Coal blending ratio prediction method, device and medium

Abstract

This application discloses a method, apparatus, and medium for predicting coal blending ratios, relating to the field of coal blending technology. This application derives a prediction model for plant power consumption based on historical plant power consumption, a prediction model for boiler efficiency based on historical boiler efficiency, and a prediction model for environmental protection costs based on historical environmental protection costs. A nonlinear programming model is established based on these models. The nonlinear programming model is then solved using information on multiple coal types currently involved in the blending to obtain the coal blending ratio. By using plant power consumption, boiler efficiency, and environmental protection costs within the unit power supply cost to construct a predictable model, and combining it with current coal type information, the optimal coal blending ratio is obtained. This method does not require historical data to contain the best current scenario and can predict the coal blending ratio according to different needs.

Description

Technical Field

[0001] This application relates to the field of coal blending technology, and in particular to a method, apparatus and medium for predicting coal blending ratio. Background Technology

[0002] In the production process of thermal power plants, coal accounts for more than 80% of the cost. How to blend coal for combustion to obtain the greatest economic benefits is worth studying.

[0003] Current coal blending schemes for thermal power plants typically aim at revenue per unit of electricity, taking into account coal prices, historical boiler efficiency, historical plant power costs, and historical limestone and liquid ammonia costs. Boiler efficiency, limestone, and urea costs all require consulting historical data, and calculations are iteratively performed based on historical data to obtain the optimal coal blending ratio. This results in low calculation efficiency, and historical data may not necessarily contain the best conditions suitable for the current situation, thus limiting its applicability.

[0004] Therefore, how to predict the coal blending ratio according to different needs is a technical problem that urgently needs to be solved by people in this field. Summary of the Invention

[0005] The purpose of this application is to provide a method, apparatus and medium for predicting coal blending ratios according to different needs.

[0006] To solve the above-mentioned technical problems, this application provides a method for predicting coal blending ratios, including: Based on historical plant power consumption, a plant power consumption prediction model is obtained; based on historical boiler efficiency, a boiler efficiency prediction model is obtained; and based on historical environmental protection costs, an environmental protection cost prediction model is obtained. A nonlinear programming model is established based on the prediction models for plant power consumption, boiler efficiency, and environmental cost. Based on information on multiple coal types currently involved in coal blending, a nonlinear programming model is solved to obtain the coal blending ratio.

[0007] Preferably, in the above-mentioned coal blending ratio prediction method, the plant power consumption prediction model is obtained based on historical plant power consumption, including: The load, coal quality, and coal weight were extracted as features, and historical plant power consumption was extracted as labels. The model was then trained to obtain a plant power consumption prediction model. A boiler efficiency prediction model is derived based on historical boiler efficiencies, including: The load, coal quality, and coal weight were extracted sequentially as features. The boiler efficiency corresponding to each set of data was calculated using the inverse balance algorithm. The model was then trained to obtain the boiler efficiency prediction model. Historical environmental costs include: historical limestone treatment costs, historical urea treatment costs, and historical coal ash and slag treatment costs. Correspondingly, environmental cost prediction models are derived based on historical environmental costs, including: A limestone treatment cost prediction model was obtained based on historical limestone treatment costs, a urea treatment cost prediction model was obtained based on historical urea treatment costs, and a coal ash and slag treatment cost prediction model was obtained based on historical coal ash and slag treatment costs.

[0008] Preferably, in the above-mentioned coal blending ratio prediction method, a nonlinear programming model is established based on the plant power consumption prediction model, boiler efficiency prediction model, and environmental cost prediction model, and then the method further includes: Obtain the preset constraints; The nonlinear programming model is constrained according to the preset constraints.

[0009] Preferably, in the above-mentioned coal blending ratio prediction method, a nonlinear programming model is established based on the plant power consumption prediction model, boiler efficiency prediction model, and environmental cost prediction model, including: A nonlinear programming model is established based on the first formula, the plant power consumption prediction model, the boiler efficiency prediction model, and the environmental protection cost prediction model. The first formula is: ; in, Cost per unit of electricity supply; Total cost; The amount of electricity supplied per unit time; For coal costs; This refers to the cost of limestone processing per unit time. Cost of urea treatment per unit time; Cost of coal ash and slag treatment per unit time; The amount of electricity generated per unit time; This refers to the amount of electricity used by the plant within a unit of time. , The blending ratio for each type of coal. Each type of coal is assigned a number.

[0010] Preferably, in the above method for predicting coal blending ratios, the steps for obtaining coal costs are as follows: The comprehensive calorific value of coal is obtained according to the second formula; The second formula is: ;in The calorific value of each type of coal; The comprehensive unit price is obtained according to the third formula; The third formula is ;in The unit price for each type of coal; The cost of coal is obtained using the fourth formula; The fourth formula is: ; Where Q represents fuel consumption; For boiler efficiency, Electricity generated per unit time The required weight of coal.

[0011] Preferably, in the above method for predicting coal blending ratios, the steps for obtaining the limestone treatment cost, urea treatment cost, and coal ash and slag treatment cost are as follows: The cost of urea treatment is obtained from the fifth formula. The fifth formula is: ; in, This refers to the unit price of urea. This represents the total nitrogen content. This refers to the nitrogen content of each type of coal. The corrected slope for urea usage; The corrected intercept for urea usage; The cost of limestone processing is obtained from the sixth formula. The sixth formula is: ; in, This refers to the unit price of limestone. This refers to the total sulfur content. This refers to the sulfur content of each type of coal. The corrected slope for limestone usage; Correction intercept for limestone usage; The cost of coal ash and slag treatment is obtained according to the seventh formula. ; in, The unit price for processing coal ash and slag; Total ash content of coal; This refers to the ash content of each type of coal.

[0012] Preferably, in the above coal blending ratio prediction method, the preset constraints include: the total coal blending ratio is 100%, the upper and lower limits of the blending ratio of different coals, the comprehensive calorific value, the comprehensive sulfur content limit, and the maximum coal feeding amount per unit time.

[0013] To solve the above-mentioned technical problems, this application also provides a coal blending ratio prediction device, comprising: The preliminary modeling module is used to obtain a prediction model for plant power consumption based on historical plant power consumption, a prediction model for boiler efficiency based on historical boiler efficiency, and a prediction model for environmental protection costs based on historical environmental protection costs. The integrated modeling module is used to establish a nonlinear programming model based on the plant power consumption prediction model, boiler efficiency prediction model, and environmental cost prediction model. The prediction and solution module is used to solve the nonlinear programming model based on information about multiple coal types currently involved in coal blending, and to obtain the coal blending ratio.

[0014] To solve the above-mentioned technical problems, this application also provides a coal blending ratio prediction device, comprising: Memory, used to store computer programs; A processor is used to execute computer programs to implement the steps of the coal blending ratio prediction method described above.

[0015] To address the aforementioned technical problems, this application also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the aforementioned coal blending ratio prediction method.

[0016] The coal blending ratio prediction method provided in this application derives a plant power consumption prediction model based on historical plant power consumption, a boiler efficiency prediction model based on historical boiler efficiency, and an environmental cost prediction model based on historical environmental costs. A nonlinear programming model is then established based on these models. The nonlinear programming model is solved using information on multiple coal types currently involved in the blending to obtain the coal blending ratio. By using plant power consumption, boiler efficiency, and environmental costs from the unit power supply cost to construct a predictable model, and combining it with current coal type information, the optimal coal blending ratio is obtained. This method does not require historical data to include the best-case scenario for the current situation and can predict the coal blending ratio according to different needs.

[0017] In addition, this application also provides an apparatus and a medium that correspond to the above method and have the same effect. Attached Figure Description

[0018] To more clearly illustrate the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 A flowchart illustrating a coal blending ratio prediction method provided in this application embodiment; Figure 2A structural diagram of a coal blending ratio prediction device provided in an embodiment of this application; Figure 3 This is a structural diagram of another coal blending ratio prediction device provided in an embodiment of this application. Detailed Implementation

[0020] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the protection scope of this application.

[0021] The core of this application is to provide a method, device, and medium for predicting coal blending ratios.

[0022] To enable those skilled in the art to better understand the present application, the present application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0023] In the production of washed raw coal, the raw coal comes from different coal mines and coal seams, and its washability varies. In order to meet the product quality requirements of different users, coal plants need to take into account washability, ash content, sulfur content and recovery rate to achieve the goal of maximizing profits. The washed raw coal is blended in different proportions to form washed raw coal with multiple components. In the production process of thermal power plants, coal costs account for more than 80%. How to blend coal to obtain the greatest economic benefits is worth studying.

[0024] Current coal blending schemes for thermal power plants employ two main approaches. One aims to minimize the overall unit price of coal, incorporating constraints such as combustion stability, environmental protection indicators, and safety indicators. An optimization model is then used to calculate the optimal blending ratio. However, due to continuously increasing environmental standards and costs, this approach fails to consider environmental costs and lacks a comprehensive understanding of influencing factors. Another approach focuses on revenue per unit of electricity, comprehensively considering coal prices, historical boiler efficiencies, historical plant power costs, and historical limestone and liquid ammonia costs. However, this approach requires consulting historical data for boiler efficiency and limestone and urea costs, necessitating iterative calculations to obtain the optimal blending ratio. This results in low computational efficiency, and historical data may not necessarily reflect the best current conditions.

[0025] To address the aforementioned technical problems, this application provides a method for predicting coal blending ratios, such as... Figure 1 As shown, it includes: S11: Based on historical plant power consumption, a plant power consumption prediction model is obtained; based on historical boiler efficiency, a boiler efficiency prediction model is obtained; and based on historical environmental protection costs, an environmental protection cost prediction model is obtained. S12: Establish a nonlinear programming model based on the plant power consumption prediction model, boiler efficiency prediction model, and environmental cost prediction model; S13: Based on the information of multiple coal types currently involved in coal blending, solve the nonlinear programming model to obtain the coal blending ratio.

[0026] In this embodiment, a basic prediction model is established based on historical implementation data, including a power consumption prediction model, a boiler efficiency prediction model, and an environmental cost prediction model. From a mechanistic perspective, different coal ratios lead to different data results, thereby establishing the prediction model.

[0027] Environmental costs mainly include the costs of treating sulfur dioxide, nitrogen oxides, and coal ash and slag. Depending on the specific application requirements, one or more methods can be selected for calculating environmental costs.

[0028] Cost calculation of limestone in environmental protection costs: From a mechanistic perspective, the purpose of limestone is to adsorb sulfur dioxide (SO2). The sulfur in SO2 comes entirely from coal, which can be calculated from the weight of coal. The sulfur content was calculated to be one part calcium (Ca) to one part sulfur (S). One ton of S requires 1.25 tons of Ca, which corresponds to 3.125 tons of limestone. There will be some loss in the use of limestone. Historical data can be combined to fit the data to obtain the actual amount of limestone consumed per ton of coal for different ratios. Multiplying this by the unit price gives the cost of limestone.

[0029] Cost calculation of urea in environmental protection costs: From a mechanistic perspective, nitrogen oxides (NOx) are converted from nitrogen (N) in coal. The NH3 produced by urea is used to absorb NOx. The conversion pathway is N → NOx → reaction with NH3 to produce nitrogen gas (N2). For complete NOx absorption, 0.23 tons of urea are needed for 1 ton of nitrogen in coal. In actual use, urea is lost, and NOx is not completely absorbed. By combining historical data and making corrections, the actual amount of urea consumed per ton of coal under different formulations can be obtained. Multiplying this by the unit price gives the cost of urea.

[0030] Environmental costs related to coal ash and slag treatment: Coal combustion produces coal ash and slag. The weight of coal ash and slag is calculated from the weight of coal and ash content data. This is then adjusted using historical data to obtain the weight of coal ash and slag produced per ton of coal with different proportions. Multiplying this weight by the unit price gives the cost of coal ash and slag treatment.

[0031] In addition, the prediction model for plant power consumption is established by acquiring historical data, extracting load, test data of coal quality entering the furnace, and weight of coal entering the furnace as features, extracting power consumption as a label, and training the model to obtain the prediction model for plant power consumption.

[0032] The boiler efficiency prediction model is established by acquiring historical data, extracting load, coal quality test data, and coal weight as features, using an inverse balance algorithm to calculate the boiler efficiency corresponding to each set of data, training the model, and obtaining the boiler efficiency prediction model.

[0033] A nonlinear programming model is established based on the prediction models of plant power consumption, boiler efficiency, and environmental protection costs. This nonlinear programming model is a nonlinear operations optimization model that minimizes the unit power supply cost and comprehensively considers multiple costs (limestone, urea, and coal ash and slag treatment costs).

[0034] The information on multiple coal types participating in coal blending mentioned in this embodiment refers to the information on various coal types that can currently participate in coal blending, including the name of the coal type, unit price Pi (yuan / ton), net calorific value hi (as received), moisture content Mti (as received), ash content Aari (as received), volatile matter Vari (as received), sulfur content Si (as received), nitrogen content Ni (as received), usable quantity, and upper and lower limits of the blending ratio.

[0035] Based on the established nonlinear programming model and combined with the current coal type information, the model is solved. Preferably, a genetic algorithm is used to solve the nonlinear programming model to obtain the coal blending ratio.

[0036] According to the coal blending ratio prediction method provided in this application, a prediction model for plant power consumption is obtained based on historical plant power consumption, a prediction model for boiler efficiency is obtained based on historical boiler efficiency, and a prediction model for environmental protection costs is obtained based on historical environmental protection costs. A nonlinear programming model is then established based on these models. The nonlinear programming model is solved using information on multiple coal types currently involved in the blending to obtain the coal blending ratio. A predictable model is constructed using plant power consumption, boiler efficiency, and environmental protection costs within the unit power supply cost. This model is then combined with current coal type information to solve for the optimal coal blending ratio. This method does not require historical data to include the best-case scenario for the current situation and can predict the coal blending ratio according to different needs.

[0037] According to the above embodiments, in practical applications, human experience is usually very important. This embodiment provides a preferred solution, a coal blending ratio prediction method, which establishes a nonlinear programming model based on a plant power consumption prediction model, a boiler efficiency prediction model, and an environmental cost prediction model, and then includes: Obtain the preset constraints; The nonlinear programming model is constrained according to the preset constraints.

[0038] The preset constraints mentioned in this embodiment are user-defined and constrain the nonlinear programming model. For example, preset constraints may include: a total coal blending ratio of 100%, upper and lower limits for the blending ratio of different coals, a comprehensive calorific value, a comprehensive sulfur content limit, a maximum coal quantity per unit time, and quantity limits for different coals. Users can select one or more constraints to set according to specific needs; this embodiment does not impose specific limitations.

[0039] Based on the above embodiments, this embodiment provides a specific application scheme, which establishes a nonlinear programming model based on the plant power consumption prediction model, boiler efficiency prediction model, and environmental cost prediction model, including: A nonlinear programming model is established based on the first formula, the plant power consumption prediction model, the boiler efficiency prediction model, and the environmental protection cost prediction model. The first formula is: ; in, Cost per unit of electricity supply; Total cost; The amount of electricity supplied per unit time; For coal costs; For a unit of time Limestone processing costs; Cost of urea treatment per unit time; Cost of coal ash and slag treatment per unit time; The amount of electricity generated per unit time; This refers to the amount of electricity used by the plant within a unit of time. , The blending ratio for each type of coal. Each type of coal is assigned a number.

[0040] A predictable model is constructed by considering factors such as the lowest unit power supply cost, plant power consumption within the unit power supply cost, boiler efficiency, and environmental protection costs. This model is a nonlinear operations research optimization model that comprehensively considers multiple costs (limestone, urea, and coal ash / slag treatment costs). By combining current coal type information, the optimal coal blending ratio is obtained. It does not require historical data to provide the best current scenario and can predict the coal blending ratio based on different needs.

[0041] Based on the above embodiments, this embodiment provides a specific application scheme, and the steps to obtain coal costs are as follows: The comprehensive calorific value of coal is obtained according to the second formula; The second formula is: ; in The calorific value of each type of coal; The comprehensive unit price is obtained according to the third formula; The third formula is: ； in The unit price for each type of coal; The cost of coal is obtained using the fourth formula; The fourth formula is: ； Where Q represents fuel consumption; For boiler efficiency, Electricity generated per unit time The required weight of coal.

[0042] Assume the proportion of each type of coal is The total calorific value of the coal produced is then... The comprehensive unit price is 。

[0043] Boiler efficiency is Historical boiler efficiency was calculated using an inverse balancing algorithm, combined with boiler efficiency data from performance tests. The expression for boiler efficiency under different ratios was obtained by fitting: 。

[0044] Steam consumption is denoted by Q. The amount of steam consumed to generate 1 kW·h of power is called steam consumption. This data is obtained from the performance tests of various power plants.

[0045] Total electricity generated The required weight of coal is: ； The total price of coal is: ； The total electricity generated is obtained through the solution provided in this embodiment. The total price of coal required.

[0046] Based on the above embodiments, this embodiment provides a specific application scheme, and the steps for obtaining the limestone treatment cost, urea treatment cost, and coal ash and slag treatment cost are as follows: The cost of urea treatment is obtained from the fifth formula. The fifth formula is: ； in, This refers to the unit price of urea. This represents the total nitrogen content. This refers to the nitrogen content of each type of coal. The corrected slope for urea usage; The corrected intercept for urea usage; The cost of limestone processing is obtained from the sixth formula. The sixth formula is: ； in, This refers to the unit price of limestone. This refers to the total sulfur content. This refers to the sulfur content of each type of coal. The corrected slope for limestone usage; Correction intercept for limestone usage; The cost of coal ash and slag treatment is obtained according to the seventh formula. ； in, The unit price for processing coal ash and slag; Total ash content of coal; This refers to the ash content of each type of coal.

[0047] In this embodiment, the overall nitrogen content of the coal is: The unit price of urea is: ; Since urea is mainly used to absorb NOx, and the NOx content is related to the nitrogen content in coal, mechanistic analysis shows that 0.23 tons of urea are needed to completely absorb the NOx generated from each ton of nitrogen in coal combustion. Considering losses and other factors, this is adjusted, and the final urea weight required per ton of coal under a given ratio is: ； The cost of urea is: ； The total sulfur content of the coal was as follows: The unit price of limestone is ; Since limestone is primarily used to absorb SO2, which is produced from sulfur (S) in coal, mechanistic analysis suggests that 3.125 tons of limestone are needed to completely absorb the SO2 generated from each ton of sulfur in coal. Considering losses and other factors, this is adjusted, and the final weight of limestone required per ton of coal under a given ratio is: ； The cost of limestone is: ； The mixed coal ash is divided into ; The unit price for processing coal ash and slag is: ; The total weight of the coal ash and slag after combustion is:

[0048] The cost of treating coal ash and slag is: ； The solution provided in this embodiment yields predictive models for limestone treatment costs, urea treatment costs, and coal ash and slag treatment costs; based on the coal blending ratio... The function is represented by the target function, and a nonlinear programming coal blending model is constructed using this target function.

[0049] In addition, the preset constraints include: the total coal blending ratio is 100%, expressed by the formula: The upper and lower limits of the blending ratio of different coals are expressed by the following formula: The comprehensive caloric limit is expressed by the formula: The comprehensive sulfur content limit is expressed by the formula: The maximum amount of coal fed per unit time is expressed by the formula: .

[0050] Using the functional expression of unit power supply cost as the optimization objective and the mathematical expression of preset constraints as constraints, a nonlinear programming operation research optimization model is established. The genetic algorithm is then used to solve the established nonlinear programming model to obtain the optimal coal blending ratio.

[0051] The coal blending ratio prediction method has been described in detail in the above embodiments. This application also provides embodiments corresponding to the coal blending ratio prediction device. It should be noted that this application describes the embodiments of the device from two perspectives: one is based on the functional modules, and the other is based on the hardware.

[0052] From the perspective of functional modules Figure 2 A structural diagram of a coal blending ratio prediction device provided in an embodiment of this application is shown below. Figure 2 As shown, the coal blending ratio prediction device includes: The preliminary modeling module 21 is used to obtain a prediction model of plant power consumption based on historical plant power consumption, a prediction model of boiler efficiency based on historical boiler efficiency, and a prediction model of environmental protection costs based on historical environmental protection costs. The integrated modeling module 22 is used to establish a nonlinear programming model based on the plant power consumption prediction model, boiler efficiency prediction model, and environmental cost prediction model. The prediction and solution module 23 is used to solve the nonlinear programming model based on the information of multiple coal types currently participating in the coal blending, and obtain the coal blending ratio.

[0053] Specifically, the preliminary modeling module 21 obtains a power consumption prediction model based on historical power consumption, a boiler efficiency prediction model based on historical boiler efficiency, and an environmental cost prediction model based on historical environmental costs. The comprehensive modeling module 22 establishes a nonlinear programming model based on the power consumption prediction model, boiler efficiency prediction model, and environmental cost prediction model. The prediction and solution module 23 solves the nonlinear programming model based on information about multiple coal types currently involved in coal blending to obtain the coal blending ratio. By using power consumption, boiler efficiency, and environmental costs from the unit power supply cost to construct a predictable model, and combining it with current coal type information, the optimal coal blending ratio is obtained. This does not require historical data to include the best current situation; the coal blending ratio can be predicted according to different needs.

[0054] The device also includes: The first modeling subunit is used to extract the test data of load, coal quality and weight into the furnace as features, extract the historical power consumption of the plant as a label, train the model and obtain the power consumption prediction model of the plant. The second modeling subunit is used to extract the test data of load, coal quality and weight into the furnace as features in sequence, use the inverse balance algorithm to calculate the boiler efficiency corresponding to each set of data, train the model and obtain the boiler efficiency prediction model. The third modeling subunit is used to obtain a limestone treatment cost prediction model based on historical limestone treatment costs, a urea treatment cost prediction model based on historical urea treatment costs, and a coal ash and slag treatment cost prediction model based on historical coal ash and slag treatment costs.

[0055] The acquisition module is used to acquire preset constraints. The constraint module is used to constrain the nonlinear programming model according to preset constraints.

[0056] Since the embodiments of the apparatus and the embodiments of the method correspond to each other, please refer to the description of the embodiments of the method for the embodiments of the apparatus, which will not be repeated here.

[0057] Figure 3 A structural diagram of another coal blending ratio prediction device provided in the embodiments of this application is shown below. Figure 3 As shown, the coal blending ratio prediction device includes: a memory 30 for storing computer programs; The processor 31 is used to execute a computer program to implement the steps of the method for obtaining user operation habit information as described in the above embodiment (coal blending ratio prediction method).

[0058] The coal blending ratio prediction device provided in this embodiment may include, but is not limited to, smartphones, tablets, laptops, or desktop computers.

[0059] The processor 31 may include one or more processing cores, such as a quad-core processor or an octa-core processor. The processor 31 may be implemented using at least one of the following hardware forms: Digital Signal Processor (DSP), Field-Programmable Gate Array (FPGA), or Programmable Logic Array (PLA). The processor 31 may also include a main processor and a coprocessor. The main processor, also known as the Central Processing Unit (CPU), is used to process data in the wake-up state; the coprocessor is a low-power processor used to process data in the standby state. In some embodiments, the processor 31 may integrate a Graphics Processing Unit (GPU), which is responsible for rendering and drawing the content to be displayed on the screen. In some embodiments, the processor 31 may also include an Artificial Intelligence (AI) processor, which handles computational operations related to machine learning.

[0060] The memory 30 may include one or more computer-readable storage media, which may be non-transitory. The memory 30 may also include high-speed random access memory and non-volatile memory, such as one or more disk storage devices or flash memory devices. In this embodiment, the memory 30 is used to store at least the following computer program 301, which, after being loaded and executed by the processor 31, is capable of implementing the relevant steps of the coal blending ratio prediction method disclosed in any of the foregoing embodiments. In addition, the resources stored in the memory 30 may also include an operating system 302 and data 303, and the storage method may be temporary or permanent storage. The operating system 302 may include Windows, Unix, Linux, etc. The data 303 may include, but is not limited to, the data involved in implementing the coal blending ratio prediction method.

[0061] In some embodiments, the coal blending ratio prediction device may further include a display screen 32, an input / output interface 33, a communication interface 34, a power supply 35, and a communication bus 36.

[0062] Those skilled in the art will understand that Figure 3The structure shown does not constitute a limitation on the coal blending ratio prediction device and may include more or fewer components than shown.

[0063] The coal blending ratio prediction device provided in this application includes a memory and a processor. When the processor executes the program stored in the memory, it can implement the following method: a coal blending ratio prediction method, which obtains a plant power consumption prediction model based on historical plant power consumption, a boiler efficiency prediction model based on historical boiler efficiency, and an environmental protection cost prediction model based on historical environmental protection costs; establishes a nonlinear programming model based on the plant power consumption prediction model, the boiler efficiency prediction model, and the environmental protection cost prediction model; and solves the nonlinear programming model based on information on multiple coal types currently involved in coal blending to obtain the coal blending ratio. It uses plant power consumption, boiler efficiency, and environmental protection costs from the unit power supply cost to construct a predictable model, and solves it in conjunction with current coal type information to obtain the optimal coal blending ratio. It does not require historical data to contain the best current situation and can predict the coal blending ratio according to different needs.

[0064] Finally, this application also provides an embodiment corresponding to a computer-readable storage medium. The computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps described in the above embodiment of the coal blending ratio prediction method.

[0065] It is understood that if the methods in the above embodiments are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and executes all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0066] The computer-readable storage medium provided in this embodiment stores a computer program. When the processor executes the program, it can implement the following method: a coal blending ratio prediction method, which obtains a plant power consumption prediction model based on historical plant power consumption, a boiler efficiency prediction model based on historical boiler efficiency, and an environmental protection cost prediction model based on historical environmental protection costs; establishes a nonlinear programming model based on the plant power consumption prediction model, the boiler efficiency prediction model, and the environmental protection cost prediction model; and solves the nonlinear programming model based on information on multiple coal types currently participating in coal blending to obtain the coal blending ratio. Using plant power consumption, boiler efficiency, and environmental protection costs from the unit power supply cost, a predictable model is constructed. Combined with current coal type information, the model is solved to obtain the optimal coal blending ratio. This method does not require historical data to contain the best current scenario and can predict the coal blending ratio according to different needs.

[0067] The coal blending ratio prediction method, apparatus, and medium provided in this application have been described in detail above. The various embodiments in the specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the apparatus disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple; relevant parts can be referred to in the method section. It should be noted that those skilled in the art can make several improvements and modifications to this application without departing from the principles of this application, and these improvements and modifications also fall within the protection scope of the claims of this application.

[0068] It should also be noted that, in this specification, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

Claims

1. A method for predicting coal blending ratios, characterized in that, include: Based on historical plant power consumption, a plant power consumption prediction model is obtained; based on historical boiler efficiency, a boiler efficiency prediction model is obtained; and based on historical environmental protection costs, an environmental protection cost prediction model is obtained. A nonlinear programming model is established based on the plant power consumption prediction model, the boiler efficiency prediction model, and the environmental protection cost prediction model. Based on the information of multiple coal types currently involved in coal blending, the nonlinear programming model is solved to obtain the coal blending ratio; The historical environmental costs include: historical limestone treatment costs, historical urea treatment costs, and historical coal ash and slag treatment costs. Correspondingly, the environmental cost prediction model derived from historical environmental costs includes: A limestone treatment cost prediction model was obtained based on historical limestone treatment costs, a urea treatment cost prediction model was obtained based on historical urea treatment costs, and a coal ash and slag treatment cost prediction model was obtained based on historical coal ash and slag treatment costs. The step of establishing a nonlinear programming model based on the plant power consumption prediction model, the boiler efficiency prediction model, and the environmental cost prediction model includes: A nonlinear programming model is established based on the first formula, the plant power consumption prediction model, the boiler efficiency prediction model, and the environmental cost prediction model. The first formula is: ； in, Cost per unit of electricity supply; Total cost; The amount of electricity supplied per unit time; For coal costs; The cost of limestone processing per unit time; The cost of urea treatment per unit time; The cost of treating the coal ash and slag per unit time; The amount of electricity generated per unit time; This refers to the amount of electricity used by the plant within a unit of time. , The blending ratio for each type of coal. Number each type of coal; The steps for obtaining the coal cost are as follows: The comprehensive calorific value of coal is obtained according to the second formula; The second formula is: ;in The calorific value of each type of coal; The comprehensive unit price is obtained according to the third formula; The third formula is: ;in The unit price for each type of coal; The coal cost is obtained according to the fourth formula; The fourth formula is: ； Where Q represents fuel consumption; For boiler efficiency, Electricity generated per unit time The required weight of coal.

2. The coal blending ratio prediction method according to claim 1, characterized in that, The plant power consumption prediction model, derived from historical plant power consumption, includes: The load, coal quality, and coal weight were extracted as features, and historical plant power consumption was extracted as labels. The model was then trained to obtain a plant power consumption prediction model. The boiler efficiency prediction model derived from historical boiler efficiencies includes: The load, coal quality, and coal weight are extracted sequentially as features. The boiler efficiency corresponding to each set of data is calculated using an inverse balance algorithm. The model is then trained to obtain a boiler efficiency prediction model.

3. The coal blending ratio prediction method according to claim 1, characterized in that, The process of establishing a nonlinear programming model based on the plant power consumption prediction model, the boiler efficiency prediction model, and the environmental cost prediction model further includes: Obtain the preset constraints; The nonlinear programming model is constrained according to the preset constraints.

4. The coal blending ratio prediction method according to claim 1, characterized in that, The steps for obtaining the limestone treatment cost, the urea treatment cost, and the coal ash and slag treatment cost are as follows: The urea treatment cost is obtained according to the fifth formula; The fifth formula is: ； in, This refers to the unit price of urea. This represents the total nitrogen content. This refers to the nitrogen content of each type of coal. The corrected slope for urea usage; The corrected intercept for urea usage; The limestone processing cost is obtained according to the sixth formula; The sixth formula is: ； in, This refers to the unit price of limestone. This refers to the total sulfur content. This refers to the sulfur content of each type of coal. The corrected slope for limestone usage; Correction intercept for limestone usage; The cost of coal ash and slag treatment is obtained according to the seventh formula; ； in, The unit price for processing coal ash and slag; Total ash content of coal; This refers to the ash content of each type of coal.

5. The coal blending ratio prediction method according to claim 3, characterized in that, The preset constraints include: the total coal blending ratio is 100%, the upper and lower limits of the blending ratio of different coals, the comprehensive calorific value, the comprehensive sulfur content limit, and the maximum coal feed rate per unit time.

6. A coal blending ratio prediction device, characterized in that, include: The preliminary modeling module is used to obtain a prediction model for plant power consumption based on historical plant power consumption, a prediction model for boiler efficiency based on historical boiler efficiency, and a prediction model for environmental protection costs based on historical environmental protection costs. The integrated modeling module is used to establish a nonlinear programming model based on the plant power consumption prediction model, the boiler efficiency prediction model, and the environmental cost prediction model. The prediction and solution module is used to solve the nonlinear programming model based on information about multiple coal types currently participating in coal blending, and to obtain the coal blending ratio. The historical environmental costs include: historical limestone treatment costs, historical urea treatment costs, and historical coal ash and slag treatment costs. Correspondingly, the environmental cost prediction model derived from historical environmental costs includes: A limestone treatment cost prediction model was obtained based on historical limestone treatment costs, a urea treatment cost prediction model was obtained based on historical urea treatment costs, and a coal ash and slag treatment cost prediction model was obtained based on historical coal ash and slag treatment costs. The step of establishing a nonlinear programming model based on the plant power consumption prediction model, the boiler efficiency prediction model, and the environmental cost prediction model includes: A nonlinear programming model is established based on the first formula, the plant power consumption prediction model, the boiler efficiency prediction model, and the environmental cost prediction model. The first formula is: ； in, Cost per unit of electricity supply; Total cost; The amount of electricity supplied per unit time; For coal costs; The cost of limestone processing per unit time; The cost of urea treatment per unit time; The cost of treating the coal ash and slag per unit time; The amount of electricity generated per unit time; This refers to the amount of electricity used by the plant within a unit of time. , The blending ratio for each type of coal. Number each type of coal; The steps for obtaining the coal cost are as follows: The comprehensive calorific value of coal is obtained according to the second formula; The second formula is: ;in The calorific value of each type of coal; The comprehensive unit price is obtained according to the third formula; The third formula is: ;in The unit price for each type of coal; The coal cost is obtained according to the fourth formula; The fourth formula is: ； Where Q represents fuel consumption; For boiler efficiency, Electricity generated per unit time The required weight of coal.

7. A coal blending ratio prediction device, characterized in that, include: Memory, used to store computer programs; A processor, configured to implement the steps of the coal blending ratio prediction method as described in any one of claims 1 to 5 when executing the computer program.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the coal blending ratio prediction method as described in any one of claims 1 to 5.

Images