Methods, equipment, and storage media for establishing a coke quality prediction model for dry quenched coke.

Abstract

This invention relates to the field of coal blending and coking technology, specifically to a method, equipment, and storage medium for establishing a dry-quenched coke quality prediction model. The method includes: acquiring a first coal blending scheme, and first reactivity data, second reactivity data, first post-reaction intensity data, and second post-reaction intensity data of the coal corresponding to the first coal blending scheme after coking; establishing a first coke quality prediction model based on first linear relationship values, second linear relationship values, the proportion of a single type of coal in the blend, and third reactivity data corresponding to a single type of coal; and determining a dry-quenched coke quality prediction model based on the first coke quality prediction model, third linear relationship values, and fourth linear relationship values. The dry-quenched coke quality prediction model established by this application has high accuracy, good generalization ability, and can quickly acquire dry-quenched coke quality data under different coal blending schemes and different coke oven production load conditions.

Description

Technical Field

[0001] This invention relates to the field of coal blending and coking technology, and in particular to a method, equipment, and storage medium for establishing a dry-quenched coke quality prediction model. Background Technology

[0002] Coking plant quenching processes are divided into wet quenching and dry quenching. Dry quenching, due to its advantages such as energy recovery, environmental protection, and improved coke quality, has gradually replaced wet quenching in the coking industry in recent years. However, because dry quenching has been less widely adopted, there are currently few methods for predicting coke quality using this process, and a systematic coke quality prediction model has not yet been developed, making the technology for predicting coke quality using dry quenching immature and unreliable. Summary of the Invention

[0003] To address the aforementioned technical problems, this invention provides a method, equipment, and storage medium for establishing a dry quenching coke quality prediction model. The established dry quenching coke quality prediction model has high accuracy and good generalization ability, and can quickly obtain dry quenching coke quality data under different coal blending schemes and different coke oven production load conditions, filling the gap in the coking industry for predicting coke quality from the dry quenching process.

[0004] In a first aspect, embodiments of the present invention provide a method for establishing a dry-quenched coke quality prediction model, the method comprising:

[0005] The process involves obtaining a first coal blending scheme, first reactivity data, second reactivity data, first post-reaction strength data, and second post-reaction strength data of the coal corresponding to the first coal blending scheme after coking. The first coal blending scheme includes multiple single types of coal. The first reactivity data and the first post-reaction strength data are obtained through a 40Kg load small coke oven test, and the second reactivity data and the second post-reaction strength data are obtained through a large coke oven dry quenching process production test.

[0006] The reactivity and post-reaction strength of each of the multiple single coal types were tested after coking using the 40Kg load small coke oven, and the third reactivity data and third post-reaction strength data corresponding to each single coal type were obtained.

[0007] The third reactivity data corresponding to multiple single coal types are weighted and calculated to obtain the first reactivity prediction data of the coal after coking corresponding to the first coal blending scheme;

[0008] Weighted calculations are performed on the third post-reaction strength data corresponding to multiple single coal types to obtain the predicted first post-reaction strength data of the coal after coking, which corresponds to the first coal blending scheme.

[0009] Based on the first reactivity data and the first reactivity prediction data, determine the value of the first linear relationship;

[0010] The second linear relationship value is determined based on the first post-reaction intensity data and the first post-reaction intensity prediction data;

[0011] A first coke quality prediction model is established based on the first linear relationship value, the second linear relationship value, the proportion of the single type of coal, and the third reactivity data corresponding to the single type of coal.

[0012] A comparative analysis of the differences between the first and second reactivity data was performed to obtain the third linear relationship value;

[0013] A comparative analysis of the differences between the intensity data after the first reaction and the intensity data after the second reaction was performed to obtain the fourth linear relationship value;

[0014] Based on the first coke quality prediction model, the third linear relationship value, and the fourth linear relationship value, a dry-quenched coke quality prediction model is determined.

[0015] According to some embodiments of the first aspect of the present invention, the first coke quality prediction model includes a first reactivity prediction model and a first post-reaction intensity prediction model for coke after coking, wherein establishing the first coke quality prediction model based on the first linear relationship value and the second linear relationship value includes:

[0016] The first reactivity prediction model is determined based on the first linear relationship value, the proportion of each type of coal added, and the third reactivity data corresponding to each type of coal.

[0017] Based on the second linear relationship value, the proportion of the single type of coal added, and the third reactivity data corresponding to the single type of coal, the first post-reaction intensity prediction model is determined.

[0018] According to some embodiments of the first aspect of the present invention, the calculation formula of the first reactivity prediction model is as follows:

[0019] CRI1=∑W i ×CRIi / ∑W i +A,

[0020] Wherein, CRI1 represents the second reactivity prediction data obtained after conducting a coal-to-coke experiment on a certain coal blending scheme using the 40kg load small coke oven, A represents the first linear relationship value, and W... i CRIi represents the proportion of the single type of coal added, and CRIi represents the third reactivity data corresponding to the single type of coal.

[0021] According to some embodiments of the first aspect of the present invention, the calculation formula of the first post-reaction intensity prediction model is as follows:

[0022] CSR1=∑W i ×CSRi / ∑W i +B,

[0023] Among them, W i The formula represents the proportion of the single type of coal used in the blending process. CSR1 represents the second post-reaction strength prediction data obtained after conducting a coal coking test on a certain coal blending scheme using the 40kg load small coke oven. B represents the second linear relationship value. CSRi represents the third post-reaction strength data corresponding to the single type of coal.

[0024] According to some embodiments of the first aspect of the present invention, the dry-quenched coke quality prediction model includes a second reactivity prediction model and a second post-reaction intensity prediction model for coke after coking. The step of determining the dry-quenched coke quality prediction model based on the first coke quality prediction model, the third linear relationship value, and the fourth linear relationship value includes:

[0025] The second reactivity prediction model is determined based on the first reactivity prediction model and the third linear relationship value.

[0026] The second post-reaction intensity prediction model is determined based on the first post-reaction intensity prediction model and the fourth linear relationship value.

[0027] According to some embodiments of the first aspect of the present invention, the calculation formula of the second reactivity prediction model is as follows:

[0028] CRI2 = CRI1 + C h ,

[0029] Wherein, CRI2 represents the third reactivity prediction data obtained after conducting a dry quenching process production test on a certain coal blending scheme using the large coke oven, C h The value of the third linear relationship is represented by CRI1, which represents the second reactivity prediction data obtained after conducting a coal coking test on a certain coal blending scheme using the 40kg load small coke oven.

[0030] According to some embodiments of the first aspect of the present invention, the calculation formula of the second reactivity prediction model is as follows:

[0031] CSR2 = CSR1 + D h ,

[0032] Wherein, CSR2 represents the third post-reaction intensity prediction data obtained after conducting a dry quenching process production test on a certain coal blending scheme using the large coke oven, and D hThe value of the fourth linear relationship is represented by CSR1, which represents the second post-reaction strength prediction data obtained after conducting a coal coking test on a certain coal blending scheme using the 40kg load small coke oven.

[0033] In a second aspect, embodiments of the present invention provide an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement: the method for establishing a dry quenching coke quality prediction model as described in the first aspect above.

[0034] Thirdly, embodiments of the present invention also provide a computer-readable storage medium storing computer-executable instructions for performing the method for establishing a dry-quenched coke quality prediction model as described in the first aspect above.

[0035] The beneficial effects of this invention are reflected in the following: obtaining a first coal blending scheme, and corresponding data on the first reactivity, second reactivity, first post-reaction strength, and second post-reaction strength of the coal after coking; the first coal blending scheme includes multiple single coal types; the first reactivity and first post-reaction strength data are obtained through a 40kg load small coke oven test; the second reactivity and second post-reaction strength data are obtained through a large coke oven dry quenching process production test; the reactivity and post-reaction strength of each of the multiple single coal types are tested after coking using a 40kg load small coke oven, obtaining corresponding third reactivity and third post-reaction strength data; the third reactivity data corresponding to the multiple single coal types are weighted and calculated to obtain the predicted first reactivity data of the coal after coking corresponding to the first coal blending scheme; and the data on the first reactivity of the coal after coking ... first reactivity of the coal after coking corresponding to the first reactivity of the coal after coking corresponding to the first reactivity of the coal after coking corresponding to the first reactivity The third post-reaction intensity data is weighted and calculated to obtain the predicted first post-reaction intensity data of the coal after coking, corresponding to the first coal blending scheme. Based on the first reactivity data and the first reactivity prediction data, the first linear relationship value is determined. Based on the first post-reaction intensity data and the first post-reaction intensity prediction data, the second linear relationship value is determined. Based on the first linear relationship value, the second linear relationship value, the proportion of a single type of coal in the blend, and the third reactivity data corresponding to a single type of coal, a first coke quality prediction model is established. A difference comparison analysis is performed on the first and second reactivity data to obtain the third linear relationship value. A difference comparison analysis is also performed on the first and second post-reaction intensity data to obtain the fourth linear relationship value. Based on the first coke quality prediction model, the third linear relationship value, and the fourth linear relationship value, a dry quenching coke quality prediction model is determined. The dry quenching coke quality prediction model established by this application has high prediction accuracy and good generalization ability. It can quickly obtain dry quenching coke quality data under different coal blending schemes and different coke oven production load conditions, filling the gap in the prediction of coke quality from the dry quenching process in the coking industry. Attached Figure Description

[0036] Figure 1 This is a flowchart illustrating a method for establishing a dry-quenched coke quality prediction model according to a first aspect embodiment of the present invention.

[0037] Figure 2 This is a flowchart illustrating another method for establishing a dry-quenched coke quality prediction model provided in the first aspect embodiment of the present invention.

[0038] Figure 3 This is a schematic diagram of an electronic device provided in a second aspect embodiment of the present invention. Detailed Implementation

[0039] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0040] The following description, in conjunction with the accompanying drawings, details a method, equipment, and storage medium for establishing a dry-quenched coke quality prediction model provided by the present invention, through specific embodiments and application scenarios.

[0041] Example 1:

[0042] Reference Figure 1 , Figure 1 This invention illustrates a method for establishing a dry-quenched coke quality prediction model according to a first aspect embodiment. This method is also applied to and executed by an electronic device. In other words, the method can be executed by software or hardware installed in an electronic device, and includes the following steps:

[0043] Step S110: Obtain the first coal blending scheme, the first reactivity data, the second reactivity data, the first post-reaction strength data, and the second post-reaction strength data of the coal corresponding to the first coal blending scheme after coking.

[0044] In this step, the first coal blending scheme includes multiple single coal types. The first reactivity data and the first post-reaction strength data were obtained through a 40Kg load small coke oven test, and the second reactivity data and the second post-reaction strength data were obtained through a large coke oven dry quenching process production test.

[0045] It should be noted that, for the first coal blending scheme, a coking test was conducted on small coke oven coal with a load of 40 kg corresponding to the first coal blending scheme, and the reactivity data and post-reaction strength data of the coal after coking were detected and collected to obtain the first reactivity data and the first post-reaction strength data; for the first coal blending scheme, a dry quenching process in a large coke oven corresponding to the first coal blending scheme was conducted, and the reactivity data and post-reaction strength data of the coal after coking were detected and collected to obtain the second reactivity data and the second post-reaction strength data.

[0046] Step S120: The reactivity and post-reaction strength of each of the multiple single coal types are tested after coking using a 40Kg load small coke oven, and the third reactivity data and third post-reaction strength data corresponding to each single coal type are obtained.

[0047] It should be noted that the 40kg load-bearing mini coke oven employs advanced technologies such as high temperature, high pressure, and high speed to simulate the actual production environment of coke in a coke oven, thereby better reflecting the performance of coke. During the experiment, coal samples are placed in the oven and heated. The coal samples decompose at high temperatures to generate coke and volatile matter. By collecting and analyzing the mass of volatile matter and coke, the reactivity of the coal and the strength after the reaction can be determined.

[0048] It should be noted that the reactivity of coal, also known as its activity, refers to the degree of reaction between coal and different gasification media under certain temperature conditions. Coal with high reactivity reacts quickly and efficiently during gasification and combustion. The post-reaction strength of coke refers to the ability of the reacted coke to resist cracking and abrasion under mechanical force and thermal stress.

[0049] Step S130: Weighted calculation of the third reactivity data corresponding to multiple single coal types is performed to obtain the first reactivity prediction data of the coal after coking corresponding to the first coal blending scheme.

[0050] In this step, based on the proportion of each type of coal in the first coal blending scheme, the third reactivity data corresponding to multiple types of coal are weighted and calculated to obtain the first reactivity prediction data of the coal after coking corresponding to the first coal blending scheme.

[0051] Step S140: Weighted calculation is performed on the third post-reaction strength data corresponding to multiple single coal types to obtain the predicted first post-reaction strength data of the coal after coking corresponding to the first coal blending scheme.

[0052] In this step, the third post-reaction strength data corresponding to multiple individual coal types are weighted and calculated based on the proportion of each individual coal type in the first coal blending scheme, thereby obtaining the predicted data of the first post-reaction strength of the coal after coking corresponding to the first coal blending scheme.

[0053] Step S151: Determine the value of the first linear relationship based on the first reactivity data and the first reactivity prediction data.

[0054] In this step, based on the first reactivity data and the first reactivity prediction data, the linear relationship between the weighted predicted coke reactivity of a single type of coal and the reactivity of coal after coking under the 40Kg load small coke oven test is obtained, i.e., the first linear relationship value.

[0055] Step S152: Determine the value of the second linear relationship based on the intensity data after the first reaction and the predicted intensity data after the first reaction.

[0056] In this step, based on the first post-reaction strength data and the first post-reaction strength prediction data, the linear relationship between the weighted predicted post-reaction strength of coke for a single type of coal in the same coal blending scheme and the post-reaction strength of coal after coking under the 40Kg load small coke oven test is obtained, which is the second linear relationship value.

[0057] Step S153: Based on the first linear relationship value, the second linear relationship value, the proportion of each type of coal, and the third reactivity data corresponding to each type of coal, establish a first coke quality prediction model.

[0058] In this step, the proportion of a single type of coal is obtained based on the first coal blending scheme. Using the reactivity and post-reaction strength data of the single type of coal after coking, a predictive model for the reactivity and post-reaction strength after coal coking tests in a 40Kg load small coke oven under different coal blending schemes is established, namely the first coke quality prediction model.

[0059] Step S160: Perform a difference comparison analysis on the first reactivity data and the second reactivity data to obtain the third linear relationship value.

[0060] In this step, the third linear relationship value is the linear relationship between the first reactivity data obtained through the 40Kg load small coke oven test and the second reactivity data obtained through the large coke oven dry quenching process production test.

[0061] Step S170: Perform a comparative analysis of the intensity data after the first reaction and the intensity data after the second reaction to obtain the fourth linear relationship value.

[0062] In this step, the fourth linear relationship value is the linear relationship between the first post-reaction strength data obtained through the 40Kg load small coke oven test and the second post-reaction strength data obtained through the large coke oven dry quenching process production test.

[0063] Step S180: Determine the coke quality prediction model for dry quenching coke based on the first coke quality prediction model, the third linear relationship value, and the fourth linear relationship value.

[0064] In this step, based on the first coke quality prediction model, the third linear relationship value, and the fourth linear relationship value, and using the reactivity data and post-reaction strength data of a single type of coal after coking, a prediction model for the reactivity and post-reaction strength of dry-quenched coke under different coke oven production load conditions is established, namely, the dry-quenched coke quality prediction model.

[0065] It should be noted that the dry quenching coke quality prediction model established in this application can quickly predict the reactivity and post-reaction strength data of dry quenching coke under different coal blending schemes and different coke oven production loads. This effectively saves the time and cost of manually formulating and verifying a large number of coal blending schemes. At the same time, it forms a systematic method for predicting the reactivity and post-reaction strength of dry quenching coke, filling the gap in the coking industry for predicting the quality of coke produced by the dry quenching process.

[0066] Coking plant quenching processes are divided into wet quenching and dry quenching. Dry quenching, due to its advantages such as energy recovery, environmental protection, and improved coke quality, has gradually replaced wet quenching in the coking industry in recent years. However, because dry quenching has been less widely adopted, there are currently few methods for predicting coke quality using this process, and a systematic coke quality prediction model has not yet been developed, making the technology for predicting coke quality using dry quenching immature and unreliable.

[0067] Therefore, the method for establishing a dry-quenched coke quality prediction model provided in this embodiment of the invention obtains a first coal blending scheme, and the first reactivity data, second reactivity data, first post-reaction strength data, and second post-reaction strength data of the coal after coking corresponding to the first coal blending scheme. The first coal blending scheme includes multiple single coal types. The first reactivity data and first post-reaction strength data are obtained through a 40kg load small coke oven test, and the second reactivity data and second post-reaction strength data are obtained through a large coke oven dry quenching process production test. The reactivity and post-reaction strength of each of the multiple single coal types are tested after coking using a 40kg load small coke oven to obtain the third reactivity data and third post-reaction strength data corresponding to each single coal type. The third reactivity data corresponding to the multiple single coal types are weighted and calculated to obtain the predicted first reactivity data of the coal after coking corresponding to the first coal blending scheme. The following steps are performed: Weighted calculations are performed on the third post-reaction intensity data corresponding to multiple single coal types to obtain the predicted first post-reaction intensity data of the coal after coking, corresponding to the first coal blending scheme; Based on the first reactivity data and the first reactivity prediction data, the first linear relationship value is determined; Based on the first post-reaction intensity data and the first post-reaction intensity prediction data, the second linear relationship value is determined; Based on the first linear relationship value, the second linear relationship value, the blending ratio of single coal types, and the third reactivity data corresponding to single coal types, a first coke quality prediction model is established; A comparative analysis of the differences between the first and second reactivity data is performed to obtain the third linear relationship value; A comparative analysis of the differences between the first and second post-reaction intensity data is performed to obtain the fourth linear relationship value; Based on the first coke quality prediction model, the third linear relationship value, and the fourth linear relationship value, a dry-quenched coke quality prediction model is determined. The dry quenching coke quality prediction model established by this application has high prediction accuracy and good generalization ability. It can quickly obtain dry quenching coke quality data under different coal blending schemes and different coke oven production load conditions, filling the gap in the coking industry for predicting the quality of coke produced by the dry quenching process.

[0068] Example 2:

[0069] Reference Figure 2 , Figure 2 This invention illustrates another method for establishing a dry-quenched coke quality prediction model according to an embodiment of the first aspect of the present invention. This method is also applied to and executed by an electronic device. In other words, the method can be executed by software or hardware installed in an electronic device, and includes the following steps:

[0070] Step S210: Obtain the first coal blending scheme, the first reactivity data, the second reactivity data, the first post-reaction strength data, and the second post-reaction strength data of the coal corresponding to the first coal blending scheme after coking.

[0071] This step can be adopted. Figure 1 The description of step S110 in the embodiment will not be repeated here.

[0072] Step S220: The reactivity and post-reaction strength of each of the multiple single coal types are tested after coking using a 40Kg load small coke oven, and the third reactivity data and third post-reaction strength data corresponding to each single coal type are obtained.

[0073] This step can be adopted. Figure 1 The description of step S120 in the embodiment will not be repeated here.

[0074] Step S230: Weighted calculation of the third reactivity data corresponding to multiple single coal types is performed to obtain the first reactivity prediction data of the coal after coking corresponding to the first coal blending scheme.

[0075] This step can be adopted. Figure 1 The description of step S130 in the embodiment will not be repeated here.

[0076] Step S240: Weighted calculation is performed on the third post-reaction strength data corresponding to multiple single coal types to obtain the predicted first post-reaction strength data of the coal after coking corresponding to the first coal blending scheme.

[0077] This step can be adopted. Figure 1 The description of step S140 in the embodiment will not be repeated here.

[0078] Step S251: Determine the value of the first linear relationship based on the first reactivity data and the first reactivity prediction data;

[0079] This step can be adopted. Figure 1 The description of step S151 in the embodiment will not be repeated here.

[0080] Step S252: Determine the value of the second linear relationship based on the intensity data after the first reaction and the predicted intensity data after the first reaction.

[0081] This step can be adopted. Figure 1 The description of step S152 in the embodiment will not be repeated here.

[0082] Step S253: Determine the first reactivity prediction model based on the first linear relationship value, the proportion of each type of coal, and the third reactivity data corresponding to each type of coal.

[0083] In one possible implementation, the calculation formula for the first reactive prediction model is as follows:

[0084] CRI1=∑W i ×CRIi / ∑W i +A,

[0085] Wherein, CRI1 represents the second reactivity prediction data obtained after conducting a coal-to-coke experiment on a certain coal blending scheme using a 40kg-loaded small coke oven, A represents the first linear relationship value, and W... i This indicates the proportion of a single type of coal in the blend, and CRIi represents the third reactivity data corresponding to a single type of coal.

[0086] Step S254: Based on the second linear relationship value, the proportion of each type of coal, and the third reactivity data corresponding to each type of coal, determine the intensity prediction model after the first reaction.

[0087] In one possible implementation, the calculation formula for the first reactive prediction model is as follows:

[0088] CRI1=∑W i ×CRIi / ∑W i +A,

[0089] Wherein, CRI1 represents the second reactivity prediction data obtained after conducting a coal-to-coke experiment on a certain coal blending scheme using a 40kg-loaded small coke oven, A represents the first linear relationship value, and W... i This indicates the proportion of a single type of coal in the blend, and CRIi represents the third reactivity data corresponding to a single type of coal.

[0090] Step S260: Perform a difference comparison analysis on the first reactivity data and the second reactivity data to obtain the third linear relationship value.

[0091] This step can be adopted. Figure 1 The description of step S140 in the embodiment will not be repeated here.

[0092] In one possible implementation, the calculation formula for the intensity prediction model after the first reaction is as follows:

[0093] CSR1=∑W i ×CSRi / ∑W i +B,

[0094] Among them, W i The formula represents the proportion of a single type of coal in the blend. CSR1 represents the second post-reaction strength prediction data obtained after conducting a coal coking test on a certain coal blending scheme using a 40kg load small coke oven. B represents the value of the second linear relationship. CSRi represents the third post-reaction strength data corresponding to a single type of coal.

[0095] Step S270: Perform a comparative analysis of the intensity data after the first reaction and the intensity data after the second reaction to obtain the fourth linear relationship value.

[0096] Step S280: Determine the second reactivity prediction model based on the first reactivity prediction model and the third linear relationship value.

[0097] In one possible implementation, the calculation formula for the second reactivity prediction model is as follows:

[0098] CRI2 = CRI1 + C h ,

[0099] Wherein, CRI2 represents the third reactivity prediction data obtained after conducting a dry quenching process production test on a certain coal blending scheme using a large coke oven, C h The value represents the third linear relationship. CRI1 represents the second reactivity prediction data obtained after conducting a coal coking test on a certain coal blending scheme using a small coke oven with a 40kg load.

[0100] That is, CRI2 = ∑W i ×CRIi / ∑W i +A+C h Where A represents the value of the first linear relationship, and W i This indicates the proportion of a single type of coal in the blend, and CRIi represents the third reactivity data corresponding to a single type of coal.

[0101] Step S290: Determine the second post-reaction intensity prediction model based on the first post-reaction intensity prediction model and the fourth linear relationship value.

[0102] In one possible implementation, the calculation formula for the second reactivity prediction model is as follows:

[0103] CSR2 = CSR1 + D h ,

[0104] Wherein, CSR2 represents the third post-reaction intensity prediction data obtained after a dry quenching process production test of a certain coal blending scheme in a large coke oven, and D h The value of the fourth linear relationship is represented by CSR1, which represents the second post-reaction strength prediction data obtained after conducting a coal coking test on a certain coal blending scheme using a small coke oven with a 40kg load.

[0105] That is, CSR2 = ∑W i ×CSRi / ∑W i +B+D h Among them, W i The formula represents the proportion of a single type of coal in the blend. CSR1 represents the second post-reaction strength prediction data obtained after conducting a coal coking test on a certain coal blending scheme using a 40kg load small coke oven. B represents the value of the second linear relationship. CSRi represents the third post-reaction strength data corresponding to a single type of coal.

[0106] Coke is an important raw material and fuel in industrial production, and the sophistication of its production technology and product quality directly affect the economic and technical indicators and production operations of industrial production. In recent years, under the advocacy of energy conservation and environmental protection, dry quenching technology has seen unprecedented development. It refers to a quenching process that uses circulating gas to cool red-hot coke. Dry quenching is superior to wet quenching not only in terms of energy conservation and environmental protection, but also in improving coke quality. However, due to the relatively short time since its adoption, there are currently few methods in the industry for predicting coke quality using dry quenching, and a systematic coke quality prediction model has not been formed, making the technology for predicting coke quality using dry quenching technology immature and unreliable.

[0107] It should be noted that C h and D h As the production load of the large coke oven changes, i.e., the coking time varies, different coking times correspond to different C values. h and D h For example, when the coking time is 27 hours, the corresponding relationship coefficient is C. 27h D 27h When the coking time is 28 hours, the corresponding relationship coefficient is C. 28h D 28h When the coking time is 30 hours, the corresponding relationship coefficient is C. 30h D 30h C h D decreases as coking time increases. h It increases with the length of time spent coking.

[0108] Therefore, the method for establishing a dry-quenched coke quality prediction model provided in this embodiment of the invention obtains a first coal blending scheme, and the first reactivity data, second reactivity data, first post-reaction strength data, and second post-reaction strength data of the coal after coking corresponding to the first coal blending scheme; it then uses a 40kg load small coke oven to detect the reactivity and post-reaction strength of each of the multiple single coal types after coking, obtaining the third reactivity data and third post-reaction strength data corresponding to each single coal type; it then performs a weighted calculation on the third reactivity data corresponding to the multiple single coal types to obtain the first reactivity prediction data of the coal after coking corresponding to the first coal blending scheme; it then performs a weighted calculation on the third post-reaction strength data corresponding to the multiple single coal types to obtain the first post-reaction strength prediction data of the coal after coking corresponding to the first coal blending scheme; and finally, based on the first reactivity data and the first reactivity prediction data, it determines... The first linear relationship value is determined; based on the first post-reaction intensity data and the first post-reaction intensity prediction data, the second linear relationship value is determined; based on the first linear relationship value, the proportion of a single type of coal and the third reactivity data corresponding to a single type of coal, the first reactivity prediction model is determined; based on the second linear relationship value, the proportion of a single type of coal and the third reactivity data corresponding to a single type of coal, the first post-reaction intensity prediction model is determined; a difference comparison analysis is performed on the first reactivity data and the second reactivity data to obtain the third linear relationship value; a difference comparison analysis is performed on the first post-reaction intensity data and the second post-reaction intensity data to obtain the fourth linear relationship value; a difference comparison analysis is performed on the first post-reaction intensity data and the second post-reaction intensity data to obtain the fourth linear relationship value; based on the first reactivity prediction model and the third linear relationship value, the second reactivity prediction model is determined. The dry quenching coke quality prediction model established by this application has high prediction accuracy and good generalization ability. It can quickly obtain dry quenching coke quality data under different coal blending schemes and different coke oven production load conditions, filling the gap in the prediction of coke quality in the coking industry. It has important guiding significance for enterprises to predict the application performance of coke in the furnace, optimize furnace production processes, and improve product quality.

[0109] Optionally, such as Figure 3 As shown, a second aspect embodiment of the present invention also provides an electronic device 300, including a processor 310 and a memory 320. The memory 320 stores a program or instructions that can run on the processor 310. When the program or instructions are executed by the processor 310, they implement the various processes of the above-described method embodiment for establishing a dry quenched coke quality prediction model and achieve the same technical effect. To avoid repetition, they will not be described again here.

[0110] It should be noted that the electronic devices in the embodiments of the present invention include: servers, terminals, or other devices besides terminals.

[0111] The above electronic device structure does not constitute a limitation on the electronic device. An electronic device may include more or fewer components than illustrated, or combine certain components, or arrange them differently. For example, an input unit may include a Graphics Processing Unit (GPU) and a microphone, and a display unit may use a liquid crystal display (LCD), organic light-emitting diode (OLED), or other similar display panels. User input units include at least one of a touch panel and other input devices. A touch panel is also called a touchscreen. Other input devices may include, but are not limited to, physical keyboards, function keys (such as volume control buttons, power buttons, etc.), trackballs, mice, and joysticks, which will not be elaborated further here.

[0112] Memory can be used to store software programs and various data. Memory can primarily consist of a first storage area for storing programs or instructions and a second storage area for storing data. The first storage area can store the operating system, application programs or instructions required for at least one function (such as sound playback, image playback, etc.). Furthermore, memory can include volatile memory or non-volatile memory, or both. Non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory can be random access memory (RAM), static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous linked dynamic random access memory (Synchlink DRAM, SLDRAM), and direct memory bus RAM (DRRAM).

[0113] The processor may include one or more processing units; optionally, the processor integrates an application processor and a modem processor, wherein the application processor mainly handles operations related to the operating system, user interface, and applications, while the modem processor mainly handles wireless communication signals, such as a baseband processor. It is understood that the aforementioned modem processor may also not be integrated into the processor.

[0114] This invention also provides a readable storage medium storing a program or instructions. When the program or instructions are executed by a processor, they implement the various processes of the above-described method embodiment for establishing a dry-quenched coke quality prediction model, and achieve the same technical effect. To avoid repetition, they will not be described again here.

[0115] The processor is the processor in the electronic device described in the above embodiments. The readable storage medium includes computer-readable storage media such as ROM, RAM, magnetic disk, or optical disk. It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover a 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 limitations, 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 that element. Furthermore, it should be noted that the scope of the methods and apparatus in the embodiments of the present invention is not limited to performing functions in the order shown or discussed, but may also include performing functions substantially simultaneously or in the reverse order, for example, the described methods may be performed in an order different from that described. Additionally, features described with reference to certain examples may be combined in other examples.

[0116] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, can be embodied in the form of a computer software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods of the various embodiments of the present invention.

[0117] In the description of embodiments of the present invention, the terms "first," "second," "third," and "fourth" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first," "second," "third," or "fourth" may explicitly or implicitly include one or more of that feature. In the description of the present invention, unless otherwise stated, "a plurality of" means two or more.

[0118] In the description of embodiments of the present invention, specific features, structures, materials or characteristics may be combined in any suitable manner in one or more embodiments or examples.

[0119] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A method for establishing a dry-quenched coke quality prediction model, characterized in that, include: The process involves obtaining a first coal blending scheme, first reactivity data, second reactivity data, first post-reaction strength data, and second post-reaction strength data of the coal corresponding to the first coal blending scheme after coking. The first coal blending scheme includes multiple single types of coal. The first reactivity data and the first post-reaction strength data are obtained through a 40Kg load small coke oven test, and the second reactivity data and the second post-reaction strength data are obtained through a large coke oven dry quenching process production test. The reactivity and post-reaction strength of each of the multiple single coal types were tested after coking using the 40Kg load small coke oven, and the third reactivity data and third post-reaction strength data corresponding to each single coal type were obtained. The third reactivity data corresponding to multiple types of coal are weighted and calculated to obtain the first reactivity prediction data of the coal after coking corresponding to the first coal blending scheme; Weighted calculations are performed on the third post-reaction strength data corresponding to multiple single coal types to obtain the predicted first post-reaction strength data of the coal after coking, which corresponds to the first coal blending scheme. Based on the first reactivity data and the first reactivity prediction data, determine the value of the first linear relationship; The second linear relationship value is determined based on the first post-reaction intensity data and the first post-reaction intensity prediction data; A first coke quality prediction model is established based on the first linear relationship value, the second linear relationship value, the proportion of the single type of coal, and the third reactivity data corresponding to the single type of coal. A comparative analysis of the differences between the first and second reactivity data was performed to obtain the third linear relationship value; A comparative analysis of the differences between the intensity data after the first reaction and the intensity data after the second reaction was performed to obtain the fourth linear relationship value; Based on the first coke quality prediction model, the third linear relationship value, and the fourth linear relationship value, a dry-quenched coke quality prediction model is determined.

2. The method for establishing a dry-quenched coke quality prediction model according to claim 1, characterized in that, The first coke quality prediction model includes a first reactivity prediction model and a first post-reaction intensity prediction model for coke after coking. The step of establishing the first coke quality prediction model based on the first linear relationship values ​​and the second linear relationship values ​​includes: The first reactivity prediction model is determined based on the first linear relationship value, the proportion of each type of coal added, and the third reactivity data corresponding to each type of coal. Based on the second linear relationship value, the proportion of the single type of coal added, and the third reactivity data corresponding to the single type of coal, the first post-reaction intensity prediction model is determined.

3. The method for establishing a dry-quenched coke quality prediction model according to claim 2, characterized in that, The calculation formula for the first reactivity prediction model is as follows: CRI1=ΣW i ×CRIi / ΣW i +A, Wherein, CRI1 represents the second reactivity prediction data obtained after conducting a coal-to-coke experiment on a certain coal blending scheme using the 40kg load small coke oven, A represents the first linear relationship value, and W... i CRIi represents the proportion of the single type of coal added, and CRIi represents the third reactivity data corresponding to the single type of coal.

4. The method for establishing a dry-quenched coke quality prediction model according to claim 2, characterized in that, The calculation formula for the first post-reaction intensity prediction model is as follows: CSR1=ΣW i ×CSRi / ΣW i +B, Among them, W i The formula represents the proportion of the single type of coal used in the blending process. CSR1 represents the second post-reaction strength prediction data obtained after conducting a coal coking test on a certain coal blending scheme using the 40kg load small coke oven. B represents the second linear relationship value. CSRi represents the third post-reaction strength data corresponding to the single type of coal.

5. The method for establishing a dry-quenched coke quality prediction model according to claim 2, characterized in that, The dry-quenched coke quality prediction model includes a second reactivity prediction model and a second post-reaction intensity prediction model. The step of determining the dry-quenched coke quality prediction model based on the first coke quality prediction model, the third linear relationship value, and the fourth linear relationship value includes: The second reactivity prediction model is determined based on the first reactivity prediction model and the third linear relationship value. The second post-reaction intensity prediction model is determined based on the first post-reaction intensity prediction model and the fourth linear relationship value.

6. The method for establishing a dry-quenched coke quality prediction model according to claim 5, characterized in that, The calculation formula for the second reactivity prediction model is as follows: CRI2=CRI1+C h , Wherein, CRI2 represents the third reactivity prediction data obtained after conducting a dry quenching process production test on a certain coal blending scheme using the large coke oven, C h The value of the third linear relationship is represented by CRI1, which represents the second reactivity prediction data obtained after conducting a coal coking test on a certain coal blending scheme using the 40kg load small coke oven.

7. The method for establishing a dry-quenched coke quality prediction model according to claim 5, characterized in that, The calculation formula for the second reactivity prediction model is as follows: CSR2=CSR1+D h , Wherein, CSR2 represents the third post-reaction intensity prediction data obtained after conducting a dry quenching process production test on a certain coal blending scheme using the large coke oven, and D h The value of the fourth linear relationship is represented by CSR1, which represents the second post-reaction strength prediction data obtained after conducting a coal coking test on a certain coal blending scheme using the 40kg load small coke oven.

8. An electronic device, characterized in that, include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements: a method for establishing a dry-quenched coke quality prediction model as described in any one of claims 1 to 7.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions for: a method for establishing a dry-quenched coke quality prediction model as described in any one of claims 1 to 7.

Images