Coal blending control method, device, equipment and medium
By solving the classification and optimization model of single coal, the problem of relying on manual experience in coking and coal mixing of coke ovens is solved, and the stability and efficiency of coke quality are improved.
Patent Information
- Application Number
- CN202510566223.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-04-30
- Publication Date
- 2025-08-15
AI Technical Summary
In the prior art, the coking coal mixing method of coke oven relies on manual experience, which makes it difficult to control the quality stability of coke, low working efficiency, and is susceptible to external factors.
By classifying single coals according to the degree of coalification and process performance indicators, constraining conditions and optimization goals are constructed, and coke quality index prediction model and mixed genetic algorithm are used to optimize the solution to obtain the optimal coal mixing ratio scheme.
The optimal proportioning scheme is achieved under the satisfaction of various constraints, the stability of coke quality and scientific operation are improved, and the working efficiency of coking coal mixing is improved.
Smart Images
Figure CN120494613A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of testing technology, and in particular to a coal blending control method, device, equipment and medium. Background Art
[0002] Coke quality is crucial to coking production. Due to production constraints, the blending ratio of individual coal types is often determined through simple speculation and empirical experience. However, given the long coke oven production cycle, this coal blending method is inefficient and susceptible to external influences, making it difficult to accurately control the blending ratio. This poses a significant challenge for coking coal blenders. Therefore, calculating the relationship between coke quality and the blending ratio of individual coal types has long been a concern for coking coal blenders.
[0003] In current production, after testing is completed, the testing laboratory automatically or manually transmits the analyzed components to coking technicians. However, for coking coal blending technicians, it is difficult to arrive at the optimal blending ratio through simple speculation and manual experience. Therefore, this current method based on manual experience is unable to maintain the stability of the quality of blended coal and coke. Summary of the Invention
[0004] In view of the above-mentioned shortcomings of the prior art, the present application provides a coal blending control method, device, equipment and medium to solve at least one defect in the prior art.
[0005] To achieve the above objectives and other objectives, the present application provides a coal blending control method, which includes:
[0006] Classify a single type of coal according to the coalification degree and / or process performance index to obtain multiple coal categories;
[0007] Constructing constraints and optimization objectives, wherein the constraints are upper and lower limits of the proportion of each coal type, and the target blend coal quality index range and the target coke quality index range. The optimization objectives include minimizing cost and optimizing coke quality.
[0008] The coal blending optimization model is solved to obtain a blending scheme that meets the constraints and the optimization objectives; the coal blending optimization model represents the correlation between the coke quality index prediction model and the coal blending scheme, and the blending scheme includes at least the proportion of each type of coal. The coke quality index prediction model is obtained by training the initial coke quality index prediction network using historical coking coal blending parameters as training samples.
[0009] In one embodiment of the present invention, the coke quality index prediction model includes at least one, and each coke quality index prediction model outputs at least one coke quality index based on input data.
[0010] In one embodiment of the present invention, the coke quality index includes at least one of the following: coke quality ash content, sulfur content, volatile matter, post-reaction strength, and reactivity index.
[0011] In one embodiment of the present invention, the training method of the coke quality index prediction model includes:
[0012] Obtain training samples; the training samples include: material inspection and testing data, material price data, matching data of material inventory data, temperature data, and coking time data;
[0013] An initial coke quality index prediction network is trained based on the training samples to obtain a coke quality index prediction model.
[0014] In one embodiment of the present invention, the types of coal include main coking coal, gas coal, fat coal, 1 / 3 coking coal, lean coal and coke dust.
[0015] In one embodiment of the present invention, solving the coal blending optimization model based on the coke quality index prediction model includes:
[0016] Relaxing some constraints of the coal blending optimization model to construct a relaxation problem;
[0017] Solve the relaxation problem based on mathematical programming to obtain an initial coal blending plan;
[0018] The initial coal blending scheme is used as an initial population, and the initial population is optimized by a hybrid genetic algorithm based on constraint conditions and optimization objectives to obtain a target coal blending scheme.
[0019] In one embodiment of the present invention, before relaxing the constraints of the coal blending optimization model, the method further includes: black-boxing the coke quality prediction model.
[0020] To achieve the above and other purposes, the present application provides a coal blending control device, which includes:
[0021] A classification module is used to classify a single type of coal according to the coalification degree and / or process performance index to obtain multiple coal types;
[0022] A construction module is used to construct constraints and optimization objectives, wherein the constraints are upper and lower limits of the proportion of each coal type, and the target blend coal quality index range and the target coke quality index range. The optimization objectives include the lowest cost and the best coke quality.
[0023] A solution module is used to solve the coal blending optimization model to obtain a blending scheme that meets the constraints and the optimization objectives; the coal blending optimization model represents the correlation between the coke quality index prediction model and the coal blending scheme, the blending scheme includes at least the proportion of each type of coal, and the coke quality index prediction model is obtained by training the initial coke quality index prediction network using historical coking coal blending parameters as training samples.
[0024] To achieve the above-mentioned and other related purposes, the present application provides a coal blending control device, comprising:
[0025] one or more processors; and
[0026] The memory is used to store one or more programs. When the one or more programs are executed by the one or more processors, the memory implements the coal blending control method.
[0027] To achieve the above objectives and other related objectives, the present application provides one or more machine-readable media having instructions stored thereon, which, when executed by one or more processors, enable the processors to execute the coal blending control method.
[0028] Beneficial effects of this application:
[0029] A coal blending control method of the present application includes: classifying a single type of coal according to the degree of coalification and / or process performance indicators to obtain multiple coal categories; constructing constraints and optimization goals, wherein the constraints are the upper and lower limits of the proportion of each coal category and the indicator range of the target blended coal quality and the indicator range of the target coke quality, and the optimization goals include lowest cost and best coke quality; solving a coal blending optimization model to obtain a blending scheme that meets the constraints and the optimization goals; the coal blending optimization model represents the correlation between the coke quality index prediction model and the coal blending scheme, and the blending scheme includes at least the proportion of each type of coal, and the coke quality index prediction model is obtained by training the initial coke quality index prediction network with historical coking coal blending parameters as training samples; the present invention uses mathematical programming and a hybrid genetic algorithm to optimize and solve the coal blending optimization model to obtain the optimal coal blending ratio scheme; it achieves the output of three optimal blending ratio schemes within the constraints, so as to facilitate making more scientific and reasonable operational response decisions.
[0030] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS
[0031] The accompanying drawings are incorporated into and constitute a part of the specification, illustrating embodiments consistent with the present application and, together with the specification, serving to explain the principles of the present application. It is obvious that the drawings described below are merely some embodiments of the present application, and a person of ordinary skill in the art can derive other drawings based on these drawings without inventive effort. In the drawings:
[0032] Figure 1 This is a flow chart of a coal blending control method according to an embodiment of the present application;
[0033] Figure 2 This is a flow chart for solving a coal blending optimization model according to an embodiment of the present application;
[0034] Figure 3 This is a principle block diagram of a coal blending control device according to an embodiment of the present application;
[0035] Figure 4 A schematic diagram of the structure of a computer system suitable for implementing the memory of an embodiment of the present application is shown. DETAILED DESCRIPTION
[0036] The following describes the embodiments of the present application through specific examples. Those skilled in the art can easily understand the other advantages and effects of the present application from the content disclosed in this specification. The present application can also be implemented or applied through other different specific embodiments. The details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present application. It should be noted that the following embodiments and features in the embodiments can be combined with each other unless they conflict.
[0037] It should be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present application. Therefore, the illustrations only show components related to the present application and are not drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component can be changed at will, and the component layout type may also be more complicated.
[0038] Although the terms "first," "second," "A," and "B," etc. may be used herein to describe various elements, these elements should not be limited by these terms and are merely used to distinguish one element from another. For example, a first element may be referred to as a second element, and similarly, a second element may be referred to as a first element without departing from the scope of the technology described below. The term "and / or" includes a combination of a plurality of related items or any of the plurality of related items.
[0039] As used herein, unless the context indicates otherwise, the singular form is intended to include the plural form, and it will be understood that the term "comprising" means the presence of stated features, quantities, steps, operations, elements, or combinations thereof, but does not preclude the presence or addition of one or more other features, quantities, steps, operations, elements, components, or combinations thereof.
[0040] Before describing the components in detail, it is intended to clarify that the components in this specification are divided only by the primary function of each component. That is, two or more components described below may be combined into one component, or may be divided into two or more components based on more detailed functions. In addition to the primary function of the component, each component described below may also perform some or all of the functions of other components, and some of the primary functions of each component may be exclusively performed by other components.
[0041] The embodiments of the present application respectively provide a coal blending control method, a coal blending control device, a coal blending control equipment, and a computer-readable storage medium, and these embodiments will be described in detail below.
[0042] See also Figure 1 , Figure 1 This is a flow chart of a coal blending control method according to an embodiment of the present application. Figure 1 As shown, the coal blending control method includes at least steps S110 to S140:
[0043] Step S110, classifying a single type of coal according to the coalification degree and / or process performance index to obtain multiple coal types;
[0044] The degree of coalification (coal rank) reflects the geological maturity of coal and directly affects its combustion, coking, and other properties. Process performance indicators include volatile matter (Vdaf%), cohesiveness (G), and maximum thickness of the colloidal layer (Y). Individual coal types can be classified based on their degree of coalification or process performance indicators.
[0045]
[0046]
[0047] Step S120, constructing constraints and optimization objectives, where the constraints are the upper and lower limits of the proportion of each coal type, the target blend coal quality index range, and the target coke quality index range, and the optimization objectives include target cost and target coke quality;
[0048] Constraints include upper and lower limits for each type of coal, specifically upper and lower limits for prime coking coal, gas coal, fat coal, 1 / 3 coking coal, lean coal, and coke dust. Constraints also include upper and lower limits for each type of coal within each category.
[0049] The index range of the target coal quality, that is, the upper and lower constraints of the target coal quality;
[0050] The index range of the target coke quality, that is, the upper limit constraint and the lower limit constraint of the target coke quality.
[0051] The target cost is the lowest cost, and the target coke quality is the best coke quality.
[0052] Step S130, solve the coal blending optimization model to obtain a blending scheme that meets the constraints and optimization objectives; the coal blending optimization model represents the correlation between the coke quality index prediction model and the coal blending scheme, and the blending scheme includes at least the proportion of each type of coal. The coke quality index prediction model is obtained by training the initial coke quality index prediction network using historical coking coal blending parameters as training samples.
[0053] In one embodiment, the coke quality index prediction model includes at least one, and each coke quality index prediction model outputs at least one coke quality index based on input data.
[0054] In one embodiment, the coke quality index includes at least one of the following: coke quality ash content, sulfur content, volatile matter, post-reaction strength, and reactivity index.
[0055] Ash, the incombustible residue remaining after complete combustion of coke; Sulfur, the sulfur content in coke, expressed as mass percentage; Volatile Matter (VM), the amount of combustible gas released by coke at high temperature, reflecting the maturity of coke; Coke Strength after Reaction (CSR), the crushing strength of coke after reaction with CO; Coke Reactivity Index (CRI), the reactivity of coke with CO2 at high temperature.
[0056] It should be noted that each coke quality indicator can be predicted using a coke quality indicator prediction model. For example, ash content is predicted using an ash prediction model, sulfur content is predicted using a sulfur prediction model, volatile matter is predicted using a volatile matter prediction model, post-reaction strength is predicted using a strength prediction model, and reactivity index is predicted using a reactivity index prediction model. In other embodiments, a single prediction model can also predict two or more coke quality indicators. For example, one prediction model can simultaneously output both ash and sulfur content, while another prediction model can simultaneously output volatile matter, ash, and sulfur content.
[0057] In one embodiment, a method for training a coke quality index prediction model includes: obtaining training samples; the training samples include: material inspection and testing data, material price data, matching data of material inventory data, temperature data, and coking time data; and training an initial coke quality index prediction network based on the training samples to obtain a coke quality index prediction model.
[0058] It should be noted that material inspection and testing data, material price data, and material inventory data are not in the same system. When performing data association, communication is established with external systems (such as L1, L2, etc.) or data sources (such as real-time databases PI, Historian, etc.), and material inspection and testing data, material price data, and material inventory data are unified into the same system. Then, based on the material name and set time, the material inspection and testing data, material price data, and material inventory data are matched and then saved in the database. Specifically, the material inspection and testing data includes the inspection and sampling time, the analysis and testing time, the test number, the material name, the analysis component name, and the analysis component value, and the material inventory data includes the material code, material name, material price, material inventory, and attribution time. After matching the material inspection and testing data, material price data, and material inventory data based on the material name and set time, matching data is obtained, including: material name, material price, material inventory, sample sampling time, analysis and testing time, analysis component name, and analysis component value.
[0059] In one embodiment, the material price data is the material price of a single type of coal, which is a moving weighted average price calculated based on time.
[0060] In one embodiment, the material inventory data is the latest inventory data obtained based on the usage time, such as historical material inventory data within a week.
[0061] In one embodiment, the material inspection and testing data includes inspection and testing data of single type coal, blended coal, and coke.
[0062] It is understood that the specific implementation process of obtaining a coke quality index prediction model based on training samples is as follows: obtaining training samples, the training samples include material inspection and testing data, material price data, material inventory data, temperature data, and coking time data, using the material inspection and testing data, material price data, material inventory data, temperature data, and coking time data as model input parameters, and the coke quality index as the model output parameter; inputting the model input parameters into the initial neural network model to obtain the coke quality index; calculating the cross entropy between the coke quality index output by the neural network model and the actual coke quality index to obtain the loss function of the neural network model; if the loss function of the neural network model converges, then determining that the neural network model training is complete; if the loss function of the neural network model does not converge, then adjusting the parameters of the neural network model and returning to the step of inputting the model input parameters into the neural network model to obtain the coke quality index until the loss function of the neural network model converges. Using the test samples in the training samples to test the trained neural network model, when the test results meet the preset conditions, the neural network model is determined to be a trained coke quality index prediction model.
[0063] See also Figure 2 , Figure 2 This is a flow chart for solving the coal blending model according to an embodiment of the present application.
[0064] exist Figure 2 In the process, based on the coke quality index prediction model, the coal blending optimization model is solved, including:
[0065] Step S210, relaxing some constraints of the coal blending optimization model to construct a relaxation problem;
[0066] Step S220, solving the relaxation problem based on mathematical programming to obtain an initial coal blending plan;
[0067] Step S230 , using the initial coal blending scheme as the initial population, optimizing the initial population through a hybrid genetic algorithm based on the constraint conditions and the optimization target, and obtaining a target coal blending scheme.
[0068] Specifically, a hybrid genetic algorithm is used to perform selection, crossover, and mutation operations to find a better solution that meets the conditions.
[0069] Specifically, the target coal blending plan includes: the proportion of a single type of coal, the predicted value of coke quality, and the predicted value of blended coal quality.
[0070] In one embodiment, the databases to which this application pertains include but are not limited to ORACLE, DB2, SQL Server, Sybase, Informix, MySQL, VF, and Access.
[0071] In one embodiment, before relaxing the constraints on the coal blending optimization model, the method further includes: black-boxing the coke quality prediction model.
[0072] The present invention establishes communication with inspection and testing laboratories and other external systems or data sources, monitors the inspection and testing components, cost price, and inventory data of each type of coal online, and uses historical coking production data to calculate a reasonable single-type coal blending ratio and corresponding coke quality data with the expected proportions of major and minor coal types, coke quality, and blending coal quality as constraints, so as to facilitate coking coal blending technicians to make more scientific and reasonable coking coal blending plans.
[0073] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.
[0074] Figure 3 FIG. 1 is a block diagram of a coal blending control device according to an embodiment of the present application. Figure 3 As shown, a coal blending control device includes:
[0075] A classification module 310 is used to classify a single type of coal according to the coalification degree and / or process performance index to obtain multiple coal types;
[0076] A construction module 320 is used to construct constraints and optimization objectives. The constraints are the upper and lower limits of the proportion of each coal type, the target blend coal quality index range, and the target coke quality index range. The optimization objectives include minimizing cost and optimizing coke quality.
[0077] The solution module 330 is used to solve the coal blending optimization model to obtain a blending scheme that meets the constraints and optimization objectives; the coal blending optimization model represents the correlation between the coke quality index prediction model and the coal blending scheme, and the blending scheme includes at least the proportion of each type of coal. The coke quality index prediction model is obtained by training the initial coke quality index prediction network using historical coking coal blending parameters as training samples.
[0078] It should be noted that the coal blending control device provided in the above embodiment and the coal blending control method provided in the above embodiment are based on the same concept. The specific manner in which each module and unit performs operations has been described in detail in the method embodiment and will not be repeated here. In actual applications, the coal blending control device provided in the above embodiment can, as needed, allocate the above functions to different functional modules, that is, divide the internal structure of the device into different functional modules to complete all or part of the functions described above, and this is not limited here.
[0079] An embodiment of the present application also provides a device, comprising: one or more processors; and a memory for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the memory implements the coal blending control method in the above embodiment.
[0080] The embodiments of the present application further provide one or more machine-readable media having instructions stored thereon, which, when executed by one or more processors, enable the processors to execute the coal blending control method in the above embodiments.
[0081] Figure 4 FIG1 shows a schematic diagram of a computer system structure suitable for implementing a memory according to an embodiment of the present invention. It should be noted that Figure 4 The computer system of the memory shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.
[0082] like Figure 4 As shown, computer system 400 includes a central processing unit (CPU) 401, which can perform various appropriate actions and processes according to programs stored in read-only memory (ROM) 402 or programs loaded from a storage portion into random access memory (RAM) 403, such as executing the methods in the above embodiments. Various programs and data required for system operation are also stored in RAM. CPU 401, ROM 402, and RAM 403 are connected to each other via bus 404. Input / output (I / O) interface 405 is also connected to bus 404.
[0083] The following components are connected to the I / O interface 405: an input section 406 including a keyboard, a mouse, and the like; an output section 407 including devices such as a cathode ray tube (CRT), a liquid crystal display (LCD), and a speaker; a storage section 408 including a hard disk and the like; and a communication section 409 including a network interface card such as a LAN (Local Area Network) card or a modem. The communication section 409 performs communication processing via a network such as the Internet. A drive 410 is also connected to the I / O interface 405 as needed. Removable media 411, such as a magnetic disk, an optical disk, a magneto-optical disk, or a semiconductor memory, is installed in the drive 410 as needed, so that computer programs read therefrom can be installed into the storage section 408 as needed.
[0084] In particular, according to an embodiment of the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present invention includes a computer program product comprising a computer program carried on a computer-readable medium, the computer program including a computer program for executing the suspension hard point determination method described above. In such an embodiment, the computer program can be downloaded and installed from a network via a communication component and / or installed from removable media 411. When executed by the central processing unit (CPU) 401, the computer program performs the various functions defined in the system of the present invention.
[0085] It should be noted that the computer-readable medium shown in the embodiments of the present invention may be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. The computer-readable storage medium may, for example, be an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or component, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, a random access memory (RAM) 403, a read-only memory (ROM) 402, an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present invention, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries a computer-readable computer program. Such a propagated data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination thereof. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. A computer program embodied on a computer-readable medium may be transmitted using any suitable medium, including but not limited to wireless, wired, or any suitable combination thereof.
[0086] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions and operations of the systems, methods and computer program products according to various embodiments of the present invention. Each box in the flowchart or block diagram can represent a module, program segment, or part of the code, and the above-mentioned module, program segment, or part of the code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the boxes can also occur in an order different from that marked in the accompanying drawings. For example, two boxes shown in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or can be implemented using a combination of dedicated hardware and computer instructions.
[0087] The units involved in the embodiments of the present invention may be implemented in software or hardware, and the units described may also be provided in a processor. In some cases, the names of these units do not limit the units themselves.
[0088] Another aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon. When executed by a computer processor, the computer program causes the computer to perform the aforementioned coal blending control method. The computer-readable storage medium may be included in the memory described in the above embodiments, or may exist independently and not be incorporated into the memory.
[0089] Another aspect of the present invention provides a computer program product or computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the coal blending control method provided in each of the above embodiments.
[0090] The above embodiments are merely illustrative of the principles and effects of this application and are not intended to limit this application. Anyone skilled in the art may modify or alter the above embodiments without departing from the spirit and scope of this application. Therefore, any equivalent modifications or alterations accomplished by a person of ordinary skill in the art without departing from the spirit and technical concepts disclosed in this application shall be covered by the claims of this application.
Claims
1. A coal blending control method, characterized in that: The coal blending control method comprises: Classify a single type of coal according to the coalification degree and / or process performance index to obtain multiple coal categories; Constructing constraints and optimization objectives, wherein the constraints are upper and lower limits of the proportion of each coal type, and the index range of the target blend coal quality and the index range of the target coke quality, and the optimization objectives include target cost and target coke quality; The coal blending optimization model is solved to obtain a blending scheme that meets the constraints and the optimization objectives; the coal blending optimization model represents the correlation between the coke quality index prediction model and the coal blending scheme, and the blending scheme includes at least the proportion of each type of coal. The coke quality index prediction model is obtained by training the initial coke quality index prediction network using historical coking coal blending parameters as training samples.
2. The coal blending control method according to claim 1, characterized in that: The coke quality index prediction model includes at least one, and each coke quality index prediction model outputs at least one coke quality index based on input data.
3. The coal blending control method according to claim 2, characterized in that: The coke quality index includes at least one of the following: coke quality ash content, sulfur content, volatile matter, post-reaction strength, and reactivity index.
4. The coal blending control method according to claim 2, characterized in that: The training method of the coke quality index prediction model comprises: Obtain training samples; the training samples include: material inspection and testing data, material price data, matching data of material inventory data, temperature data, and coking time data; An initial coke quality index prediction network is trained based on the training samples to obtain a coke quality index prediction model.
5. The coal blending control method according to claim 1, characterized in that: The coal categories include prime coking coal, gas coal, fat coal, 1 / 3 coking coal, lean coal and coke dust.
6. The coal blending control method according to claim 1, characterized in that: The coal blending optimization model is solved based on the coke quality index prediction model, including: Relaxing some constraints of the coal blending optimization model to construct a relaxation problem; Solve the relaxation problem based on mathematical programming to obtain an initial coal blending plan; The initial coal blending scheme is used as an initial population, and the initial population is optimized by a hybrid genetic algorithm based on constraint conditions and optimization objectives to obtain a target coal blending scheme.
7. The coal blending control method according to claim 6, characterized in that: Before relaxing the constraints on the coal blending optimization model, the method further includes: black-boxing the coke quality prediction model.
8. A coal blending control device, characterized in that: The coal blending control device comprises: A classification module is used to classify a single type of coal according to the coalification degree and / or process performance index to obtain multiple coal types; A construction module is used to construct constraint conditions and optimization objectives, wherein the constraint conditions are upper and lower limits of the proportion of each coal type, and the index range of the target blend coal quality and the index range of the target coke quality. The optimization objectives include target cost and target coke quality. A solution module is used to solve the coal blending optimization model to obtain a blending scheme that meets the constraints and the optimization objectives; the coal blending optimization model represents the correlation between the coke quality index prediction model and the coal blending scheme, the blending scheme includes at least the proportion of each type of coal, and the coke quality index prediction model is obtained by training the initial coke quality index prediction network using historical coking coal blending parameters as training samples.
9. A coal blending control device, characterized in that: include: one or more processors; and A memory is used to store one or more programs, and when the one or more programs are executed by the one or more processors, the memory implements the coal blending control method according to any one of claims 1 to 7.
10. A machine-readable medium, characterized in that Instructions are stored thereon, which, when executed by one or more processors, enable the processors to execute the coal blending control method according to any one of claims 1 to 7.