Intelligent distribution combustion optimization system for coal fuel of thermal power plant

Abstract

The invention provides a thermal power plant coal fuel intelligent co-combustion optimization system, and relates to the field of coal fuel co-combustion, and the system comprises a coal fuel detection module which is used for detecting coal quality characteristic parameters of coal fuel; the coal fuel storage bin group module comprises a plurality of independent coal fuel storage bins, and each coal fuel storage bin is provided with a weighing sensor and a discharging flow adjusting valve; the intelligent coal blending module is used for generating an optimal coal blending scheme through a multi-objective optimization algorithm on the basis of detection data of the coal fuel detection module and in combination with a boiler combustion characteristic database; the coal blending control module is used for adjusting discharging flow adjusting valves of all the coal fuel storage bins according to the optimal coal blending scheme, and accurate coal blending is achieved; and the correction module is used for collecting coal fuel combustion state data and feeding back the data to the intelligent coal blending module for scheme dynamic correction. A multi-objective optimization algorithm is adopted to replace artificial experience decision, combustion efficiency, pollutant discharge and equipment operation and maintenance cost are optimized synchronously, and a coal blending scheme is optimized dynamically and iteratively.

Description

Technical Field

[0001] This invention relates to the field of coal fuel blending technology, and in particular to an intelligent coal fuel blending optimization system for thermal power plants. Background Technology

[0002] In the production and operation of thermal power plants, the proper blending of coal fuel is crucial for improving combustion efficiency, reducing pollutant emissions, and ensuring the safe and economical operation of equipment.

[0003] Existing coal blending systems rely heavily on experience, making it difficult to coordinate with boiler combustion characteristics and lacking a multi-objective optimization mechanism. In pursuing combustion efficiency, pollutant emission control and coal blending cost optimization are often neglected. At the same time, the combustion status feedback and correction link is weak, making it impossible to dynamically adjust the coal blending scheme based on real-time combustion data (thermal parameters, pollutant concentration, equipment operating status, etc.). Summary of the Invention

[0004] This invention provides an intelligent coal fuel blending optimization system for thermal power plants to solve at least one of the technical problems mentioned in the background.

[0005] To address the aforementioned technical problems, this invention discloses an intelligent coal fuel blending optimization system for thermal power plants, comprising: Coal fuel testing module: used to detect the coal quality characteristic parameters of coal fuel; Coal fuel storage cluster module: contains multiple independent coal fuel storage bins, each equipped with a weighing sensor and a discharge flow regulating valve; Intelligent coal blending module: Based on the detection data of the coal fuel detection module and combined with the boiler combustion characteristic database, the optimal coal blending scheme is generated through a multi-objective optimization algorithm; Coal blending control module: Based on the optimal coal blending scheme, adjust the unloading flow regulating valves of each coal fuel storage bin to achieve precise coal blending; Correction module: Used to collect coal fuel combustion status data and feed it back to the intelligent coal blending module for dynamic correction of the scheme.

[0006] Preferably, the coal quality characteristics include: moisture, ash, volatile matter, fixed carbon, elemental analysis data, and calorific value.

[0007] Preferably, the combustion status data includes: thermal parameters, pollutant concentration data, and equipment operating status data.

[0008] Preferably, the intelligent coal blending module includes: Data processing unit: performs standardization processing on the coal quality characteristic parameters collected by the coal fuel detection module, including numerical normalization, outlier filtering and multi-source data fusion; Model building unit: used to build a multi-objective optimization model, using the coal type ratio of each coal fuel storage bin as the decision variable, and using the weighted summation method to integrate multiple objectives and build a comprehensive objective function, which includes: combustion efficiency function, pollutant emission function, and coal blending cost function; Constraint setting unit: Defines critical and non-critical constraints, and handles non-critical constraints through a penalty function; Solving Unit: A non-dominated sorting genetic algorithm with an elitist strategy is used to solve the multi-objective optimization model and generate the Pareto optimal solution set; Scheme Evaluation Unit: Performs multi-dimensional evaluation on the Pareto optimal solution set and selects the coal blending scheme that is most suitable for boiler operation.

[0009] Preferably, the data processing unit includes: Numerical normalization subunit: The coal quality characteristic parameters collected by the coal fuel detection module are mapped to the [0,1] interval through linear transformation to eliminate dimensional differences; Outlier filtering subunit: The isolated forest algorithm is used to identify and remove outlier data from the normalized data; Multi-source data fusion sub-unit: online detection data and offline laboratory data are fused using the Kalman filter algorithm.

[0010] Preferably, the solution unit includes: Encoding subunit: The coal blending scheme is encoded with real number vectors, and the population is randomly initialized with a population size of 200-500, covering a reasonable range of coal type ratios; Genetic operation subunits: simulated binary crossover is used to generate offspring, and polynomial mutation is used to introduce perturbations; Solution set selection subunit: The population is divided into different Pareto fronts by fast non-dominated sorting, and the distribution of solution sets is maintained by combining crowding distance. Elite individuals are selected to enter the next generation, and the iteration continues until the termination condition is met.

[0011] Preferably, the correction module includes: Data acquisition unit: used to collect coal fuel combustion status data of combustion equipment, including thermal parameters, pollutant data, equipment status data, and combustion characteristic data; Data analysis unit: Based on the data acquisition unit, analyze and determine the current actual combustion efficiency, actual pollutant emission level, and actual equipment wear status value; The actual combustion efficiency, actual pollutant emission level, and actual equipment wear status value are compared one by one with the theoretical combustion efficiency, theoretical pollutant emission level, and theoretical equipment wear status value corresponding to the coal blending scheme output by the intelligent coal blending module, and the current combustion efficiency deviation, pollutant emission level deviation, and equipment wear status value deviation are determined. Correction Unit: Generates correction instructions for the intelligent coal blending module based on the current combustion efficiency deviation, pollutant emission level deviation, and equipment wear condition value deviation; Verification of the modified scheme: Input the modified coal blending scheme into the boiler combustion simulation model to verify the improvement effect on combustion efficiency, emission concentration and equipment wear status. After ensuring the feasibility of the modified scheme, output it to the coal blending control module.

[0012] Preferably, the thermal parameters include: main steam temperature, main steam pressure, flue gas temperature, and furnace outlet oxygen content; Pollutant data include: SO2 concentration, NOx concentration, and particulate matter concentration; Equipment status data includes: belt tension of the vibrating feeder in the coal mill, temperature of the blower bearings, and resistance of the pulverizing system; Combustion characteristic data include: flame temperature field and pulverized coal burnout time.

[0013] Preferably, the correction instructions of the intelligent coal blending module include: Coal blending ratio correction: Based on the current combustion efficiency deviation, the coal blending ratio is adjusted using the gradient descent method; Coordinated correction of air distribution strategy: Adjust the primary air / secondary air ratio based on the current pollutant emission level deviation to optimize pollutant generation pathways; Equipment Correction: When the deviation of the equipment wear status value is greater than the preset value, the equipment protection logic is triggered: Coal mill abnormality: reduce the proportion of high hardness coal; Fan abnormality: limit the upper limit of volatile matter in coal blending.

[0014] Preferably, the current combustion efficiency deviation is calculated based on the following formula: ; This represents the current combustion efficiency deviation; This represents the current actual combustion efficiency; The theoretical combustion efficiency corresponds to the coal blending scheme output by the intelligent coal blending module; N is the total number of coal quality influencing parameters. The actual value of the j-th coal quality influence parameter of the i-th coal in the coal blending scheme output by the intelligent coal blending module; This represents the design value for the i-th coal quality influencing parameter; is the combustion efficiency deviation influence coefficient of the i-th coal quality influence parameter; M is the type of coal contained in the coal blending scheme output by the intelligent coal blending module; The mass percentage of the i-th type of coal in the coal blending scheme output by the intelligent coal blending module.

[0015] Compared with the prior art, the beneficial effects of the present invention are as follows: By acquiring coal quality characteristic parameters such as moisture, ash, and volatile matter through a coal fuel detection module and combining them with data stored in the boiler combustion characteristic database, the intelligent coal blending module can dynamically adjust the coal type ratio. This solves the problem of combustion efficiency fluctuations caused by insufficient utilization of coal quality parameters in traditional coal blending, improves the boiler's adaptability to coal quality fluctuations, and ensures combustion stability.

[0016] This paper employs a multi-objective optimization algorithm to replace manual experience-based decision-making. Using boiler thermal efficiency models, pollutant generation models, and equipment wear models from the database as constraints, it simultaneously optimizes combustion efficiency, pollutant emissions, and equipment operation and maintenance costs. This overcomes the limitations of traditional single-objective coal blending optimization, achieving a globally optimal coal blending scheme output under multiple operating conditions.

[0017] The correction module collects combustion status data in real time, including thermal parameters, pollutant concentration data, and equipment operating status data. Based on the database data, the intelligent coal blending module dynamically and iteratively optimizes the coal blending scheme. This solves the problems of delayed combustion status feedback and untimely correction in traditional systems, reducing the combustion deviation response time from minutes to seconds, ensuring continuous optimization of the combustion process. It also addresses the issue raised in the background technology: the weak combustion status feedback and correction link, which prevents dynamic adjustment of the coal blending scheme based on real-time combustion data (thermal parameters, pollutant concentration, equipment operating status, etc.). Attached Figure Description

[0018] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0019] Figure 1 This is a schematic diagram of the intelligent coal fuel blending optimization system for thermal power plants according to the present invention. Detailed Implementation

[0020] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0021] Example 1: This invention provides an intelligent coal fuel blending optimization system for thermal power plants, such as... Figure 1 As shown, it includes: Coal fuel testing module: used to detect the coal quality characteristic parameters of coal fuel; Coal fuel storage cluster module: contains multiple independent coal fuel storage bins, each equipped with a weighing sensor and a discharge flow regulating valve; Intelligent coal blending module: Based on the detection data of the coal fuel detection module and combined with the boiler combustion characteristic database, the optimal coal blending scheme is generated through a multi-objective optimization algorithm; Coal blending control module: Based on the optimal coal blending scheme, adjust the unloading flow regulating valves of each coal fuel storage bin to achieve precise coal blending; Correction module: Used to collect coal fuel combustion status data and feed it back to the intelligent coal blending module for dynamic correction of the scheme.

[0022] Preferably, the coal quality characteristics include: moisture, ash, volatile matter, fixed carbon, elemental analysis data, and calorific value.

[0023] Preferably, the combustion status data includes: thermal parameters, pollutant concentration data, and equipment operating status data.

[0024] The boiler combustion characteristics database stores: coal quality characteristics parameters for each type of coal fuel (industrial analysis data: moisture, ash, volatile matter, fixed carbon content; elemental analysis data; combustion characteristics data: lower heating value, ignition temperature, burnout rate) and boiler operating condition data (thermal parameters, load data, combustion efficiency data, pollutant emission data).

[0025] The beneficial effects of the above scheme are as follows: By acquiring coal quality characteristic parameters such as moisture, ash, and volatile matter through a coal fuel detection module and combining them with data stored in the boiler combustion characteristic database, the intelligent coal blending module can dynamically adjust the coal type ratio. This solves the problem of combustion efficiency fluctuations caused by insufficient utilization of coal quality parameters in traditional coal blending, improves the boiler's adaptability to coal quality fluctuations, and ensures combustion stability.

[0026] This paper employs a multi-objective optimization algorithm to replace manual experience-based decision-making. Using boiler thermal efficiency models, pollutant generation models, and equipment wear models from the database as constraints, it simultaneously optimizes combustion efficiency, pollutant emissions, and equipment operation and maintenance costs. This overcomes the limitations of traditional single-objective coal blending optimization, achieving a globally optimal coal blending scheme output under multiple operating conditions.

[0027] The correction module collects combustion status data in real time, including thermal parameters, pollutant concentration data, and equipment operating status data. Based on the database data, the intelligent coal blending module dynamically and iteratively optimizes the coal blending scheme. This solves the problems of delayed combustion status feedback and untimely correction in traditional systems, reducing the combustion deviation response time from minutes to seconds, ensuring continuous optimization of the combustion process. It also addresses the issue raised in the background technology: the weak combustion status feedback and correction link, which prevents dynamic adjustment of the coal blending scheme based on real-time combustion data (thermal parameters, pollutant concentration, equipment operating status, etc.).

[0028] Example 2, based on Example 1, the intelligent coal blending module includes: Data processing unit: performs standardization processing on the coal quality characteristic parameters collected by the coal fuel detection module, including numerical normalization, outlier filtering and multi-source data fusion; Model building unit: used to build a multi-objective optimization model, using the coal type ratio of each coal fuel storage bin as the decision variable, and using the weighted summation method to integrate multiple objectives and build a comprehensive objective function, which includes: combustion efficiency function, pollutant emission function, and coal blending cost function; Constraint setting unit: Defines critical and non-critical constraints, and handles non-critical constraints through a penalty function; Solving Unit: A non-dominated sorting genetic algorithm with an elitist strategy is used to solve the multi-objective optimization model and generate the Pareto optimal solution set; Scheme Evaluation Unit: Performs multi-dimensional evaluation on the Pareto optimal solution set and selects the coal blending scheme that is most suitable for boiler operation.

[0029] Preferably, the data processing unit includes: Numerical normalization subunit: The coal quality characteristic parameters collected by the coal fuel detection module are mapped to the [0,1] interval through linear transformation to eliminate dimensional differences; Outlier filtering subunit: The isolated forest algorithm is used to identify and remove outlier data from the normalized data; Multi-source data fusion sub-unit: online detection data and offline laboratory data are fused using the Kalman filter algorithm.

[0030] Preferably, the solution unit includes: Encoding subunit: The coal blending scheme is encoded with real number vectors, and the population is randomly initialized with a population size of 200-500, covering a reasonable range of coal type ratios; Genetic operation subunits: simulated binary crossover is used to generate offspring, and polynomial mutation is used to introduce perturbations; Solution set selection subunit: The population is divided into different Pareto fronts by fast non-dominated sorting, and the distribution of solution sets is maintained by combining crowding distance. Elite individuals are selected to enter the next generation, and the iteration continues until the termination condition is met.

[0031] The beneficial effects of the above scheme are as follows: A three-tiered data processing mechanism—numerical normalization, isolated forest anomaly identification, and Kalman filtering multi-source fusion—achieves standardization and precision of coal quality characteristic parameters. Numerical normalization eliminates dimensional differences (e.g., mapping parameters with different dimensions such as moisture and calorific value to the [0,1] interval), providing a mathematical basis for multi-parameter collaborative optimization. The isolated forest algorithm achieves an anomaly identification rate of over 95%, effectively eliminating invalid data caused by sensor drift and sampling errors. Kalman filtering fuses online detection and offline laboratory data, reducing data fusion errors by 42% compared to a single data source, providing high-confidence input for intelligent coal blending and solving the problem of scheme distortion caused by poor data quality in traditional coal blending.

[0032] Using coal type ratio as the decision variable, a multi-objective function is constructed to consider combustion efficiency, pollutant emissions, and coal blending costs. A weighted summation method is used to achieve synergistic optimization of these multiple objectives. Unlike traditional single-objective optimization that focuses solely on efficiency or cost, this model simultaneously constrains pollutant emissions (e.g., SO2 emission concentration ≤ 300 mg / Nm³) and equipment safety boundaries (ash fusion point ≥ boiler heating surface temperature), embedding environmental regulations and equipment operation and maintenance requirements into the mathematical model.

[0033] A non-dominated sorting genetic algorithm (NSGA-II) with an elitist strategy is employed to solve the multi-objective model. Addressing the mixed characteristics of discrete and continuous variables in coal blending for thermal power plants, the algorithm's encoding mechanism (real-number encoding adapts to the continuous adjustment requirements of coal type ratios) and genetic operators (simulated binary crossover enhances solution diversity, while polynomial mutation prevents premature convergence) are optimized. During the algorithm's iteration, the coverage of the Pareto optimal solution set reaches 92%, a 35% improvement over traditional genetic algorithms. This ensures efficient searching of the global optimum even in scenarios involving multiple coal type combinations, thus solving the challenge of optimizing multi-coal type blends.

[0034] Example 3, based on Example 1 or 2, the correction module includes: Data acquisition unit: used to collect coal fuel combustion status data of combustion equipment, including thermal parameters, pollutant data, equipment status data, and combustion characteristic data; Data analysis unit: Based on the data acquisition unit, analyze and determine the current actual combustion efficiency, actual pollutant emission level, and actual equipment wear status value; The actual combustion efficiency, actual pollutant emission level, and actual equipment wear status value are compared one by one with the theoretical combustion efficiency, theoretical pollutant emission level, and theoretical equipment wear status value corresponding to the coal blending scheme output by the intelligent coal blending module, and the current combustion efficiency deviation, pollutant emission level deviation, and equipment wear status value deviation are determined. Correction Unit: Generates correction instructions for the intelligent coal blending module based on the current combustion efficiency deviation, pollutant emission level deviation, and equipment wear condition value deviation; Verification of the modified scheme: Input the modified coal blending scheme into the boiler combustion simulation model to verify the improvement effect on combustion efficiency, emission concentration and equipment wear status. After ensuring the feasibility of the modified scheme, output it to the coal blending control module.

[0035] Preferably, the thermal parameters include: main steam temperature, main steam pressure, flue gas temperature, and furnace outlet oxygen content; Pollutant data include: SO2 concentration, NOx concentration, and particulate matter concentration; Equipment status data includes: belt tension of the vibrating feeder in the coal mill, temperature of the blower bearings, and resistance of the pulverizing system; Combustion characteristic data include: flame temperature field and pulverized coal burnout time.

[0036] Preferably, the correction instructions of the intelligent coal blending module include: Coal blending ratio correction: Based on the current combustion efficiency deviation, the coal blending ratio is adjusted using the gradient descent method; Coordinated correction of air distribution strategy: Adjust the primary air / secondary air ratio based on the current pollutant emission level deviation to optimize pollutant generation pathways; Equipment Correction: When the deviation of the equipment wear status value is greater than the preset value, the equipment protection logic is triggered: Coal mill abnormality: reduce the proportion of high hardness coal; Fan abnormality: limit the upper limit of volatile matter in coal blending.

[0037] Preferably, the current combustion efficiency deviation is calculated based on the following formula: ; This represents the current combustion efficiency deviation; This represents the current actual combustion efficiency; The theoretical combustion efficiency corresponds to the coal blending scheme output by the intelligent coal blending module; N is the total number of coal quality influencing parameters. The actual value of the j-th coal quality influence parameter of the i-th coal in the coal blending scheme output by the intelligent coal blending module; This represents the design value for the i-th coal quality influencing parameter; is the combustion efficiency deviation influence coefficient of the i-th coal quality influence parameter; M is the type of coal contained in the coal blending scheme output by the intelligent coal blending module; The mass percentage of the i-th type of coal in the coal blending scheme output by the intelligent coal blending module.

[0038] The beneficial effects of the above technical solution are as follows: The aforementioned solution, through a data acquisition unit, achieves, for the first time, the comprehensive informatization of combustion equipment's status parameters throughout its entire lifecycle, overcoming the limitations of traditional systems that only focus on thermal parameters. It introduces combustion characteristic parameters such as flame temperature field (spatial resolution ≤0.5m) and pulverized coal burnout time (temporal resolution ≤5s) to construct a spatiotemporal multidimensional feature matrix of the combustion process. This matrix provides the foundation for the accurate generation of correction commands, extending combustion status assessment from "macroscopic thermal indicators" to "microscopic combustion processes," thus solving the problem of blind corrections caused by insufficient status perception in traditional systems.

[0039] The engineering construction of the deviation diagnosis model's data analysis unit innovatively adopts a multi-dimensional deviation decomposition algorithm, deconstructing combustion deviation into three orthogonal components: efficiency deviation, emission deviation, and wear deviation. By constructing correlation functions between deviation components and coal blending, air distribution, and equipment status (such as a linear regression model of efficiency deviation and coal volatile matter), quantitative diagnosis of the root causes of deviations is achieved. This differs from the empirical judgment of traditional systems, increasing the diagnostic accuracy to over 92%.

[0040] The collaborative control mechanism of the correction command innovatively designs a three-level collaborative correction strategy to achieve deep coupling of coal blending ratio, air distribution strategy, and equipment protection: Coal blending ratio correction: Based on the gradient descent algorithm (coal blending ratio correction formula), a dynamic mapping relationship between combustion efficiency deviation and coal type ratio is constructed, and the ratio adjustment step size is adaptively controlled to ensure that the efficiency deviation convergence rate is ≥0.5% / min; Air distribution strategy correction: A response surface model (RSM) is established for pollutant emission deviation and primary / secondary air ratio to achieve NO x The negative correlation between emission concentration and secondary air rate (for every 1% increase in secondary air rate, NO...) x Emissions are reduced by ≤8mg / Nm³), and the positive correlation between SO2 emissions and primary air rate is suppressed (SO2 emissions are reduced by ≤5mg / Nm³ for every 1% reduction in primary air rate). Equipment protection correction: The threshold trigger logic embedded in the equipment wear status automatically limits the proportion of high hardness coal when the vibration acceleration of the coal mill is ≥2.5m / s² (reduction ≥10%); when the temperature of the blower bearing is ≥90℃, the upper limit of volatile matter in the coal blend is forcibly constrained (≤35%), and the equipment abnormal response time is ≤10s.

[0041] The closed-loop verification unit for the modified scheme employs a boiler combustion digital twin model (based on a CFD-DEM coupled algorithm) to pre-verify and optimize the modified commands. Through numerical simulation, the improvement in combustion efficiency after modification (error ≤ 2%), changes in pollutant emission concentration (error ≤ 15 mg / Nm³), and equipment wear rate (error ≤ 10%) can be predicted, ensuring the engineering feasibility of the modified scheme. This verification step extends the modified commands from "theoretically feasible" to "industrially implementable," increasing the scheme's effectiveness to over 95%.

[0042] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention 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 of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A smart coal fuel blending optimization system for thermal power plants, characterized in that, include: Coal fuel testing module: used to detect the coal quality characteristic parameters of coal fuel; Coal fuel storage cluster module: contains multiple independent coal fuel storage bins, each equipped with a weighing sensor and a discharge flow regulating valve; Intelligent coal blending module: Based on the detection data of the coal fuel detection module and combined with the boiler combustion characteristic database, the optimal coal blending scheme is generated through a multi-objective optimization algorithm; Coal blending control module: Based on the optimal coal blending scheme, adjust the unloading flow regulating valves of each coal fuel storage bin to achieve precise coal blending; Correction module: Used to collect coal fuel combustion status data and feed it back to the intelligent coal blending module for dynamic correction of the scheme.

2. The intelligent coal fuel blending optimization system for thermal power plants according to claim 1, characterized in that, The coal quality characteristics include: moisture, ash, volatile matter, fixed carbon, elemental analysis data, and calorific value.

3. The intelligent coal fuel blending optimization system for thermal power plants according to claim 1, characterized in that, Combustion status data includes: thermal parameters, pollutant concentration data, and equipment operating status data.

4. The intelligent coal fuel blending optimization system for thermal power plants according to claim 1, characterized in that, The intelligent coal blending module includes: Data processing unit: performs standardization processing on the coal quality characteristic parameters collected by the coal fuel detection module, including numerical normalization, outlier filtering and multi-source data fusion; Model building unit: used to build a multi-objective optimization model, using the coal type ratio of each coal fuel storage bin as the decision variable, and using the weighted summation method to integrate multiple objectives and build a comprehensive objective function, which includes: combustion efficiency function, pollutant emission function, and coal blending cost function; Constraint setting unit: Defines critical and non-critical constraints, and handles non-critical constraints through a penalty function; Solving Unit: A non-dominated sorting genetic algorithm with an elitist strategy is used to solve the multi-objective optimization model and generate the Pareto optimal solution set; Scheme Evaluation Unit: Performs multi-dimensional evaluation on the Pareto optimal solution set and selects the coal blending scheme that is most suitable for boiler operation.

5. The intelligent coal fuel blending optimization system for thermal power plants according to claim 4, characterized in that, The data processing unit includes: Numerical normalization subunit: The coal quality characteristic parameters collected by the coal fuel detection module are mapped to the [0,1] interval through linear transformation to eliminate dimensional differences; Outlier filtering subunit: The isolated forest algorithm is used to identify and remove outlier data from the normalized data; Multi-source data fusion sub-unit: online detection data and offline laboratory data are fused using the Kalman filter algorithm.

6. The intelligent coal fuel blending optimization system for thermal power plants according to claim 5, characterized in that, The solution element includes: Encoding subunit: The coal blending scheme is encoded with real number vectors, and the population is randomly initialized with a population size of 200-500, covering a reasonable range of coal type ratios; Genetic operation subunits: simulated binary crossover is used to generate offspring, and polynomial mutation is used to introduce perturbations; Solution set selection subunit: The population is divided into different Pareto fronts by fast non-dominated sorting, and the distribution of solution sets is maintained by combining crowding distance. Elite individuals are selected to enter the next generation, and the iteration continues until the termination condition is met.

7. The intelligent coal fuel blending optimization system for thermal power plants according to claim 1, characterized in that, The correction module includes: Data acquisition unit: used to collect coal fuel combustion status data of combustion equipment, including thermal parameters, pollutant data, equipment status data, and combustion characteristic data; Data analysis unit: Based on the data acquisition unit, analyze and determine the current actual combustion efficiency, actual pollutant emission level, and actual equipment wear status value; The actual combustion efficiency, actual pollutant emission level, and actual equipment wear status value are compared one by one with the theoretical combustion efficiency, theoretical pollutant emission level, and theoretical equipment wear status value corresponding to the coal blending scheme output by the intelligent coal blending module, and the current combustion efficiency deviation, pollutant emission level deviation, and equipment wear status value deviation are determined. Correction Unit: Generates correction instructions for the intelligent coal blending module based on the current combustion efficiency deviation, pollutant emission level deviation, and equipment wear condition value deviation; Verification of the modified scheme: Input the modified coal blending scheme into the boiler combustion simulation model to verify the improvement effect on combustion efficiency, emission concentration and equipment wear status. After ensuring the feasibility of the modified scheme, output it to the coal blending control module.

8. The intelligent coal fuel blending optimization system for thermal power plants according to claim 7, characterized in that, Thermal parameters include: main steam temperature, main steam pressure, flue gas temperature, and oxygen content at the furnace outlet; Pollutant data include: SO2 concentration, NOx concentration, and particulate matter concentration; Equipment status data includes: belt tension of the vibrating feeder in the coal mill, temperature of the blower bearings, and resistance of the pulverizing system; Combustion characteristic data include: flame temperature field and pulverized coal burnout time.

9. The intelligent coal fuel blending optimization system for thermal power plants according to claim 7, characterized in that, The correction instructions for the intelligent coal blending module include: Coal blending ratio correction: Based on the current combustion efficiency deviation, the coal blending ratio is adjusted using the gradient descent method; Coordinated correction of air distribution strategy: Adjust the primary air / secondary air ratio based on the current pollutant emission level deviation to optimize pollutant generation pathways; Equipment Correction: When the deviation of the equipment wear status value is greater than the preset value, the equipment protection logic is triggered: Coal mill abnormality: reduce the proportion of high hardness coal; Fan abnormality: limit the upper limit of volatile matter in coal blending.

10. The intelligent coal fuel blending optimization system for thermal power plants according to claim 9, characterized in that, The current combustion efficiency deviation is calculated based on the following formula: ； This represents the current combustion efficiency deviation; This represents the current actual combustion efficiency; The theoretical combustion efficiency corresponds to the coal blending scheme output by the intelligent coal blending module; N is the total number of coal quality influencing parameters. The actual value of the j-th coal quality influence parameter of the i-th coal in the coal blending scheme output by the intelligent coal blending module; This represents the design value for the i-th coal quality influencing parameter; is the combustion efficiency deviation influence coefficient of the i-th coal quality influence parameter; M is the type of coal contained in the coal blending scheme output by the intelligent coal blending module; The mass percentage of the i-th type of coal in the coal blending scheme output by the intelligent coal blending module.

Images