Thermal power plant boiler dynamic coal blending management system and method based on cloud platform

Abstract

The invention provides a thermal power plant boiler dynamic coal blending management system and method based on a cloud platform, and the system comprises a data collection layer which is used for obtaining multi-source data; the cloud platform processing layer comprises a constraint generation module and an optimization decision module, the constraint generation module is used for constructing an optimization constraint condition according to the multi-source data, the optimization decision module is used for determining an optimal coal blending scheme according to the optimization constraint condition and a preset optimization target, and the optimal coal blending scheme at least comprises the blending combustion proportion of each coal type in the total coal feeding amount; and the execution control layer is used for generating a control instruction of the coal feeder according to the optimal coal blending scheme. According to the method, the multi-source data and the intelligent algorithm are integrated through the cloud platform, the constraint condition of actual operation is considered, the blending combustion proportion of each coal type in the total coal feeding amount is determined, real-time dynamic optimization of the coal blending process of the thermal power plant is achieved, the preset optimization target is met, the safety, reliability and response rate of system operation are greatly improved, and the coal blending efficiency of the thermal power plant is improved. Different operation requirements of a thermal power plant are met.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of thermal power plant fuel management, in particular to a cloud platform-based dynamic coal blending management system and method for thermal power plant boilers. BACKGROUND

[0002] Thermal power generation still plays an important role in China's energy structure, and coal-fired costs are the main component of thermal power plant operating costs. Traditional coal blending and combustion management relies heavily on human experience, and usually a static coal blending scheme is formulated based on recent coal yard inventory, incoming coal plans, and rough boiler operating parameters. This approach has significant drawbacks: first, it cannot respond in real time to dynamic changes in power grid load, coal market prices, and boiler operating conditions, making it difficult to maximize economic benefits; second, it lacks precise quantitative analysis of the complex coupling relationship between coal quality characteristics (such as moisture, sulfur content, and calorific value) and boiler combustion efficiency, environmental emissions, which can lead to unstable combustion, reduced efficiency, or excessive pollution; third, when encountering special conditions, adjustments relying on human experience often lag, which can cause coal feeding system blockage, boiler tail flue low-temperature corrosion, and other equipment safety issues. SUMMARY

[0003] The purpose of the embodiments of the present disclosure is to provide a cloud platform-based dynamic coal blending management system and method for thermal power plant boilers to solve the problems in the prior art.

[0004] The embodiments of the present disclosure adopt the following technical solutions: a cloud platform-based dynamic coal blending management system for thermal power plant boilers, comprising: a data acquisition layer for acquiring multi-source data from different management subjects of the thermal power plant; a cloud platform processing layer comprising a constraint generation module and an optimization decision module, the constraint generation module being configured to construct optimization constraint conditions based on the multi-source data, and the optimization decision module being configured to determine an optimal coal blending scheme based on the optimization constraint conditions and a preset optimization target, the optimal coal blending scheme at least including: a blending ratio of each coal type in the total coal supply; and an execution control layer configured to generate control instructions for coal feeders at storage points of the coal types based on the optimal coal blending scheme.

[0005] In some embodiments, the multi-source data includes: the price of incoming coal for each coal type, the quantity of incoming coal for each coal type, the coal inventory of each storage point, the daily unloading quantity of each storage point, the real-time coal supply quantity of each coal feeder, the real-time operating parameters of the boiler, and the real-time power supply demand quantity of the power grid.

[0006] In some embodiments, the optimization constraints at least include: a total coal supply constraint, a boiler load constraint, an environmental protection constraint, and a coal inventory constraint; wherein the total coal supply constraint includes that the total coal supply meets the real-time power supply demand of the power grid; the boiler load constraint includes that the real-time operation parameters of the boiler are within a safe range; the environmental protection constraint includes that the sum of the pollutant emission concentrations of each coal type is less than or equal to a concentration threshold; and the coal inventory constraint includes that the consumption of each coal type cannot exceed the current available inventory.

[0007] In some embodiments, the multi-source data further includes: a water content of each coal type, an environmental humidity, and a moisture content of the coal to be mixed; and the constraint generation module is further configured to determine whether a high-humidity environment exists according to the environmental humidity or the moisture content of the coal to be mixed, and construct a high-humidity environment adaptive constraint in a case where it is determined that the high-humidity environment exists; and the high-humidity environment adaptive constraint includes that the sum of the water contents of all coal types is less than a safe moisture threshold, and the safe moisture threshold is inversely proportional to the environmental humidity.

[0008] In some embodiments, the multi-source data further includes: an environmental temperature, a concentration of a current exhaust flue gas, ; and the constraint generation module is further configured to calculate an acid dew point temperature according to the concentration of the current exhaust flue gas, , and determine whether a low-temperature environment exists according to the environmental temperature and the acid dew point temperature, and construct a low-temperature environment adaptive constraint in a case where it is determined that the low-temperature environment exists; and the low-temperature environment adaptive constraint includes that the exhaust gas temperature after all coal types are mixed and combusted is greater than or equal to a minimum exhaust gas temperature, and the minimum exhaust gas temperature is inversely proportional to the environmental temperature.

[0009] In some embodiments, the optimization decision module is specifically configured to: take a lowest power generation cost or a highest comprehensive benefit as the preset optimization target; construct an optimization model according to the optimization constraints and the preset optimization target, wherein a decision variable of the optimization model is a blending ratio of each coal type in the total coal supply; and calculate an optimal solution of the decision variable in the optimization model by a preset optimization algorithm, as the optimal coal blending scheme.

[0010] In some embodiments, the power generation cost is represented based on the following formula:

[0011] wherein, represents the power generation cost, represents a coal type, represents a coal type number, represents a coal type number, represents a coal type, represents a coal type, represents a coal type, The blending ratio of each coal type in the total coal supply For the first The calorific value of each type of coal Indicates boiler combustion efficiency; The overall benefits are expressed based on the following formula:

[0012] in, Indicates comprehensive benefits, Indicates the grid connection price. This indicates the real-time power supply demand of the power grid. Indicates the first The cost of penalties for exceeding emission standards for various pollutants Indicates the first The emission concentration of various pollutants.

[0013] In some embodiments, the coal inventory at each storage point is determined based on a three-dimensional model of the coal pile at the storage point using a drone or laser scanning device.

[0014] In some embodiments, the execution control layer is specifically used to: determine the target coal feeder to be started based on the optimal coal blending scheme, the equipment health status of each coal feeder, and the operating efficiency of the coal feeder; determine the coal feeding rate of the target coal feeder based on the blending ratio; and generate control commands based on the target coal feeder and the coal feeding rate of the target coal feeder.

[0015] This disclosure also provides a cloud-based method for dynamic coal blending management of boilers in thermal power plants, comprising: acquiring multi-source data from different management entities of the thermal power plant; constructing optimization constraints based on the multi-source data; determining an optimal coal blending scheme based on the optimization constraints and a preset optimization objective, wherein the optimal coal blending scheme includes at least: the blending ratio of each coal type in the total coal feed; and generating control instructions for the coal feeder at the storage point where the coal type is located based on the optimal coal blending scheme.

[0016] The beneficial effects of this disclosure are as follows: by integrating multi-source data and intelligent algorithms through a cloud platform and considering the constraints of actual operation, the blending ratio of each type of coal in the total coal feed is determined, thereby realizing real-time dynamic optimization of the coal blending process in thermal power plants to meet preset optimization goals, greatly enhancing the safety, reliability and response rate of system operation, and meeting the different operating needs of thermal power plants. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in one or more embodiments of this specification or in the prior art, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments recorded in this specification. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is a schematic diagram of the architecture of the cloud platform-based dynamic coal distribution management system for thermal power plant boilers in the first embodiment of this disclosure. Figure 2 This is a schematic diagram of the cloud platform processing layer in the first embodiment of this disclosure; Figure 3 This is a flowchart of a cloud-based dynamic coal allocation management method for thermal power plant boilers, as described in the second embodiment of this disclosure. Detailed Implementation

[0019] To enable those skilled in the art to better understand the technical solutions in one or more embodiments of this specification, the technical solutions in one or more embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this specification, and not all of the embodiments. Based on one or more embodiments of this specification, all other embodiments obtained by those skilled in the art without creative effort should fall within the protection scope of this document.

[0020] To address the problems existing in the prior art, the first embodiment of this disclosure provides a cloud-based dynamic coal distribution management system for thermal power plant boilers, the architecture of which is shown in the schematic diagram below. Figure 1 As shown, it mainly includes: a data acquisition layer 10, used to acquire multi-source data from different management entities of the thermal power plant; a cloud platform processing layer 20, including a constraint generation module and an optimization decision module. The constraint generation module is used to construct optimization constraints based on multi-source data, and the optimization decision module is used to determine the optimal coal blending scheme based on the optimization constraints and preset optimization objectives. The optimal coal blending scheme includes at least the blending ratio of each coal type in the total coal feed; and an execution control layer 30, used to generate control instructions for the coal feeder at the storage point where the coal type is located based on the optimal coal blending scheme.

[0021] The multi-source data in this embodiment includes at least the following parameters: coal price for each type of coal, coal quantity for each type of coal, coal inventory at each storage point, daily coal unloading volume at each storage point, real-time coal feeding volume for each coal feeder, real-time boiler operating parameters, and real-time power supply demand from the power grid. This data can be collected in real-time by sensors and data interfaces at locations such as the coal yard, unloading point, coal feeder, and boiler. These sensors or data structures include, but are not limited to, FID (Fiber Optic Identifier), weight sensors, flow meters, and temperature / pressure sensors. This multi-source heterogeneous data can undergo preprocessing steps such as raw data cleaning, alignment, and standardization before being uploaded to the cloud platform processing layer 20 via an industrial IoT gateway. In some embodiments, the coal inventory at each storage point can also be determined by three-dimensional modeling of the coal pile at the storage point using a drone or laser scanning equipment.

[0022] The cloud platform processing layer 20 can adopt a microservice architecture, modularizing functions such as data storage, constraint generation, and optimization decision-making to form a constraint generation module 21 and an optimization decision-making module 22. It may further include a data storage module 23, such as... Figure 2 As shown. Specifically, the constraint generation module 21 is mainly used to generate multiple constraints for the constraint optimization decision-making process based on actual operational needs, so as to ensure that the obtained optimal coal blending scheme is safe and feasible, and at the same time, it can achieve the fastest response of the optimal coal blending scheme when the environment or demand changes. Under normal circumstances, the constraints include at least: total coal supply constraint, boiler load constraint, environmental protection constraint, and coal inventory constraint; among which, the total coal supply constraint includes: the total coal supply meets the real-time power supply demand of the power grid; the boiler load constraint includes: the real-time operating parameters of the boiler are within a safe range, and the real-time operating parameters of the boiler include but are not limited to boiler efficiency, furnace temperature, main steam temperature and pressure, flue gas temperature, oxygen content, etc.; the environmental protection constraint includes: the sum of pollutant emission concentrations of each type of coal is less than or equal to the concentration threshold. The concentration threshold should also be different for different types of pollutants (including but not limited to sulfur dioxide, nitrogen oxides, dust, etc.), and the total emission of all pollutants should be less than their corresponding concentration threshold when setting the environmental protection constraint; the coal inventory constraint includes: the consumption of each type of coal cannot exceed the current available inventory.

[0023] It should be noted that the optimal coal blending scheme output in this embodiment is the mixing ratio of each coal type in the total coal feed. It is assumed that the thermal power plant has a total of... Planting coal, For the first The blending ratio of each coal type in the total coal feed must be subject to the following constraints:

[0024] That is, the sum of the mixing ratios of all coal types equals 1, and , .

[0025] In some embodiments, the system should also have the ability to proactively optimize the coal blending scheme according to environmental changes. For example, for high humidity and low temperature environments, the blockage problem caused by excessively high coal moisture content should be considered in high humidity environments. In this case, coal with lower moisture content should be selected first, or coal that can improve fluidity after being mixed with high moisture content coal should be selected to prevent blockage of the coal feeding system. Low temperature environments will significantly reduce the flue gas temperature of the boiler and the metal wall temperature of the tail heating surface (such as the air preheater). When the wall temperature is lower than the "acid dew point" of sulfuric acid vapor in the flue gas, severe low temperature corrosion will occur. Therefore, it is necessary to limit the flue gas temperature for low temperature environments.

[0026] Specifically, the multi-source data collected by the data acquisition layer 10 also includes: the moisture content of each type of coal, ambient humidity, and the moisture content of the coal to be blended. The constraint generation module 21 will determine whether the current environment is high humidity based on the collected data. In this embodiment, the standard for judging a high humidity environment is a combination of an absolute threshold or a direct signal trigger. The absolute threshold is the ambient humidity threshold set by the system. This threshold is set based on the local climate and the plant's operating experience. When the collected ambient humidity is higher than the ambient humidity threshold and persists for a certain period of time, it can be considered to be in a high humidity environment. It should be noted that this ambient humidity threshold is not fixed. For example, it can be lowered before the rainy season to take more conservative preventive measures in advance. Compared with changes in ambient humidity, a more direct basis for judgment is the humidity signal of the coal itself. If the online moisture meter installed in the coal yard or on the coal conveyor belt detects a sudden and significant increase in the surface moisture or total moisture of the coal entering the furnace or the coal to be blended (for example, exceeding the benchmark value by 3-5 percentage points), even if the ambient humidity does not reach the threshold, the constraint generation module 21 will consider the current environment to be high humidity. In a high-humidity environment, the constraint generation module 21 will construct an additional high-humidity adaptive constraint on the basis of the above constraint conditions. That is, the sum of the moisture content of all coal types is less than the safe moisture threshold. It should be understood that the safe moisture threshold is mainly based on historical data, equipment characteristics and coal quality experiments. A safe moisture threshold is preset as a hard condition to prevent blockage. However, the safe moisture threshold itself is not static. It is mainly inversely proportional to the ambient humidity and can also be finely adjusted according to the operating status of the coal feeder.

[0027] For low-temperature environments, the multi-source data collected by data acquisition layer 10 also includes: ambient temperature and the concentration of pollutants in the current emitted flue gas. Under these conditions, when the ambient temperature remains below 5°C to 10°C, the system will become alert for the risk of low-temperature corrosion. Simultaneously, the system will adjust its response based on the concentration of pollutants in the emitted flue gas. The acid dew point temperature is calculated in real time based on the concentration. A safety margin (e.g., 10°C to 20°C) is added to this value and set as the lower limit constraint value for the flue gas temperature. When the sulfur content of the coal increases, causing the predicted flue gas temperature to approach or fall below this lower limit constraint value, the constraint generation module 21 determines that the current environment is low-temperature and performs low-temperature environment adaptive constraints to prevent corrosion. The low-temperature environment adaptive constraints include: the flue gas temperature after the co-combustion of all coal types is greater than or equal to the minimum flue gas temperature. By forcibly maintaining the flue gas temperature at a relatively high level (e.g., not lower than 150°C), it can be ensured that the temperature of the metal wall at the very end is always higher than the acid dew point, thereby preventing corrosion in principle. In this embodiment, the minimum flue gas temperature is inversely proportional to the ambient temperature. It should be noted that the constraint generation module 21 dynamically estimates the current acid dew point temperature based on the real-time sulfur and moisture content of the co-combusted coal types using the empirical formula acid dew point ≈ 120 + 20 * log(S), where S is the sulfur content of the flue gas in the current emission. The concentration of acid dew point temperature is dynamic, and the corresponding conditions for determining whether a low-temperature environment is present are also dynamic. It integrates ambient temperature signals and coal quality characteristics to achieve a more accurate low-temperature corrosion response. Furthermore, when generating constraints, the constraint generation module 21 can default to minimizing the proportion of high-sulfur coal to reduce pollution emissions and prevent corrosion.

[0028] In practice, special environments may also include high-temperature environments. Since flue gas temperature is one of the most critical factors affecting boiler efficiency, excessively high flue gas temperature means that a large amount of heat is wasted, resulting in reduced boiler efficiency and increased coal consumption. Therefore, in high-temperature environments, flue gas temperature should be reduced as much as possible to ensure boiler efficiency, provided that corrosion does not occur (i.e., it is still above the acid dew point).

[0029] After the constraint generation module 21 clarifies the constraints, the optimization decision module 22 determines the optimal coal blending scheme based on the constraints and the current preset optimization objective using an optimization algorithm. This yields the blending ratio of each coal type in the total coal feed, indicating that when generating electricity from coal based on the optimized blending ratio, the optimal objective can be achieved while satisfying the constraints. In this embodiment, the preset optimization objective is the lowest power generation cost or the highest overall benefit. Subsequently, an optimization model is constructed based on the optimization constraints and the preset optimization objective. The decision variables of the optimization model are the blending ratio of each coal type in the total coal feed. Finally, the optimal solution for the decision variables in the optimization model is calculated using a preset optimization algorithm, which serves as the optimal coal blending scheme.

[0030] Specifically, the cost of electricity generation is expressed based on the following formula:

[0031] in, Indicates the cost of electricity generation. Indicates the first One type of coal, Indicates the quantity of coal type. Indicates the first The price of coal for each type of coal. For the first The blending ratio of each coal type in the total coal supply For the first The calorific value of each type of coal This represents the boiler combustion efficiency, which is a value output by the boiler combustion efficiency model. It depends on the current blending scheme, indicating that the combustion efficiency of blended coal is not a simple weighted average of the efficiencies of each coal type, but rather involves a complex nonlinear relationship.

[0032] The overall benefits are expressed by the following formula:

[0033] in, Indicates comprehensive benefits, Indicates the grid connection price. This indicates the real-time power supply demand of the power grid. Indicates the first The cost of penalties for exceeding emission standards for various pollutants Indicates the first The emission concentration of each pollutant is output by the online pollutant emission prediction model, and also depends on the co-firing scheme.

[0034] Based on the above expressions for power generation costs and overall benefits, the following objective function can be constructed: OR

[0035] By combining the constraints, an optimization model is formed. With the powerful computing support of the cloud platform, the optimization decision module 22 can solve the decision variables of the above optimization model through genetic algorithm, particle swarm algorithm or other intelligent algorithms that can achieve the same goal of finding the optimal solution to the problem. The final optimal solution is the optimal coal blending scheme.

[0036] In some embodiments, power plant operators can assign importance coefficients to different objectives that determine overall benefits, wherein... Indicates economic cost, Indicates efficiency costs, The environmental cost can also be represented by the following formula when calculating the overall benefit (CB):

[0037] in, Indicates economic weight, Indicates efficiency weight, The weights represent environmental considerations because economic (cost), environmental (emissions), and efficiency (boiler performance) objectives are often conflicting (e.g., burning low-priced coal may be low-cost but high-emission). The system needs to weigh these conflicting objectives, and the weights are the quantitative representation of this trade-off. When the power plant's market strategy, environmental requirements, or operational tasks change, operators do not need to modify the underlying model and algorithm; they can simply adjust the aforementioned weight parameters to ensure the system's optimization direction remains highly consistent with the power plant's actual needs.

[0038] After generating the optimal coal blending scheme, the cloud platform processing layer 20 outputs it to the execution control layer 30. The execution control layer 30 can be a distributed control system or a PLC system within the power plant, used to control the coal feeders according to the optimal coal blending scheme to achieve the co-combustion of the corresponding proportion of coal types. Specifically, the execution control layer 30 first determines the target coal feeders to be started based on the optimal coal blending scheme, the equipment health status of each coal feeder, and the operating efficiency of the coal feeders. That is, the target coal feeders must be coal feeders used for storing the corresponding coal types for which the co-combustion ratio in the optimal coal blending scheme is not zero, and these feeders must not be in a faulty or under-maintenance state. Simultaneously, it must ensure that the selected target coal feeders can operate within their optimal output range, rather than experiencing low-load operation due to an excessive number of feeders. After identifying the target coal feeders to be started, the coal feeding rate of each target coal feeder is determined according to the co-combustion ratio to ensure that the co-combustion ratio of the corresponding coal type entering the boiler meets the requirements of the optimal coal blending scheme. Finally, the distributed control system generates control commands based on the target coal feeder and its coal feeding rate, and distributes them to each target coal feeder to achieve precise control of the coal blending process. It should be noted that the coal feeding rates of different target coal feeders may differ, so the commands for each target coal feeder are generated and issued independently.

[0039] Furthermore, the system can also monitor boiler combustion status data and pollutant emission data in real time through the data acquisition layer 10. This includes data characterizing boiler combustion status such as actual boiler efficiency, furnace temperature, main steam temperature and pressure, flue gas temperature, and oxygen content, as well as actual emission concentrations measured in real time by the online emission monitoring system (CEMS), such as SO2, NOx, and dust concentrations, to characterize pollutant emissions. The cloud platform processing layer 20 compares the actual measured values ​​of these monitoring data with the prediction results of the boiler combustion efficiency model and the online pollutant emission prediction model, generates feedback information, and uses this feedback information to optimize the boiler combustion efficiency model and the online pollutant emission prediction model, making their prediction results closer to the actual boiler operation performance and pollutant emission results.

[0040] In fact, boiler combustion efficiency models and online pollutant emission prediction models are crucial components of preset optimization objectives. Their accuracy affects the accuracy of these objectives, and consequently, the optimization decision results. The optimization process for these models can specifically involve calibrating their internal parameters, which reflect the unique characteristics of specific coal types or boiler equipment. For example, boiler combustion efficiency... , Indicates the volatile matter content of coal. This indicates the calorific value of coal. Indicates moisture content. For boiler load, For the oxygen content within the boiler, each parameter has a corresponding weighting coefficient to characterize its impact on boiler combustion efficiency. Model modification and optimization involve adjusting these weighting coefficients. For instance, if the system detects that the moisture content of the currently burned coal has a greater negative impact on efficiency than the model predicts, it will adjust the weighting coefficient of the moisture variable accordingly to make the prediction results closer to reality. For online pollutant emission prediction models, different models can be set for different pollutants to achieve separate predictions; for example, for nitrogen oxides... In terms of its emission concentration ,in, This indicates the nitrogen content of the coal type. Indicates the furnace temperature. This indicates the air distribution method, which corresponds to the parameters in each online pollution emission prediction model. It also has corresponding weight coefficients to characterize the impact of the parameters on emission concentrations. During optimization, the model is updated by adjusting the weight coefficients of each parameter.

[0041] In some embodiments, the system may further include a human-computer interaction layer, providing users with a monitoring interface for data visualization, model management, parameter configuration, and report generation. Simultaneously, the cloud platform should also have the function of health management for various main equipment in the thermal power plant, including but not limited to the ability to predict and warn of risks such as boiler wear, coking, and corrosion based on changes in coal quality, in order to provide decision support for equipment maintenance.

[0042] This embodiment integrates multi-source data and intelligent algorithms through a cloud platform, takes into account the constraints of actual operation, determines the blending ratio of each type of coal in the total coal feed, realizes real-time dynamic optimization of the coal blending process of thermal power plants, meets the preset optimization objectives, greatly enhances the safety, reliability and response rate of system operation, and meets the different operating needs of thermal power plants.

[0043] Based on the same inventive concept, the second embodiment of this disclosure provides a dynamic coal distribution management method for boilers in thermal power plants based on a cloud platform, the flowchart of which is shown below. Figure 3As shown, it includes: S1, obtain multi-source data from different management entities of the thermal power plant; S2, construct optimization constraints based on multi-source data; S3. Determine the optimal coal blending scheme based on the optimization constraints and preset optimization objectives. The optimal coal blending scheme shall include at least the blending ratio of each type of coal in the total coal feed. S4 generates control commands for the coal feeder at the storage point of the coal type based on the optimal coal blending scheme.

[0044] Specifically, this embodiment utilizes a sensor network deployed at key nodes such as coal yards, coal conveyor belts, coal feeders, and boilers, combined with UAV laser scanning 3D modeling technology, to collect massive amounts of heterogeneous data from multiple sources in real time, including coal inventory, type, quantity, price, boiler operating parameters, and grid demand. This data is aggregated through an industrial IoT gateway and uploaded to a cloud platform for centralized storage and management. On the cloud platform, the system employs big data analytics and machine learning algorithms to train and construct high-precision boiler combustion efficiency models, coal cost function models, and online pollutant emission prediction models based on historical and real-time data. These models dynamically reflect the complex relationships between multiple variables such as coal quality characteristics and boiler load. Subsequently, the system's optimization decision module, aiming for the lowest power generation cost or the highest overall benefit, integrates environmental and safety constraints and uses intelligent optimization algorithms to solve for the current optimal coal blending scheme in real time. This process possesses strong environmental adaptability: in high-humidity environments, the algorithm automatically introduces anti-clogging constraints, prioritizing the blending of dry coal or mixed coal that improves fluidity; in low-temperature environments, it introduces anti-corrosion constraints to ensure flue gas temperature and preferentially select low-sulfur coal, thereby intelligently balancing economy, environmental protection, and safety. Finally, with precise execution and continuous optimization, the optimal coal blending scheme generated by the cloud platform is directly sent to the distributed control system or PLC control system at the bottom of the power plant. The latter automatically adjusts the coal feeding rate of each coal feeder to achieve precise execution of the coal blending scheme. At the same time, the system continuously monitors the combustion status and pollutant emission data of the boiler after execution and sends this feedback data back to the cloud platform for dynamic correction and iterative optimization of the above model, forming a closed-loop feedback control system that continuously learns and improves itself, ensuring that the system always remains in the optimal operating state.

[0045] This embodiment integrates multi-source data and intelligent algorithms through a cloud platform, takes into account the constraints of actual operation, determines the blending ratio of each type of coal in the total coal feed, realizes real-time dynamic optimization of the coal blending process of thermal power plants, meets the preset optimization objectives, greatly enhances the safety, reliability and response rate of system operation, and meets the different operating needs of thermal power plants.

[0046] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this disclosure, and are not intended to limit them. Although this disclosure has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this disclosure.

Claims

1. A cloud-based dynamic coal distribution management system for thermal power plant boilers, characterized in that, include: The data acquisition layer is used to obtain multi-source data from different management entities in the thermal power plant; The cloud platform processing layer includes a constraint generation module and an optimization decision module. The constraint generation module is used to construct optimization constraints based on the multi-source data. The optimization decision module is used to determine the optimal coal blending scheme based on the optimization constraints and the preset optimization objective. The optimal coal blending scheme includes at least the blending ratio of each coal type in the total coal feed. The execution control layer is used to generate control instructions for the coal feeder at the storage point where the coal type is located, based on the optimal coal blending scheme.

2. The dynamic coal distribution management system for thermal power plant boilers according to claim 1, characterized in that, The multi-source data includes: the price of coal for each type, the quantity of coal for each type, the coal inventory at each storage point, the daily unloading volume at each storage point, the real-time coal feeding volume of each coal feeder, the real-time operating parameters of the boiler, and the real-time power supply demand of the power grid.

3. The dynamic coal distribution management system for thermal power plant boilers according to claim 2, characterized in that, The optimization constraints include at least: total coal supply constraint, boiler load constraint, environmental protection constraint, and coal inventory constraint; among which, The total coal supply constraint includes: the total coal supply must meet the real-time power supply demand of the power grid; The boiler load constraint includes: the real-time operating parameters of the boiler are within a safe range; The environmental constraints include: the sum of pollutant emission concentrations for each type of coal is less than or equal to a concentration threshold; The coal inventory constraints include: the consumption of each type of coal cannot exceed the current available inventory.

4. The dynamic coal distribution management system for thermal power plant boilers according to claim 3, characterized in that, The multi-source data also includes: the moisture content of each coal type, ambient humidity, and moisture content of the coal to be blended; The constraint generation module is further configured to determine whether the environment is in a high humidity environment based on the ambient humidity or the moisture content of the coal to be mixed, and to construct an adaptive constraint for a high humidity environment if it is determined to be in a high humidity environment. The adaptive constraint for a high humidity environment includes: the sum of the moisture content of all coal types is less than a safe moisture threshold, and the safe moisture threshold is inversely proportional to the ambient humidity.

5. The dynamic coal distribution management system for thermal power plant boilers according to claim 3, characterized in that, The multi-source data also includes: ambient temperature, current emissions of flue gas, and other data. concentration; The constraint generation module is further configured to, based on the current emitted flue gas... The concentration is used to calculate the acid dew point temperature. Based on the ambient temperature and the acid dew point temperature, it is determined whether the environment is low-temperature. If the environment is low-temperature, an adaptive constraint for the low-temperature environment is constructed. The adaptive constraint for the low-temperature environment includes: the flue gas temperature after combustion of all coal types is greater than or equal to the minimum flue gas temperature, and the minimum flue gas temperature is inversely proportional to the ambient temperature.

6. The dynamic coal distribution management system for thermal power plant boilers according to claim 2, characterized in that, The optimization decision module is specifically used for: The preset optimization objective is to achieve either the lowest power generation cost or the highest overall benefit. An optimization model is constructed based on the optimization constraints and the preset optimization objective. The decision variable of the optimization model is the blending ratio of each coal type in the total coal feed. The optimal solution for the decision variables in the optimization model is calculated using a preset optimization algorithm, and is taken as the optimal coal blending scheme.

7. The dynamic coal distribution management system for thermal power plant boilers according to claim 6, characterized in that, The power generation cost is expressed based on the following formula: in, Indicates the cost of electricity generation. Indicates the first One type of coal, Indicates the quantity of coal type. Indicates the first The price of coal for each type of coal. For the first The blending ratio of each coal type in the total coal supply For the first The calorific value of each type of coal Indicates boiler combustion efficiency; The overall benefits are expressed based on the following formula: in, Indicates comprehensive benefits, Indicates the grid connection price. This indicates the real-time power supply demand of the power grid. Indicates the first The cost of penalties for exceeding emission standards for various pollutants Indicates the first The emission concentration of various pollutants.

8. The dynamic coal distribution management system for thermal power plant boilers according to any one of claims 2, characterized in that, The coal inventory at each storage point is determined based on a three-dimensional model of the coal pile at the storage point using a drone or laser scanning device.

9. The dynamic coal distribution management system for thermal power plant boilers according to any one of claims 1 to 8, characterized in that, The execution control layer is specifically used for: Based on the optimal coal blending scheme, the equipment health status of each coal feeder, and the operating efficiency of the coal feeder, the target coal feeder to be started is determined; The coal feeding rate of the target coal feeder is determined based on the blending ratio. Control commands are generated based on the target coal feeder and its coal feeding rate.

10. A method for dynamic coal blending management of boilers in thermal power plants based on a cloud platform, characterized in that, include: Obtain multi-source data from different management entities within thermal power plants; Optimization constraints are constructed based on the multi-source data; The optimal coal blending scheme is determined based on the optimization constraints and the preset optimization objectives. The optimal coal blending scheme includes at least the blending ratio of each of the coal types in the total coal feed. Based on the optimal coal blending scheme, control instructions are generated for the coal feeder at the storage point where the coal type is located.

Images