Boiler coal blending management optimization method and system

Abstract

The application provides a boiler coal blending management optimization method and system. The method comprises the following steps: obtaining coal quality online monitoring data of coal flow on an inlet belt of a boiler; predicting combustion characteristic parameters of blended coal through a blended coal characteristic prediction model based on the coal quality online monitoring data; generating a boiler coal blending and combustion scheme with optimal comprehensive power supply cost according to the combustion characteristic parameters, coal prices and pollution emission control costs; and optimizing the operation oxygen content, air distribution mode and pulverizing system operation parameters in the boiler coal blending and combustion scheme in real time according to actual inlet coal quality and boiler operation parameters, so as to guide the boiler combustion optimization. The method can improve the coal quality detection accuracy, realize intelligent optimization of the coal blending and combustion scheme, and improve the boiler combustion efficiency and economy.

Description

Technical Field

[0001] This application relates to the field of boiler coal blending technology, and in particular to a method and system for optimizing boiler coal blending management. Background Technology

[0002] Currently, coal-fired power generation is a crucial pillar of the power industry, and its fuel management directly impacts the safety and economy of unit operation. With changes in coal market supply and demand and the increasing diversity of coal types, thermal power plants often need to blend multiple coal types. Through collaborative operations involving online coal quality monitoring, blending characteristic prediction, and combustion optimization adjustments, a coal blending management technology system has been established.

[0003] However, in the coal blending schemes of related technologies, the coal quality monitoring alarm is directly used without effectively linking the coal quality data with the blending scheme formulation and combustion optimization. This may result in alarm lag when the coal quality deviation is too large, or the blending ratio cannot be dynamically adjusted according to real-time coal quality changes, thereby affecting the boiler combustion stability and overall power supply cost. Summary of the Invention

[0004] This application aims to at least partially address one of the technical problems in the related art.

[0005] Therefore, the first objective of this application is to propose an optimization method for boiler coal blending management.

[0006] The second objective of this application is to propose a boiler coal blending management optimization system.

[0007] The third objective of this application is to propose an electronic device.

[0008] To achieve the above objectives, the first aspect of this application is to propose a method for optimizing boiler coal blending management, comprising the following steps:

[0009] Acquire online coal quality monitoring data of the coal flow on the boiler feed conveyor belt, wherein the online coal quality monitoring data includes moisture, ash, volatile matter, calorific value and sulfur content; Based on the online coal quality monitoring data, the combustion characteristic parameters of the blended coal are predicted by the blended coal characteristic prediction model. The combustion characteristic parameters include ignition temperature, burnout rate, boiler efficiency, nitrogen oxide generation concentration and sulfur dioxide generation concentration. Based on the combustion characteristic parameters, combined with coal prices and pollutant emission control costs, a boiler coal blending scheme with the optimal overall power supply cost is generated. Based on the actual coal quality and boiler operating parameters, the operating oxygen content, air distribution method, and pulverizing system operating parameters in the boiler coal blending and combustion scheme are optimized in real time to guide boiler combustion optimization.

[0010] To achieve the above objectives, the second aspect of this application also proposes a boiler coal blending management optimization system, comprising the following modules: The acquisition module is used to acquire online coal quality monitoring data of the coal flow on the boiler feed conveyor belt, wherein the online coal quality monitoring data includes moisture, ash, volatile matter, calorific value and sulfur content; The prediction module is used to predict the combustion characteristic parameters of the blended coal based on the online coal quality monitoring data and through the blended coal characteristic prediction model. The combustion characteristic parameters include ignition temperature, burnout rate, boiler efficiency, nitrogen oxide generation concentration and sulfur dioxide generation concentration. The generation module is used to generate a boiler coal blending scheme with the optimal overall power supply cost based on the combustion characteristic parameters, combined with coal price and pollutant emission control costs. The optimization module is used to optimize the operating oxygen content, air distribution method, and pulverizing system operating parameters in the boiler coal blending and combustion scheme in real time based on the actual coal quality and boiler operating parameters, so as to guide boiler combustion optimization.

[0011] To achieve the above objectives, a third aspect of this application also provides an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the boiler coal blending management optimization method as described in any one of the first aspects above.

[0012] To achieve the above objectives, the fourth aspect of this application also proposes a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the boiler coal blending management optimization method described in any one of the first aspects above.

[0013] The technical solutions provided by the embodiments of this application offer at least the following beneficial effects: This application provides a strategy for formulating blending schemes by conducting comprehensive online monitoring of coal quality, online monitoring of slagging, and online monitoring of unit operating parameters, guiding boiler combustion optimization. It can improve the accuracy of coal quality detection, achieve real-time monitoring, and optimize coal blending schemes based on multi-source data, thereby improving the rationality and accuracy of boiler coal blending schemes and enhancing boiler combustion efficiency and economy.

[0014] Additional aspects and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. Attached Figure Description

[0015] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein: Figure 1 This is a flowchart of a boiler coal blending management optimization method proposed in an embodiment of this application; Figure 2 This is a schematic diagram illustrating the principle of online monitoring of coal quality in a conveyor belt of a furnace, as proposed in an embodiment of this application. Figure 3 This is a schematic diagram of the structure of a boiler coal blending management optimization system proposed in an embodiment of this application. Detailed Implementation

[0016] Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain the present invention, and should not be construed as limiting the present invention.

[0017] The following description, with reference to the accompanying drawings, illustrates a method and system for optimizing boiler coal blending management, as proposed in an embodiment of this application.

[0018] Example 1 Figure 1 This is a flowchart of a boiler coal blending management optimization method proposed in an embodiment of this application, as shown below. Figure 1 As shown, the method includes the following steps: Step S101: Obtain online coal quality monitoring data of the coal flow on the boiler feed conveyor belt, wherein the online coal quality monitoring data includes moisture, ash, volatile matter, calorific value and sulfur content.

[0019] Specifically, in the optimization of boiler coal blending management, it is first necessary to acquire the coal quality parameters of the coal flow into the furnace in real time to provide basic data for subsequent prediction of blending characteristics, formulation of blending schemes, and combustion optimization. To this end, an online coal quality monitoring device is installed on the conveyor belt. This device can continuously or quasi-continuously monitor the coal flow passing through the belt and output multiple coal quality indicators, including moisture, ash, volatile matter, calorific value, and sulfur content. These indicators cover the main industrial and elemental analysis characteristics of coal, comprehensively reflecting the combustion characteristics, pollutant generation potential, and economic value of the coal entering the furnace.

[0020] The monitoring principle is based on non-contact measurement technology, such as the interaction between radiation or spectroscopy and elements in coal. By analyzing the radiation attenuation or spectral characteristics in different energy ranges, the content of each component can be calculated.

[0021] Specifically, multi-energy rays are generated by an artificial X-ray source. After passing through the coal flow, the rays are received by a detector. Based on the different sensitivities of different energy rays to elements such as carbon, silicon, aluminum, calcium, iron, and sulfur in the coal, a multi-element mixture model is established and the equation system is solved to obtain the ash content, sulfur content, and calorific value. At the same time, the moisture content is obtained by combining a moisture detection module, and the volatile matter is calculated by using correlation models or empirical formulas.

[0022] One possible implementation is to use a belt-mounted online coal quality monitoring device. This device, installed at the head of the conveyor belt, can output parameters such as moisture, ash content, and calorific value of the coal flow in real time, and possesses high detection accuracy. For example, the root mean square error (RMS) of ash content measurement can be controlled within the range of 0.5% to 1.5%, the RMS error of calorific value measurement can be controlled within the range of 100 to 150 kcal, and the RMS error of moisture measurement can be controlled within the range of 0.5% to 2.0%. This step ensures the real-time nature, continuity, and accuracy of coal quality data, avoiding the lag and dispersion of traditional manual sampling and testing, and providing reliable data support for subsequent prediction and optimization decisions regarding blended coal characteristics.

[0023] Therefore, this step, by acquiring comprehensive coal quality parameters of the coal flow into the furnace in real time online, can promptly reflect coal quality fluctuations, overcome the lag defects of traditional sampling and testing, and provide an accurate and real-time data foundation for subsequent prediction of blended coal characteristics and optimization of blending schemes. This significantly improves the scientific nature and response speed of coal blending management, and lays the data prerequisite for the safe, economical and environmentally friendly operation of the boiler.

[0024] Step S102: Based on online coal quality monitoring data, predict the combustion characteristic parameters of the blended coal using a blended coal characteristic prediction model. The combustion characteristic parameters include ignition temperature, burnout rate, boiler efficiency, nitrogen oxide generation concentration, and sulfur dioxide generation concentration.

[0025] Specifically, this step, based on online coal quality monitoring data, constructs and utilizes a coal blending characteristic prediction model to predict key combustion characteristic parameters of the blended coal during boiler combustion. This prediction model uses basic coal quality parameters obtained from online coal quality monitoring data, such as moisture, ash, volatile matter, calorific value, and sulfur content of the coal feed stream, as input variables. It combines these parameters with the blending ratios of various individual coal types in the blend, and calculates the comprehensive combustion characteristic index of the blended coal based on the inherent correlation between coal quality parameters and combustion characteristics. These combustion characteristic parameters include at least the ignition temperature (characterizing the ease of ignition of the blended coal), the burnout rate (reflecting the degree of pulverized coal burnout), the boiler efficiency (reflecting the boiler's energy conversion efficiency), and the concentrations of nitrogen oxides and sulfur dioxide generated during combustion.

[0026] The prediction model can be established based on linear weighted relationships or nonlinear regression relationships. Linear relationships are suitable for weighted average calculations of some coal quality parameters (such as volatile matter, ash content, moisture, calorific value, and sulfur content), while nonlinear relationships are used to describe more complex mapping relationships between ignition temperature, burnout rate, and coal quality parameters. This model can quantitatively assess the combustion stability, combustion economy, and pollutant emission characteristics of blended coal under different blending schemes, providing a scientific basis for the formulation of subsequent coal blending and combustion plans.

[0027] As one possible implementation method, the mixed coal characteristic prediction model can specifically adopt the multiple linear regression method to establish the regression relationship between ignition temperature, burnout rate, boiler efficiency, nitrogen oxide generation concentration and sulfur dioxide generation concentration and coal quality parameters and operating parameters based on a large amount of experimental data, and use online coal quality monitoring data to calculate the above combustion characteristic parameters in real time.

[0028] This step, by establishing a coal blending characteristic prediction model, enables quantitative and forward-looking prediction of coal blending combustion characteristics. It overcomes the limitations of traditional reliance on experience-based judgment or post-event testing, significantly improving the scientificity and accuracy of coal blending scheme formulation, and providing reliable data support for ensuring the safety, economy, and environmental protection of boiler operation.

[0029] Step S103: Based on combustion characteristic parameters, combined with coal price and pollutant emission control costs, generate a boiler coal blending scheme with optimal overall power supply cost.

[0030] Specifically, the core of this step is to comprehensively weigh the combustion characteristic prediction results with fuel costs and environmental governance expenses in order to construct an evaluation index that can truly reflect the economics of the entire coal-fired power generation chain.

[0031] Specifically, combustion characteristic parameters encompass key dimensions such as the efficiency performance, pollutant generation potential, and operational safety of blended coal during boiler combustion. Coal price reflects the fuel procurement cost, while pollutant emission control costs include the desulfurization and denitrification agents and related equipment operating expenses required to treat emissions such as nitrogen oxides, sulfur dioxide, and particulate matter. This application establishes an optimization model with comprehensive power supply cost as the objective function, incorporating these multi-dimensional factors into a unified calculation framework. This allows for the automatic search and determination of the coal combination and its blending ratio that minimizes unit power supply cost, while meeting boiler safety and environmental emission constraints. This optimization process not only considers the inherent economics of the fuel itself but also quantifies the impact of coal quality variations on boiler efficiency, auxiliary equipment power consumption, and environmental protection facility operating costs, thus avoiding a one-sided decision that solely pursues low-priced coal while ignoring combustion efficiency and environmental costs.

[0032] As one possible implementation method, this scheme can calculate the coal quality parameters of the blended coal based on the linear relationship model of coal quality parameters, then call the combustion characteristic prediction model to obtain the boiler efficiency, nitrogen oxide generation concentration and sulfur dioxide generation concentration, and then combine the coal price delivered to the plant of each individual coal to calculate the standard coal price of the blended coal through inherent economics. At the same time, the desulfurization and denitrification costs are estimated based on the pollutant generation concentration. Finally, the power generation cost (i.e., the cost of the blended coal price converted to the unit power generation and the sum of the desulfurization and denitrification costs) is used as the comprehensive power supply cost index. The blending ratio is automatically assigned using an exhaustive method or optimization algorithm to select the most economical scheme that meets the boiler load capacity and safety and environmental protection requirements.

[0033] This step integrates combustion characteristic parameters, coal prices, and pollutant emission control costs into a comprehensive assessment, achieving a leap from single fuel costs to full-chain power supply costs. It significantly improves the economic efficiency and scientific nature of coal blending schemes, and can minimize the overall operating costs of power generation companies while ensuring safe boiler operation and environmental compliance.

[0034] Step S104: Based on the actual coal quality and boiler operating parameters, optimize the operating oxygen content, air distribution method, and pulverizing system operating parameters in the boiler coal blending and combustion scheme in real time to guide boiler combustion optimization.

[0035] Specifically, this step involves obtaining real-time monitoring data on the quality of coal entering the furnace and the current operating parameters of the boiler. Through the construction of a dynamic optimization model or preset optimization rules, key operating parameters affecting the combustion process are adjusted online.

[0036] The optimization of operating oxygen content aims to adjust the excess air coefficient in the furnace based on coal quality characteristics and load requirements, thereby balancing combustion efficiency and pollutant generation. Optimization of air distribution involves adjusting the airflow allocation in the burner area, including the burnout air opening and the air distribution ratio for each burner layer, to improve the aerodynamic and temperature fields within the furnace, suppress nitrogen oxide generation, and ensure complete combustion. Optimization of pulverizing system operating parameters involves adjusting parameters such as the pulverizer outlet temperature, pulverized coal fineness, and coal feed rate to adapt to the impact of coal quality changes on grindability and drying output, ensuring stable operation of the pulverizing system and pulverized coal quality.

[0037] The above optimization process can be based on a pre-established correlation model between coal quality, operating parameters, and combustion performance, or by using a real-time data-driven adaptive algorithm to dynamically adjust each parameter to the target value while ensuring the safe operation of the boiler.

[0038] As one implementation method, the system can combine online coal quality monitoring data with operating parameters in the unit's distributed control system. Through the combustion optimization scheme management module, it can recommend appropriate key operating parameters in real time, such as operating oxygen content, burnout damper opening, and coal mill outlet air temperature. When there are significant differences in coal quality, it can promptly adjust the blending ratio of each coal bunker or activate the standby mill to optimize the coal quality entering the furnace and ensure the safety and economy of boiler combustion.

[0039] This step, by optimizing key operating parameters in real time, can dynamically adapt to fluctuations in coal quality and load changes, effectively improving the stability and economy of boiler combustion, while reducing pollutant emissions, and achieving safe, environmentally friendly and efficient operation of the unit.

[0040] The following describes in detail the specific implementation process of each step in the boiler coal blending management optimization method proposed in this application using several specific embodiments.

[0041] Example 2 Based on the above embodiments, this embodiment provides a detailed description of the specific implementation of step S101, "obtaining online monitoring data of coal quality of the coal flow on the boiler feed belt".

[0042] In this embodiment, the specific implementation method for obtaining online monitoring data of coal quality from the coal flow entering the furnace conveyor belt is as follows. For example... Figure 2 As shown, a belt-type online coal quality detection device is installed at the head of the conveyor belt to be monitored. This device uses multi-energy artificial rays to detect the coal flow on the conveyor belt.

[0043] Specifically, artificial rays are generated by bombarding a metal target with electrons accelerated by an electric field. These artificial rays contain rays of different energy ranges, each with a different interaction cross-section with the elements in the coal. Lower-energy rays are sensitive to changes in elements such as silicon, aluminum, calcium, and iron; mid-energy rays are more sensitive to changes in elements such as calcium and iron; and higher-energy rays are sensitive to density changes but not to changes in elemental content. When the coal conveyor passes through the detection area, the detector measures the energy spectrum of the rays after attenuation by the coal, thus analyzing the changes in ray intensity in the three energy ranges. By establishing and solving a system of equations based on the attenuation laws of the rays, the content ratios of carbon, silicon, aluminum, calcium, iron, and sulfur can be obtained, leading to the calculation of the coal's ash content, sulfur content, and calorific value. By selecting more energy ranges, calculation errors can be further reduced, and measurement accuracy improved.

[0044] This equipment is capable of online detection of moisture, ash, and calorific value in conveyor belt coal flow. Its detection accuracy meets the following requirements: root mean square error (RMS) not exceeding 0.5% when ash content is less than 15%, not exceeding 1% when ash content is between 15% and 30%, and not exceeding 1.5% when ash content is greater than 30%; RMS not exceeding 100 kcal when calorific value is greater than 4600 kcal, and not exceeding 150 kcal when calorific value is less than 4600 kcal; RMS less than 0.5% when moisture content is between 5% and 12%, less than 1.5% when moisture content is between 12% and 20%, and less than 2.0% when moisture content is above 20%. Therefore, the equipment outputs online coal quality monitoring data including moisture, ash, volatile matter, calorific value, and sulfur content, providing accurate input parameters for subsequent prediction of blended coal characteristics.

[0045] This embodiment utilizes multi-energy artificial X-ray detection technology to achieve online, real-time, and high-precision monitoring of coal quality in conveyor belt coal flow. This avoids the lag and random errors of traditional sampling and testing, providing a reliable data foundation for the subsequent formulation of coal blending schemes, thereby improving the accuracy and practicality of the entire optimization method.

[0046] Example 3 Based on the above embodiments, this embodiment provides a detailed description of the specific implementation of step S102, "predicting the combustion characteristic parameters of blended coal based on the online coal quality monitoring data and the blended coal characteristic prediction model".

[0047] In this embodiment, firstly, the system acquires the online coal quality monitoring data of the coal flow entering the furnace, which is measured in real time by the belt-type online coal quality monitoring equipment in step S101. This data specifically includes basic coal quality parameters such as moisture, ash, volatile matter, calorific value and sulfur content of each single coal type.

[0048] Subsequently, based on these basic coal quality parameters and the preset blending ratios of each individual coal type, the system calculates the coal quality parameters of the blended coal using a linear weighted model. Specifically, for coal quality parameters such as volatile matter, ash content, moisture, sulfur content, and calorific value that exhibit a linear relationship, the formula is used. Calculations are performed, in which, The linear coal quality parameters of the blended coal to be determined are as follows: , , These represent the blending ratios for each type of coal. , , These are the coal quality parameters corresponding to each individual coal type. For ash-related indicators such as ash content, calculations are performed using a weighted average linear relationship related to ash content; the calculation formula is as follows: In the formula, The ash content is calculated on an as-received basis. Based on the above calculations, the system outputs the coal quality parameters of the blended coal, including the combustible volatile matter, net calorific value on an as-received basis, ash content, moisture content, and sulfur content.

[0049] After obtaining the coal quality parameters of the blended coal, the system uses them as input to call multiple prediction models to predict the combustion characteristic parameters of the blended coal.

[0050] Specifically, the system inputs the coal quality parameters of the blended coal into the ignition temperature prediction model. This model, based on the regression relationship between coal quality parameters and ignition temperature, outputs the ignition temperature IT of the blended coal. Simultaneously, the system inputs the coal quality parameters of the blended coal into the burnout rate prediction model. This model, based on the functional relationship between the burnout rate of a one-dimensional flame furnace and the coal quality parameters, outputs the burnout rate Bp of the blended coal. For boiler efficiency prediction, the system calls the boiler efficiency prediction model, which further includes sub-models for predicting fly ash carbon content, ash and slag carbon content, and flue gas temperature. The fly ash carbon content prediction sub-model is... The sub-model for predicting carbon content in ash slag is The sub-model for predicting flue gas temperature is The system predicts the carbon content of fly ash, the carbon content of ash residue, and the flue gas temperature based on these sub-models, and then calculates the boiler efficiency using the inverse balance method formula.

[0051] In addition, the system inputs the coal quality parameters of the blended coal into the nitrogen oxide generation prediction model, which is... YMNOx represents the NOx formation characteristics of different coal types under non-low-NOx combustion conditions, thus outputting the NOx formation concentration.

[0052] Finally, the system inputs the coal quality parameters of the blended coal into the sulfur dioxide generation prediction model, which is... This outputs the sulfur dioxide formation concentration. Thus, the system has completed a comprehensive prediction of the mixed coal ignition temperature, burnout rate, boiler efficiency, nitrogen oxide formation concentration, and sulfur dioxide formation concentration.

[0053] This specific implementation method establishes a complete prediction chain from online coal quality monitoring data to blended coal quality parameters, and then to various combustion characteristic parameters. This enables a quantitative assessment of the combustion performance of blended coal, providing an accurate data foundation for generating the optimal coal blending and combustion scheme with the best overall power supply cost, and significantly improving the scientificity and reliability of coal blending decisions.

[0054] Example 4 Based on the above embodiments, this embodiment provides a detailed description of the specific implementation of step S103 above, which involves "generating a boiler coal blending scheme with the optimal overall power supply cost based on the combustion characteristic parameters, combined with coal prices and pollutant emission control costs".

[0055] In this embodiment, firstly, the system obtains the combustion characteristic parameters calculated by the coal blending characteristic prediction model in step S102, including ignition temperature, burnout rate, boiler efficiency, nitrogen oxide generation concentration and sulfur dioxide generation concentration. At the same time, it obtains the coal price delivered to the plant for each raw coal and the pollutant emission control cost, wherein the pollutant emission control cost includes the cost of adding desulfurizing agent and denitrification agent.

[0056] Then, the system invokes the economic prediction model, which consists of two parts: inherent economic calculation and operational economic calculation. In the inherent economic calculation, the system calculates the actual price of the blended coal using a weighted average formula based on the blending ratio of each raw coal and the actual coal price. Specifically, the actual price of the blended coal... Based on the actual coal price of each raw coal Its blending ratio The sum of the products divided by 100 gives the result, i.e. Furthermore, the lower heating value of each raw coal and mixed coal is converted into the standard coal price to eliminate the impact of differences in calorific value on cost comparison.

[0057] In the operational economic calculation, the system calculates the impact of boiler efficiency changes on power generation coal consumption based on the predicted boiler efficiency value in the combustion characteristic parameters. Simultaneously, based on the impact of coal quality changes on the power consumption of major auxiliary equipment such as coal mills, forced draft fans, induced draft fans, primary air fans, and desulfurization system booster fans, the impact of auxiliary equipment power consumption changes on coal consumption is calculated. The sum of the two yields the change in total coal consumption.

[0058] In addition, the system calculates the changes in the dosage of denitrification and desulfurization agents based on the predicted concentrations of nitrogen oxides and sulfur dioxide, thereby obtaining the changes in the operating costs of the desulfurization and denitrification systems.

[0059] Ultimately, the system integrates the cost changes caused by variations in mixed coal price, coal consumption, and desulfurization and denitrification costs into a single power generation cost, which is equal to the mixed coal price multiplied by [missing information]. Then multiply by the coal consumption and divide by 100, and add the changes in the cost of desulfurizing and denitrifying agents. To determine the optimal blending ratio, the system uses an exhaustive method to automatically assign values ​​to the coal blending ratio. That is, it iterates through all possible blending ratio combinations, calls the coal quality parameter calculation submodule and the coal property evaluation submodule for each ratio, calculates the corresponding blended coal quality parameters and combustion characteristic parameters, and then calculates the comprehensive power supply cost under that ratio through an economic prediction model. During the iteration process, the system simultaneously checks whether the boiler output meets the load requirements and whether the inventory of each type of coal is sufficient. When a certain ratio simultaneously meets the boiler's safe operation and coal quantity constraints, its comprehensive power supply cost is recorded. After the iteration is completed, the system selects the blending ratio with the lowest comprehensive power supply cost as the optimal coal blending and combustion scheme, and outputs the corresponding coal demand and coal feeding scheme for this scheme.

[0060] This specific implementation method, by introducing an economic prediction model and exhaustive search for automatic optimization, can quantitatively assess the comprehensive impact of coal quality changes on boiler efficiency, auxiliary power consumption, and pollutant emission control costs. Thus, under the premise of ensuring the safe and environmentally friendly operation of the unit, it can accurately select the coal blending ratio with the lowest comprehensive power supply cost, significantly improving the economy and scientific nature of the coal blending scheme.

[0061] Example 5 Based on the above embodiments, this embodiment provides a detailed description of the specific implementation of step S104, "based on the actual coal quality and boiler operating parameters, optimize the operating oxygen content, air distribution method, and pulverizing system operating parameters in the boiler coal blending and combustion scheme in real time to guide boiler combustion optimization."

[0062] In this embodiment, firstly, the system acquires real-time data on the actual coal quality fed into the furnace. This data originates from an online coal quality monitoring device installed on the feed conveyor belt, whose output includes key coal quality parameters such as moisture, ash content, volatile matter, calorific value, and sulfur content. Simultaneously, the system obtains real-time boiler operating parameters from the unit's distributed control system (DCS) or plant-level monitoring information system (SIS). These parameters include at least the current unit load, furnace outlet oxygen content, burnout damper opening of each burner layer, pulverizer outlet air temperature, and pulverized coal fineness.

[0063] Subsequently, the aforementioned coal quality data and operating parameters are fed into a pre-constructed and trained combustion optimization model. This combustion optimization model is a multi-objective optimization model based on a large amount of historical operating data and hot-state test data. Its core lies in dynamically calculating the optimal combination of operating parameters that can take into account combustion stability, combustion economy, and nitrogen oxide emission control, according to different coal quality characteristics and unit load conditions.

[0064] Specifically, the model first assesses the ignition stability and burnout characteristics of the coal fed into the furnace based on parameters such as volatile matter, calorific value, and ash content, combined with the unit load. Based on this, the model recommends an optimal operating oxygen level using an internal algorithm. This oxygen level aims to balance the increased heat loss from incomplete combustion of solids due to deteriorating coal quality (such as increased ash content or decreased volatile matter) with the increased flue gas heat loss caused by excessive oxygen. Simultaneously, based on the coal's slagging tendency and nitrogen oxide formation characteristics, the model recommends the burnout damper opening for each burner layer. By adjusting the airflow distribution between the main combustion zone and the burnout zone, it suppresses the formation of fuel-type nitrogen oxides while ensuring complete combustion of pulverized coal. Furthermore, the model recommends a suitable pulverizer outlet temperature based on the coal's grindability index and moisture content to ensure that the drying output of pulverized coal matches the grinding output, preventing pulverizer blockage or insufficient output due to changes in coal quality. The recommended operating oxygen content, burnout damper opening, and coal mill outlet temperature output by the combustion optimization model are ultimately presented to operators in the form of operation instructions, or directly sent to the unit's automatic control system via an interface, thereby enabling real-time and precise adjustments to the boiler combustion process.

[0065] This specific implementation method introduces a combustion optimization model based on the actual coal quality and operating parameters, which enables dynamic and accurate recommendations for key boiler operating parameters. It can effectively address issues such as combustion instability, efficiency decline, and increased pollutant emissions caused by coal quality fluctuations, and significantly improve the safety and economy of unit operation.

[0066] Example 6 Based on the above embodiments, this embodiment will describe in detail the complete implementation of the boiler coal blending management optimization method, including data flow, processing logic and parameter configuration of specific links such as online coal quality monitoring, coal blending characteristic prediction, coal blending and combustion scheme generation and combustion optimization.

[0067] Specifically, firstly, in the online monitoring of coal quality during the conveyor belt feed into the furnace, this embodiment installs a belt-mounted online coal quality detection device at the head of the conveyor belt to be monitored. This device employs multi-energy artificial X-ray technology, generating artificial rays by bombarding a metal target with electrons accelerated by an electric field. Utilizing the differences in the interaction cross-sections between rays of different energy ranges and various elements in the coal, the energy spectrum of the rays after attenuation by the coal is measured using a detector. The intensity changes of the rays in various energy ranges are analyzed, and a system of equations is established and solved using the attenuation law of the rays to obtain the content ratios of carbon and elements such as silicon, aluminum, calcium, iron, and sulfur, thereby determining the ash content, sulfur content, and calorific value of the coal. This device does not use a radioactive source; there is no radiation output when the X-ray generator is turned off, and the radiation energy is low, making it easier to obtain or exempt from radioactive source permits. To ensure measurement accuracy, the coal flow being measured must have a particle size of less than 13mm, a coal flow thickness of more than 3cm on the conveyor belt, and a coal flow width of more than 10cm. This equipment is capable of online detection of moisture, ash content, and calorific value of coal flow from conveyor belts. Its detection accuracy is as follows: Root mean square error (RMSE) not exceeding 0.5% when ash content is less than 15%; not exceeding 1% when ash content is between 15% and 30%; and not exceeding 1.5% when ash content is greater than 30%. Regarding calorific value, the RMS error is not exceeding 100 kcal when calorific value is greater than 4600 kcal; and not exceeding 150 kcal when calorific value is less than 4600 kcal. For moisture content, the RMS error is less than 0.5% when moisture content is between 5% and 12%; less than 1.5% when moisture content is between 12% and 20%; and less than 2.0% when moisture content is above 20%. The industrial control computer is installed in the central control room to receive and process the detection data, thereby obtaining online monitoring data of the coal quality of the coal flow entering the furnace via the conveyor belt. This data includes parameters such as moisture, ash, volatile matter, calorific value, and sulfur content.

[0068] After acquiring online coal quality monitoring data, this embodiment predicts the combustion characteristic parameters of the blended coal using a blended coal characteristic prediction model. Specifically, firstly, based on the online coal quality monitoring data, the coal quality parameters of the blended coal are calculated using a linear weighted model. For linear coal quality parameters such as volatile matter, ash content, moisture, sulfur content, and calorific value, a weighted average linear relationship model is used for calculation, and the calculation formula is as follows: For parameters related to ash content, such as ash component indices, a weighted average linear relationship model related to ash content is adopted, and the calculation formula is as follows: ,in The ash content was determined based on the received data. For the combustion characteristic parameters of the blended coal, such as ignition temperature and burnout rate, a nonlinear relationship model was used. Through multiple linear regression, statistical principles were applied to process the blended coal combustion test data, and the regression relationships between the blended coal ignition temperature (IT), burnout rate (Bp), and slagging index (Sc) and various influencing factors were derived. The general relationship is expressed as follows: ,in Represents IT, Bp, or Sc. For each influencing factor or a combination thereof, The coefficient is used. Conventional analytical indicators affecting the ignition stability and combustion economy of blended coal include the dry ash-free volatile matter content of the blended coal. Received low-grade heat of heat Ash content , moisture And the blending ratio of the coal, etc. Indicators affecting the slagging index of blended coal include the ash fusion softening temperature (ST) of the blended coal, and the lower heating value on an as-received basis. Factors such as the coal ash-alkali-acid ratio (B / A), the coal ash-silicon ratio (Sp), and the blending ratio of mixed coal are considered.

[0069] Regarding the prediction of blended coal ignition characteristics, this embodiment, based on a large number of coal quality parameters and combustion performance test results, combined with the coal combustion characteristics of power plants, obtains a prediction model for the ignition temperature IT of pulverized coal airflow and a calculation method for the minimum non-oil-injection stable combustion load of the blended coal boiler. First, the minimum non-oil-injection stable combustion load Dmini for each burner is calculated using the following formula:

[0070] in, It is the ignition temperature of the pulverized coal gas flow corresponding to the coal type of the burner numbered i, in °C; It is the net calorific value of the coal type corresponding to burner number i, expressed in MJ / kg; This is the boiler furnace cross-sectional heat load under BMCR conditions, expressed in MW / m². This is the boiler burner zone wall heat load under BMCR conditions, expressed in MW / m². Then, based on the location of the pulverizer in operation, calculate the minimum non-oil-injection stable combustion load Dminh for the final coal feed. The calculation formula is as follows:

[0071] When a coal mill is shut down, the burners in that layer are not included in the Dmini calculation. This model fully considers the impact of different combustion methods, burner arrangements, and the impact of shut-down burners on combustion stability.

[0072] Regarding the prediction of burnout performance of blended coal, this embodiment, based on a large amount of coal quality parameters and combustion performance test results, combined with the coal combustion characteristics of the power plant, obtains a one-dimensional flame furnace burnout rate prediction model (Bp). Regarding the prediction of boiler efficiency of blended coal, this embodiment, based on a large amount of experimental and statistical data from the power plant, establishes prediction models for fly ash carbon content, ash residue carbon content, and flue gas temperature for different coal types under different loads. Among them, the fly ash carbon content prediction sub-model is... The sub-model for predicting carbon content in ash slag is The sub-model for predicting flue gas temperature is Wherein, Cfh is the predicted carbon content of fly ash in mixed coal, Cdz is the predicted carbon content of slag in mixed coal, and Tpy is the predicted flue gas temperature of mixed coal; F1, F2, and F3 represent the influence functions of coal quality parameters on fly ash carbon content, slag carbon content, and flue gas temperature, respectively; F1fh, F2fh, and F3fh are the load influence functions; F1rjf, F2rjf, and F3rjf are the burnout air opening influence functions; F1O2, F2O2, and F3O2 are the furnace outlet excess air coefficient influence functions; F1mp, F2mp, and F3mp are the pulverizer location influence functions; F1r and F2r are the pulverized coal fineness influence functions; and F3fw is the inlet air temperature influence function. Boiler efficiency is calculated using the inverse balance method according to the formula. Calculate the heat loss of flue gas, where q2 is the heat loss from incomplete chemical combustion, q3 is the heat loss from incomplete solid combustion, q4 is the heat loss from incomplete solid combustion, q5 is the heat dissipation loss, and q6 is the physical heat loss from ash and slag. The formula for calculating the heat loss of flue gas q2 is as follows: Where Ipy is the enthalpy of the flue gas, apy is the excess air coefficient at the outlet of the flue gas side air preheater, IIK0 is the enthalpy of the flue gas, and Qr is the heat input to the boiler. The formula for calculating the heat loss q3 due to incomplete combustion is as follows: Where CO, H2, and CH4 are the volume fractions of carbon monoxide, hydrogen, and methane in the dry flue gas, and RO2 is the volume fraction of triatomic gases in the dry flue gas. The formula for calculating the heat loss q4 from incomplete combustion of solids is as follows: ,in α fh and α lz These represent the proportions of fly ash and ash residue in the total ash content of the fuel, respectively. C lz and C fh These represent the percentage of combustible matter in ash and fly ash, respectively. The formula for calculating heat loss q5 is... Where De is the rated evaporation capacity of the boiler, and D0 is the actual evaporation capacity of the boiler. The formula for calculating the physical heat loss q6 of ash and slag is as follows: ,in( )lz is 1kg of ash residue at a temperature of θ enthalpy of time a lz The mass percentage of ash and slag discharged relative to the total ash content of the fuel fed into the furnace.

[0073] Regarding NOx formation prediction for blended coal, this embodiment combines the characteristics of the power plant's boiler equipment and the variation of key operating parameters with load. It applies the nonlinear dynamics of artificial neural networks to establish a NOx emission characteristic model for a large-scale tangential combustion boiler, predicting NOx formation concentrations under different loads. The NOx formation concentration prediction model is as follows: Where YMNOx represents the NOx formation characteristics of different coal types under non-low-NOx combustion conditions, and this value is related to the moisture, ash, volatile matter, and nitrogen content of the coal; F4fh represents the effect of load on NOx formation concentration; F4rjf represents the effect of burnout air opening on NOx formation concentration; and F4O2 represents the effect of the furnace outlet excess air coefficient on NOx formation concentration. Regarding SO2 formation prediction for blended coal, this embodiment combines the SO2 formation concentration patterns of different sulfur coal types in a one-dimensional flame furnace with the influence of different load operating parameters on SO2 formation concentration to obtain a prediction model for SO2 formation concentration under different loads, the expression of which is: F5S is related to the moisture, ash, volatile matter, and sulfur content of the coal, F5Ks,self is the effect of the self-desulfurization rate in the coal on the SO2 generation concentration, F5fh is the effect of the load on the SO2 generation concentration, and F5O2 is the effect of the excess air coefficient at the furnace outlet on the SO2 generation concentration.

[0074] In generating the optimal coal blending scheme for overall power supply cost, this embodiment calculates the overall power supply cost for each blending ratio using an economic prediction model, based on the aforementioned combustion characteristic parameters and considering coal prices and pollutant emission control costs. The economic prediction model includes inherent economic calculations and operational economic calculations. The inherent economic calculations employ the formula... Calculate the actual price of blended coal, where Mh is the actual price of blended coal, Mi is the actual price of raw coal, and Xi is the blending ratio of raw coal. The standard coal price for blended coal and mixed coal is calculated using the formula... , , Calculate, where MIb, M2b, and Mhb are the standard coal prices of raw coal 1, 2, and the mixed coal, respectively. Q net,ar 1. ( Q net,ar )2、( Q net,ar ) h These are the lower heating values ​​of raw coal 1, 2, and the mixed coal, respectively. The operational economic calculation includes the impact of boiler efficiency on coal consumption and the impact of auxiliary equipment power consumption on coal consumption. The formula for the impact of boiler efficiency on coal consumption is as follows: The impact of auxiliary equipment power consumption on coal consumption considers the changes in power consumption of the coal mill, forced draft fan, induced draft fan, primary air fan, and desulfurization system booster fan. The operating cost of the desulfurization and denitrification systems considers the changes in the dosage of desulfurizing and denitrifying agents due to variations in SO2 and NOx formation. The formula for calculating power generation cost is: Power generation cost = Mixed coal price × 10 -6× Coal consumption / 100 + Changes in desulfurization and denitrification agent costs. This embodiment uses an exhaustive method to automatically assign values ​​to the coal blending ratio and calls the coal quality calculation and coal property evaluation submodule to calculate and evaluate the quality of the blended coal, seeking the most economical coal blending scheme. When both the boiler and coal quantity meet the requirements, this scheme is the optimal coal blending scheme, and the demand for each type of coal is calculated to obtain the optimal coal feeding scheme; otherwise, a less economical scheme is sought until the coal quantity and boiler operation meet the requirements.

[0075] In the combustion optimization stage, this embodiment optimizes the operating oxygen content, air distribution method, and pulverizing system operating parameters in real time using a combustion optimization model based on the actual coal quality and boiler operating parameters. Specifically, it recommends appropriate operating oxygen content based on the coal quality characteristics and load of the coal fed into the furnace; it recommends appropriate burnout air opening based on the coal quality characteristics and load of the coal fed into the furnace; and it recommends appropriate key operating parameters such as the coal mill outlet temperature based on the coal quality parameters and combustion performance of each coal mill. Simultaneously, by combining real-time online coal quality monitoring data, real-time coal quality data, and boiler operating data, it displays boiler efficiency, coal consumption, and power generation and supply costs in real time. When there are significant differences in coal quality or when coal types with special ash content are present, the coal quality fed into the furnace is optimized in a timely manner by optimizing the blending ratio of each coal bunker or activating a backup mill, ensuring the safe operation of the boiler.

[0076] Furthermore, this embodiment also constructs a coal blending and combustion case evaluation module. This module evaluates the actual operational effectiveness of the implemented coal blending and combustion scheme through statistical analysis of actual unit operating data. This module includes safety evaluation, environmental evaluation, and economic evaluation sub-modules. The safety evaluation sub-module mainly includes the over-temperature judgment of high-temperature superheater and high-temperature reheater temperatures; the environmental evaluation sub-module mainly includes the evaluation of NOx, SO2, and particulate pollutant emission concentrations; and the economic evaluation sub-module mainly includes the evaluation of boiler efficiency, power generation coal consumption, and overall power supply cost. The coal blending and combustion evaluation module automatically filters the historical stable operating conditions of a specific blending scheme in the system background and evaluates it according to the safety, environmental, and economic evaluation sub-modules. Finally, the excellent rate of all compliant operating conditions is used to reflect the blending effect of the scheme. The excellent rate of the blending scheme is recorded in the historical database, providing reference data for formulating blending schemes and coal procurement. The coal blending evaluation is conducted by matching and searching for stable operating conditions during the actual operation of the unit according to load conditions, blended coal types, and blending ratios. The stable operating conditions are then evaluated, and the evaluation information for each stable operating condition of the corresponding blending scheme can be viewed according to the dimensions of the blending scheme. The evaluation conclusions can be adjusted based on the actual operating conditions. By summarizing existing successful and unsuccessful blending cases, a blending case experience database is formed to provide suggestions for future blending of similar coal qualities.

[0077] In summary, this embodiment, by integrating online coal quality monitoring data, blending characteristic prediction models, economic prediction models, and combustion optimization models, achieves closed-loop management of the entire process from coal quality testing and blending scheme formulation to combustion optimization. It can provide power generation companies with scientific and reasonable coal blending and combustion schemes, maximizing the blending of inexpensive, low-quality coal while ensuring the safe and environmentally friendly operation of the units, thereby improving the economic benefits of power generation companies.

[0078] To achieve the above embodiments, this application also proposes a boiler coal blending management optimization system, such as... Figure 3 As shown, the system includes: The acquisition module 100 is used to acquire online coal quality monitoring data of the coal flow on the boiler feed conveyor belt, wherein the online coal quality monitoring data includes moisture, ash, volatile matter, calorific value and sulfur content; The prediction module 200 is used to predict the combustion characteristic parameters of the blended coal based on the online coal quality monitoring data and through the blended coal characteristic prediction model. The combustion characteristic parameters include ignition temperature, burnout rate, boiler efficiency, nitrogen oxide generation concentration and sulfur dioxide generation concentration. The generation module 300 is used to generate a boiler coal blending scheme with the optimal overall power supply cost based on the combustion characteristic parameters, combined with coal price and pollutant emission control costs. The optimization module 400 is used to optimize the operating oxygen content, air distribution method, and pulverizing system operating parameters in the boiler coal blending and combustion scheme in real time based on the actual coal quality and boiler operating parameters, so as to guide boiler combustion optimization.

[0079] It should be noted that the aforementioned descriptions of the embodiments of the optimization method for boiler coal blending management also apply to the system of this application, and will not be repeated here.

[0080] In summary, the boiler coal blending management optimization method system of this application can improve the accuracy of coal quality detection, realize intelligent optimization of coal blending schemes, and improve boiler combustion efficiency and economy.

[0081] To implement the above embodiments, this application also proposes an electronic device, including: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the boiler coal blending management optimization method as described in any one of the first aspect embodiments above.

[0082] To implement the above embodiments, this application also proposes a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the boiler coal blending management optimization method as described in any one of the first aspect embodiments above.

[0083] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0084] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "multiple" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0085] Any process or method description in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0086] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0087] It should be understood that various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0088] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0089] Furthermore, the functional units in the various embodiments of this application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0090] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of this application.

Claims

1. A method for optimizing boiler coal blending management, characterized in that, Includes the following steps: Acquire online coal quality monitoring data of the coal flow on the boiler feed conveyor belt, wherein the online coal quality monitoring data includes moisture, ash, volatile matter, calorific value and sulfur content; Based on the online coal quality monitoring data, the combustion characteristic parameters of the blended coal are predicted by the blended coal characteristic prediction model. The combustion characteristic parameters include ignition temperature, burnout rate, boiler efficiency, nitrogen oxide generation concentration and sulfur dioxide generation concentration. Based on the combustion characteristic parameters, combined with coal prices and pollutant emission control costs, a boiler coal blending scheme with the optimal overall power supply cost is generated. Based on the actual coal quality and boiler operating parameters, the operating oxygen content, air distribution method, and pulverizing system operating parameters in the boiler coal blending and combustion scheme are optimized in real time to guide boiler combustion optimization.

2. The method according to claim 1, characterized in that, The acquisition of online coal quality monitoring data of the coal flow on the boiler feed conveyor belt includes: The coal quality online monitoring data is obtained by using a belt-type coal quality online detection device installed at the head of the furnace feed belt to detect the coal flow on the belt using multi-energy artificial rays.

3. The method according to claim 1, characterized in that, The prediction of combustion characteristic parameters of blended coal using the blended coal characteristic prediction model includes: Based on the online coal quality monitoring data, the coal quality parameters of the blended coal are calculated using a linear weighted model; Based on the aforementioned coal quality parameters, the ignition temperature, burnout rate, boiler efficiency, nitrogen oxide concentration, and sulfur dioxide concentration are predicted using ignition temperature prediction models, burnout rate prediction models, boiler efficiency prediction models, nitrogen oxide generation prediction models, and sulfur dioxide generation prediction models, respectively.

4. The method according to claim 3, characterized in that, The calculation of coal quality parameters of the blended coal using a linear weighted model includes: The linear coal quality parameters are calculated using the following formula: in, For linear coal quality parameters, , , These represent the blending ratios for each type of coal. , , These are the coal quality parameters corresponding to each individual coal type.

5. The method according to claim 3, characterized in that, The boiler efficiency prediction model includes: a fly ash carbon content prediction sub-model, an ash slag carbon content prediction sub-model, and a flue gas temperature prediction sub-model; wherein... The fly ash carbon content prediction sub-model is expressed by the following formula: ， The carbon content prediction sub-model for ash slag is expressed by the following formula: ， The flue gas temperature prediction sub-model is expressed by the following formula: ， in, F1 ( M t ，A ar ，V daf ，Q net,ar The effect of coal quality parameters on the carbon content of fly ash is shown in the figure. F1 fh The effect of load on the carbon content of fly ash. F1 rjf The effect of burnout ventilation opening on the carbon content of fly ash. F1 O2 The effect of the excess air coefficient at the furnace outlet on the carbon content of fly ash. F1 mp The impact of the location of the coal mill in operation on the carbon content of fly ash. F1 r The effect of pulverized coal fineness on the carbon content of fly ash. F2 ( M t ，A ar ，V daf ，Q net,ar The influence of coal quality parameters on the carbon content of slag is shown in the figure. F2 fh The effect of load on the carbon content of slag. F2 rjf The effect of burnout air opening on the carbon content of slag. F2 O2 The effect of the excess air coefficient at the furnace outlet on the carbon content of slag. F2 mp To investigate the impact of the location of the coal mill on the carbon content of the slag. F2 r The effect of coal powder fineness on the carbon content of slag. F3 ( M t ，A ar ，V daf ，Q net,ar The influence of coal quality parameters on flue gas temperature is shown in the figure. F3 fh The effect of load on flue gas temperature, F3 rjf The effect of burnout air opening on exhaust gas temperature. F3 O2 The effect of the excess air coefficient at the furnace outlet on the flue gas temperature. F3 mp To investigate the impact of the location of the coal mill on the flue gas temperature. F3 fw The effect of inlet air temperature on exhaust gas temperature.

6. The method according to claim 1, characterized in that, The method for generating the boiler coal blending scheme with the optimal overall power supply cost includes: Based on the combustion characteristic parameters, combined with coal prices and pollutant emission control costs, the comprehensive power supply cost under each blending ratio is calculated using an economic prediction model. An exhaustive method is used to automatically assign values ​​to the coal blending ratio, and the coal blending ratio with the lowest overall power supply cost is determined as the optimal coal blending scheme.

7. The method according to claim 6, characterized in that, The economic forecasting model is used to perform inherent economic calculations and operational economic calculations. In the inherent economic calculations, the actual price of mixed coal is calculated using the following formula: in, This refers to the actual price of mixed coal. This refers to the actual price of raw coal. This refers to the blending ratio of the raw coal.

8. The method according to claim 1, characterized in that, The real-time optimization of the boiler coal blending scheme, including the operating oxygen content, air distribution method, and pulverizing system operating parameters, includes: Based on the actual coal quality and boiler operating parameters, the combustion optimization model recommends the operating oxygen content, burnout damper opening, and pulverizer outlet temperature.

9. A boiler coal blending management and optimization system, characterized in that, Includes the following modules: The acquisition module is used to acquire online coal quality monitoring data of the coal flow on the boiler feed conveyor belt, wherein the online coal quality monitoring data includes moisture, ash, volatile matter, calorific value and sulfur content; The prediction module is used to predict the combustion characteristic parameters of the blended coal based on the online coal quality monitoring data and through the blended coal characteristic prediction model. The combustion characteristic parameters include ignition temperature, burnout rate, boiler efficiency, nitrogen oxide generation concentration and sulfur dioxide generation concentration. The generation module is used to generate a boiler coal blending scheme with the optimal overall power supply cost based on the combustion characteristic parameters, combined with coal price and pollutant emission control costs. The optimization module is used to optimize the operating oxygen content, air distribution method, and pulverizing system operating parameters in the boiler coal blending and combustion scheme in real time based on the actual coal quality and boiler operating parameters, so as to guide boiler combustion optimization.

10. An electronic device, comprising: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the boiler coal blending management optimization method as described in any one of claims 1-8.

Images