Coal blending structure optimization method and apparatus, and device and storage medium

Abstract

A coal blending structure optimization method and apparatus, and an electronic device and a computer storage medium. The method comprises: acquiring an initial coal blending structure, wherein the initial coal blending structure comprises mixing-ratio information of initial coals; and on the basis of the initial coal blending structure, constructing an optimization objective for coal blending cost minimization, and performing an optimization search by taking the coal blending structure as an unknown quantity, so as to obtain a target coal blending structure. Compared with a mode of manually determining a coal blending structure, the method improves the efficiency of determining a coal blending structure; in addition, since the optimization search is performed on the basis of the initial coal blending structure and by means of constructing the optimization objective for coal blending cost minimization, the coal blending cost corresponding to the finally obtained target coal blending structure can be lower. In summary, the provided coal blending structure optimization method can improve the efficiency of determining a coal blending structure, and can reduce the economic cost of coal blending.

Description

Coal blending structure optimization method, device, equipment and storage medium Technical Field

[0001] The embodiments of the present application relate to the field of industrial production technology, and in particular to a method, device, electronic device, and computer storage medium for optimizing coal blending structure. Background Art

[0002] Coal blending is a widely used technique in coking plants to optimize coke quality. The process involves mixing different types of coal with varying qualities and prices in a specific proportion (the blending structure) to create a blended coal. This blended coal is then processed through the coking process to produce coke that meets quality requirements.

[0003] At present, the specific coal blending structure is mainly determined manually, specifically: the mixing ratio between coals of different quality and price is mainly set manually.

[0004] The above method not only has high labor costs, but also the economic costs of the coal blending structure usually determined are also high.

[0005] Summary of the Invention

[0006] In view of this, one of the technical problems solved by the embodiments of the present application is to provide a coal blending structure optimization method, device, electronic equipment and computer storage medium to improve the efficiency of determining the coal blending structure and reduce the economic cost of coal blending.

[0007] In a first aspect, an embodiment of the present application provides a method for optimizing coal blending structure, the method comprising:

[0008] Acquire an initial coal blending structure; the initial coal blending structure includes information on the mixing ratios of the initial coals;

[0009] Based on the initial coal blending structure, an optimization objective is constructed with the coal blending cost minimized, and an optimization search is performed with the coal blending structure as an unknown quantity to obtain a target coal blending structure.

[0010] In a second aspect, an embodiment of the present application provides a coal blending structure optimization device, comprising:

[0011] An initial coal blending structure acquisition module is used to acquire an initial coal blending structure; the initial coal blending structure includes information on the mixing ratios between the initial coals;

[0012] The optimization module is used to construct an optimization target based on the initial coal blending structure with the coal blending cost minimized, and to perform optimization search with the coal blending structure as an unknown quantity to obtain a target coal blending structure.

[0013] In a third aspect, an embodiment of the present application provides an electronic device comprising a processor, a communication interface, a memory and a communication bus, wherein the processor, the memory and the communication interface communicate with each other through the communication bus; the memory is used to store computer programs, and the processor is used to execute the programs stored in the memory to implement the coal blending structure optimization method described in the first aspect.

[0014] In a fourth aspect, an embodiment of the present application provides a computer storage medium having a computer program stored thereon, which, when executed by a processor, implements the coal blending structure optimization method as described in the first aspect or any one of the embodiments of the first aspect.

[0015] The embodiments of the present application provide a method, device, electronic device and computer storage medium for optimizing coal blending structure. After obtaining the initial coal blending structure, the optimization target is constructed based on the initial coal blending structure with the coal blending cost minimized, and the target coal blending structure that meets the requirements is automatically searched using an optimization search algorithm. Compared with the method of manually determining the coal blending structure, the automatic optimization search method provided by the embodiments of the present application improves the efficiency of determining the coal blending structure. In addition, since the optimization search is performed based on the initial coal blending structure and with the optimization target constructed with the coal blending cost minimized in the embodiments of the present application, the coal blending cost corresponding to the target coal blending structure finally obtained can be lower. In summary, the coal blending structure optimization method provided by the embodiments of the present application can improve the efficiency of determining the coal blending structure and reduce the economic cost of coal blending. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Hereinafter, some specific embodiments of the present application will be described in detail in an exemplary and non-limiting manner with reference to the accompanying drawings. The same reference numerals in the accompanying drawings indicate the same or similar components or parts. It should be understood by those skilled in the art that these drawings are not necessarily drawn to scale. In the accompanying drawings:

[0017] Figure 1 is a schematic diagram of the coal blending process;

[0018] FIG2 is a schematic flow chart of a method for optimizing coal blending structure provided in an embodiment of the present application;

[0019] FIG3 is a schematic diagram of the training process of the result prediction model provided in an embodiment of the present application;

[0020] FIG4 is a schematic diagram of the coal blending structure optimization process provided in an embodiment of the present application;

[0021] FIG5 is a schematic diagram of a display page for a target coal blending structure;

[0022] FIG6 is a schematic structural diagram of a coal blending structure optimization device provided in an embodiment of the present application.

[0023] List of reference numerals: A: coking coal with high performance; B; coking coal with medium volatility; C: non-stick coal with low performance; D: blending coal; E: coke; 201: obtaining an initial coal blending structure; 202: based on the initial coal blending structure, constructing an optimization target with the coal blending cost minimized, performing optimization search with the coal blending structure as the unknown quantity, and obtaining a target coal blending structure; 301: obtaining historical data; 302: preprocessing and standardizing the above historical data; 303: using the principal component analysis method to screen and normalize the attribute characteristic data of each initial coal obtained based on the fusion of the initial coal attribute information; 304: using the coal blending structure, the blending coal quality attribute information and the corresponding initial coal attribute characteristic data to train a complex quality prediction model, and obtain a trained complex quality prediction model; 305: using the coal blending structure, the coke quality attribute information and the corresponding initial coal attribute characteristic data to train a coke quality prediction model, and obtain a trained coke quality prediction model; 306: Save the name of the attribute feature data of the initial coal input to the complex quality prediction model and the name of the complex quality attribute information output by the complex quality prediction model; save the name of the attribute feature data of the initial coal input to the coke quality prediction model and the name of the coke quality attribute information output by the coke quality prediction model; 307: Save the trained complex quality prediction model and coke quality prediction model; 401: Obtain the inventory data and price data of the initial coal; 402: Preprocess the data obtained in step 401; 403: Determine whether to use a conservative optimization method for optimization search; if so, execute step 404; if not, execute step 406; 404: With the structural difference between the coal blending structure and the initial coal blending structure being less than a preset structural difference threshold as a constraint, and / or, with the result difference between the coal blending result corresponding to the coal blending structure and the initial coal blending result corresponding to the initial coal blending structure being less than a preset result difference threshold as a constraint, with minimizing the coal blending cost as the optimization goal, and with the coal blending structure as the unknown quantity, perform optimization search to obtain the target coal blending structure; 405: Output the target coal blending structure; 406: Generate an initial coal blending structure based on the historical coal blending structure; 407: Update the current coal blending structure when the update conditions of the current coal blending structure are met; 408: Use the complex quality prediction model to predict the complex quality attribute information of the current coal blending structure; 409: Use the coke quality prediction model to predict the coke quality attribute information of the current coal blending structure; 410: Based on minimizing the coal blending cost and the difference between the predicted complex quality attribute information and the preset complex quality attribute information, and / or based on minimizing the difference between the predicted coke quality attribute information and the preset coke quality attribute information, construct an optimization target, perform optimization search with the coal blending structure as the unknown quantity, and obtain a new coal blending structure;411: Based on the preset update probability, the target value corresponding to the new coal blending structure is used to update the target value corresponding to the current coal blending structure. 412: Based on the preset update probability, the current coal blending structure is updated using the new coal blending structure. 413: Determine whether the target value meets the preset convergence condition. If so, execute step 405; if not, return to execute step 407. I: Interface; Ui1: Attribute feature data customization interface; Ui2: Constraint condition setting page; Ui3: Target value setting page; C1, C2, ..., C10: Initial coal; Q1: Quality attribute information of the blend calculated according to the theoretical formula; Q2: Quality attribute information of the coke calculated according to the theoretical formula; Q3: Quality attribute information of the blend predicted by the quality prediction model; Q4: Quality attribute information of the coke predicted by the quality prediction model; 60: Coal blending structure optimization device; 601: Initial coal blending structure acquisition module; 602: Optimization module. DETAILED DESCRIPTION

[0024] In order to enable those skilled in the art to better understand the technical solutions in the embodiments of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field should fall within the scope of protection of the embodiments of the present application.

[0025] It should be noted that the first and second in this application are only for distinguishing names and do not represent the order.

[0026] It should not be understood as indicating or implying relative importance or implicitly indicating the quantity of the indicated technical features, for example, first user, second user, third user, which is only for distinguishing different users.

[0027] The specific implementation of the embodiment of the present application is further explained below in conjunction with the accompanying drawings of the embodiment of the present application.

[0028] The coal blending process primarily involves mixing different types of coal with varying qualities and prices in a specific proportion (coal blending structure) to form a blended coal. This blended coal is then subjected to a coking process to produce coke that meets quality requirements. See Figure 1, which shows a schematic diagram of the coal blending process. In Figure 1, several types of high-performance coking coals A, several types of medium-volatility coking coals B, and several types of low-performance non-caking coals C are mixed in proportions of 50%, 30%, and 20% (the proportions are for illustration only and may vary). After the blending process, a mixture, blended coal D, is obtained. This blended coal D is then subjected to a coking process to produce coke E with the corresponding properties. The blending structure used in the coal blending process shown in Figure 1 is: the three initial coal types, high-performance coking coal A, medium-volatility coking coal B, and low-performance non-caking coal C, are mixed in a ratio of 50%:30%:20%. With regard to FIG1 , the main goal of the solution provided in the embodiment of the present application is to optimize the above-mentioned coal blending structure to ensure that the coal blending cost is reduced as much as possible while ensuring that the final coke meets the preset performance requirements.

[0029] The present application provides a method for optimizing coal blending structure. FIG2 is a flow chart of a method for optimizing coal blending structure provided in the present application. As shown in FIG2 , the method includes the following steps:

[0030] Step 201: Obtain an initial coal blending structure.

[0031] The initial coal blending structure includes the mixing ratio information between the initial coals.

[0032] Specifically, the initial coal blending structure may be an artificially given coal blending structure, or a coal blending structure obtained based on a historical coal blending structure and relatively similar to the historical coal blending structure.

[0033] Step 202 : Based on the initial coal blending structure, an optimization objective is established with the coal blending cost minimized, and an optimization search is performed with the coal blending structure as an unknown quantity to obtain a target coal blending structure.

[0034] Specifically, in the embodiment of the present application, there is no limitation on the specific optimization search algorithm used in step 202, and it can be set according to actual conditions.

[0035] In the embodiment of this application, at least two different optimization schemes may be included:

[0036] The first one is an innovative optimization algorithm: the initial coal blending structure obtained in step 201 is used as the initial solution, the difference between the coal blending result corresponding to the coal blending structure and the preset coal blending result is minimized, and the optimization goal is constructed by minimizing the coal blending cost, and the coal blending structure is used as an unknown quantity for optimization search to obtain the target coal blending structure.

[0037] In the embodiments of the present application, for the above-mentioned innovative optimization algorithm, the type of specific optimization search algorithm used in the optimization search is not limited. Any optimization search algorithm with the initial coal blending structure as the initial search solution can be customized according to actual needs, such as: heuristic search algorithm, etc.

[0038] The second type is a conservative optimization algorithm: the initial coal blending structure obtained in step 201 is used as the main reference, and the target coal blending structure is obtained by fine-tuning the initial coal blending structure. Specifically: the structural difference between the coal blending structure and the initial coal blending structure is constrained to be less than a preset structural difference threshold, and / or the result difference between the coal blending result corresponding to the coal blending structure and the initial coal blending result corresponding to the initial coal blending structure is constrained to be less than a preset result difference threshold, the coal blending cost is minimized as the optimization goal, and the coal blending structure is used as an unknown quantity for optimization search to obtain the target coal blending structure.

[0039] In the embodiment of the present application, for the above-mentioned conservative optimization algorithm, the type of specific optimization search algorithm used in the optimization search is not limited. It is also possible to customize any optimization search algorithm based on actual needs, which takes the initial coal blending structure as the main reference and fine-tunes the target coal blending structure, such as: operations research optimization algorithm, etc.

[0040] Optionally, in one embodiment of the present application, the above two different optimization schemes may be provided, and before executing a specific optimization scheme, the user may first specify a specific optimization search method. After the specific optimization search method is specified (determined), the corresponding optimization algorithm may be executed. The specific process may include:

[0041] Determine the optimization search method; the optimization search method includes conservative optimization method or innovative optimization method;

[0042] If the optimization search method is an innovative optimization method, then based on the initial coal blending structure, the optimization objective is to minimize the coal blending cost, and the optimization search is performed with the coal blending structure as the unknown quantity to obtain the target coal blending structure, which may include:

[0043] Taking the initial coal blending structure as the initial solution, the optimization objective is constructed based on minimizing the difference between the coal blending result corresponding to the coal blending structure and the preset coal blending result, as well as minimizing the coal blending cost. The target coal blending structure is obtained by performing an optimization search with the coal blending structure as the unknown quantity.

[0044] If the optimization search method is conservative, then based on the initial coal blending structure, the optimization objective is to minimize the coal blending cost, and the optimization search is performed with the coal blending structure as the unknown quantity to obtain the target coal blending structure, which may include:

[0045] The constraint is that the structural difference between the coal blending structure and the initial coal blending structure is less than a preset structural difference threshold, and / or the constraint is that the result difference between the coal blending result corresponding to the coal blending structure and the initial coal blending result corresponding to the initial coal blending structure is less than a preset result difference threshold, with minimizing the coal blending cost as the optimization goal and the coal blending structure as the unknown quantity for optimization search to obtain the target coal blending structure.

[0046] Specifically, the embodiments of the present application do not limit the specific process of determining the optimized search method. For example, an optimized search method selection page can be displayed to the user for the user to select one of the optimized search methods from the conservative optimization method or innovative optimization method provided on the above selection page; or one of the two optimized search methods can be selected by detecting the user's preset operation (such as single-click, double-click, long press, etc.) on the physical button / virtual button of the electronic device that executes the method of the embodiment of the present application, and so on.

[0047] When the optimization search method is determined to be an innovative optimization method, the first optimization scheme mentioned above is executed: the innovative optimization algorithm; when the optimization search method is determined to be a conservative optimization method, the second optimization scheme mentioned above is executed: the conservative optimization algorithm.

[0048] This approach provides users with two different optimization solutions, namely, a dual-path strategy. This allows users to customize and select one of the two strategies to optimize coal blending structure based on their specific circumstances, effectively improving user experience.

[0049] In the embodiments of the present application, the coal blending result corresponding to the coal blending structure primarily refers to the quality attribute information of the product obtained after blending according to the coal blending structure. Quality attribute information refers to attribute information that can characterize the quality of the product, such as the composition of the product, the proportion of each component, and other parameter information. Since the coal blending process generates an intermediate product, the complex, and a final product, coke, in the embodiments of the present application, the coal blending result corresponding to the coal blending structure may include the quality attribute information of the complex and / or the quality attribute information of the coke.

[0050] Optionally, for the first optimization solution above:

[0051] Based on minimizing the difference between the coal blending result corresponding to the coal blending structure and the preset coal blending result, and minimizing the coal blending cost, the optimization goal is established. The coal blending structure is used as an unknown quantity for optimization search to obtain the target coal blending structure. Specifically, it may include:

[0052] Calculate the difference between the coal blending result corresponding to the coal blending structure and the preset coal blending result;

[0053] Calculate the coal blending cost corresponding to the coal blending structure;

[0054] The fusion result difference value and coal blending cost are combined to obtain the fusion result;

[0055] The fusion result is used as the objective function, and the coal blending structure is used as the unknown quantity for optimization search to obtain the target coal blending structure.

[0056] Specifically, for the first optimization scheme mentioned above, in the process of coal blending structure optimization search, for the current coal blending structure obtained by the search, the difference value between the coal blending result corresponding to the current coal blending structure and the preset coal blending result, as well as the coal blending cost corresponding to the current coal blending structure can be calculated, and then the two can be fused, so that the fusion result is used as the objective function, and optimization iteration is performed to search for the optimal target coal blending structure.

[0057] Furthermore, constraints can often be set during the optimization search process. These constraints can include both mandatory hard constraints and optional constraints. Examples of hard constraints include: the sum of the initial coal proportions must be 1; the amount of each initial coal used cannot exceed the inventory; the percentage of the coal blending ratio must be an integer; the total number of initial coal types cannot exceed a certain threshold; and so on. Optional constraints include: the range of initial coal proportions; the range of attribute values ​​in the coal blending results; or pre-dividing the initial coal into multiple clusters and the range of proportions within each cluster.

[0058] In an embodiment of the present application, before performing an optimized search, a constraint condition setting page and / or a target value setting page can be displayed to the user, so that the user can customize the specific constraint conditions and target value calculation methods (such as: the calculation of the result difference value, the importance factor of different attribute information of the generated object, etc.). When the user makes customized settings through the above pages, the optimized search is performed according to the content set by the user; when the user does not make customized settings, the default setting content can be used for the optimized search.

[0059] Optionally, the process of obtaining the coal blending result corresponding to the above coal blending structure may include:

[0060] Obtaining initial coal property information;

[0061] Perform fusion processing on the initial coal attribute information to obtain the initial coal attribute characteristics;

[0062] The coal blending structure and the attribute characteristics of each initial coal are input into the pre-trained result prediction model, and the coal blending result corresponding to the coal blending structure is output through the result prediction model.

[0063] Specifically, the attribute information of the initial coal may refer to the quality attribute information of the initial coal, such as its composition, the proportion of each component, etc. The attribute characteristics in the embodiments of the present application may be attribute characteristics that have a significant impact on the coal blending results, obtained manually (e.g., by frontline operators) based on experience, or obtained by filtering and fusing various attribute information of the initial coal using principal component analysis methods. For example, the initial coal's name, ash content, volatile matter, sulfur content, caking index, hot strength, maximum vitrinite reflectance, region, and mineral location, etc.

[0064] Since the coal blending process generates two products, a complex and coke, in the embodiment of the present application, the result prediction model can also include two independent models: a complex quality prediction model for predicting the quality attribute information of the complex; and a coke quality prediction model for predicting the quality attribute information of the coke. Correspondingly, the coal blending structure and the attribute characteristics of each initial coal are input into the pre-trained result prediction model, and the coal blending result corresponding to the coal blending structure is output by the result prediction model, which may include:

[0065] The coal blending structure and the property characteristics of each initial coal are input into the complex quality prediction model to obtain the quality property information of the complex; the coal blending structure and the property characteristics of each initial coal are input into the coke quality prediction model to obtain the quality property information of the carbon.

[0066] Optionally, the training process of the above result prediction model may include:

[0067] Obtaining sample data and an initial result prediction model, the sample data including: historical coal blending structure data, attribute characteristic data of each initial coal, and coal blending results corresponding to the historical coal blending structure data;

[0068] The initial result prediction model is trained based on the sample data to obtain a trained result prediction model.

[0069] Specifically, since the result prediction model may include two independent models: a complex quality prediction model and a coke quality prediction model; therefore, in the model training stage, correspondingly, each model may be trained independently.

[0070] In addition, before model training, the attribute feature data customization interface can also be displayed to the user for the user to customize and set specific attribute feature data. When the user makes customized settings through the above page, the model training will be carried out according to the user settings; when the user does not make customized settings, the default settings can be used for model training.

[0071] In the embodiments of the present application, there is no limit on the number of target coal blending structures ultimately obtained, and the number can be customized based on actual conditions. For example, it can be a single or multiple target coal blending structures. After obtaining the target coal blending structures, each target coal blending structure, as well as the coal blending results corresponding to the target coal blending structures predicted by the above-mentioned result prediction model, can be displayed in the interface, so that the user can determine the coal blending structure to be ultimately adopted from the target coal blending structures based on the coal blending results.

[0072] In addition, the user can also customize the coal blending result and input the customized coal blending structure into the above-mentioned result prediction model, so as to obtain the coal blending result corresponding to the customized coal blending structure through prediction by the model.

[0073] See Figure 3, which is a schematic diagram of the training process of the result prediction model provided in the embodiment of the present application. The following is an explanation of the training process of the result prediction model in conjunction with Figure 3:

[0074] Step 301: Acquire historical data, such as the coal blending structure, initial coal attribute information, blended coal quality attribute information, and coke quality attribute information during the historical coal blending process; Step 302: Preprocess and standardize the above historical data; Step 303: Use principal component analysis to filter and normalize the attribute characteristic data of each initial coal obtained based on the fusion of the initial coal attribute information; Step 304: Use the coal blending structure, blended coal quality attribute information, and the corresponding initial coal attribute characteristic data to train a complex mass prediction model to obtain a trained complex mass prediction model; Step 305: , use the coal blending structure, coke quality attribute information and the corresponding initial coal attribute characteristic data to train the coke quality prediction model to obtain the trained coke quality prediction model; step 306, save the name of the attribute characteristic data of the initial coal input to the complex quality prediction model and the name of the complex quality attribute information output by the complex quality prediction model; save the name of the attribute characteristic data of the initial coal input to the coke quality prediction model and the name of the coke quality attribute information output by the coke quality prediction model; step 307, save the trained complex quality prediction model and the coke quality prediction model.

[0075] See Figure 4, which is a schematic diagram of the coal blending structure optimization process provided in the embodiment of the present application. The coal blending structure optimization solution provided in the embodiment of the present application is explained below in conjunction with Figure 4:

[0076] Step 401, obtain the initial coal inventory data and price data; Step 402, pre-process the data obtained in step 401; Step 403, determine whether to use conservative optimization to perform optimization search; if so, execute step 404; if not, execute step 406; Step 404, take the structural difference between the coal blending structure and the initial coal blending structure as a constraint that is less than a preset structural difference threshold, and / or, take the result difference between the coal blending result corresponding to the coal blending structure and the initial coal blending result corresponding to the initial coal blending structure as a constraint that is less than a preset result difference threshold, take minimizing the coal blending cost as the optimization goal, take the coal blending structure as the unknown quantity to perform optimization search, and obtain the target coal blending structure; Step 405, output the target coal blending structure; Step 406, generate the initial coal blending structure based on the historical coal blending structure; Step 407, when the update condition of the current coal blending structure is met, update the current coal blending structure; Step 408, adopt The complex quality prediction model predicts the complex quality attribute information of the current coal blending structure; step 409, using the coke quality prediction model to predict the coke quality attribute information of the current coal blending structure; step 410, based on minimizing the coal blending cost, and the difference between the predicted complex quality attribute information and the preset complex quality attribute information, and / or based on minimizing the difference between the predicted coke quality attribute information and the preset coke quality attribute information, construct an optimization target, and perform optimization search with the coal blending structure as an unknown quantity to obtain a new coal blending structure; step 411, according to the preset update probability, use the target value corresponding to the new coal blending structure to update the target value corresponding to the current coal blending structure; step 412, according to the preset update probability, use the new coal blending structure to update the current coal blending structure; step 413, judge whether the target value meets the preset convergence condition, if so, execute step 405; if not, return to execute step 407.

[0077] In addition, referring to the lower right corner of FIG4 , an interface I can also be pre-set to display the attribute feature data customization interface Ui1 to the user before model training, or to display the constraint condition setting page Ui2 and / or the target value setting page Ui3 to the user before performing an optimization search, so that the user can customize specific attribute feature data, constraint conditions, or target value calculation methods.

[0078] See Figure 5, which shows a schematic diagram of the target coal blending page. As can be seen from Figure 5, there are 10 initial coal types in inventory: C1, C2, ..., C10. The final optimized target coal blending structure is: C2 at 10%, C4 at 20%, C5 at 20%, and C9 at 50%. The remaining initial coal proportions are all 0. The page also displays the quality attribute information Q1 of the blend and Q2 of the coke, calculated according to the theoretical formula, as well as the quality attribute information Q3 of the blend and Q4 of the coke, predicted according to the quality prediction model.

[0079] The coal blending structure optimization method provided in the embodiment of the present application, after obtaining the initial coal blending structure, constructs an optimization target with the coal blending cost minimization based on the initial coal blending structure, and uses an optimization search algorithm to automatically search for a target coal blending structure that meets the requirements. Compared with the method of manually determining the coal blending structure, the automatic optimization search method provided in the embodiment of the present application improves the efficiency of determining the coal blending structure. In addition, since the optimization search is performed based on the initial coal blending structure and with the optimization target constructed with the coal blending cost minimization in the embodiment of the present application, the coal blending cost corresponding to the target coal blending structure finally obtained can be lower. In summary, the coal blending structure optimization method provided in the embodiment of the present application can improve the efficiency of determining the coal blending structure and reduce the economic cost of coal blending.

[0080] Based on a coal blending structure optimization method provided in any of the above embodiments, an embodiment of the present application provides a coal blending structure optimization device, as shown in FIG6 , which is a schematic structural diagram of a coal blending structure optimization device provided in an embodiment of the present application. The coal blending structure optimization device 60 includes: an initial coal blending structure acquisition module 601 and an optimization module 602;

[0081] The initial coal blending structure acquisition module 601 is used to acquire the initial coal blending structure; the initial coal blending structure includes the mixing ratio information between the initial coals;

[0082] The optimization module 602 is used to construct an optimization target based on the initial coal blending structure with the coal blending cost minimized, and to perform optimization search with the coal blending structure as an unknown quantity to obtain a target coal blending structure.

[0083] Optionally, in one embodiment of the present application, the optimization module 602 is specifically configured to:

[0084] Taking the initial coal blending structure as the initial solution, the optimization objective is constructed based on minimizing the difference between the coal blending results corresponding to the coal blending structure and the preset coal blending results, as well as minimizing the coal blending cost. The optimization search is performed with the coal blending structure as the unknown quantity to obtain the target coal blending structure.

[0085] Optionally, in one embodiment of the present application, the optimization module 602 is further configured to:

[0086] Obtaining initial coal property information;

[0087] Perform fusion processing on the initial coal attribute information to obtain the initial coal attribute characteristics;

[0088] The coal blending structure and the attribute characteristics of each initial coal are input into the pre-trained result prediction model, and the coal blending result corresponding to the coal blending structure is output through the result prediction model.

[0089] Optionally, in one embodiment of the present application, the coal blending structure optimization device 60 further includes:

[0090] The model training module is used to: obtain sample data and an initial result prediction model. The sample data includes historical coal blending structure data, attribute characteristic data of each initial coal, and coal blending results corresponding to the historical coal blending structure data; train the initial result prediction model based on the sample data to obtain a trained result prediction model.

[0091] Optionally, in one embodiment of the present application, the optimization module 602, when executing the steps of minimizing the difference between the coal blending result corresponding to the coal blending structure and the preset coal blending result, and minimizing the coal blending cost to construct an optimization objective, performing an optimization search with the coal blending structure as an unknown quantity, and obtaining a target coal blending structure, is specifically configured to:

[0092] Calculate the difference between the coal blending result corresponding to the coal blending structure and the preset coal blending result;

[0093] Calculate the coal blending cost corresponding to the coal blending structure;

[0094] The fusion result difference value and coal blending cost are combined to obtain the fusion result;

[0095] The fusion result is used as the objective function, and the coal blending structure is used as the unknown quantity for optimization search to obtain the target coal blending structure.

[0096] Optionally, in one embodiment of the present application, the optimization module 602 is specifically configured to:

[0097] The constraint is that the structural difference between the coal blending structure and the initial coal blending structure is less than a preset structural difference threshold, and / or the constraint is that the result difference between the coal blending result corresponding to the coal blending structure and the initial coal blending result corresponding to the initial coal blending structure is less than a preset result difference threshold, with minimizing the coal blending cost as the optimization goal and the coal blending structure as the unknown quantity for optimization search to obtain the target coal blending structure.

[0098] Optionally, in one embodiment of the present application, the optimization module 602, before executing the optimization search based on the initial coal blending structure, with the coal blending cost minimized to obtain the target coal blending structure, is further configured to:

[0099] Determine the optimization search method; the optimization search method includes conservative optimization method or innovative optimization method;

[0100] If the optimization search mode is the innovative optimization mode, the optimization module 602 is specifically used to:

[0101] Taking the initial coal blending structure as the initial solution, the optimization objective is constructed based on minimizing the difference between the coal blending result corresponding to the coal blending structure and the preset coal blending result, as well as minimizing the coal blending cost. The target coal blending structure is obtained by performing an optimization search with the coal blending structure as the unknown quantity.

[0102] If the optimization search mode is a conservative optimization mode, the optimization module 602 is specifically used to:

[0103] The constraint is that the structural difference between the coal blending structure and the initial coal blending structure is less than a preset structural difference threshold, and / or the constraint is that the result difference between the coal blending result corresponding to the coal blending structure and the initial coal blending result corresponding to the initial coal blending structure is less than a preset result difference threshold, with minimizing the coal blending cost as the optimization goal and the coal blending structure as the unknown quantity for optimization search to obtain the target coal blending structure.

[0104] The coal blending structure optimization device of the present embodiment is used to implement the corresponding coal blending structure optimization methods of the aforementioned multiple method embodiments and has the beneficial effects of the corresponding method embodiments, which will not be described in detail here. In addition, the functional implementation of each module in the coal blending structure optimization device of the present embodiment can refer to the description of the corresponding parts in the aforementioned method embodiments, which will not be described in detail here.

[0105] Based on the coal blending structure optimization method described in any of the above embodiments, an embodiment of the present application provides an electronic device, including: a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; the memory is used to store computer programs, and the processor is used to execute the programs stored in the memory to implement the method described in any of the above embodiments.

[0106] Based on the coal blending structure optimization method described in any of the above embodiments, an embodiment of the present application provides a computer storage medium storing a computer program, which implements the method described in any of the above embodiments when executed by a processor.

[0107] It should be pointed out that, according to the needs of implementation, the various components / steps described in the embodiments of the present application can be split into more components / steps, or two or more components / steps or partial operations of components / steps can be combined into new components / steps to achieve the purpose of the embodiments of the present application.

[0108] The above-described method according to the embodiment of the present application can be implemented in hardware, firmware, or as software or computer code that can be stored in a recording medium (such as a CD ROM, RAM, floppy disk, hard disk, or magneto-optical disk), or as computer code originally stored in a remote recording medium or non-transitory machine-readable medium downloaded via a network and then stored in a local recording medium, so that the method described herein can be stored in such software processing on a recording medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware (such as an ASIC or FPGA). It can be understood that a computer, processor, microprocessor controller, or programmable hardware includes a storage component (e.g., RAM, ROM, flash memory, etc.) that can store or receive software or computer code. When the software or computer code is accessed and executed by the computer, processor, or hardware, the control method of the adjustment machine described herein is implemented. In addition, when a general-purpose computer accesses the code for implementing the control method of the adjustment machine shown herein, the execution of the code converts the general-purpose computer into a dedicated computer for executing the coal blending structure optimization method shown herein.

[0109] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

[0110] Those skilled in the art will appreciate that the units and method steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the embodiments of this application.

[0111] The various embodiments in this specification are described in a progressive manner. Similar parts between the various embodiments can be referred to in conjunction with each other. Each embodiment focuses on the differences between the other embodiments. In particular, the system embodiments are generally similar to the method embodiments, so the description is relatively simple. For relevant parts, refer to the description of the method embodiments.

[0112] The above implementation methods are only used to illustrate the embodiments of the present application, and are not intended to limit the embodiments of the present application. Ordinary technicians in the relevant technical field can make various changes and modifications without departing from the spirit and scope of the embodiments of the present application. Therefore, all equivalent technical solutions also fall within the scope of the embodiments of the present application, and the scope of patent protection of the embodiments of the present application should be defined by the claims.

Claims

1. A method for optimizing coal blending structure, wherein: The method comprises: Acquire an initial coal blending structure; the initial coal blending structure includes mixing ratio information between various initial coals; Based on the initial coal blending structure, an optimization target is constructed by minimizing the coal blending cost, and an optimization search is performed with the coal blending structure as an unknown quantity to obtain a target coal blending structure.

2. The method according to claim 1, wherein: Based on the initial coal blending structure, the optimization target is constructed by minimizing the coal blending cost, and the optimization search is performed with the coal blending structure as an unknown quantity to obtain the target coal blending structure, including: The initial coal blending structure is taken as the initial solution, and an optimization target is constructed based on minimizing the difference between the coal blending result corresponding to the coal blending structure and the preset coal blending result, as well as minimizing the coal blending cost. The coal blending structure is used as an unknown quantity for optimization search to obtain the target coal blending structure.

3. The method according to claim 2, wherein: The process of obtaining the coal blending result corresponding to the coal blending structure includes: Obtaining initial coal property information; Perform fusion processing on the initial coal attribute information to obtain the initial coal attribute characteristics; The coal blending structure and the attribute characteristics of each initial coal are input into a pre-trained result prediction model, and the coal blending result corresponding to the coal blending structure is output through the result prediction model.

4. The method according to claim 3, wherein: The method further comprises: Obtaining sample data and an initial result prediction model, the sample data including: historical coal blending structure data, attribute characteristic data of each initial coal, and coal blending results corresponding to the historical coal blending structure data; The initial result prediction model is trained based on the sample data to obtain a trained result prediction model.

5. The method according to any one of claims 2 to 4, wherein: The optimization goal is constructed by minimizing the difference between the coal blending result corresponding to the coal blending structure and the preset coal blending result, and minimizing the coal blending cost, and performing optimization search with the coal blending structure as an unknown quantity to obtain the target coal blending structure, including: Calculate the difference between the coal blending result corresponding to the coal blending structure and the preset coal blending result; Calculate the coal blending cost corresponding to the coal blending structure; Merging the result difference value and the coal blending cost to obtain a fusion result; The fusion result is used as the objective function, and the coal blending structure is used as an unknown quantity for optimization search to obtain the target coal blending structure.

6. The method according to claim 1, wherein: Based on the initial coal blending structure, the optimization target is constructed by minimizing the coal blending cost, and the optimization search is performed with the coal blending structure as an unknown quantity to obtain the target coal blending structure, including: The structural difference between the coal blending structure and the initial coal blending structure is constrained to be less than a preset structural difference threshold, and / or, The constraint condition is that the difference between the coal blending result corresponding to the coal blending structure and the initial coal blending result corresponding to the initial coal blending structure is less than a preset result difference threshold, the optimization goal is to minimize the coal blending cost, and the coal blending structure is used as an unknown quantity for optimization search to obtain the target coal blending structure.

7. The method according to claim 1, wherein: Before constructing an optimization target based on the initial coal blending structure and minimizing the coal blending cost, and performing optimization search with the coal blending structure as an unknown quantity to obtain the target coal blending structure, the method further includes: Determine an optimization search method; the optimization search method includes a conservative optimization method or an innovative optimization method; If the optimization search method is an innovative optimization method, then based on the initial coal blending structure, the optimization target is constructed by minimizing the coal blending cost, and the optimization search is performed with the coal blending structure as an unknown quantity to obtain the target coal blending structure, including: Taking the initial coal blending structure as the initial solution, constructing an optimization target based on minimizing the difference between the coal blending result corresponding to the coal blending structure and the preset coal blending result, and minimizing the coal blending cost, performing optimization search with the coal blending structure as an unknown quantity, and obtaining a target coal blending structure; If the optimization search method is a conservative optimization method, then based on the initial coal blending structure, the optimization target is constructed by minimizing the coal blending cost, and the optimization search is performed with the coal blending structure as an unknown quantity to obtain the target coal blending structure, including: The constraint is that the structural difference between the coal blending structure and the initial coal blending structure is less than a preset structural difference threshold, and / or the constraint is that the result difference between the coal blending result corresponding to the coal blending structure and the initial coal blending result corresponding to the initial coal blending structure is less than a preset result difference threshold, the optimization goal is to minimize the coal blending cost, and the coal blending structure is used as an unknown quantity for optimization search to obtain the target coal blending structure.

8. A coal blending structure optimization device, wherein: The device comprises: An initial coal blending structure acquisition module is used to acquire an initial coal blending structure; the initial coal blending structure includes the mixing ratio information between the initial coals; The optimization module is used to construct an optimization target based on the initial coal blending structure with the coal blending cost minimized, and to perform optimization search with the coal blending structure as an unknown quantity to obtain a target coal blending structure.

9. An electronic device, comprising: A processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus; Memory, used to store computer programs; A processor, for implementing the method steps described in any one of claims 1 to 7 when executing a program stored in a memory.

10. A computer-readable storage medium having computer instructions stored thereon, wherein when the computer instructions are executed by a processor, the processor is caused to execute the method according to any one of claims 1 to 7.

11. A computer program product tangibly stored on a computer readable medium and comprising computer executable instructions which, when executed, cause at least one processor to perform the method according to any one of claims 1-7.

Images