Time-sharing coal blending combustion method, device and equipment for coal-fired power plant and storage medium

Abstract

The invention discloses a time-sharing coal blending combustion method, device and equipment for a coal-fired power plant and a storage medium, and relates to the technical field of coal blending control, and the method comprises the following steps: establishing a dynamic database containing coal reserves and coal quality parameters of the coal-fired power plant, and updating coal characteristic data in real time; dividing the whole day into a plurality of time periods according to a power grid dispatching instruction and historical load data, and setting a reference load range for each time period; and by taking the fire coal characteristic data and the reference load range as constraint conditions and taking the maximum fire coal profit as a target function, generating a fire coal blending combustion scheme of the coal mill in each time period. According to the method, coal quality parameters and inventory data are integrated in real time by constructing a dynamic database, time periods are intelligently divided and a load reference is set in combination with a power grid dispatching instruction, and a coal blending combustion scheme of each time period is generated by using a mathematical optimization algorithm; the problems of poor coal quality fluctuation adaptation, lagging load adjustment, high fuel cost, difficulty in emission control and the like of a traditional artificial experience method are effectively solved.

Description

Technical Field

[0001] The present application relates to the field of coal blending control technology, and more specifically, to a method, device, equipment and storage medium for time-sharing coal blending and combustion in a coal-fired power plant. Background Art

[0002] Faced with increasingly stringent regulations in the electricity spot market, traditional coal blending and combustion solutions are no longer able to keep pace. As coal resources become increasingly scarce and competition in the electricity spot market intensifies, power plants need to find ways to reduce their power generation costs. Power plants often need to blend low-priced, low-quality coal (such as high-sulfur, high-ash coal) to reduce costs. Coal blending and combustion is a crucial technical approach.

[0003] In the existing technology, the coal blending scheme is generally controlled by manual experience. A stable ratio can be designed according to the coal type, and uniform mixing can be achieved through mechanical stirring or pneumatic conveying systems. Alternatively, inferior coal can be mixed with main coal at the inlet of the pulverizer, and the proportion of coal entering the burner can be controlled by a coarse powder separator, or the combustion zone can be divided into an oxygen-rich main combustion zone and an oxygen-depleted reduction zone, and the oxygen concentration can be adjusted by flue gas recirculation.

[0004] However, traditional manual coal blending methods have significant limitations. Decisions rely on subjective judgment, making it difficult to adapt to coal quality fluctuations and load changes in real time. This leads to unstable combustion efficiency and increased heat loss. They are also economically unsustainable, failing to dynamically adapt to the characteristics of multiple coal types, resulting in high fuel costs. Equipment wear is exacerbated by the inability to precisely control the hardness differences between coal types, shortening maintenance cycles. Furthermore, operating standards are inconsistent, making experience transfer difficult, impacting operational safety and stability. This model no longer meets the requirements for efficient, low-carbon, and flexible operation of power plants. Intelligent technologies are urgently needed to achieve dynamic coal blending optimization. Summary of the Invention

[0005] In response to at least one defect or improvement need in the prior art, the present invention provides a method, device, equipment and storage medium for time-sharing coal blending and combustion in a coal-fired power plant, which is used to solve the problem that the method of implementing coal blending and combustion in the prior art relying on manual experience is difficult to adapt to coal quality fluctuations and load adjustments in real time, resulting in the combustion state deviating from the optimal operating condition, affecting efficiency and emission control, relying on trial and error adjustment to optimize fuel costs, excessive use of high-priced high-quality coal or underutilization of low-priced low-quality coal, and high comprehensive fuel consumption lead to high fuel costs.

[0006] To achieve the above objectives, according to a first aspect of the present invention, a method for time-sharing coal blending and combustion in a coal-fired power plant is provided, comprising:

[0007] Establish a dynamic database containing coal reserves and coal quality parameters for coal-fired power plants, and update coal characteristic data in real time;

[0008] According to the grid dispatch instructions and historical load data, the whole day is divided into multiple time periods, and the benchmark load range is set for each time period;

[0009] Taking the coal characteristic data and the benchmark load range as constraints and the maximum coal profit as the objective function, the coal blending plan for the pulverizer in each period is generated.

[0010] In one possible implementation, a dynamic database containing coal reserves and coal quality parameters of coal-fired power plants is established, and coal characteristic data is updated in real time, including:

[0011] Scan coal storage yards of different coal types in real time and update the coal reserves of each coal type according to the coal flow rate;

[0012] Sampling and testing of different coal types in each batch are carried out to obtain coal quality parameters, and associated labels are set for different coal types in each batch;

[0013] Clean and verify coal reserves and coal quality parameters, and update the dynamic database at a preset period.

[0014] In one possible implementation, based on grid dispatch instructions and historical load data, the entire day is divided into multiple time periods, and a benchmark load range is set for each time period. This also includes:

[0015] Pre-process the grid dispatch instructions and historical load data and extract key parameter data from them;

[0016] Clustering key parameter data using clustering algorithms to divide the day into multiple time periods, and label the load type of each time period;

[0017] The load upper and lower limits are calculated based on the load type of the time period and historical load data to obtain the benchmark load range for each time period.

[0018] In one possible implementation, preprocessing the grid dispatch instructions and historical load data and extracting key parameter data therefrom also includes:

[0019] Clean the grid dispatch instructions and historical load data, align the time series, and correct outliers;

[0020] The load change rate and peak-to-valley difference rate are calculated based on the revised grid dispatch instructions, historical load data and time series.

[0021] In one possible implementation, a coal blending plan for the pulverizer at each time period is generated with coal characteristic data and a reference load range as constraints and maximum coal profit as the objective function, and also includes:

[0022] Extract coal-fired economic parameters based on historical coal-fired power generation data and establish a coal-fired profit objective function;

[0023] Under the constraints, determine the coal blending ratio in each period when the coal profit objective function is maximized;

[0024] Based on the coal blending ratio and mill property parameters in each period, a coal blending plan for the mill is formulated for each period.

[0025] In a possible implementation, determining the coal blending ratio in each time period when the coal profit objective function is maximized under the constraints also includes:

[0026] Combining the constraints with the coal burning profit objective function, the coal blending ratios in several time periods are calculated when the coal burning profit objective function is maximized.

[0027] A coal blending ratio evaluation function is established to score the coal blending ratios in several time periods, and the coal blending ratios in each time period that meet the preset requirements are determined based on the scores.

[0028] In one possible implementation, a coal blending plan for a coal mill in each time period is formulated based on the coal blending ratio and coal mill attribute parameters in each time period, and further includes:

[0029] Calculate the coal demand for different types of coal in each period based on the coal blending ratio in each period;

[0030] According to the coal mill attribute parameters and the coal consumption demand of different coal types in each period, the coal blending plan for the coal mill in each period is formulated.

[0031] According to a second aspect of the present invention, there is also provided a time-sharing coal blending and combustion device for a coal-fired power plant, comprising:

[0032] A dynamic update module configured to establish a dynamic database containing coal reserves and coal quality parameters of a coal-fired power plant and update coal characteristic data in real time;

[0033] A load calculation module is configured to divide the entire day into multiple time periods based on grid dispatch instructions and historical load data, and set a benchmark load range for each time period;

[0034] The blending and burning plan formulation module is configured to generate a coal blending and burning plan for the coal mill in each time period based on the coal characteristic data and the benchmark load range as constraints and the maximum coal profit as the objective function.

[0035] According to the third aspect of the present invention, there is also provided a time-sharing coal blending and combustion device for a coal-fired power plant, which includes at least one processing unit and at least one storage unit, wherein the storage unit stores a computer program, and when the computer program is executed by the processing unit, the processing unit executes the steps of any one of the above-mentioned time-sharing coal blending and combustion methods for a coal-fired power plant.

[0036] According to the fourth aspect of the present invention, a storage medium is also provided, which stores a computer program that can be executed by the time-sharing coal blending and combustion equipment of a coal-fired power plant. When the computer program is run on the time-sharing coal blending and combustion equipment of a coal-fired power plant, the time-sharing coal blending and combustion equipment of the coal-fired power plant executes the steps of any of the above-mentioned time-sharing coal blending and combustion methods for a coal-fired power plant.

[0037] In general, the above technical solutions conceived by the present invention can achieve the following beneficial effects compared with the prior art:

[0038] The present invention provides a time-sharing coal blending method for coal-fired power plants. By building a dynamic database to integrate coal reserves and coal quality parameters, combining power grid dispatch instructions with historical load data to intelligently divide time periods and set a benchmark load range, the coal blending scheme for each time period is generated with coal profit maximization as the objective function, achieving dynamic matching of coal type characteristics, load demand and time period characteristics. By establishing an objective function for coal profit, the blending ratio of different coal types is adjusted, thereby improving the economic efficiency and operating efficiency of the power plant. Specifically, the real-time update capability of the dynamic database effectively responds to coal quality fluctuations and avoids the decline in combustion efficiency caused by sudden changes in coal type characteristics in the manual experience method; the combination of the time-sharing load benchmark and the objective function realizes differentiated control of fuel costs during peak and valley periods, precise input of high-priced high-quality coal during peak load periods and rational use of low-priced coal during valley periods, alleviating the high fuel cost problem in the traditional trial-and-error method, shifting decision-making from experience-driven to quantitative optimization, reducing the frequency of manual intervention, improving load response speed and boiler operating efficiency, and ultimately achieving the coordinated goals of reducing fuel costs, strengthening emission control and maximizing economic benefits. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0040] Figure 1 A schematic flow chart of an embodiment of the time-sharing coal blending and combustion method for a coal-fired power plant provided by the present invention;

[0041] Figure 2 The present invention provides Figure 1 A flow chart of an embodiment of step S101;

[0042] Figure 3 The present invention provides Figure 1 A flow chart of an embodiment of step S102;

[0043] Figure 4 The present invention provides Figure 1 A flow chart of an embodiment of step S103;

[0044] Figure 5 This is a structural schematic diagram of an embodiment of a time-sharing coal blending and combustion device for a coal-fired power plant provided by the present invention;

[0045] Figure 6 This is a structural diagram of the time-sharing coal blending and combustion equipment for a coal-fired power plant provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0046] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely for the purpose of explaining the present invention and are not intended to limit the present invention. In addition, the technical features involved in the various embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other.

[0047] The terms "first," "second," "third," and the like in the specification and claims of this application and the accompanying drawings are used to distinguish between different objects, not to describe a particular order. Furthermore, the terms "including," "having," and any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or apparatus comprising a series of steps or elements is not limited to the listed steps or elements, but may optionally include steps or elements not listed, or may optionally include other steps or elements inherent to the process, method, product, or apparatus.

[0048] The present invention provides a method, device, equipment and storage medium for time-sharing coal blending and combustion in a coal-fired power plant, which are described below respectively.

[0049] See also Figure 1 , Figure 1 The present invention provides a flow chart of an embodiment of a method for time-sharing coal blending and combustion in a coal-fired power plant. In a specific embodiment of the present invention, a method for time-sharing coal blending and combustion in a coal-fired power plant is disclosed, comprising:

[0050] S101. Establish a dynamic database containing coal reserves and coal quality parameters of coal-fired power plants, and update coal characteristic data in real time;

[0051] S102. Divide the entire day into multiple time periods based on grid dispatch instructions and historical load data, and set a benchmark load range for each time period;

[0052] S103. Using the coal characteristic data and the reference load range as constraints and the maximum coal profit as the objective function, generate a coal blending plan for the coal mill in each time period.

[0053] In the above example, coal yard automation equipment (such as conveyor belt scales and online coal quality testers) is integrated to collect key coal parameters such as calorific value, sulfur content, and moisture in real time. This data is then combined with historical operational data to build a dynamic database. This database not only tracks inventory levels in real time but also, through an abnormality warning mechanism, automatically triggers alerts when sulfur or ash content exceeds specified limits.

[0054] According to the grid dispatch instructions and historical load data, the whole day can be divided into three periods: peak, flat, and valley, and a flexible load benchmark range can be set for each period. As a preferred embodiment, during peak hours (such as 08:00-12:00), the load demand is high and the electricity price premium is obvious. The benchmark range is set to 2800-3000MW, and high calorific value (≥5500kcal / kg) and low sulfur (≤0.5%) coal are preferentially used to ensure instantaneous output; during valley hours (such as 22:00-06:00), the load demand is low and the electricity price discount is significant. The benchmark range is adjusted to 1200-1500MW, and low-priced lignite (calorific value 4000kcal / kg) is mixed in to reduce costs, while reserving 10% flexibility to cope with sudden fluctuations.

[0055] With the goal of maximizing coal-fired profits, a dynamic database and load benchmark are combined to generate blending plans for each time period. The objective function considers electricity prices, coal costs, and inventory losses, while the constraints are coal characteristics and the benchmark load range. For example, during peak hours, high-calorific-value coal is used to improve combustion efficiency to match high electricity prices, while low-priced coal is used during off-peak hours to reduce costs. This ensures combustion efficiency and equipment stability, avoiding the costly consequences of unplanned downtime.

[0056] Compared with the existing technology, the present embodiment provides a time-sharing coal blending method for coal-fired power plants. By building a dynamic database to integrate coal reserves and coal quality parameters, combining grid dispatch instructions with historical load data to intelligently divide time periods and set a benchmark load range, the present embodiment generates coal blending plans for each time period using coal profit maximization as the objective function. This achieves a dynamic matching of coal type characteristics, load demand, and time period characteristics. By establishing a coal profit objective function to adjust the blending ratio of different coal types, the economic efficiency and operating efficiency of the power plant are improved. Specifically, the real-time update capability of the dynamic database effectively responds to coal quality fluctuations and avoids the decline in combustion efficiency caused by sudden changes in coal type characteristics in the manual experience method. The combination of the time-sharing load benchmark and the objective function enables differentiated control of fuel costs during peak and valley periods, accurately investing high-priced, high-quality coal during peak load periods and rationally utilizing low-priced coal during valley periods. This alleviates the high fuel cost problem in the traditional trial-and-error method, shifts decision-making from experience-driven to quantitative optimization, reduces the frequency of manual intervention, improves load response speed and boiler operating efficiency, and ultimately achieves the coordinated goals of reducing fuel costs, strengthening emission control, and maximizing economic benefits.

[0057] See also Figure 2 , Figure 2 The present invention provides Figure 1 FIG. 1 is a flow chart of an embodiment of step S101 in FIG. 1 . In some embodiments of the present invention, a dynamic database including coal reserves and coal quality parameters of a coal-fired power plant is established, and coal characteristic data is updated in real time, further comprising:

[0058] S201, scanning coal storage yards of different coal types in real time, and updating the coal reserves of each coal type according to the coal flow rate;

[0059] S202: Sampling and testing different types of coal in each batch to obtain coal quality parameters, and setting associated tags for different types of coal in each batch;

[0060] S203: Clean and verify the coal reserves and coal quality parameters, and update the dynamic database at a preset period.

[0061] In the above example, a coal storage yard is monitored around the clock by integrating RFID tags, laser scanners, and a drone inspection system. Each storage yard for each coal type (e.g., bituminous coal, lignite, anthracite) is equipped with a lidar and weight sensor to collect real-time data on stockpile height, volume, and weight, automatically calculating the real-time reserves of each type of coal.

[0062] When each batch of coal enters the warehouse, it undergoes rapid multi-parameter testing using automated sampling equipment and online detectors. This testing covers each individual coal's calorific value (Q), volatile matter (V), ash content (A), moisture (W), sulfur content (S), ash melting point (ST), ash composition, and coal price (P). The test data is uploaded to the database in real time, and a unique associated tag is generated for each batch, including the coal source, test time, quality grade, and historical combustion performance data (such as combustion efficiency and coking tendency) to facilitate subsequent traceability and analysis. For example, the high-sulfur coal tag will automatically be associated with the desulfurization system parameters, providing constraints for the generation of blending solutions.

[0063] A rules engine filters out significant outliers (such as extreme values with a calorific value greater than 7000 kcal / kg or a sulfur content less than 0.1%). Regression models trained on historical data (such as random forests) are used to identify potential deviations and verify them. The cleaned data is then batch-updated to the database, and a data quality report is generated simultaneously. The dynamic update mechanism also supports historical data version rollback, facilitating comparative analysis of coal quality trends.

[0064] See also Figure 3 , Figure 3 The present invention provides Figure 1 In some embodiments of the present invention, the whole day is divided into multiple time periods according to the grid dispatch instruction and historical load data, and a reference load range is set for each time period, which also includes:

[0065] S301, pre-processing the power grid dispatching instructions and historical load data, and extracting key parameter data therefrom;

[0066] S302. Clustering the key parameter data using a clustering algorithm to divide the entire day into multiple time periods, and marking the load type of each time period;

[0067] S303: Calculate the load upper limit and load lower limit based on the load type of each time period and historical load data to obtain the reference load range for each time period.

[0068] In the above embodiment, the collected grid dispatch instructions and historical load data are cleaned to remove outliers, missing values, or duplicate data to ensure data accuracy and completeness. Considering the potential for dimensional inconsistencies in data from different sources or at different time points, data standardization is performed to enable all data to be compared and analyzed on the same scale. Key parameters crucial for time period segmentation and load forecasting, such as peak load, valley load, average load, and load change rate, are extracted from the cleaned and standardized data.

[0069] Based on the characteristics of the data and the requirements of the problem, select an appropriate clustering algorithm, such as K-means clustering, hierarchical clustering, or a density-based clustering algorithm (such as DBSCAN), to effectively group the key parameter data. Apply the selected clustering algorithm to cluster the key parameter data. Based on the clustering results, divide the entire day into multiple time periods, each representing a specific load pattern or demand characteristic. Based on the clustering results, assign a load type label to each time period, such as peak period, off-peak period, or off-peak period, to facilitate subsequent analysis and application.

[0070] For each defined time period, historical load data is collected, including maximum, minimum, average, and load fluctuation ranges. Based on these statistical analysis results and in conjunction with the safety and economic requirements of power system operation, the upper load limit (i.e., the maximum load value that can be reached within that period) and lower load limit (i.e., the minimum load value that can be reached within that period) for each time period are calculated. Using these upper and lower load limits as boundaries, a baseline load range is determined for each time period, which serves as a reference for power system scheduling, planning, and operation and maintenance.

[0071] In some embodiments of the present invention, preprocessing the grid dispatch instructions and historical load data and extracting key parameter data therefrom further includes:

[0072] Clean the grid dispatch instructions and historical load data, align the time series, and correct outliers;

[0073] The load change rate and peak-to-valley difference rate are calculated based on the revised grid dispatch instructions, historical load data and time series.

[0074] In the above embodiment, the grid dispatch instructions and historical load data are checked to remove invalid or missing data caused by equipment failure, data transmission errors, etc. Statistical methods (such as box plots, Z-score, etc.) or machine learning algorithms (such as isolation forests) are used to detect outliers in the data and correct or delete them according to the actual situation. Outliers may include abnormally high load values, sudden changes in dispatch instructions, etc. For short-term data missing due to certain reasons (such as equipment maintenance), appropriate data interpolation methods (such as linear interpolation, nearest neighbor interpolation, etc.) are used to fill in the gaps.

[0075] Ensure that the timestamps of grid dispatch instructions and historical load data match exactly, aligning the time series for subsequent time series analysis. Convert grid dispatch instructions and historical load data to a unified numerical type to facilitate subsequent mathematical operations and model training, ensuring that all data is measured in consistent units to avoid calculation errors caused by different units.

[0076] The load change rate refers to the degree of change in load values between two consecutive time points, usually expressed as a percentage. For each time point t, the load change rate is calculated relative to the previous time point t-1. The load change rate formula is: Load Change Rate = (Load Value (t) - Load Value (t-1)) / Load Value (t-1) * 100%. The load change rate reflects the dynamic characteristics of power system load and is important for predicting future load trends and assessing system stability.

[0077] The peak-to-valley ratio is the ratio of the difference between the highest and lowest loads in a day to the highest load, often expressed as a percentage. For daily load data, the highest load value (peak) and the lowest load value (valley) are found and the peak-to-valley ratio is calculated using the formula: Peak-to-valley ratio = (peak value - valley value) / peak value * 100%. The peak-to-valley ratio reflects the degree of load fluctuation in the power system and is valuable for formulating scheduling strategies and optimizing resource allocation.

[0078] See also Figure 4 , Figure 4 The present invention provides Figure 1 The flowchart of an embodiment of step S103 in FIG. 1 is a flow chart of an embodiment of step S103. In some embodiments of the present invention, the coal blending scheme for the pulverizer in each time period is generated with the coal characteristic data and the reference load range as constraints and the maximum coal profit as the objective function, further comprising:

[0079] S401, extracting coal-fired economic parameters based on historical coal-fired power generation data and establishing a coal-fired profit objective function;

[0080] S402, determining the coal blending ratio in each time period when the coal profit objective function is maximized under the constraint conditions;

[0081] S403. Formulate a coal blending plan for the coal mill in each time period based on the coal blending ratio and coal mill property parameters in each time period.

[0082] In the above example, coal economic parameters are extracted from historical coal-fired power generation data and analyzed to determine the extent and direction of their impact on coal profits. For example, coal with a high calorific value can improve power generation efficiency, but this may also result in higher procurement costs. Based on the analysis of coal economic parameters, a coal profit objective function is established. This function comprehensively considers factors such as coal procurement costs and power generation revenue, and is solved with the goal of maximizing coal profits.

[0083] Based on coal characteristics and the benchmark load range, set constraints for coal blending. Select an appropriate optimization algorithm, such as linear programming, nonlinear programming, or genetic algorithm, to maximize the coal profit objective function within these constraints. Apply this optimization algorithm to calculate the coal blending ratio for each time period, maximizing the coal profit objective function while satisfying the constraints.

[0084] As a preferred embodiment, the constraints in the present invention are:

[0085] Single coal ratio: ΣX i =1,i=1,2,…,n,X i ≥0;

[0086] Calorific value: Q = f Q (X i , Q i )≥Q 下界 ;

[0087] Volatile matter: V = f V (X i , V i )≥V 下界 ;

[0088] Ash content: A = f A (X i , A i )≤A 上界 ;

[0089] Water content: W = f M (X i , M i )≤W 上界 ;

[0090] Sulfur content: S = f S (X i , S i )≤S 上界 ;

[0091] Ash melting point: ST ≥ ST 下界 ;

[0092] Among them, X i It represents the proportion of the i-th type of coal, and f() is the weighted function corresponding to each parameter.

[0093] Analyze the coal mill's attribute parameters, including its type, processing capacity, coal grinding efficiency, and coal grinding fineness. These parameters will affect the mill's adaptability to different coals and the blending effect. Based on the coal blending ratio and coal mill attribute parameters for each time period, formulate coal blending plans for each time period. Define the coal mill's operating parameters (such as mill speed, coal feed rate, etc.) and coal blending ratio for each time period to ensure sufficient coal combustion and stable mill operation. Verify and optimize the formulated blending plan. Based on actual operating data feedback, adjust the mill's operating parameters and coal blending ratio to improve coal combustion efficiency and mill operation stability.

[0094] In some embodiments of the present invention, determining the coal blending ratio in each time period when the coal profit objective function is maximized under the constraints further includes:

[0095] Combining the constraints with the coal burning profit objective function, the coal blending ratios in several time periods are calculated when the coal burning profit objective function is maximized.

[0096] A coal blending ratio evaluation function is established to score the coal blending ratios in several time periods, and the coal blending ratios in each time period that meet the preset requirements are determined based on the scores.

[0097] In the above embodiment, the electricity sales revenue is calculated as follows:

[0098]

[0099] Where p is the time-of-use electricity price and M is the time-of-use electricity consumption.

[0100] The coal cost forecast adopts the coal consumption fitting calculation scheme to calculate the fuel cost. The detailed scheme is as follows: collect the load and coal consumption of the unit under the historical conditions of mixed coal burning, and obtain the coal consumption curves of different coal types under different loads; in addition, the calorific value can be used as the characteristic parameter instead of the coal type to obtain the coal consumption curve of the unit under the conditions of different calorific values of mixed coal types and loads, that is, c=f(Q net , l); thus, the fuel cost under different coal blending schemes for the next day is obtained, which is calculated as follows:

[0101]

[0102] Among them A i The price of coal for mixing and burning in the furnace is c i is the average coal consumption in the current period, which can be calculated by combining the above method with the historical operating parameters of the unit; i is the average load of the current period, i.e. i =M i / 1h; t is in hours (h), which is the time period. The profit P is calculated as follows:

[0103]

[0104] When designing an evaluation function for coal blending ratio, it is necessary to comprehensively consider the impact of coal blending ratio on multiple aspects, including coal profit, combustion efficiency, environmental performance, and mill operation stability. The evaluation function can be constructed using methods such as weighted summation, fuzzy evaluation, and the analytic hierarchy process to ensure comprehensiveness and accuracy.

[0105] Each coal blending ratio scheme is substituted into the evaluation function to calculate its comprehensive score. Based on the comprehensive score, a coal blending ratio scheme that meets preset requirements is selected. Preset requirements may include coal profit reaching or exceeding a certain threshold, and indicators such as combustion efficiency and environmental performance meeting industry or enterprise standards. The optimal scheme is further analyzed and optimized, and the coal blending ratio is fine-tuned based on factors such as coal supply stability and mill maintenance cycle. At the same time, the coal blending scheme is dynamically adjusted based on actual operating data and feedback to ensure its effectiveness and adaptability.

[0106] In some embodiments of the present invention, formulating a coal blending plan for a coal mill in each time period based on the coal blending ratio and coal mill property parameters in each time period further includes:

[0107] Calculate the coal demand for different types of coal in each period based on the coal blending ratio in each period;

[0108] According to the coal mill attribute parameters and the coal consumption demand of different coal types in each period, the coal blending plan for the coal mill in each period is formulated.

[0109] In the above embodiment, the coal blending ratio set for each time period is combined with the total coal demand for that time period to split the coal consumption of different types proportionally. For example, if the total demand for a certain time period is 896 tons (peak), and the ratio of coal types A / B / C is 70%:20%:10%, then coal type 1 requires 627.2 tons, coal type 2 requires 179.2 tons, and coal type 3 requires 89.6 tons. The following factors need to be considered during the calculation:

[0110] Dynamic inventory matching: Real-time query of the available quantity of coal types in the dynamic database. If the inventory of a certain coal type is insufficient (for example, only 100 tons of coal type 2 are left), the proportion of other coal types will be automatically adjusted proportionally (for example, coal type 2 is reduced to 15%, and C is increased to 15%), and a replenishment warning will be triggered.

[0111] Transportation and loss correction: For long-distance transportation of coal, the transportation loss rate (such as 2%-5%) is introduced to calculate the actual purchase quantity required (for example, the purchase quantity of coal type 1 is 627.2 / (1-3%)≈646 tons).

[0112] Calorific value decay compensation: For coal types that have been stored for a long time (such as lignite stored for more than 30 days), the blending ratio is dynamically adjusted according to the calorific value decay curve (such as 1% decay per month) to ensure that the calorific value of the mixed coal meets the load requirements.

[0113] Based on the above calculation results, the coal mill combined operation strategy is formulated:

[0114] Load response configuration: During peak hours, the pulverizer suitable for coal type 1 is started first, using a "coal type 1 (70%) + coal type 2 (30%)" blended combustion mode to ensure that the pulverized coal fineness R90 is ≤ 18%, thereby improving the boiler's thermal response speed.

[0115] Sulfur balance configuration: When the blending rate of coal type 3 exceeds 20%, the coal mill equipped with a dynamic classifier is activated, and the coal fineness is controlled to R90 = 22-25% by adjusting the angle of the deflection baffle to reduce the combustion rate of high-sulfur coal;

[0116] Dynamic compensation mechanism: When a coal mill suddenly fails, the coal blending ratio of adjacent coal mills is quickly redistributed (for example, the coal type 2 of the failed mill is distributed to the remaining coal mills) to maintain the stability of the total calorific value.

[0117] In order to better implement the time-sharing coal blending method for coal-fired power plants in the embodiment of the present invention, based on the time-sharing coal blending method for coal-fired power plants, please refer to Figure 5 , Figure 5 This is a schematic structural diagram of an embodiment of a time-sharing coal blending and combustion device for a coal-fired power plant provided by the present invention. The embodiment of the present invention provides a time-sharing coal blending and combustion device 500 for a coal-fired power plant, comprising:

[0118] A dynamic update module 510 is configured to establish a dynamic database containing coal reserves and coal quality parameters of a coal-fired power plant and update coal characteristic data in real time;

[0119] The load calculation module 520 is configured to divide the entire day into multiple time periods based on the grid dispatch instructions and historical load data, and set a reference load range for each time period;

[0120] The blending scheme formulation module 530 is configured to generate a coal blending scheme for the coal mill in each time period with the coal characteristic data and the reference load range as constraints and the maximum coal profit as the objective function.

[0121] It should be noted here that the device 500 provided in the above embodiment can implement the technical solutions described in the above method embodiments. The specific implementation principles of the above modules or units can be found in the corresponding contents in the above method embodiments, which will not be repeated here.

[0122] See also Figure 6 , Figure 6A schematic diagram of the structure of a time-sharing coal blending and combustion device for a coal-fired power plant, provided in an embodiment of the present invention. Based on the above-described method for time-sharing coal blending and combustion in a coal-fired power plant, the present invention also provides a corresponding time-sharing coal blending and combustion device for a coal-fired power plant. The time-sharing coal blending and combustion device for a coal-fired power plant can be a computing device such as a mobile terminal, desktop computer, notebook, PDA, or server. The time-sharing coal blending and combustion device 600 for a coal-fired power plant includes a processor 610, a memory 620, and a display 630. Figure 6 Only some components of the time-sharing coal blending and combustion equipment of a coal-fired power plant are shown, but it should be understood that it is not required to implement all the shown components, and more or fewer components may be implemented instead.

[0123] In some embodiments, the memory 620 can be an internal storage unit of the coal-fired power plant time-sharing coal blending and combustion equipment 600, such as a hard drive or memory of the coal-fired power plant time-sharing coal blending and combustion equipment 600. In other embodiments, the memory 620 can also be an external storage device of the coal-fired power plant time-sharing coal blending and combustion equipment 600, such as a plug-in hard drive, a smart media card (SMC), a secure digital (SD) card, a flash memory card, etc. equipped on the coal-fired power plant time-sharing coal blending and combustion equipment 600. Furthermore, the memory 620 can also include both the internal storage unit of the coal-fired power plant time-sharing coal blending and combustion equipment 600 and an external storage device. The memory 620 is used to store application software and various data installed in the coal-fired power plant time-sharing coal blending and combustion equipment 600, such as the program code for installing the coal-fired power plant time-sharing coal blending and combustion equipment 600. The memory 620 can also be used to temporarily store data that has been output or is about to be output. In one embodiment, a time-sharing coal blending and combustion program 640 for a coal-fired power plant is stored in the memory 620. The time-sharing coal blending and combustion program 640 for a coal-fired power plant can be executed by the processor 610, thereby realizing the time-sharing coal blending and combustion method for a coal-fired power plant in each embodiment of the present application.

[0124] In some embodiments, the processor 610 can be a central processing unit (CPU), a microprocessor or other data processing chip, used to run the program code or process data stored in the memory 620, such as executing the time-sharing coal blending method in a coal-fired power plant.

[0125] In some embodiments, display 630 can be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen. Display 630 is used to display information about the coal-fired power plant time-sharing coal blending and combustion equipment 600 and to display a visual user interface. Components 610-630 of the coal-fired power plant time-sharing coal blending and combustion equipment 600 communicate with each other via a system bus.

[0126] In one embodiment, when the processor 610 executes the coal-fired power plant time-sharing coal blending and combustion program 640 in the memory 620 , the steps in the above method for coal-fired power plant time-sharing coal blending and combustion are implemented.

[0127] This embodiment further provides a computer-readable storage medium storing a time-sharing coal blending and combustion program for a coal-fired power plant. When the time-sharing coal blending and combustion program for a coal-fired power plant is executed by a processor, the following steps are implemented:

[0128] Establish a dynamic database containing coal reserves and coal quality parameters for coal-fired power plants, and update coal characteristic data in real time;

[0129] According to the grid dispatch instructions and historical load data, the whole day is divided into multiple time periods, and the benchmark load range is set for each time period;

[0130] Taking the coal characteristic data and the benchmark load range as constraints and the maximum coal profit as the objective function, the coal blending plan for the pulverizer in each period is generated.

[0131] In summary, the present invention provides a method for time-sharing coal blending and burning in a coal-fired power plant. By building a dynamic database to integrate coal reserves and coal quality parameters, combining power grid dispatching instructions with historical load data to intelligently divide time periods and set a benchmark load range, the coal blending scheme for each time period is generated with coal profit maximization as the objective function, realizing the dynamic matching of coal type characteristics, load demand and time period characteristics, and adjusting the blending ratio of different coal types by establishing the objective function of coal profit, thereby improving the economic efficiency and operating efficiency of the power plant. Specifically, the real-time update capability of the dynamic database effectively responds to coal quality fluctuations and avoids the decrease in combustion efficiency caused by sudden changes in coal type characteristics in the manual experience method; the combination of the time-based load benchmark and the objective function realizes the differentiated control of fuel costs in peak and valley periods, the precise input of high-priced high-quality coal during peak load periods and the rational use of low-priced coal during valley periods, alleviating the problem of high fuel costs in the traditional trial and error method, shifting decision-making from experience-driven to quantitative optimization, reducing the frequency of manual intervention, improving load response speed and boiler operating efficiency, and ultimately achieving the coordinated goals of reducing fuel costs, strengthening emission control and maximizing economic benefits.

[0132] The present application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the above method. The computer-readable storage medium may include, but is not limited to, any type of disk, including a floppy disk, an optical disk, a DVD, a CD-ROM, a microdrive, a magneto-optical disk, a ROM, a RAM, an EPROM, an EEPROM, a DRAM, a VRAM, a flash memory device, a magnetic card or an optical card, a nanosystem (including a molecular memory IC), or any type of medium or device suitable for storing instructions and / or data.

[0133] It should be noted that for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that this application is not limited by the order of the actions described, because according to this application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by this application.

[0134] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0135] In the several embodiments provided in this application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some service interface, and the indirect coupling or communication connection of the device or unit can be electrical or other forms.

[0136] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0137] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0138] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application is essentially 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, and the computer software product is stored in a memory, including a number of instructions for enabling a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned memory includes: various media that can store program codes, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk.

[0139] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable memory, which may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0140] The above is only an exemplary embodiment of the present disclosure and cannot be used to limit the scope of the present disclosure. That is, any equivalent changes and modifications made according to the teachings of the present disclosure are still within the scope of the present disclosure. After considering the specification and practicing the disclosure herein, those skilled in the art will easily think of the implementation scheme of the present disclosure. This application is intended to cover any variation, use or adaptation of the present disclosure, which follows the general principles of the present disclosure and includes common knowledge or customary technical means in the art that are not recorded in the present disclosure. The description and examples are to be regarded as exemplary only, and the scope and spirit of the present disclosure are defined by the claims.

[0141] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0142] It will be easily understood by those skilled in the art that the above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for time-sharing coal blending and combustion in a coal-fired power plant, characterized in that: include: Establish a dynamic database containing coal reserves and coal quality parameters for coal-fired power plants, and update coal characteristic data in real time; According to the grid dispatch instructions and historical load data, the whole day is divided into multiple time periods, and the benchmark load range is set for each time period; The coal blending scheme for the pulverizer in each time period is generated with the coal characteristic data and the reference load range as constraints and the maximum coal profit as the objective function.

2. The method for time-sharing coal blending and combustion in a coal-fired power plant according to claim 1, characterized in that: The establishment of a dynamic database containing coal reserves and coal quality parameters of a coal-fired power plant and updating coal characteristic data in real time also includes: Scan coal storage yards of different coal types in real time and update the coal reserves of each type of coal according to the coal flow rate; Sampling and testing of different coal types in each batch are carried out to obtain coal quality parameters, and associated labels are set for different coal types in each batch; The coal reserves and the coal quality parameters are cleaned and verified, and a dynamic database is updated at a preset period.

3. The method for time-sharing coal blending and combustion in a coal-fired power plant according to claim 1, characterized in that: The method of dividing the whole day into multiple time periods according to the grid dispatch instructions and historical load data and setting a benchmark load range for each time period also includes: Preprocessing the power grid dispatching instructions and the historical load data, and extracting key parameter data therefrom; Clustering the key parameter data using a clustering algorithm to divide the entire day into multiple time periods, and marking the load type of each time period; The load upper limit and the load lower limit are calculated based on the load type of the time period and the historical load data to obtain a reference load range for each time period.

4. The method for time-sharing coal blending and combustion in a coal-fired power plant according to claim 3, characterized in that: The preprocessing of the power grid dispatching instruction and the historical load data and extracting key parameter data therefrom further includes: Performing data cleaning on the power grid dispatch instructions and the historical load data, aligning time series and correcting outliers; The load change rate and peak-to-valley difference rate are calculated based on the revised grid dispatch instructions, historical load data and time series.

5. The method for time-sharing coal blending and combustion in a coal-fired power plant according to claim 1, characterized in that: The method of generating a coal blending scheme for a coal mill in each time period based on the coal characteristic data and the reference load range as constraints and the maximum coal profit as an objective function further includes: Extract coal-fired economic parameters based on historical coal-fired power generation data and establish a coal-fired profit objective function; Determine the coal blending ratio in each time period when the coal profit objective function is maximized under the constraint conditions; A coal blending plan for the coal mill in each time period is formulated based on the coal blending ratio and coal mill property parameters in each time period.

6. The method for time-sharing coal blending and combustion in a coal-fired power plant according to claim 5, characterized in that: The step of determining the coal blending ratio in each time period when the coal profit objective function is maximized under the constraint conditions further includes: Combining the constraint conditions with the coal burning profit objective function, calculating the coal blending ratios for a plurality of time periods when the coal burning profit objective function is maximized; A coal blending ratio evaluation function is established to score the coal blending ratios in a number of time periods, and the coal blending ratio in each time period that meets the preset requirements is determined based on the scores.

7. The method for time-sharing coal blending and combustion in a coal-fired power plant according to claim 5, characterized in that: The method of formulating a coal blending plan for the coal mill for each time period based on the coal blending ratio and coal mill property parameters for each time period further includes: Calculating the coal demand for different types of coal in each period based on the coal blending ratio in each period; A coal blending plan for the coal mill in each time period is formulated according to the coal mill property parameters and the coal burning quantity requirements of different coal types in each time period.

8. A time-sharing coal blending and combustion device for a coal-fired power plant, characterized in that: include: A dynamic update module configured to establish a dynamic database containing coal reserves and coal quality parameters of a coal-fired power plant and update coal characteristic data in real time; A load calculation module is configured to divide the entire day into multiple time periods based on grid dispatch instructions and historical load data, and set a benchmark load range for each time period; The blending and burning scheme formulation module is configured to generate a coal blending and burning scheme for the coal mill in each time period with the coal characteristic data and the reference load range as constraints and the maximum coal profit as the objective function.

9. A time-sharing coal blending and combustion equipment for a coal-fired power plant, characterized in that: The method comprises at least one processing unit and at least one storage unit, wherein the storage unit stores a computer program. When the computer program is executed by the processing unit, the processing unit executes the steps of the method for time-sharing coal blending and combustion in a coal-fired power plant as claimed in any one of claims 1 to 7.

10. A storage medium, characterized in that: It stores a computer program that can be executed by the time-sharing coal blending and combustion equipment of a coal-fired power plant. When the computer program is run on the time-sharing coal blending and combustion equipment of a coal-fired power plant, the time-sharing coal blending and combustion equipment of the coal-fired power plant executes the steps of the time-sharing coal blending and combustion method of a coal-fired power plant according to any one of claims 1 to 7.

Images