstructure composition of coking coal and its flow expansion characteristics are the main intrinsic factors affecting coke quality, especially the influence of microstructure on coke thermal properties. Many domestic steel enterprises have also conducted correlation studies on the microstructure composition of coke and its thermal properties; for example, coke with a high content of coarse-grained mosaic structure has high thermal strength.

[0003] However, testing the microstructure composition of coking coal is no easy task. Most domestic steel mills use the microstructure composition of produced coke to reflect coal blending quality, which is technically instructive, but the representativeness of the produced coke samples and the requirements for the testers at each testing point are high. Different testers yield significantly different results. Moreover, even if coals of different metamorphic degrees have the same microstructure composition, their fundamental nature remains quite different. Different coking coals exhibit significant differences in flow and expansion characteristics, necessitating the use of high-flow, high-expansion coking coal characteristics to control coke quality. Currently, there is no suitable method to solve the above problems. Therefore, it is necessary to propose a method for constructing a coke quality prediction model to at least address some of the aforementioned issues. Summary of the Invention

[0004] The summary section introduces a series of simplified concepts, which will be further explained in detail in the detailed description section. This summary section is not intended to limit the key features and essential technical features of the claimed technical solution, nor is it intended to determine the scope of protection of the claimed technical solution.

[0005] In a first aspect, embodiments of this application provide a method for constructing a coke quality prediction model, the method comprising:

[0006] Obtain the actual quality of coking coal and coke, wherein the coking coal includes gas coal, 1 / 3 coking coal, fat coal, lean coal and coking coal;

[0007] The coking coal is pretreated to obtain influencing factors, which include the coal coking microstructure, the first high-flowability coal flowability, the second high-flowability coal flowability, and the expansion.

[0008] A prediction model is constructed using the actual quality of the coke, the influencing factors, and the random forest algorithm.

[0009] In one embodiment of the present invention, the step of pretreating the coking coal to obtain the influencing factor includes:

[0010] The coking coal is heated to obtain coke dust for making bright sheets;

[0011] The microstructure of the focal length light-emitting film was obtained by testing.

[0012] The dimensions of the microstructure are corrected according to the coking coal to obtain correction coefficients and coal type ratios. The correction coefficients include coarse-grained mosaic correction coefficients for gas coal, isotropic correction coefficients for gas coal, coarse-grained mosaic correction coefficients for 1 / 3 coking coal, isotropic correction coefficients for 1 / 3 coking coal, coarse-grained mosaic correction coefficients for fat coal, coarse-grained mosaic correction coefficients for coking coal, coarse-grained mosaic correction coefficients for lean coal, fibrous correction coefficients for lean coal, and flaky correction coefficients for lean coal.

[0013] The microstructure of coal coking was obtained based on the revision coefficient and the coal type ratio.

[0014] In one embodiment of the present invention, the step of pretreating the coking coal to obtain the influencing factor further includes:

[0015] The correction coefficients for the fluidity and expansion of the coking coal are determined based on the volatile matter content of the coking coal.

[0016] The volatile matter content of 1 / 3 coking coal is used to determine the 1 / 3 coking coal flowability correction coefficient and the 1 / 3 coking coal expansion correction coefficient.

[0017] When the thickness of the plastic layer of the coking coal is greater than or equal to the preset thickness, the flowability correction coefficient of the coking coal and the coal type ratio are adjusted and summed to obtain the first high-flowability coal.

[0018] In one embodiment of the present invention, the step of pretreating the coking coal to obtain the influencing factor further includes:

[0019] When the Gibbs mobility of the 1 / 3 coking coal is greater than the preset mobility, the mobility correction coefficient of the 1 / 3 coking coal and the coal type ratio are adjusted and summed to obtain the second high mobility coal mobility.

[0020] In one embodiment of the present invention, the step of pretreating the coking coal to obtain the influencing factor further includes:

[0021] When the Kierkegaard fluidity of the 1 / 3 coking coal is greater than the preset fluidity and the Kierkegaard fluidity of the fat coal is greater than the preset fluidity, the expansion degree is obtained by adjusting and summing the coal type ratio, the expansion degree correction coefficient of the fat coal and the expansion degree correction coefficient of the 1 / 3 coking coal.

[0022] In one embodiment of the present invention, the step of correcting the dimensions of the microstructure according to the coking coal to obtain the correction coefficient includes:

[0023] Based on the volatile matter and caking index of the gas coal, the coarse-grained mosaic and isotropic properties of the gas coal in the microstructure are corrected by coefficients to obtain the coarse-grained mosaic correction coefficient and the isotropic property correction coefficient of the gas coal.

[0024] Based on the volatile matter and caking index of 1 / 3 coking coal, coefficients were used to correct the coarse-grained mosaic and isotropic properties of the microstructure of 1 / 3 coking coal, resulting in correction coefficients for coarse-grained mosaic and isotropic properties of 1 / 3 coking coal.

[0025] The coarse-grained mosaic of the microstructure of the coarse-grained coal is corrected based on the volatile matter content of the coarse-grained coal to obtain the coarse-grained mosaic correction coefficient.

[0026] In one embodiment of the present invention, the step of correcting the dimensions of the microstructure according to the coking coal to obtain the correction coefficient further includes:

[0027] Based on the coking strength of coking coal, the coking coal coarse grain mosaic of the microstructure is corrected by coefficients to obtain the coking coal coarse grain mosaic correction coefficient.

[0028] Based on the lean coal bonding index, coefficients for the lean coal coarse-grained mosaic, lean coal fiber, and lean coal flaky structures in the microstructure are corrected to obtain the lean coal coarse-grained mosaic correction coefficient, lean coal fiber correction coefficient, and lean coal flaky correction coefficient.

[0029] Secondly, this application proposes a system for constructing a coke quality prediction model, the system comprising: a data acquisition module, a data preprocessing module, and a model construction module;

[0030] The data acquisition module is configured to acquire the actual quality of coking coal and coke, wherein the coking coal includes gas coal, 1 / 3 coking coal, fat coal, lean coal and coking coal;

[0031] The data preprocessing module is configured to preprocess the coking coal to obtain influencing factors, including the coal coking microstructure, the first high-flowability coal flowability, the second high-flowability coal flowability, and the expansion degree.

[0032] The model building module is configured to construct a prediction model using the actual quality of the coke, the influencing factors, and the random forest algorithm.

[0033] Thirdly, an electronic device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program stored in the memory to implement the steps of a method for constructing a coke quality prediction model as described in any of the first aspects above.

[0034] Fourthly, this application also proposes a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, it implements the steps of the method for constructing a coke quality prediction model according to any one of the first aspects.

[0035] In summary, the method for constructing a coke quality prediction model according to an embodiment of this application includes: obtaining the actual quality of coking coal and coke, wherein the coking coal includes gas coal, 1 / 3 coking coal, fat coal, lean coal, and coking coal; preprocessing the coking coal to obtain influencing factors, wherein the influencing factors include the coal coking microstructure, the first high-flowability coal flowability, the second high-flowability coal flowability, and the expansion degree; and constructing a prediction model using the actual coke quality, the influencing factors, and a random forest algorithm. By using the preprocessed coal coking microstructure, the first high-flowability coal flowability, the second high-flowability coal flowability, and the expansion degree as influencing factors to establish a prediction model, the prediction model has high accuracy, good generalization ability, effectively prevents overfitting, and can more accurately fit complex nonlinear relationships.

[0036] The method for constructing the coke quality prediction model proposed in this application, as well as other advantages, objectives, and features of this application, will be partly apparent from the following description and partly understood by those skilled in the art through research and practice of this application. Attached Figure Description

[0037] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit this specification. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings:

[0038] Figure 1 A flowchart illustrating a method for constructing a coke quality prediction model provided in this application embodiment;

[0039] Figure 2 In the method for constructing a coke quality prediction model provided in the embodiments of this application, M 40 A diagram illustrating the prediction process;

[0040] Figure 3 In the method for constructing a coke quality prediction model provided in the embodiments of this application, M 10 A diagram illustrating the prediction process;

[0041] Figure 4 A schematic diagram of CRI prediction in a method for constructing a coke quality prediction model provided in this application embodiment;

[0042] Figure 5 A schematic diagram illustrating CSR prediction in a method for constructing a coke quality prediction model provided in this application embodiment;

[0043] Figure 6 A schematic diagram of a coke quality prediction model construction system provided in this application embodiment;

[0044] Figure 7 This is a schematic diagram of an electronic device structure for constructing and controlling a coke quality prediction model, as provided in an embodiment of this application. Detailed Implementation

[0045] To better understand the technical solutions provided in the embodiments of this specification, the technical solutions of the embodiments of this specification will be described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the embodiments of this specification and the specific features in the embodiments are detailed descriptions of the technical solutions of the embodiments of this specification, rather than limitations on the technical solutions of this specification. In the absence of conflict, the embodiments of this specification and the technical features in the embodiments can be combined with each other.

[0046] In this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, without necessarily requiring or implying any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element. The term "two or more" includes two or more cases.

[0047] Please see Figure 1 This is a flowchart illustrating a method for constructing a coke quality prediction model according to an embodiment of this application, which may specifically include:

[0048] S110. Obtain the actual quality of coking coal and coke, wherein the coking coal includes gas coal, 1 / 3 coking coal, fat coal, lean coal and coking coal;

[0049] For example, the actual quality of coking coal and coke was obtained. The coking coal was selected according to national standards, including gas coal, 1 / 3 coking coal, bituminous coal, coking coal, and lean coal. 1 / 3 coking coal is a new coal type, a medium-to-high volatile matter bituminous coal with strong caking properties, a transitional coal between coking coal, bituminous coal, and gas coal. The G-value of coking coal was limited to >= 70; the G-value of lean coal was limited to < 70. The coking strength of a single type of coking coal was obtained from coking in a 2kg test coke oven. The G-value is the caking index, reflecting the degree of coke bonding during the coking process. The results of the conventional index analysis of single types of coking coal are shown in Table 1.

[0050] Table 1:

[0051]

[0052] S120. The coking coal is pretreated to obtain influencing factors, which include the microstructure of coal coking, the first high-flowability coal flowability, the second high-flowability coal flowability, and the expansion.

[0053] For example, when pre-treating coking coal, it is necessary to determine the coking microstructure of each individual coal type based on volatile matter and G value, and then perform coefficient correction on the coking microstructure to obtain the influencing factors after pre-treatment.

[0054] S130. Construct a prediction model using the actual quality of the coke, the influencing factors, and the random forest algorithm.

[0055] For example, a random forest algorithm is selected to construct a prediction model based on various influencing factors and the actual quality of coke.

[0056] The core technology of the Random Forest algorithm is Bootstrap. Bootstrap is a random sampling method that generates multiple training sets by randomly sampling subsets from the original dataset multiple times, and then uses these training sets to train multiple decision trees. The purpose of Bootstrap is to reduce overfitting and improve generalization ability through diversity. The specific steps of Bootstrap are as follows:

[0057] 1. Given a sample of size N, N samples are drawn with replacement, one sample drawn each time, resulting in N samples. These N selected samples are used to train a decision tree, serving as the samples at the root node of the decision tree.

[0058] 2. When each sample has M attributes, when splitting is required at each node of the decision tree, randomly select m attributes from these M attributes, satisfying the condition m << M. Then, select 1 attribute from these m attributes using a certain strategy (such as information gain) as the splitting attribute for this node.

[0059] 3. During the formation of the decision tree, each node needs to be split according to step 2 (it is easy to understand that if the one attribute selected by this node next time is the same as the one used by its parent node for splitting, then this node has reached the leaf node and does not need to be split anymore). Keep splitting until it is no longer possible to split. Note that no pruning is performed during the entire decision tree formation process.

[0060] 4. Build a large number of decision trees according to steps 1 to 3, thus forming a random forest. Suppose we have a training set D containing n samples, where xi represents the feature vector of the sample and yi represents the label of the sample. We use Bootstrap to generate T training sets Dt, and then use these training sets to train T decision trees.

[0061] The prediction result of each decision tree can be expressed as a function ft(x), where t = 1, 2,..., T. We fuse these prediction results through a certain strategy, such as majority voting or average value, etc., to obtain the final prediction result f(x).

[0062] Specifically, we can use the average value to fuse these prediction results:

[0063]

[0064] where ft(x) represents the prediction result of the t-th decision tree for the sample x.

[0065] Compare the predicted value with the true result, and select three evaluation indicators commonly used to evaluate the regression prediction effect, namely the mean square error MSE, the root mean square error RMSE, and the coefficient of determination R2. The expressions are shown in equations (2) to (4) respectively.

[0066]

[0067] Select a model with as high R2 and as low RMSE and MSE as possible to predict the coke quality.

[0068] As Figure 2 shown, this application proposes a prediction schematic diagram of M 40 in the construction method of a coke quality prediction model;

[0069] M40 = RFM40(X with coarse, X with fine, X with fiber + X with chip, X with same, X with inert, lgMF1, lgMF2, b);

[0070] like Figure 3 As shown, M is the M in the method for constructing a coke quality prediction model proposed in this application. 10 A diagram illustrating the prediction process;

[0071] M10 = RFM10(X with coarse, X with fine, X with fiber + X with sheet, X with same, X with inert, lgMF1, lgMF2, b);

[0072] like Figure 4 The diagram shown is a schematic representation of CRI prediction in the construction method of the coke quality prediction model proposed in this application.

[0073] CRI = RFCRI(X coarse, X fine, X fiber + X sheet, X same, X inert, lgMF1, lgMF2, b);

[0074] CRI stands for Coke Reactivity Index. It indicates the ability of coke to react with carbon dioxide at high temperatures; the lower the value, the lower the reactivity of the coke and the better its quality.

[0075] like Figure 5 The diagram shown is a schematic representation of CSR prediction in the construction method of the coke quality prediction model proposed in this application.

[0076] CSR = RFCSR(X coarse, X fine, X fiber + X sheet, X same, X inert, lgMF1, lgMF2, b).

[0077] CSR stands for Coke Strength after Reaction, which measures the strength of coke after a certain reaction. A higher value indicates better shatter resistance and higher quality coke.

[0078] In summary, the coke quality prediction model proposed in this application constructs a prediction model by using the pre-treated coal coking microstructure, the first high-flowability coal flowability, the second high-flowability coal flowability, and the expansion as influencing factors. Therefore, the prediction model has high accuracy, good generalization ability, effectively prevents overfitting, and can more accurately fit complex nonlinear relationships.

[0079] In some examples, the step of pretreating the coking coal to obtain the influencing factors includes:

[0080] The coking coal is heated to obtain coke dust for making bright sheets;

[0081] The microstructure of the focal length light-emitting film was obtained by testing.

[0082] The dimensions of the microstructure are corrected according to the coking coal to obtain correction coefficients and coal type ratios. The correction coefficients include coarse-grained mosaic correction coefficients for gas coal, isotropic correction coefficients for gas coal, coarse-grained mosaic correction coefficients for 1 / 3 coking coal, isotropic correction coefficients for 1 / 3 coking coal, coarse-grained mosaic correction coefficients for fat coal, coarse-grained mosaic correction coefficients for coking coal, coarse-grained mosaic correction coefficients for lean coal, fibrous correction coefficients for lean coal, and flaky correction coefficients for lean coal.

[0083] The microstructure of coal coking was obtained based on the revision coefficient and the coal type ratio.

[0084] For example, each type of coking coal is placed in a crucible and placed in a muffle furnace at 950 degrees Celsius for 2 hours to obtain a coke dust polished sheet. The obtained coke dust polished sheet is tested to obtain its microstructure, and the X-rays of each microstructure are recorded. 粗 X 细 X 纤维 X 片 X 惰 The microstructure of each individual coal type was corrected by applying coefficients to the dimensions of the microstructure according to the coal type, resulting in correction coefficients and coal type ratios. The dimensions of the microstructure include coarse-grained mosaic, isotropic, fibrous, and lamellar structures. The correction coefficients include correction coefficients for coarse-grained mosaic of gas coal, isotropic of gas coal, coarse-grained mosaic of 1 / 3 coking coal, isotropic of 1 / 3 coking coal, coarse-grained mosaic of fat coal, coking coal, coarse-grained mosaic of lean coal, fibrous correction coefficient of lean coal, and lamellar correction coefficient of lean coal.

[0085] After obtaining the coal type ratio, the gas coal is denoted as Y. 气 1 / 3 coking coal is denoted as Y 1 / 3焦 Coking coal is denoted as Y. 焦 Coal fat is denoted as Y 肥 Lean coal is denoted as Y. 瘦 The microstructure of coal-derived coke was calculated based on the revision coefficient and coal type ratio. The microstructure of coal-derived coke includes coarse-grained mosaic structure, fine-grained mosaic structure, fibrous structure, lamellar structure, and isotropic structure.

[0086] The coarse-grained mosaic structure of coal-derived coke is denoted as: X 配粗 =Y 气 *K 气粗 *X 气粗 +Y 1 / 3焦 *K 1 / 3焦粗 *X 1 / 3焦粗 +Y 焦 *K 焦粗 *X 焦粗 +Y 肥 *K 肥粗 *X 肥粗+Y 瘦 *K 瘦粗 *X 瘦粗 (5);

[0087] The fine-grained mosaic structure of coal-derived coke is denoted as: X 配细 =Y 气 *X 气细 +Y 1 / 3焦 *X 1 / 3焦细 +Y 焦 *X 焦细 +Y 肥 *X 肥细 +Y 瘦 *X 瘦细 (6);

[0088] The fibrous structure of coal-derived coke is denoted as: X 配纤 =Y 气 *X 气纤 +Y 1 / 3焦 *X 1 / 3焦纤维 +Y 焦 *X 焦纤 +Y 肥 *X 肥纤 +Y 瘦 *K 瘦纤 *X 瘦纤 (7);

[0089] The flaky structure of coal as coke is denoted as: X 配片 =Y 气 *X 气片 +Y 气肥 *X 气肥片 +Y 1 / 3焦 *X 1 / 3焦片 +Y 焦 *X 焦片 +Y 肥 *X 肥片 +Y 瘦 *K 瘦片 *X 瘦片 (8);

[0090] The isotropic structure of coal-to-coke formation is denoted as: X 配同 =Y 气 *K 气同 *X 气同 +Y 1 / 3焦 *K 1 / 3焦同 *X 1 / 3焦同 +Y 焦 X 焦同 +Y 肥 *X 肥同 +Y 瘦 X 瘦同 (9);

[0091] The inert structure of coal-to-coke formation is denoted as: X配惰 =Y 气 *X 气惰 +Y 1 / 3焦 *X 1 / 3焦惰 +Y 焦 *X 焦惰 +Y 肥 *X 肥惰 +Y 瘦 *X 瘦惰 (10);

[0092] In some examples, the step of pretreating the coking coal to obtain the influencing factor further includes:

[0093] The correction coefficients for the fluidity and expansion of the coking coal are determined based on the volatile matter content of the coking coal.

[0094] The volatile matter content of 1 / 3 coking coal is used to determine the 1 / 3 coking coal flowability correction coefficient and the 1 / 3 coking coal expansion correction coefficient.

[0095] When the thickness of the plastic layer of the coking coal is greater than or equal to the preset thickness, the flowability correction coefficient of the coking coal and the coal type ratio are adjusted and summed to obtain the first high-flowability coal.

[0096] For example, the flow correction factor and expansion correction factor for each coal type are determined based on the volatile matter (Vdaf), with the flow correction factor being K. MF Expansion correction factor K b .

[0097] Table 2:

[0098]

[0099] The fluidity correction coefficient and expansion correction coefficient of coking coal are determined based on the volatile matter content of coking coal. The fluidity correction coefficient and expansion correction coefficient of 1 / 3 coking coal are determined based on the volatile matter content of 1 / 3 coking coal. The specific correction coefficients are shown in Table 2. The fluidity expansion data of 1 / 3 coking coal and coking coal are shown in Table 3.

[0100] Table 3:

[0101] Coal sample Log MF b / ％ 1 / 3 coking coal 1 3.3 50 1 / 3 coking coal 2 3.3 40 1 / 3 coking coal 3 2.6 10 Fat coal 1 4.3 150 Fat coal 2 4.1 140

[0102] If the thickness of the plastic layer in the coking coal is greater than or equal to a preset thickness, then the coking coal flowability correction coefficient and the coal type ratio are adjusted and summed to obtain the first high-flowability coal flowability, where the preset thickness is 25. The expression for the first high-flowability coal flowability is:

[0103] lgMF1=Y 肥煤 *K MF肥 *lgMF肥 (11);

[0104] Where lgMF is the Gibbs freeness.

[0105] Table 4:

[0106]

[0107] The revision coefficients for the coking structure and the correction coefficients for the process characteristics of a single type of coal are shown in Table 4.

[0108] Table 5:

[0109]

[0110] The pretreatment of the coking structure and process properties of a single type of coal is shown in Table 5.

[0111] In some examples, the step of pretreating the coking coal to obtain the influencing factor further includes:

[0112] When the Gibbs mobility of the 1 / 3 coking coal is greater than the preset mobility, the mobility correction coefficient of the 1 / 3 coking coal and the coal type ratio are adjusted and summed to obtain the second high mobility coal mobility.

[0113] For example, if the Gibbs freeness (Y value) of 1 / 3 coking coal is greater than the preset freeness, then the freeness correction coefficient of 1 / 3 coking coal and the coal type ratio are adjusted and summed to obtain the second highest freeness of the coal. The preset freeness is 3.0, and the expression for the second highest freeness of the coal is:

[0114] lgMF2=Y 1 / 3焦煤 *K MF1 / 3焦煤 *lgMF 1 / 3焦煤 (12);

[0115] Where lgMF is the Gibbs freeness.

[0116] In some examples, the step of pretreating the coking coal to obtain the influencing factor further includes:

[0117] When the Kierkegaard fluidity of the 1 / 3 coking coal is greater than the preset fluidity and the Kierkegaard fluidity of the fat coal is greater than the preset fluidity, the expansion degree is obtained by adjusting and summing the coal type ratio, the expansion degree correction coefficient of the fat coal and the expansion degree correction coefficient of the 1 / 3 coking coal.

[0118] For example, if the Kierkegaard fluidity of 1 / 3 coking coal is greater than the preset fluidity and the Kierkegaard fluidity of bituminous coal is greater than the preset fluidity, then the expansion degree is obtained by adjusting and summing the fluidity based on the coal type ratio, the expansion degree correction coefficient of bituminous coal, and the expansion degree correction coefficient of 1 / 3 coking coal. The preset fluidity is 3.0, and the expression for the expansion degree is:

[0119] b = Y 肥煤 *K b肥 *b 肥 +Y 1 / 3焦煤 *K b1 / 3焦煤 *b 1 / 3焦煤 (13);

[0120] Among them, the proportion of single coal in each coal blending scheme is shown in Table 6, the coke quality influencing factors are shown in Table 7, and the dry quenched coke quality of each scheme in a 6-meter coke oven is shown in Table 8.

[0121] Table 6:

[0122] Scheme Gas 2 1 / 3 coking 1 1 / 3 coking 2 1 / 3 coking 3 Fat 1 Fat 2 Coke 1 Coke 2 Coke 3 Lean 2 Lean 1 1 4％ 13％ 5％ 7％ 0％ 12％ 27％ 18％ 4％ 10％ 0％ 2 4％ 11％ 8％ 6％ 4％ 10％ 25％ 18％ 4％ 7％ 3％ 3 5％ 11％ 11％ 4％ 5％ 11％ 23％ 17％ 4％ 6％ 3％ 4 5％ 11％ 13％ 4％ 5％ 10％ 23％ 13％ 5％ 11％ 0％ 5 5％ 11％ 0％ 5％ 4％ 12％ 30％ 18％ 5％ 10％ 0％ 6 6％ 14％ 9％ 5％ 4％ 9％ 26％ 14％ 3％ 7％ 3％ 7 6％ 14％ 9％ 5％ 5％ 8％ 26％ 14％ 3％ 10％ 0％ 8 6％ 12％ 7％ 5％ 5％ 9％ 24％ 19％ 3％ 7％ 3％ 9 6％ 13％ 8％ 6％ 5％ 9％ 27％ 13％ 3％ 7％ 3％ 10 7％ 10％ 12％ 4％ 5％ 11％ 22％ 13％ 5％ 11％ 0％ 11 7％ 11％ 12％ 0％ 5％ 11％ 22％ 16％ 5％ 11％ 0％ 12 7％ 10％ 10％ 0％ 3％ 11％ 25％ 18％ 5％ 11％ 0％ 13 9％ 11％ 13％ 0％ 5％ 12％ 22％ 14％ 5％ 6％ 3％ 14 9％ 12％ 11％ 0％ 7％ 10％ 22％ 18％ 3％ 5％ 3％ 15 9％ 12％ 10％ 0％ 5％ 10％ 24％ 17％ 4％ 9％ 0％ 16 9％ 10％ 5％ 0％ 7％ 12％ 21％ 19％ 5％ 9％ 3％ 17 9％ 10％ 5％ 0％ 6％ 10％ 22％ 21％ 5％ 12％ 0％ 18 9％ 10％ 5％ 0％ 8％ 3％ 30％ 18％ 5％ 9％ 3％ 19 11％ 12％ 9％ 0％ 7％ 10％ 22％ 18％ 3％ 8％ 0％ 20 11％ 12％ 9％ 0％ 7％ 10％ 22％ 18％ 3％ 5％ 3％

[0123] Table 7:

[0124]

[0125]

[0126] Table 8:

[0127] Scheme M 40 / %]]> M 10 / %]]> CRI / % CSR / % 1 88.80 5.89 22.20 68.90 2 88.47 5.90 21.49 69.20 3 88.39 6.00 20.90 68.23 4 88.67 5.98 22.82 67.02 5 89.03 5.72 21.00 69.63 6 88.20 5.98 21.88 68.72 7 88.87 5.90 22.00 68.72 8 88.48 5.90 21.84 69.04 9 88.33 5.45 21.80 68.60 10 88.40 5.91 23.43 67.03 11 88.40 5.90 22.95 66.70 12 88.72 5.80 23.20 67.50 13 87.85 6.05 22.40 67.75 14 88.01 6.05 21.60 68.80 15 88.16 5.90 22.53 68.12 16 88.42 5.84 21.70 68.60 17 88.72 5.86 22.87 68.30 18 88.59 5.78 22.98 68.50 19 87.82 5.91 22.18 68.35 20 87.41 6.08 21.93 68.65

[0128] In some examples, the step of correcting the dimensions of the microstructure according to the coking coal to obtain the correction coefficient includes:

[0129] Based on the volatile matter and caking index of the gas coal, the coarse-grained mosaic and isotropic properties of the gas coal in the microstructure are corrected by coefficients to obtain the coarse-grained mosaic correction coefficient and the isotropic property correction coefficient of the gas coal.

[0130] Based on the volatile matter and caking index of 1 / 3 coking coal, coefficients were used to correct the coarse-grained mosaic and isotropic properties of the microstructure of 1 / 3 coking coal, resulting in correction coefficients for coarse-grained mosaic and isotropic properties of 1 / 3 coking coal.

[0131] The coarse-grained mosaic of the microstructure of the coarse-grained coal is corrected based on the volatile matter content of the coarse-grained coal to obtain the coarse-grained mosaic correction coefficient.

[0132] For example, coefficients are applied to the coarse-grained mosaic and isotropic properties of gas coal in multiple dimensions of the microstructure based on the volatile matter and caking index of gas coal to obtain the coarse-grained mosaic correction coefficient and the isotropic property correction coefficient of gas coal. Similarly, coefficients are applied to the coarse-grained mosaic and isotropic properties of 1 / 3 coking coal in multiple dimensions of the microstructure based on the volatile matter and caking index of 1 / 3 coking coal to obtain the coarse-grained mosaic correction coefficient and the isotropic property correction coefficient of 1 / 3 coking coal. The constraints on the volatile matter, caking index, volatile matter, and caking index of gas coal are shown in Table 9.

[0133] Table 9:

[0134]

[0135] The coefficients of coarse-grained mosaic in the microstructure of coarse-grained coal in multiple dimensions were corrected based on the volatile matter content of coarse-grained coal to obtain the coarse-grained mosaic correction coefficients. The constraints on the volatile matter content of coarse-grained coal are shown in Table 10.

[0136] Table 10:

[0137]

[0138] In some examples, the step of correcting the dimensions of the microstructure according to the coking coal to obtain the correction coefficients further includes:

[0139] Based on the coking strength of coking coal, the coking coal coarse grain mosaic of the microstructure is corrected by coefficients to obtain the coking coal coarse grain mosaic correction coefficient.

[0140] Based on the lean coal bonding index, coefficients for the lean coal coarse-grained mosaic, lean coal fiber, and lean coal flaky structures in the microstructure are corrected to obtain the lean coal coarse-grained mosaic correction coefficient, lean coal fiber correction coefficient, and lean coal flaky correction coefficient.

[0141] For example, the coking strength of coking coal is used to correct the coarse grain mosaic of coking coal in the multidimensional microstructure to obtain the coarse grain mosaic correction coefficient of coking coal. The range of coking strength of coking coal and the coarse grain mosaic correction coefficient of coking coal corresponding to each range are shown in Table 11.

[0142] Table 11:

[0143]

[0144] Based on the lean coal bonding index, coefficients were corrected for the coarse-grained mosaic, fiber, and flaky structure of lean coal in the multidimensional microstructure to obtain the correction coefficients for coarse-grained mosaic, fiber, and flaky structure of lean coal, respectively. The range of the lean coal bonding index and the corresponding correction coefficient for coarse-grained mosaic of lean coal in each range are shown in Table 12.

[0145] Table 12:

[0146]

[0147] like Figure 6 As shown, this application proposes a coke quality prediction model construction system, which includes: a data acquisition module 21, a data preprocessing module 22, and a model construction module 23.

[0148] The data acquisition module 21 is configured to acquire the actual mass of coking coal and coke, wherein the coking coal includes gas coal, 1 / 3 coking coal, fat coal, lean coal and coking coal;

[0149] The data preprocessing module 22 is configured to preprocess the coking coal to obtain influencing factors, the influencing factors including the microstructure of coal coking, the first high-flowability coal flowability, the second high-flowability coal flowability and expansion.

[0150] The model building module 23 is configured to build a prediction model using the actual quality of the coke, the influencing factors, and the random forest algorithm.

[0151] The effects of applying the aforementioned method in the above system can be found in the description of the aforementioned method embodiments, and will not be repeated here.

[0152] like Figure 7 As shown, this application embodiment also provides an electronic device 300, including a memory 310, a processor 320, and a computer program 311 stored in the memory 310 and executable on the processor. When the processor 320 executes the computer program 311, it implements the steps of any of the above-described methods for tire position self-learning.

[0153] Since the electronic device described in this embodiment is the device used to implement the degradation trend prediction device for a weighing sensor in this application embodiment, those skilled in the art can understand the specific implementation method and various variations of the electronic device in this embodiment based on the method described in this application embodiment. Therefore, how the electronic device implements the method in this application embodiment will not be described in detail here. Any device used by those skilled in the art to implement the method in this application embodiment is within the scope of protection of this application.

[0154] In practical implementation, when the computer program 311 is executed by the processor, it can achieve the following: Figure 1 Any of the corresponding implementation methods in the embodiments.

[0155] It should be noted that the descriptions of each embodiment in the above embodiments have different focuses. For parts that are not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0156] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-readable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-readable program code.

[0157] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create a machine for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0158] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0159] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0160] This application also provides a computer program product, which includes computer software instructions that, when executed on a processing device, cause the processing device to execute the LDPC decoding method of a solid-state drive controller.

[0161] A computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the flow or function according to the embodiments of this application is generated. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can store or a data storage device such as a server or data center that integrates one or more available media. The available medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid-state disk (SSD)).

[0162] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0163] In the several embodiments provided in this application, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces, or indirect coupling or communication connection between devices or units, and may be electrical, mechanical, or other forms.

[0164] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0165] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0166] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0167] The above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

[0168] Although preferred embodiments have been described in this specification, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of this specification.

[0169] Obviously, those skilled in the art can make various modifications and variations to this specification without departing from its spirit and scope. Therefore, if such modifications and variations fall within the scope of the claims and their equivalents, this specification is also intended to include such modifications and variations.

Claims

1. A method for constructing a coke quality prediction model, characterized in that, The method includes: Obtain the actual quality of coking coal and coke, wherein the coking coal includes gas coal, 1 / 3 coking coal, fat coal, lean coal and coking coal; The coking coal is pretreated to obtain influencing factors, which include the coal coking microstructure, the first high-flowability coal flowability, the second high-flowability coal flowability, and the expansion. A prediction model is constructed using the actual quality of the coke, the influencing factors, and the random forest algorithm. The steps for pretreating the coking coal to obtain the influencing factors include: The coking coal is heated to obtain coke dust for making bright sheets; The microstructure of the focal length light-emitting film was obtained by testing. The dimensions of the microstructure are corrected according to the coking coal to obtain correction coefficients and coal type ratios. The correction coefficients include coarse-grained mosaic correction coefficients for gas coal, isotropic correction coefficients for gas coal, coarse-grained mosaic correction coefficients for 1 / 3 coking coal, isotropic correction coefficients for 1 / 3 coking coal, coarse-grained mosaic correction coefficients for fat coal, coarse-grained mosaic correction coefficients for coking coal, coarse-grained mosaic correction coefficients for lean coal, fibrous correction coefficients for lean coal, and flaky correction coefficients for lean coal. The microstructure of coal coking is obtained based on the correction coefficient and the coal type ratio. The correction coefficients for the fluidity and expansion of the coking coal are determined based on the volatile matter content of the coking coal. The volatile matter content of 1 / 3 coking coal is used to determine the 1 / 3 coking coal flowability correction coefficient and the 1 / 3 coking coal expansion correction coefficient. When the thickness of the plastic layer of the coking coal is greater than or equal to the preset thickness, the flowability correction coefficient of the coking coal and the coal type ratio are corrected and summed to obtain the first high-flowability coal flowability. When the Gibbs flowability of the 1 / 3 coking coal is greater than the preset flowability, the flowability correction coefficient of the 1 / 3 coking coal and the coal type ratio are corrected and summed to obtain the second high-flowability coal flowability. When the Kierkegaard fluidity of the 1 / 3 coking coal is greater than the preset fluidity and the Kierkegaard fluidity of the fat coal is greater than the preset fluidity, the expansion degree is obtained by adjusting and summing the coal type ratio, the expansion degree correction coefficient of the fat coal and the expansion degree correction coefficient of the 1 / 3 coking coal. The steps of correcting the dimensions of the microstructure according to the coking coal to obtain the correction coefficients include: Based on the volatile matter and caking index of the gas coal, the coarse-grained mosaic and isotropic properties of the gas coal in the microstructure are corrected by coefficients to obtain the coarse-grained mosaic correction coefficient and the isotropic property correction coefficient of the gas coal. Based on the volatile matter and caking index of 1 / 3 coking coal, coefficients were used to correct the coarse-grained mosaic and isotropic properties of the microstructure of 1 / 3 coking coal, resulting in correction coefficients for coarse-grained mosaic and isotropic properties of 1 / 3 coking coal. The coarse-grained mosaic of the microstructure of the coarse-grained coal is corrected based on the volatile matter content of the coarse-grained coal to obtain the coarse-grained mosaic correction coefficient of the coarse-grained coal. Based on the coking strength of coking coal, the coking coal coarse grain mosaic of the microstructure is corrected by coefficients to obtain the coking coal coarse grain mosaic correction coefficient. Based on the lean coal bonding index, coefficients for the lean coal coarse-grained mosaic, lean coal fiber, and lean coal flaky structures in the microstructure are corrected to obtain the lean coal coarse-grained mosaic correction coefficient, lean coal fiber correction coefficient, and lean coal flaky correction coefficient.

2. A system for constructing a coke quality prediction model, characterized in that, The system includes: a data acquisition module, a data preprocessing module, and a model building module; The data acquisition module is configured to acquire the actual quality of coking coal and coke, wherein the coking coal includes gas coal, 1 / 3 coking coal, fat coal, lean coal and coking coal; The data preprocessing module is configured to: preprocess the coking coal to obtain influencing factors, the influencing factors including the microstructure of coal forming coke, the first high-flowability coal flowability, the second high-flowability coal flowability, and the expansion degree; the steps of preprocessing the coking coal to obtain influencing factors include: heating the coking coal to obtain a coke dust polishing sheet; testing the coke dust polishing sheet to obtain a microstructure; and correcting the dimensions of the microstructure according to the coking coal to obtain correction coefficients and coal type ratios, the correction coefficients including the coarse-grained mosaic correction coefficient for gas coal, the isotropic correction coefficient for gas coal, the coarse-grained mosaic correction coefficient for 1 / 3 coking coal, the isotropic correction coefficient for 1 / 3 coking coal, and the coarse-grained mosaic correction coefficient for fat coal. The following parameters are used: a coefficient for correcting the coking coal coarse-grained mosaic, a coefficient for correcting the lean coal coarse-grained mosaic, a coefficient for correcting the lean coal fiber, and a coefficient for correcting the lean coal flaky structure; the microstructure of the coal coking structure is obtained based on the correction coefficients and the coal type ratio; the fluidity correction coefficient and the expansion correction coefficient of the fat coal are determined based on the volatile matter content of the fat coal; the fluidity correction coefficient and the expansion correction coefficient of the 1 / 3 coking coal are determined based on the volatile matter content of the 1 / 3 coking coal; when the thickness of the plastic layer of the fat coal is greater than or equal to a preset thickness, the fluidity correction coefficient of the fat coal and the coal type ratio are corrected and summed to obtain the first high-fluidity coal fluidity; when the Kierkegaard fluidity of the 1 / 3 coking coal is greater than the preset fluidity... The second high-flowability coal flowability is obtained by correcting and summing the 1 / 3 coking coal flowability correction coefficient and the coal type ratio; when the Kierkegaard flowability of the 1 / 3 coking coal is greater than the preset flowability and the Kierkegaard flowability of the fat coal is greater than the preset flowability, the expansion degree is obtained by correcting and summing the coal type ratio, the fat coal expansion degree correction coefficient, and the 1 / 3 coking coal expansion degree correction coefficient; the step of correcting the dimensions of the microstructure according to the coking coal to obtain the correction coefficient includes: correcting the coarse-grained mosaic and isotropic properties of the microstructure of the gas coal according to the volatile matter and caking index of the gas coal to obtain the coarse-grained mosaic correction coefficient and the isotropic property correction coefficient of the gas coal; Based on the volatile matter and caking index of 1 / 3 coking coal, coefficients are applied to correct the coarse-grained mosaic and isotropic properties of the microstructure of 1 / 3 coking coal, resulting in correction coefficients for coarse-grained mosaic and isotropic properties of 1 / 3 coking coal. Similarly, based on the volatile matter of bituminous coal, coefficients are applied to correct the coarse-grained mosaic of the microstructure of bituminous coal, resulting in correction coefficients for coarse-grained mosaic. Furthermore, based on the coking strength of coking coal, coefficients are applied to correct the coarse-grained mosaic, fiber, and flaky properties of lean coal, resulting in correction coefficients for coarse-grained mosaic, fiber, and flaky properties of lean coal. The model building module is configured to construct a prediction model using the actual quality of the coke, the influencing factors, and the random forest algorithm.

3. An electronic device, comprising: The memory and processor are characterized in that the processor is used to execute a computer program stored in the memory to implement the steps of the method for constructing a coke quality prediction model as described in claim 1.

4. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the method for constructing a coke quality prediction model as described in claim 1.

Images