Operation optimization method and device for coal blending combustion of coal-fired unit

Abstract

The invention relates to an operation optimization method and device for coal blending combustion of a coal-fired unit, and the method comprises the steps: obtaining at least one of parameters related to the operation state of the coal-fired unit, flue gas component parameters related to combustion, parameters related to a coal pulverizing system, historical coal quality parameter data and coal price; performing data cleaning on at least one item of data; establishing at least one of a safety index, an environmental protection index, an economic index and a combustibility index of the coal-fired unit, and establishing a case library of the coal-fired unit according to the target working condition; retrieving operation parameters of the load interval of the corresponding coal-fired unit in the case library; and optimizing the stock coal type blending scheme by using the at least one piece of historical coal blending quality information to generate a predicted blending scheme meeting a preset optimal condition. According to the embodiment, the requirement for the temporary peak in the operation process can be met with the highest load historical coal blending quality as the target, and the situation that a unit cannot respond to the high load requirement is avoided.

Description

Technical Field

[0001] This application relates to the technical fields of power plant boiler coal blending technology and operation optimization technology, and particularly relates to an operation optimization method and device for coal blending and co-firing in a coal-fired unit. Background Art

[0002] Currently, there have been many studies on coal blending optimization technology for thermal power plants, mainly including neural network models and particle swarm algorithms, etc.

[0003] In related technologies, the coal blending method based on the BP (Back Propagation) neural network mainly relies on a large amount of operation data. By constructing the BP neural network structure, setting appropriate hidden layer numbers, and selecting appropriate activation functions, an optimized coal blending model can be obtained. And the algorithm based on PSO (Particle Swarm Optimization) optimized feedforward neural network establishes a coal quality prediction model for blended coal, and solves it through the non-dominated sorting multi-objective genetic algorithm to obtain a coal blending result with better indexes such as combustibility and economy.

[0004] However, in related technologies, the BP neural network requires a large amount of data for early training, which takes a long time, and the control accuracy in the early stage is not ideal. In addition, this algorithm may also have the situation of local convergence, which means that the algorithm may fall into a local optimal solution instead of the global optimal solution. The particle swarm algorithm has high requirements for the selection of initial parameters and the quality of data preprocessing. Different parameters and data processing methods may lead to different results, and a large number of experiments need to be conducted for comparison to determine the optimization scheme. Summary of the Invention

[0005] This application provides an operation optimization method and device for coal blending and co-firing in a coal-fired unit to solve the problems in related technologies that the BP neural network requires a large amount of data for early training, takes a long time, and the control accuracy in the early stage is not ideal. In addition, this algorithm may also have the situation of local convergence, resulting in falling into a local optimal solution, and the particle swarm algorithm has high requirements for the selection of initial parameters and the quality of data preprocessing. Different parameters and data processing methods may lead to different results.

[0006] An embodiment of the first aspect of the present application provides an operation optimization method for coal blending combustion in a coal-fired unit, including the following steps: obtaining at least one piece of data among parameters related to the operation state of the coal-fired unit, flue gas composition parameters related to combustion, parameters related to the coal pulverizing system, historical coal quality parameter data, and coal type prices; cleaning the at least one piece of data to remove outliers in the at least one piece of data and generating parameter data that meets preset conditions; based on the parameter data that meets the preset conditions, establishing at least one of the safety index, environmental protection index, economic index, and combustion index of the coal-fired unit, and screening out the target operating conditions during boiler operation according to the at least one index, so as to establish a case library for the coal-fired unit according to the target operating conditions; retrieving the operating parameters corresponding to the load range of the coal-fired unit in the case library, and generating reference information for optimizing the operation adjustment of the coal-fired unit according to the operating parameters; based on the reference information, using at least one piece of historical coal blending coal quality information to optimize the coal blending plan for the stock coal types, so as to generate a predicted coal blending plan that meets preset optimal conditions.

[0007] The embodiment of the present application can target the historical coal quality of the highest load coal blending, meet the requirements for temporary peak shaving during operation, avoid the situation where the unit cannot respond to high load requirements, solve the problems of poor prediction accuracy and slow operation of the existing model, the results are more reasonable, combine the excellent case library and the genetic algorithm, provide the coal blending plan in real time, and achieve the goals of the unit's safety, environmental protection, combustion, and economy in operation. When providing excellent cases, the operation data can be output at the same time to provide the operation data of excellent cases for the reference of operators.

[0008] Optionally, in an embodiment of the present application, the obtaining at least one piece of data among parameters related to the unit operation state, flue gas composition parameters related to combustion, parameters related to the coal pulverizing system, historical coal quality parameter data, and coal type prices includes: obtaining the parameters related to the unit operation state including boiler load, main steam pressure, main steam flow rate, main steam temperature, reheated steam temperature, feed water flow rate, total air volume, secondary air volume, and boiler efficiency from the power station monitoring information system; obtaining the flue gas composition parameters related to combustion including carbon monoxide content in the flue gas at the inlet of the selective catalytic reduction reactor, oxygen content in the flue gas, sulfur dioxide content in the flue gas at the inlet of the desulfurization system, carbon content in fly ash, carbon content in slag, and flue gas temperature; obtaining the parameters related to the coal pulverizing system including coal feeding amount, mill current, primary air volume of the mill, primary air temperature of the mill, and outlet temperature of the mill; obtaining the historical coal quality parameter data including carbon content on an as-received basis, sulfur content on an as-received basis, ash content on an as-received basis, moisture content on an as-received basis, volatile matter content on an as-received basis, and net calorific value on an as-received basis.

[0009] The embodiments of the present application can obtain detailed parameters related to the operating status of coal-fired units, flue gas composition parameters related to combustion, parameters related to the coal pulverizing system, historical coal quality parameter data, coal type prices, etc. from the power plant SIS (Supervisory Information System) system, further reflecting the real-time working conditions of the units, facilitating the evaluation of combustion efficiency and environmental impacts, and further providing data references for coal reserve and operation optimization of the power plant.

[0010] Optionally, in an embodiment of the present application, the establishment formula of the safety index is: , Wherein, is the given main steam temperature value, and are the lower and upper limits of the interval, and are the score values corresponding to the two endpoints of the interval.

[0011] The embodiments of the present application can improve the calculation accuracy according to the formula of the safety index, ensuring the stability of power supply.

[0012] Optionally, in an embodiment of the present application, the establishment formula of the environmental protection index is: , Wherein, ai is the weight, a1 + a2 + a3 = 1, s represents the emission standard, min represents the best level value in the operation of boilers of the same type of parameters, is sulfur dioxide, is nitrogen oxides, is soot.

[0013] The embodiments of the present application can improve the calculation accuracy according to the formula of the environmental protection index, helping to reduce the impact on the environment.

[0014] Optionally, in an embodiment of the present application, the coal consumption cost calculation formula of the economic index is: , Wherein, and are both blending ratios, and are both coal prices, is the weighted average calorific value of blended coal, is the actual power supply coal consumption; The normalization formula of the economic index is: , Wherein, The electricity generated per unit fuel cost of the unit and are respectively the minimum and maximum values of the data in the case base; The establishment formula of the combustion index is: , wherein, is the combustion index.

[0015] The embodiments of the present application can further improve the calculation accuracy, improve the economic benefits, and improve the energy utilization efficiency according to the formulas of the economic index and the combustion index.

[0016] Optionally, in an embodiment of the present application, after retrieving the operation parameters of the corresponding load interval in the case base, it further includes: based on the case base, determining whether the case index satisfying the first preset condition is greater than the case index satisfying the second preset condition; if the case index satisfying the first preset condition is greater than the case index satisfying the second preset condition, then retain the case index satisfying the first preset condition in the case base and delete the case index satisfying the second preset condition; if there are both greater than and less than the case index satisfying the second preset condition among the case indexes satisfying the first preset condition, then retain the case index satisfying the first preset condition and the case index satisfying the second preset condition.

[0017] The embodiments of the present application can further output the operation data together when providing excellent cases, and provide the operation data of excellent cases for the reference of operation personnel.

[0018] Optionally, in an embodiment of the present application, the calculation formula for optimizing the blending plan of the stock coal types by using at least one piece of historical coal blending coal quality information is: , wherein, Q is the calorific value of the predicted blended coal, S is the S content of the predicted blended coal, A is the ash content of the predicted blended coal, and p is the price of the predicted blended coal.

[0019] The purpose of taking the historical coal blending coal quality at the highest load as the target in the embodiments of the present application is to meet the requirements for temporary peak shaving during the operation process, and further avoid the situation where the unit cannot respond to the high load requirements.

[0020] The second aspect of the present application provides an operation optimization device for coal blending combustion in a coal-fired unit, including: an acquisition module, configured to acquire at least one piece of data among parameters related to the operation state of the coal-fired unit, flue gas component parameters related to combustion, parameters related to the coal pulverizing system, historical coal quality parameter data, and coal type prices; a preprocessing module, configured to perform data cleaning on the at least one piece of data to eliminate outliers in the at least one piece of data and generate parameter data that meets preset conditions; a building module, configured to establish at least one of the safety index, environmental protection index, economic index, and combustion index of the coal-fired unit based on the parameter data that meets the preset conditions, and screen out the target operating conditions during boiler operation according to the at least one index, so as to establish a case library for the coal-fired unit according to the target operating conditions; a retrieval module, configured to retrieve the operating parameters corresponding to the load range of the coal-fired unit in the case library and generate reference information for optimizing the operation adjustment of the coal-fired unit according to the operating parameters; an optimization module, configured to optimize the blending plan of the in-stock coal types based on the reference information by using at least one piece of historical coal blending coal quality information to generate a predicted blending plan that meets preset optimal conditions.

[0021] Optionally, in an embodiment of the present application, the acquisition module includes: a first acquisition unit, configured to acquire the parameters related to the unit operation state including boiler load, main steam pressure, main steam flow rate, main steam temperature, reheated steam temperature, feed water flow rate, total air volume, secondary air volume, and boiler efficiency from the power station monitoring information system; a second acquisition unit, configured to acquire the flue gas component parameters related to combustion including carbon monoxide content in the flue gas at the inlet of the selective catalytic reduction reactor, oxygen content in the flue gas, sulfur dioxide content in the flue gas at the inlet of the desulfurization system, carbon content in fly ash, carbon content in slag, and flue gas temperature; a third acquisition unit, configured to acquire the parameters related to the coal pulverizing system including coal feeding amount, mill current, primary air volume of the mill, primary air temperature of the mill, and outlet temperature of the mill; a fourth acquisition unit, configured to acquire the historical coal quality parameter data including carbon content on an as-received basis, sulfur content on an as-received basis, ash content on an as-received basis, moisture content on an as-received basis, volatile matter on an as-received basis, and lower calorific value on an as-received basis.

[0022] Optionally, in an embodiment of the present application, the establishment formula of the safety index is: , where is the given main steam temperature value, and are the lower and upper limits of the interval, and are the score values corresponding to the two endpoints of the interval.

[0023] Optionally, in an embodiment of the present application, the establishment formula for the environmental protection index is: , wherein, ai is the weight, a1 + a2 + a3 = 1, s represents the emission standard, min represents the optimal level value during the operation of boilers with the same type of parameters, is sulfur dioxide, is nitrogen oxides, is soot.

[0024] Optionally, in an embodiment of the present application, the calculation formula for the coal consumption cost of the economic index is: , wherein, and are both blending ratios, and are both coal prices, is the weighted average calorific value of the blended coal, is the actual coal consumption for power supply; The normalization formula for the economic index is: , wherein, is the electricity that can be supplied by the unit fuel cost of the unit, and are respectively the minimum value and the maximum value of the data in the case library; The establishment formula for the combustibility index is: , wherein, is the combustibility index.

[0025] Optionally, in an embodiment of the present application, it further includes: a judgment module, configured to, after retrieving the operation parameters of the corresponding load interval in the case library, judge whether the case index that meets the first preset condition is greater than the case index that meets the second preset condition based on the case library; a deletion module, configured to, when the case index that meets the first preset condition is greater than the case index that meets the second preset condition, retain the case index that meets the first preset condition in the case library and delete the case index that meets the second preset condition; a retention module, configured to, when there are both case indexes that are greater than and less than the case index that meets the second preset condition among the case indexes that meet the first preset condition, retain the case indexes that meet the first preset condition and the case indexes that meet the second preset condition.

[0026] Optionally, in an embodiment of the present application, the formula for optimizing the blending plan of the stock coal types using at least one piece of historical blended coal quality information is: , Among them, Q is the calorific value of the predicted blended coal, S is the S content of the predicted blended coal, A is the ash content of the predicted blended coal, and p is the price of the predicted blended coal.

[0027] An embodiment of the third aspect of the present application provides an electronic device, including: a memory, a processor, and a computer program stored on the memory and executable on the processor. The processor executes the program to implement the operation optimization method for coal blending and co-firing of a coal-fired unit as described in the above embodiment.

[0028] An embodiment of the fourth aspect of the present application provides a computer-readable storage medium, which stores a computer program that, when executed by a processor, implements the operation optimization method for coal blending and co-firing of a coal-fired unit as described above.

[0029] Embodiments of the present application can take the coal quality of the historical coal blending at the highest load as the target, meet the requirements for temporary peak shaving during operation, avoid the situation where the unit cannot respond to high load requirements, solve the problems of poor prediction accuracy and slow operation of the existing model, and the results are more reasonable. By combining the excellent case library and the genetic algorithm, a coal blending plan is provided in real time, achieving the goals of safe, environmental, combustible, and economic operation of the unit. When providing excellent cases, the operation data can be output at the same time, providing the operation data of excellent cases for operators to refer to. Thus, it solves the problems in the related art that a large amount of data is required for the pre-training of the BP neural network, which takes a long time, and the control accuracy in the early stage is not ideal. In addition, the algorithm may also have the situation of local convergence, resulting in falling into a local optimal solution, and the particle swarm algorithm has high requirements for the selection of initial parameters and the quality of data preprocessing, and different parameters and data processing methods may lead to different results.

[0030] Additional aspects and advantages of the present application will be given in part in the following description, become apparent in part from the following description, or be understood through the practice of the present application. Description of the Drawings

[0031] The above and / or additional aspects and advantages of the present application will become apparent and be readily understood from the following description of the embodiments in conjunction with the drawings, where: Figure 1 is a flowchart of an operation optimization method for coal blending and co-firing of a coal-fired unit according to an embodiment of the present application; Figure 2 is an algorithm structure diagram of an operation optimization method for coal blending and co-firing of a coal-fired unit according to an embodiment of the present application; Figure 3 is a schematic flowchart of an operation optimization method for coal blending and co-firing of a coal-fired unit according to an embodiment of the present application; Figure 4 It is a schematic structural diagram of an operation optimization device for blending different coals in a coal-fired unit according to an embodiment of the present application; Figure 5 It is a schematic structural diagram of an electronic device according to an embodiment of the present application. Detailed implementation manners

[0032] The embodiments of the present application will be described in detail below. Examples of the embodiments are shown in the accompanying drawings, where 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 are intended to explain the present application, and should not be construed as a limitation to the present application.

[0033] The operation optimization method and device for blending different coals in a coal-fired unit according to an embodiment of the present application will be described below with reference to the accompanying drawings. In view of the problems in the related art mentioned in the above background art that a large amount of data is required for the pre-training of the BP neural network, which takes a long time, and the control accuracy in the early stage is not ideal. In addition, the algorithm may also have a situation of local convergence, resulting in falling into a local optimal solution, and the particle swarm algorithm has high requirements for the selection of initial parameters and the quality of data preprocessing, and different parameters and data processing methods may lead to different results, the present application provides an operation optimization method for blending different coals in a coal-fired unit. In this method, the coal quality of the historical coal blending with the highest load can be used as the target to meet the requirements for temporary peak shaving during the operation process, and avoid the situation that the unit cannot respond to the high-load requirements, solve the problems of poor prediction accuracy and slow operation of the existing model, and the results are more reasonable. By combining the excellent case library and the genetic algorithm, a coal blending plan is provided in real time to achieve the goals of the safe, environmental, combustible and economic operation of the unit. When providing excellent cases, the operation data can be output at the same time to provide the operation data of excellent cases for the reference of operators. Thus, the problems in the related art that a large amount of data is required for the pre-training of the BP neural network, which takes a long time, and the control accuracy in the early stage is not ideal. In addition, the algorithm may also have a situation of local convergence, resulting in falling into a local optimal solution, and the particle swarm algorithm has high requirements for the selection of initial parameters and the quality of data preprocessing, and different parameters and data processing methods may lead to different results, etc. are solved.

[0034] Specifically, Figure 1 It is a schematic flow chart of an operation optimization method for blending different coals in a coal-fired unit provided by an embodiment of the present application.

[0035] As Figure 1 shown, the operation optimization method for blending different coals in a coal-fired unit includes the following steps: In step S101, at least one piece of data is obtained, including parameters related to the operating state of the coal-fired unit, flue gas component parameters related to combustion, parameters related to the coal pulverizing system, historical coal quality parameter data, and coal type prices.

[0036] It can be understood that the coal-fired unit in the embodiment of the present application can convert the thermal energy generated by coal combustion into mechanical energy, and then into electrical energy through a generator; the coal pulverizing system can grind raw coal into pulverized coal with a fineness meeting the combustion requirements and transport it to the burner.

[0037] In the actual execution process, the embodiment of the present application can obtain data such as parameters related to the operating state of the coal-fired unit, flue gas component parameters related to combustion, parameters related to the coal pulverizing system, historical coal quality parameter data, and coal type prices, so as to reflect the real-time working condition of the unit, facilitate the evaluation of combustion efficiency and environmental impact, and provide data reference for the coal reserve and operation optimization of the power plant.

[0038] Optionally, in an embodiment of the present application, obtaining at least one piece of data including parameters related to the unit operating state, flue gas component parameters related to combustion, parameters related to the coal pulverizing system, historical coal quality parameter data, and coal type prices includes: obtaining parameters related to the unit operating state including boiler load, main steam pressure, main steam flow rate, main steam temperature, reheated steam temperature, feed water flow rate, total air volume, secondary air volume, and boiler efficiency from the power station monitoring information system; obtaining flue gas component parameters related to combustion including carbon monoxide content in the flue gas at the inlet of the selective catalytic reduction reactor, oxygen content in the flue gas, sulfur dioxide content in the flue gas at the inlet of the desulfurization system, carbon content in fly ash, carbon content in slag, and flue gas temperature at the outlet; obtaining parameters related to the coal pulverizing system including coal feeding amount, mill current, primary air volume of the mill, primary air temperature of the mill, and outlet temperature of the mill; obtaining historical coal quality parameter data including carbon content on the as-received basis, sulfur content on the as-received basis, ash content on the as-received basis, moisture content on the as-received basis, volatile matter on the as-received basis, and lower calorific value on the as-received basis.

[0039] It can be understood that the boiler load in the embodiment of the present application can be the thermal power currently generated by the boiler; the carbon content in fly ash / slag can reflect the degree of incomplete combustion and affect the combustion efficiency; the coal feeding amount can be the quantity of coal controlled to enter the mill and affect the coal pulverizing efficiency.

[0040] Among them, the embodiment of the present application can select parameters related to the operating status of the unit from the SIS system of a 660MW ultra-supercritical coal-fired power generation unit, including boiler load, main steam pressure, main steam flow, main steam temperature, reheat steam temperature, feed water flow, total air volume, secondary air volume and boiler efficiency, select flue gas composition parameters related to combustion, including SCR inlet flue gas CO content, flue gas oxygen content, desulfurization system inlet SO2 content, fly ash carbon content, slag carbon content and exhaust temperature, select parameters related to the pulverizing system, including coal feed rate, mill current, mill primary air volume, mill primary air temperature and mill outlet temperature, obtain historical coal quality parameter data and coal type price, coal quality parameters include elemental analysis and industrial analysis data of coal types, including received basis carbon content C, received basis sulfur content S, received basis ash content A, received basis moisture content M, received basis volatile matter V, received basis low calorific value Q.

[0041] The embodiment of the present application can obtain detailed parameters related to the operating status of the coal-fired unit, combustion-related flue gas composition parameters, pulverizing system-related parameters, historical coal quality parameter data, and coal type price data from the power plant SIS system, further reflecting the real-time working status of the unit, facilitating the evaluation of combustion efficiency and environmental impact, and further providing data reference for coal reserves and operation optimization of power plants.

[0042] In step S102 , at least one item of data is cleaned to remove abnormal values in the at least one item of data and generate parameter data that meets preset conditions.

[0043] It can be understood that the parameter data of the preset conditions in the embodiment of the present application can be normal parameter data after eliminating abnormal values; the data cleaning method in the embodiment of the present application includes date field formatting, removing missing values, deleting abnormal data, etc.

[0044] Specifically, the embodiments of the present application can perform data preprocessing and data cleaning to eliminate outliers, generate normal parameter data after eliminating outliers, improve the quality of the data set, and make the analysis results more reliable.

[0045] The embodiment of the present application can convert the date format of the acquired data, remove missing data, and use a mean filtering method to remove abnormal fluctuating data, thereby eliminating irregular short-term fluctuations and making the data smoother, which facilitates better evaluation of equipment performance, combustion efficiency and environmental impact.

[0046] It should be noted that the preset conditions can be set by those skilled in the art according to actual conditions and are not specifically limited here.

[0047] In step S103, based on the parameter data that meet the preset conditions, at least one of the safety index, environmental protection index, economic index, and combustion index of the coal-fired unit is established, and the target operating conditions during boiler operation are screened according to the at least one index, so as to establish a case base of the coal-fired unit according to the target operating conditions.

[0048] It can be understood that in the process of screening the operating conditions when the boiler is in a good operating state and establishing a case base in the embodiments of the present application, the screening and calibration of good cases are as follows: the safety index is above 85 points, or the environmental protection index is above 85 points, or the economic index is above 85 points, or the combustion index is above 92. Based on a large amount of data, the screening criteria for good cases are: the safety index is above 90 points, or the environmental protection index is above 90 points, or the economic index is above 90 points, or the combustion index is above 93.

[0049] In the actual execution process, the embodiments of the present application can establish the safety index of the coal-fired unit, such as equipment failure rate, number of accidental shutdowns, etc., based on the normal parameter data after removing outliers; environmental protection index, such as nitrogen oxides, sulfur oxides, particulate matter emissions, etc.; economic index, such as fuel cost, power generation efficiency, maintenance cost, etc.; combustion index, such as combustion efficiency, carbon content in fly ash, carbon content in slag, etc., and screen the target operating conditions when the boiler is in a good operating state according to the above indexes, so as to establish a case base of the coal-fired unit according to the target operating conditions.

[0050] The embodiments of the present application can establish an excellent case base, solve the problems of poor prediction accuracy and slow operation of the existing model, and the results are more reasonable. By combining the excellent case base with the genetic algorithm, a coal blending scheme is provided in real time to achieve the goals of the unit's safety, environmental protection, combustion, and economy operation.

[0051] It should be noted that the preset conditions can be set by those skilled in the art according to the actual situation, and no specific limitation is made here.

[0052] Optionally, in an embodiment of the present application, the establishment formula of the safety index is: , Wherein, is the given main steam temperature value, and are the lower and upper limits of the interval, and are the corresponding score values at both ends of the interval.

[0053] Among them, the embodiment of the present application takes the main steam temperature in the main parameters of the boiler as an example, based on the main steam temperature value x given in the boiler design book, assuming that the real-time main steam temperature parameter is xi, and uses m=|xi-x| to judge the size of the real-time parameter deviation from the design value. The larger m is, the greater the deviation of the unit from the design value, and the more unsafe it is. The setting method of the score y corresponding to m is as follows: when 0<m≤3, its score range is [100, 90], and linear interpolation is used for scoring; when 3<m≤10, its score range is [90,60]; when m>10, the score is uniformly 0. Linear interpolation is used for scoring, that is, the value range is divided into K segments, and the values of the endpoints of each interval are a1, a2, a3...ak-1, and the corresponding score values are s1, s2, s3...sk-1, then in the corresponding interval (ai, ai+1), the score of the parameter is obtained by the following formula: .

[0054] The embodiment of the present application can improve the accuracy of calculation based on the formula of the safety index and ensure the stability of power supply.

[0055] Optionally, in one embodiment of the present application, the formula for establishing the environmental performance index is: , Among them, ai is the weight, a1+a2+a3=1, s represents the emission standard, and min represents the optimal level value of the same parameter in boiler operation. is sulfur dioxide, For nitrogen oxides, For smoke and dust.

[0056] The embodiment of the present application may consider the actual unit emission (i.e., after desulfurization) indicators, assuming that the emission parameters are: SO2, NOx and k (smoke), and define the following emission evaluation indicators: , Among them, ai is the weight, a1+a2+a3=1; subscript s represents the emission standard, subscript min represents the optimal level value of the same parameter in boiler operation, or the appropriate value set manually. The meaning of the I value is that when the emissions just meet the standards, the environmental protection score is 60 points, and when the optimal state is reached, the score is 100 points. The larger the I value, the lower the pollutant emissions.

[0057] The embodiments of the present application can improve the accuracy of calculations based on the formula of environmental protection indicators, which helps to reduce the impact on the environment.

[0058] Optionally, in one embodiment of the present application, the coal consumption cost calculation formula of the economic indicator is: , Among them, and are both co-firing ratios, and are both coal prices, is the weighted average calorific value of blended coal, is the actual power supply coal consumption; The normalization formula for the economic index is: , Among them, is the power that can be supplied by the unit fuel cost of the unit, and are respectively the minimum and maximum values of the data in the case library; The establishment formula for the combustion index is: , Among them, is the combustion index.

[0059] Among them, in the embodiment of the present application, taking the co-firing of two kinds of coal as an example, assuming the calorific values of the two kinds of coal are Q1 and Q2 respectively, the co-firing ratios are a1 and a2 respectively, and the coal prices are P1 and P2 respectively, the coal consumption cost is calculated according to the following formula:

[0060] Among them, Qavg is the weighted average calorific value of blended coal, bg is the actual power supply coal consumption, and the physical meaning of Pu is the power that can be supplied by the unit fuel cost of the unit (kWh / yuan). The larger P is, the more fuel-efficient the case is and the better the economy. Further, the economic index is normalized: , Pumin and Pumax are respectively the minimum and maximum values of the data in all cases. The larger P is, the better the economy.

[0061] The combustion index r is represented by the boiler efficiency and is calculated according to the following formula: .

[0062] The embodiment of the present application can further improve the calculation accuracy, improve the economic benefit, and improve the energy utilization efficiency according to the formulas of the economic index and the combustion index.

[0063] In step S104, retrieve the operation parameters of the corresponding load interval of the coal-fired unit in the case library, and generate reference information for the operation optimization and adjustment of the coal-fired unit according to the operation parameters.

[0064] It can be understood that in the specific retrieval process of the embodiment of the present application, the load change interval issued by the power grid can be divided according to 10MW, and the retrieval is carried out according to the divided intervals.

[0065] In the actual implementation process, the embodiment of the present application can retrieve the operating parameters of the corresponding load interval in the case library according to the load curve sent by the power grid in advance, obtain the operating parameters, coal quality parameters, coal price and coal feeding amount when the unit operates well in the corresponding load interval, and output the retrieved historical operating parameters as a reference for operation optimization and adjustment.

[0066] The embodiment of the present application can retrieve the operating parameters of the load interval of the corresponding coal-fired unit, generate reference information for the operation optimization and adjustment of the coal-fired unit, and output the operation data together when providing excellent cases, providing the operation data of excellent cases for the operation personnel to refer to. It can not only effectively respond to the change of the power grid load, but also maximize the economic benefits on the premise of ensuring safety and environmental protection.

[0067] Optionally, in an embodiment of the present application, after retrieving the operating parameters of the corresponding load interval in the case library, it further includes: based on the case library, determining whether the case index that meets the first preset condition is greater than the case index that meets the second preset condition; if the case index that meets the first preset condition is greater than the case index that meets the second preset condition, then retain the case index that meets the first preset condition in the case library and delete the case index that meets the second preset condition; if there are both case indexes that are greater than and less than the case index that meets the second preset condition among the case indexes that meet the first preset condition, then retain the case indexes that meet the first preset condition and the case indexes that meet the second preset condition.

[0068] It can be understood that the case index of the first preset condition in the embodiment of the present application can be the index of a certain case and is a case with a larger index, and the case index of the second preset condition can be the index of another case and is a case with a smaller index.

[0069] Among them, the embodiment of the present application can, based on the case library, take the cases with a load change within 10MW as a category of cases in the obtained results, compare the indexes in the category of cases, determine whether the index of a certain case is greater than the index of another case. If the index of a certain case is greater than the index of another case, then retain the case with the larger index in the case library and output the parameters of this case, and at the same time delete the case with the smaller index in the case library; if there are both cases with indexes greater than and less than the index of another case, then retain both cases and output them at the same time.

[0070] For example, for cases ai and aj, if it satisfies |load(ai) - load(aj)| < 10MW, and for any index x ∈ (y, I, P, r), satisfies ai.x > aj.x, then retain case ai and delete aj; For cases ai and aj, if the load satisfies |(ai) - load(aj)| < 10MW, and there is at least one index x ∈ (y, I, P, r) such that ai.x < aj.x, and at the same time there is at least one x ∈ (y, I, P, r) such that ai.x > aj.x, then both cases ai and aj are retained.

[0071] In the embodiments of the present application, when providing excellent cases, the operation data can be output together to provide the operation data of excellent cases for the reference of operators.

[0072] It should be noted that the first preset condition and the second preset condition can be set by those skilled in the art according to the actual situation, and no specific limitation is made here.

[0073] In step S105, based on the reference information, at least one piece of historical coal blending quality information is used to optimize the inventory coal blending plan to generate a predicted blending plan that meets the preset optimal conditions.

[0074] It can be understood that the embodiments of the present application give the retrieval results according to the load curve issued by the power grid within 2 hours. The results include all the data in step S101 for the reference of operators; the predicted blending plan that meets the preset optimal conditions in the embodiments of the present application can be the optimal predicted blending plan.

[0075] As a possible implementation manner, the embodiments of the present application can optimize the inventory coal blending plan based on the reference information and use at least one piece of historical coal blending quality information to generate an optimal predicted blending plan. The NSGA-II algorithm is used to optimize the coal blending plan with the goal of minimizing the difference in the historical coal blending quality at the highest load among the retrieved cases and the lowest price. The crossover ratio is set to 0.7, the number of iterations is 300, and the population size is 30. The algorithm structure is as Figure 2 shown.

[0076] The objective function is written as follows: y(1)= Qd -(x(1)*Q1+x(2)*Q2+x(3)*Q3), y(2)=x(1)*P1+x(2)*P2+x(3)*P3, y(3)=Sd-(x(1)*S1+x(2)*S2+x(3)*S3), y(3)=Ad-(x(1)*A1+x(2)*A2+x(3)*A3).

[0077] Among them, Ai, Qi, Pi, and Si are the ash content, calorific value, price, and sulfur content of each coal type respectively, Qd, Sd, and Ad are the calorific value, sulfur content, and ash content of the blended coal obtained after retrieval respectively, and x(i) is the proportion of the coal type, that is, the parameter to be optimized.

[0078] The embodiments of the present application can optimize the blending plan of the stockpiled coal types to generate an optimal predicted blending plan, thereby outputting the predicted coal blending data and its corresponding objective function value, meeting the requirements for temporary peak shaving during operation, and avoiding the situation where the unit cannot respond to high load requirements.

[0079] Among them, in one embodiment of the present application, the formula for optimizing the blending plan of the stockpiled coal types using at least one piece of historical coal blending coal quality information is: , where Q is the calorific value of the predicted coal blend, S is the S content of the predicted coal blend, A is the ash content of the predicted coal blend, and p is the price of the predicted coal blend.

[0080] The above optimization process aims to minimize the difference from the historical coal blending coal quality at the highest load of the retrieved cases and to have the lowest price, that is: .

[0081] The purpose of the embodiments of the present application to target the historical coal blending coal quality at the highest load is to meet the requirements for temporary peak shaving during operation and further avoid the situation where the unit cannot respond to high load requirements.

[0082] Specifically, as can be combined with Figure 2 and Figure 3 shown, a specific embodiment is used to elaborate in detail the working principle of the operation optimization method for coal blending and firing in a coal-fired unit in the embodiments of the present application.

[0083] As Figure 2 shown, the embodiments of the present application may include the following steps: Step S201: Set the number of objectives and the variable range.

[0084] Step S202: Randomly generate the initial population P0.

[0085] Step S203: Calculate the objective function value of each individual in the current population Pt.

[0086] Step S204: Perform a fast non-dominated sorting on the current population.

[0087] Step S205: Calculate the crowding degree of each individual in the population.

[0088] Step S206: Perform a selection operation using the tournament algorithm.

[0089] Step S207: Perform a crossover operation with probability p and a mutation operation with p + 1.

[0090] Step S208: Generate the intermediate sub-population Qt.

[0091] Step S209: Rt == Pt ∪ Qt.

[0092] Step S210: Calculate the objective function values of the individuals in Rt.

[0093] Step S211: Perform non-dominated sorting according to the objective function values.

[0094] Step S212: Select N individuals according to the rank and crowding degree of the solutions to fill Pt+1.

[0095] Step S213: Determine whether the termination condition is reached? If so, end the process; if not, execute Step S203.

[0096] Further, as Figure 3 shown, the embodiments of the present application may include the following steps: Step S301: Select parameters related to the unit operation status, flue gas composition, coal pulverizing system, and coal quality data from the power plant SIS system.

[0097] Step S302: Establish safety indexes, environmental protection indexes, economic indexes, and combustion indexes, and screen the working conditions when the boiler operation status is good to form a case library.

[0098] Step S303: The load curve issued in advance by the power grid.

[0099] Step S304: According to the load curve issued in advance by the power grid, retrieve the operation parameters corresponding to the load interval in the above case library, and obtain the operation parameters, coal quality parameters, coal price, and coal feeding amount when the unit operates well within the corresponding load interval.

[0100] Step S305: The calorific value, sulfur content, ash content, and other coal quality data of the existing coal types in the coal bunker.

[0101] Step S306: Use the historical coal blending coal quality information as the optimization objective, and use the multi-objective genetic algorithm to optimize and predict the existing inventory coal blending plan.

[0102] Step S307: Output historical operation data and coal quality data; output predicted coal blending data.

[0103] According to the operation optimization method of coal blending and combustion of coal-fired units proposed in the embodiment of the present application, it can take the highest load historical coal blending and coal quality as the target, meet the requirements for temporary peaks during operation, avoid the situation where the unit cannot respond to high load requirements, solve the problems of poor prediction accuracy and slow calculation of existing models, and the results are more reasonable. It combines the excellent case library with the genetic algorithm to provide coal blending solutions in real time to achieve the goals of unit safety, environmental protection, combustion and economic operation. When providing excellent cases, the operation data can be output at the same time to provide excellent case operation data for reference by operators. Thus, it solves the problem in the related art that the early training of the BP neural network requires a large amount of data, takes a long time, and the early control accuracy is not ideal. In addition, the algorithm may also experience local convergence, resulting in falling into a local optimal solution, and the particle swarm algorithm has high requirements on the selection of initial parameters and the quality of data preprocessing. Different parameters and data processing methods may lead to different results.

[0104] Next, the operation optimization device for coal blending and combustion of a coal-fired unit proposed in accordance with an embodiment of the present application will be described with reference to the accompanying drawings.

[0105] Figure 4 It is a structural schematic diagram of the operation optimization device for coal blending and combustion of a coal-fired unit in an embodiment of the present application.

[0106] like Figure 4 As shown, the operation optimization device 10 for coal blending of a coal-fired unit includes: an acquisition module 100 , a pre-processing module 200 , a creation module 300 , a retrieval module 400 and an optimization module 500 .

[0107] Specifically, the acquisition module 100 is used to obtain at least one of the parameters related to the operating status of the coal-fired unit, the flue gas composition parameters related to combustion, the parameters related to the pulverizing system, historical coal quality parameter data and coal price.

[0108] The pre-processing module 200 is used for data cleaning of at least one item of data to remove abnormal values in at least one item of data and generate parameter data that meets preset conditions.

[0109] Establish module 300, which is used to establish at least one indicator of the safety index, environmental protection index, economic index and combustibility index of the coal-fired unit based on parameter data that meets preset conditions, and filter out the target operating conditions when the boiler is in operation according to at least one indicator, so as to establish a case library of the coal-fired unit according to the target operating conditions.

[0110] The retrieval module 400 is used to retrieve the operating parameters of the load range corresponding to the coal-fired unit in the case library, and generate reference information for optimizing and adjusting the operation of the coal-fired unit based on the operating parameters.

[0111] An optimization module 500 is configured to optimize the blending scheme of the in - stock coal types based on reference information and by using at least one piece of historical coal blending quality information, so as to generate a predicted blending scheme that meets preset optimal conditions.

[0112] Optionally, in an embodiment of the present application, the acquisition module 100 includes: a first acquisition unit, a second acquisition unit, a third acquisition unit, and a fourth acquisition unit.

[0113] Among them, the first acquisition unit is configured to acquire parameters related to the operating state of the unit, including boiler load, main steam pressure, main steam flow rate, main steam temperature, reheated steam temperature, feed water flow rate, total air volume, secondary air volume, and boiler efficiency, from the power station monitoring information system.

[0114] The second acquisition unit is configured to acquire flue gas composition parameters related to combustion, including carbon monoxide content in the flue gas at the inlet of the selective catalytic reduction reactor, oxygen content in the flue gas, sulfur dioxide content in the flue gas at the inlet of the desulfurization system, carbon content in fly ash, carbon content in slag, and flue gas discharge temperature.

[0115] The third acquisition unit is configured to acquire parameters related to the coal pulverizing system, including coal feeding amount, mill current, primary air volume of the mill, primary air temperature of the mill, and outlet temperature of the mill.

[0116] The fourth acquisition unit is configured to acquire historical coal quality parameter data, including carbon content on the as - received basis, sulfur content on the as - received basis, ash content on the as - received basis, moisture content on the as - received basis, volatile matter content on the as - received basis, and lower calorific value on the as - received basis.

[0117] Optionally, in an embodiment of the present application, the establishment formula for the safety index is: , Among them, is the given value of the main steam temperature, and are the lower and upper limits of the interval, and are the corresponding score values at the two endpoints of the interval.

[0118] Optionally, in an embodiment of the present application, the establishment formula for the environmental protection index is: , Among them, ai is the weight, a1 + a2 + a3 = 1, s represents the emission standard, min represents the best level value in the operation of boilers of the same type of parameters, is sulfur dioxide, is nitrogen oxides, is soot.

[0119] Optionally, in an embodiment of the present application, the calculation formula for the coal consumption cost of the economic index is: , Among them, and are both co - firing ratios, and are both coal prices, is the weighted average calorific value of blended coal, is the actual coal consumption for power supply; The normalization formula for the economic index is: , Among them, is the power that can be supplied by the unit fuel cost of the unit, and are respectively the minimum and maximum values of the data in the case base; The establishment formula for the combustion index is: , Among them, is the combustion index.

[0120] Optionally, in an embodiment of the present application, the operation optimization device 10 for coal blending in a coal - fired unit further includes: a judgment module, a deletion module, and a retention module.

[0121] Among them, the judgment module is used to judge whether the case index satisfying the first preset condition is greater than the case index satisfying the second preset condition based on the case base after retrieving the operation parameters of the corresponding load interval in the case base.

[0122] The deletion module is used to retain the case index satisfying the first preset condition and delete the case index satisfying the second preset condition in the case base when the case index satisfying the first preset condition is greater than the case index satisfying the second preset condition.

[0123] The retention module is used to retain the case index satisfying the first preset condition and the case index satisfying the second preset condition when there are both case indexes greater than and less than the case index satisfying the second preset condition among the case indexes satisfying the first preset condition.

[0124] Optionally, in an embodiment of the present application, the formula for optimizing the blending plan of the in - stock coal types using at least one piece of historical coal blending coal quality information is: , Among them, Q is the calorific value of the predicted blended coal, S is the S content of the predicted blended coal, A is the ash content of the predicted blended coal, and p is the price of the predicted blended coal.

[0125] It should be noted that the foregoing explanatory description of the embodiments of the operation optimization method for co - firing of blended coal in coal - fired units is also applicable to the operation optimization device for co - firing of blended coal in coal - fired units of this embodiment, and will not be elaborated here.

[0126] The operation optimization device for co - firing of blended coal in coal - fired units proposed according to the embodiments of the present application can target the coal quality of the highest - load historical blended coal, meet the requirements for temporary peak shaving during operation, avoid the situation where the unit cannot respond to high - load requirements, solve the problems of poor prediction accuracy and slow operation speed in existing models, and the results are more reasonable. By combining an excellent case library and a genetic algorithm, it can provide a coal blending plan in real - time, achieving the goals of the unit's safety, environmental protection, combustion performance, and economic operation. When providing excellent cases, it can also output the operation data at the same time, providing the operation data of excellent cases for operators to refer to. Thus, it solves the problems in related technologies that the BP neural network requires a large amount of data for pre - training, takes a long time, and the control accuracy in the early stage is not ideal. In addition, this algorithm may also have the situation of local convergence, resulting in falling into a local optimal solution, and the particle swarm algorithm has high requirements for the selection of initial parameters and the quality of data pre - processing, and different parameters and data processing methods may lead to different results.

[0127] Figure 5 The following is a schematic structural diagram of an electronic device provided by an embodiment of the present application. The electronic device may include: A memory 501, a processor 502, and a computer program stored on the memory 501 and executable on the processor 502.

[0128] When the processor 502 executes the program, it implements the operation optimization method for co - firing of blended coal in coal - fired units provided in the above - mentioned embodiment.

[0129] Furthermore, the electronic device further includes: A communication interface 503 for communication between the memory 501 and the processor 502.

[0130] The memory 501 is used to store a computer program executable on the processor 502.

[0131] The memory 501 may include a high - speed RAM memory, and may also include non - volatile memory, such as at least one disk memory.

[0132] If the memory 501, the processor 502, and the communication interface 503 are implemented independently, the communication interface 503, the memory 501, and the processor 502 can be interconnected via a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 5 only a thick line is used in Figure 5 , but it does not mean that there is only one bus or one type of bus.

[0133] Optionally, in a specific implementation, if the memory 501, the processor 502, and the communication interface 503 are integrated on a single chip, the memory 501, the processor 502, and the communication interface 503 can communicate with each other via an internal interface.

[0134] The processor 502 may be a Central Processing Unit (CPU), or an Application Specific Integrated Circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application.

[0135] This embodiment also provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the above-mentioned operation optimization method for coal blending combustion of a coal-fired unit is implemented.

[0136] In the description of this specification, the descriptions with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples", etc. mean that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in any one or N embodiments or examples in a suitable manner. In addition, without contradiction, those skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples.

[0137] In addition, 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 quantity of the indicated technical features. Thus, features defined with "first" and "second" may explicitly or implicitly include at least one such feature. In the description of this application, the meaning of "N" is at least two, such as two, three, etc., unless otherwise specifically defined.

[0138] Any process or method description represented in a flowchart or described otherwise herein can be understood to represent a module, segment, or portion of code including one or N executable instructions for implementing a customized logical function or process. The scope of the preferred embodiments of this application includes additional implementations, where functions may be executed in a substantially simultaneous manner or in a reverse order according to the functions involved, rather than in the order shown or discussed, which should be understood by those skilled in the technical field to which the embodiments of this application pertain.

[0139] The logic and / or steps represented in a flowchart or described otherwise herein, for example, can be considered as a sequenced list of executable instructions for implementing a logical function, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other systems that can fetch and execute instructions from the instruction execution system, apparatus, or device), or in conjunction with such instruction execution systems, apparatus, or devices. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by or in conjunction with an instruction execution system, apparatus, or device. More specific examples (non-exhaustive list) of computer-readable media include the following: an electrical connection portion with one or N wirings (electronic device), a portable computer diskette (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically by optically scanning the paper or other media, followed by editing, interpretation, or other appropriate processing as necessary, and then stored in a computer memory.

[0140] It should be understood that each part of the present application can be implemented by hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, any one of the following techniques known in the art or a combination thereof can be used: discrete logic circuits with logic gate circuits for implementing logical functions on data signals, application-specific integrated circuits with suitable combinational logic gate circuits, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0141] Those of ordinary skill in the art can understand that all or part of the steps carried by the method of the above embodiments can be completed by instructing relevant hardware through a program, and the program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiments.

[0142] In addition, in each embodiment of the present application, the functional units can be integrated into a processing module, or each unit can exist physically alone, or two or more units can be integrated into one module. The above integrated module can be implemented in the form of hardware or in the form of a software functional module. When the above integrated module is implemented in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0143] The above-mentioned storage medium can be a read-only memory, a magnetic disk, an optical disc, etc. Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and should not be construed as limiting the present application. Those of ordinary skill in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present application.

Claims

1. An operation optimization method for coal blending and co-firing in a coal-fired unit, characterized in that It includes the following steps: Obtain at least one piece of data among parameters related to the operating status of a coal-fired unit, flue gas component parameters related to combustion, parameters related to the coal pulverizing system, historical coal quality parameter data, and coal type prices; Clean the at least one piece of data to eliminate outliers in the at least one piece of data and generate parameter data that meets preset conditions; Based on the parameter data that meets the preset conditions, establish at least one of the safety index, environmental protection index, economic index, and combustion index of the coal-fired unit, and screen out the target operating conditions during boiler operation according to the at least one index, so as to establish a case library for the coal-fired unit according to the target operating conditions; Retrieve the operating parameters corresponding to the load range of the coal-fired unit in the case library, and generate reference information for optimizing the operation adjustment of the coal-fired unit according to the operating parameters; Based on the reference information, optimize the blending plan of the in-stock coal types using at least one piece of historical blended coal quality information to generate a predicted blending plan that meets preset optimal conditions.

2. The method according to claim 1, wherein The obtaining of at least one piece of data among parameters related to the unit operating status, flue gas component parameters related to combustion, parameters related to the coal pulverizing system, historical coal quality parameter data, and coal type prices includes: Obtain the parameters related to the unit operating status including boiler load, main steam pressure, main steam flow rate, main steam temperature, reheated steam temperature, feed water flow rate, total air volume, secondary air volume, and boiler efficiency from the power station monitoring information system; Obtain the flue gas component parameters related to combustion including the carbon monoxide content in the flue gas at the inlet of the selective catalytic reduction reactor, oxygen content in the flue gas, sulfur dioxide content in the flue gas at the inlet of the desulfurization system, carbon content in fly ash, carbon content in slag, and flue gas temperature; Obtain the parameters related to the coal pulverizing system including coal feeding amount, mill current, primary air volume of the mill, primary air temperature of the mill, and outlet temperature of the mill; Obtain the historical coal quality parameter data including carbon content on as-received basis, sulfur content on as-received basis, ash content on as-received basis, moisture content on as-received basis, volatile matter on as-received basis, and net calorific value on as-received basis.

3. The method according to claim 1, wherein The establishment formula for the safety index is: ， wherein, is the given main steam temperature value, and are the lower and upper limits of the interval, and are the corresponding score values at both ends of the said interval.

4. The method according to claim 1, wherein The establishment formula for the environmental protection index is: ， Among them, \(a_i\) is the weight, \(a_1 + a_2 + a_3 = 1\), \(s\) represents the emission standard, and min represents the best level value during the operation of boilers of the same type of parameters. is sulfur dioxide, is nitrogen oxides, is soot.

5. The method according to claim 1, wherein The coal consumption cost calculation formula for the economic index is: ， wherein, and are both co-firing ratios, and are both coal prices, is the weighted average calorific value of blended coal, is the actual power supply coal consumption; The normalization formula for the economic index is: ， Among them, is the power that can be supplied by the unit fuel cost of the unit, and are respectively the minimum value and the maximum value of the data in the case base; The establishment formula for the combustion index is: ， Among them, is the combustibility index.

6. The method according to claim 1, characterized in that, After retrieving the operating parameters corresponding to the load range in the case library, it further includes: Based on the case library, determine whether the case index that meets the first preset condition is greater than the case index that meets the second preset condition; If the case index that meets the first preset condition is greater than the case index that meets the second preset condition, retain the case index that meets the first preset condition in the case library and delete the case index that meets the second preset condition; If there are both case indexes that are greater than and less than the case index that meets the second preset condition among the case indexes that meet the first preset condition, retain the case indexes that meet the first preset condition and the case indexes that meet the second preset condition.

7. The method according to claim 1, wherein The formula for optimizing the blending plan of the in-stock coal types using at least one piece of historical blended coal quality information is: ， Wherein, Q is the calorific value of the predicted coal blend, S is the S content of the predicted coal blend, A is the ash content of the predicted coal blend, and p is the price of the predicted coal blend.

8. An operation optimization device for coal blending combustion in a coal-fired unit, characterized in that, include: An acquisition module, configured to acquire at least one of parameters related to the operating status of the coal-fired unit, flue gas composition parameters related to combustion, parameters related to the pulverizing system, historical coal quality parameter data, and coal price; A preprocessing module, configured to clean the at least one item of data to remove abnormal values in the at least one item of data and generate parameter data that meets preset conditions; an establishment module for establishing at least one indicator of a safety index, an environmental index, an economic index, and a combustibility index of the coal-fired unit based on the parameter data that meets the preset conditions, and screening a target operating condition for boiler operation according to the at least one indicator, so as to establish a case library for the coal-fired unit according to the target operating condition; a retrieval module, configured to retrieve operating parameters corresponding to the load range of the coal-fired unit from the case library, and generate reference information for optimizing and adjusting the operation of the coal-fired unit based on the operating parameters; The optimization module is used to optimize the inventory coal blending scheme based on the reference information and using at least one historical coal blending and coal quality information to generate a predicted blending scheme that meets the preset optimal conditions.

9. An electronic device, characterized in that, include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the method for optimizing the operation of coal blending and combustion in a coal-fired unit as described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, The program is executed by a processor to implement the operation optimization method for coal blending and combustion of a coal-fired unit as described in any one of claims 1 to 7.

Images