Coal blending coking method using single coal reactivity kmeans algorithm

Abstract

The invention provides a coal blending and coking method using a single coal reactivity kmeans algorithm, and relates to the technical field of metallurgical raw materials and pretreatment technologies. Comprising the following steps: carrying out test detection analysis on coal quality properties, coal rock characteristics and coal catalytic indexes MBI of coke reactivity of actual single coking coal used for production according to the national standard to form an index I database; carrying out test detection analysis on the caking property, the Aoya expansion degree and the Gieseler fluidity property of the single coking coal to form an index number II data library; and according to the index I database and the index number II database, realizing Kmeans algorithm analysis of the quality of the coke coking by the coking coal. And analyzing and generating a coal blending scheme according to the Kmeans algorithm of the coke quality. On the basis of high-reactivity coke preparation experience and a coking coal Kmeans algorithm, high-reactivity high-post-reaction strength coke is prepared.

Description

Technical Field

[0001] The invention relates to the technical field of metallurgical raw materials and pretreatment technology, and in particular to a coal blending and coking method using a single-type coal reactivity kmeans algorithm. Background Art

[0002] Blast furnace ironmaking has always focused on the cold and hot indicators of coke, especially the strengthening of the high coke reaction strength CSR and coke crushing strength M40 indicators, but the application of the strengthening requirements of this indicator is proposed from the output of molten iron in the blast furnace ironmaking process. Therefore, in order to meet the requirements of the hot performance indicators of metallurgical coke in blast furnace production, coking enterprises need to add a large amount of high-quality coking coal and fat coal when blending coal for coking. The current shortage of high-quality coking coal resources affects the hot performance of coke in coking production, and also leads to high costs of blending coal for coking. At the same time, in response to the national dual-carbon strategic goals, blast furnace production needs to implement carbon reduction requirements. On the basis of ensuring that coke has a certain CSR and M40 strength, it is necessary to ensure the coke CSR index while appropriately improving the coke CRI index, so as to ensure that the blast furnace can maintain a high utilization coefficient while achieving the technical goal of carbon reduction. At present, Nippon Steel Corporation has developed low-carbonized coke raw materials using high-calcium coal. When the original coke CSR and DI15015 are 58% and 81.8% respectively, adding 0.5% calcium (CaO) catalyst to the coking coal can achieve about 5% carbon reduction in the coking and blast furnace continuous system; of course, when the coke reactivity CRI is increased, the strength CSR of the coke after reaction decreases, so the experiment needs to develop a process technology that can ensure the stability of the coke CSR, so as to achieve carbon reduction in the blast furnace while ensuring stable production and operation of the blast furnace. The extreme case of domestic coke thermal performance is the blast furnace coke quality index of the Bayi Steel Plant, whose CSR index is less than 40%, while the CRI can reach about 40%. Of course, its CSR is too low and its blast furnace operation utilization coefficient is not high. Summary of the invention

[0003] According to the technical problems mentioned in the above background technology, a method for coking coal using a single coal reactivity kmeans algorithm is provided. The present invention uses a single coal reactivity kmeans algorithm to prepare coke, while ensuring the cold strength M of the coke. 40 Under these conditions, the CRI of coke can be increased by 1-2%, while the hot strength CSR of coke can be guaranteed to maintain the relatively stable performance of the original index.

[0004] The technical means adopted by the present invention are as follows:

[0005] A method for preparing coke and blending coal by using a single-type coal reactivity kmeans algorithm comprises the following steps:

[0006] Step 1: Conduct test and analysis on the coal quality properties, coal rock characteristics and coal catalytic index MBI of coke reactivity of the actual single coking coal used in production according to national standards to form an index I database;

[0007] Step 2: Conduct test and analysis on the bonding performance, Oya expansion and Kiel fluidity of a single type of coking coal to form an index database;

[0008] Step 3: Implementing Kmeans algorithm analysis of the quality of coke produced by coking coal according to the index I database and the index II database;

[0009] Step 4: Generate a coal blending plan based on the Kmeans algorithm analysis of the coke quality.

[0010] Furthermore, the coal properties include: industrial analysis, total sulfur and gelatinous layer thickness.

[0011] Furthermore, in step 3, the coke quality Kmeans algorithm analysis is implemented by SPSS software.

[0012] Furthermore, the step 3 comprises the following steps:

[0013] Step 31: Conduct coking coal test to determine the mechanical strength of coke M 40 、M 10 and preparation of raw data of thermal properties CRI and CSR;

[0014] Step 32: Perform Z-score standardization on the original data;

[0015] Step 33: Perform K-means cluster analysis on the experimental coke mechanical strength and thermal property data after Z-score standardization to obtain the coking coal classification of each group;

[0016] Step 34: Mark and group the coke according to the mechanical strength and thermal properties based on the grouping results of the Kmeans algorithm;

[0017] Step 35: Determine the coal grade for the same type of coking coal according to national standards.

[0018] Furthermore, the coal blending scheme is formulated by selecting primary coal and secondary coal from the coal grade on the basis of meeting the requirements of ash content, sulfur content, volatile matter and adhesiveness of the blended coal.

[0019] Furthermore, the coal grades include: primary coal, secondary coal and auxiliary coal.

[0020] Compared with the prior art, the present invention has the following advantages:

[0021] The invention is based on the experience of preparing high-reactivity coke and the Kmeans algorithm for coking coal, and prepares coke with high reactivity and high post-reaction strength. The preparation of coke with high reactivity and post-reaction strength is achieved through experiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0023] Figure 1 It is a schematic diagram of the overall process of the present invention. DETAILED DESCRIPTION

[0024] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. 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 creative work should fall within the scope of protection of the present invention.

[0025] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0026] like Figure 1 As shown, the present invention provides a coal blending and coking method using a single coal reactivity kmeans algorithm, comprising the following steps:

[0027] Step 1: Conduct test and analysis on the coal quality properties (industrial analysis, total sulfur and gelatinous layer thickness) of the actual single coking coal used in production, coal rock characteristics and coal catalytic index MBI of coke reactivity according to national standards to form an index I database;

[0028] Step 2: Conduct test and analysis on the bonding performance, Oya expansion and Kiel fluidity of a single type of coking coal to form an index database;

[0029] Step 3: Based on the index I database and the index II database, implement the Kmeans algorithm analysis of the quality of coke produced by coking coal; implement the Kmeans algorithm analysis of the quality of coke by SPSS software. Step 3 includes the following steps:

[0030] Step 31: Conduct coking coal test to determine the mechanical strength of coke M 40 、M 10 and preparation of raw data of thermal properties CRI and CSR;

[0031] Step 32: Perform Z-score standardization on the original data;

[0032] Step 33: Perform K-means cluster analysis on the experimental coke mechanical strength and thermal property data after Z-score standardization to obtain the coking coal classification of each group;

[0033] Step 34: Mark and group the coke according to the mechanical strength and thermal properties based on the grouping results of the Kmeans algorithm;

[0034] Step 35: Determine the coal grade of the same type of coking coal according to national standards. The coal grade includes: primary coal, secondary coal and auxiliary coal.

[0035] Step 4: Generate a coal blending scheme based on the Kmeans algorithm analysis of the coke quality. The coal blending scheme is formulated by selecting the primary coal and the secondary coal in the coal grade on the basis of meeting the requirements of ash content, sulfur content, volatile matter and cohesiveness of the blended coal.

[0036] Embodiment 1:

[0037] The experiment selected production coking coal and carried out a 40kg experimental coke oven experiment; and conducted M40, M10, CRI, and CSR tests; based on the experimental results, the coking coal was refined and a coal blending plan was formed.

[0038] Table 1 Quality indicators

[0039]

[0040]

[0041] According to the coke quality, the Kmeans algorithm is used to classify coking coal as follows:

[0042] (1) Gas fertilizer coal: primary choice: none; secondary choice: Q1; auxiliary: Q2.

[0043] (2) Gas coal: the primary choice is Q4; the secondary choice is Q3.

[0044] (3) 1 / 3 coking coal: primary selection: 1 / 3J3, 1 / 3J4; secondary selection: 1 / 3J1; auxiliary selection: 1 / 3J2.

[0045] (4) Fat coal: F1, F2, F6 as the main choice; F3 as the secondary choice; F4, F5, F7 as the auxiliary choice.

[0046] (5) Coking coal: Mainly selected are J3, J7, J10, and J11; Secondary selected are J2, J5, and J6; Auxiliary selected are J1, J4, J8, and J9.

[0047] (6) Lean coal: primary choice: None; secondary choices: S1 and S2.

[0048] Table 2 Refinement classification results

[0049]

[0050]

[0051] Analysis of the experimental effect of 40kg coke oven coal blending:

[0052] According to the classification results, a 40kg experimental coke oven experiment was conducted. Scheme 1# is the original blend, with 1 / 3 J4 blended in 13%, F1 fat coal 7%, F7 fat coal 11%, coking coal J4, J5, J8 and J9 totaling 50%, and S2 lean coal blended in 14%. Schemes 2# to 9# increase the reactivity of coke while maintaining the stability or small fluctuation of the strength after the coke reaction. Schemes 2# to 4# increase 1 / 3 coking coal on the basis of 1#, blend low metamorphic fat coal and gas coal, and reduce lean coal. The main coal types account for 30%, 14% and 30%. Schemes 5# to 9# are mainly selected at 85% to 90%, supplemented by secondary selection and other coking coal.

[0053] Table 3 Experimental scheme of 40kg coke oven coal blending

[0054]

[0055] Table 4 and Table 5 are the indicators of some blended coal and coke quality respectively. The coke reactivity CRI and post-reaction strength CSR of the 1# production scheme are 22.3% and 67.4% respectively.

[0056] Table 4 Coal quality indexes of coal blending coking experiment

[0057]

[0058]

[0059] Table 5 Thermal properties of 2kg coke from coke oven

[0060]

[0061] From the data, we can see that the CRI of 2#~4# increases, and the strength after reaction decreases; the reactivity of 3# and 9# coke increases by 6.8 and 6.6 percentage points respectively, and the strength after reaction of coke also meets the requirements; it can be seen that by analyzing coking coal through Kmeans algorithm, the coal blending scheme of high-reactivity coke can be obtained.

[0062] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0063] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts not described in detail in a certain embodiment, reference can be made to the relevant description of other embodiments. In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways.

[0064] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A coal blending and coking method using a single coal reactivity kmeans algorithm, characterized in that: The following steps are involved: Step 1: Conduct test and analysis on the coal quality properties, coal rock characteristics and coal catalytic index MBI of coke reactivity of the actual single coking coal used in production according to national standards to form an index I database; Step 2: Conduct test and analysis on the bonding performance, Oya expansion and Kiel fluidity of a single type of coking coal to form an index database; Step 3: Implementing Kmeans algorithm analysis of the quality of coke produced by coking coal according to the index I database and the index II database; Step 4: Generate a coal blending plan based on the Kmeans algorithm analysis of the coke quality.

2. A method for coking coal using a single coal reactivity kmeans algorithm according to claim 1, characterized in that: The coal properties include: industrial analysis, total sulfur and thickness of the colloidal layer.

3. The method for coking coal using the kmeans algorithm for the reactivity of a single coal according to claim 1, characterized in that: In step 3, the coke quality Kmeans algorithm analysis is implemented by SPSS software.

4. A coal blending and coking method using a single coal reactivity kmeans algorithm according to claim 1 or 3, characterized in that: The step 3 comprises the following steps: Step 31: Conduct coking coal test to determine the mechanical strength of coke M 40 、M 10 and preparation of raw data of thermal properties CRI and CSR; Step 32: Perform Z-score standardization on the original data; Step 33: Perform K-means cluster analysis on the experimental coke mechanical strength and thermal property data after Z-score standardization to obtain the coking coal classification of each group; Step 34: Mark and group the coke according to the mechanical strength and thermal properties based on the grouping results of the Kmeans algorithm; Step 35: Determine the coal grade for the same type of coking coal according to national standards.

5. The method for coking coal using a single-coal reactivity kmeans algorithm according to claim 1, characterized in that: The coal blending scheme is formulated by selecting primary coal and secondary coal from the coal grade on the basis of meeting the requirements of ash content, sulfur content, volatile matter and adhesiveness of the blended coal.

6. The method for coking coal using the kmeans algorithm for the reactivity of a single coal according to claim 1, characterized in that: The coal grades include: primary coal, secondary coal and auxiliary coal.

Images