Thermal power unit operation method, device, equipment and storage medium

Abstract

The present invention discloses a method for operating a thermal power unit, including obtaining a corresponding relationship model between operating factors and intermediate variables using a DDQN algorithm in advance; searching a pre-created benchmark database for theoretical intermediate variables corresponding to the highest economic benefit of the thermal power unit under the boundary conditions of the current operation of the thermal power unit according to the boundary conditions; determining and outputting theoretical operating factors corresponding to the theoretical intermediate variables according to the theoretical intermediate variables and the corresponding relationship model, so as to control the operation of the thermal power unit according to the theoretical operating factors. The present application uses a DDQN algorithm to determine a corresponding relationship model between operating factors and intermediate variables, and the theoretical intermediate variables when the economic benefit is the highest determine the theoretical operating factors to ensure that the thermal power unit maintains a relatively high economic benefit operation state. The present application also provides a thermal power unit operation device, equipment, and computer-readable storage medium, which have the above-mentioned beneficial effects.

Description

Technical Field

[0001] The present invention relates to the field of thermal power generation technology, and in particular to a method, device, equipment and computer-readable storage medium for operating a thermal power unit. Background Art

[0002] Electric energy is a kind of clean energy that is currently widely used. Existing power stations include thermal power stations, hydroelectric power stations, wind power stations and nuclear power stations. Among the various power stations currently put into use in my country, thermal power stations still account for a relatively high proportion of power generation and are widely used in industrial and household electricity. It can be seen that reducing the cost of electricity use and improving the economic benefits of thermal power stations are of great significance to the economic operation of all walks of life. In order to maximize the economic benefits of thermal power stations, it is necessary to increase the power generation efficiency of thermal power units as much as possible and reduce the power generation cost of thermal power units. Summary of the invention

[0003] The purpose of the present invention is to provide a method, device, equipment and computer-readable storage medium for operating a thermal power unit, which can improve the economic benefits of the thermal power unit to a certain extent.

[0004] In order to solve the above technical problems, the present invention provides a method for operating a thermal power unit, comprising:

[0005] The corresponding relationship model between the operating factors and the intermediate variables is obtained in advance using the DDQN algorithm through the historical operating factors and the corresponding historical intermediate variables;

[0006] According to the boundary conditions of the current operation of the thermal power unit, searching in a pre-created benchmark database the theoretical intermediate variables corresponding to the highest economic benefit of the thermal power unit under the boundary conditions;

[0007] According to the theoretical intermediate variable and the corresponding relationship model, the theoretical operating factor corresponding to the theoretical intermediate variable is determined and output, so as to control the operation of the thermal power unit according to the theoretical operating factor.

[0008] In an optional embodiment of the present application, after determining and outputting the theoretical operation factor corresponding to the theoretical intermediate variable, the method further includes:

[0009] Collecting actual intermediate variables generated by controlling the thermal power unit according to multiple groups of theoretical operating factors within a period of time according to a predetermined period;

[0010] According to the actual intermediate variables and the corresponding theoretical operating factors, the corresponding relationship model is modified using the DDQN algorithm.

[0011] In an optional embodiment of the present application, a corresponding relationship model between the operation factors and the intermediate variables is obtained in advance by using the DDQN algorithm through the historical operation factors and the corresponding historical intermediate variables, including:

[0012] Collect historical operating factors and corresponding historical intermediate variables;

[0013] Performing Lasso regression and data clustering on both the historical operation factors and the historical intermediate variables;

[0014] The historical operation factors and the historical intermediate variables after data processing are learned using the DDQN algorithm to obtain the corresponding relationship model.

[0015] In an optional embodiment of the present application, the process of pre-creating a theoretical intermediate variable corresponding to the highest economic benefit in the benchmark database includes:

[0016] Pre-collecting multiple groups of historical intermediate variables corresponding to the thermal power unit and the historical coal consumption per unit power generation corresponding to each group of the historical intermediate variables;

[0017] Neural network training is performed on the historical intermediate variables and the corresponding historical coal consumption under different boundary conditions to obtain the corresponding relationship between the intermediate variables and the corresponding coal consumption under different boundary conditions, and based on the corresponding relationship, it is determined that the intermediate variable with the lowest coal consumption under each different boundary condition is the theoretical intermediate variable corresponding to the highest economic benefit.

[0018] In an optional embodiment of the present application, after determining and outputting the theoretical operation factor corresponding to the theoretical intermediate variable, the method further includes:

[0019] Collecting boundary conditions corresponding to actual intermediate variables of the thermal power unit within a period of time and actual coal consumption per unit power generation according to a preset period;

[0020] According to the actual intermediate variables and the corresponding actual coal consumption under different boundary conditions, the theoretical intermediate variables corresponding to the highest economic benefit in the benchmark database are updated.

[0021] The present application also provides a thermal power unit operation device, comprising:

[0022] Create a module for obtaining a corresponding relationship model between operation factors and intermediate variables using the DDQN algorithm through historical operation factors and corresponding historical intermediate variables in advance;

[0023] A search module is used to search, according to the boundary conditions of the current operation of the thermal power unit, in a pre-created benchmark database for the theoretical intermediate variable corresponding to the highest economic benefit of the thermal power unit under the boundary conditions;

[0024] The operation module is used to determine and output the theoretical operation factor corresponding to the theoretical intermediate variable according to the theoretical intermediate variable and the corresponding relationship model, so as to control the operation of the thermal power unit according to the theoretical operation factor.

[0025] In an optional embodiment of the present application, it also includes a first correction module, which is used to control the actual intermediate variables generated by the thermal power unit according to multiple groups of the theoretical operating factors within a predetermined period acquisition period after determining and outputting the theoretical operating factors corresponding to the theoretical intermediate variables; and to correct the corresponding relationship model using the DDQN algorithm based on the actual intermediate variables and the corresponding theoretical operating factors.

[0026] In an optional embodiment of the present application, it also includes a learning and training module, which is used to pre-collect multiple groups of historical intermediate variables corresponding to the thermal power units and the historical coal consumption per unit power generation corresponding to each group of the historical intermediate variables; neural network training is performed on the historical intermediate variables and the corresponding historical coal consumption under different boundary conditions to obtain the corresponding relationship between the intermediate variables and the corresponding coal consumption under different boundary conditions; and based on the corresponding relationship, under each different boundary condition, the intermediate variable with the least coal consumption is the theoretical intermediate variable corresponding to the highest economic benefit.

[0027] The present application also provides a thermal power unit operation device, comprising:

[0028] Memory for storing computer programs;

[0029] A processor is used to implement the steps of the thermal power unit operation method as described in any of the above items when executing the computer program.

[0030] The present application also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the method for operating a thermal power unit as described in any one of the above items are implemented.

[0031] The present invention provides an operation method for a thermal power unit, comprising obtaining a corresponding relationship model between operation factors and intermediate variables by using a DDQN algorithm in advance through historical operation factors and corresponding historical intermediate variables; searching, according to the boundary conditions of the current operation of the thermal power unit, for theoretical intermediate variables corresponding to the highest economic benefits of the thermal power unit under the boundary conditions in a pre-created benchmark database; and determining and outputting theoretical operation factors corresponding to the theoretical intermediate variables according to the theoretical intermediate variables and the corresponding relationship model, so as to control the operation of the thermal power unit according to the theoretical operation factors.

[0032] In this application, the DDQN algorithm is used to predetermine the corresponding relationship model between the operating factors and intermediate variables for the operation of the thermal power unit, and the theoretical operating factors are determined in combination with the theoretical intermediate variables corresponding to the highest economic benefits under the boundary conditions of the current thermal power unit. Therefore, the operation of the thermal power unit can be controlled according to the theoretical operating factors, which can ensure that the thermal power unit maintains a relatively high economic efficiency operating state to a certain extent, which is conducive to reducing the operating costs of the thermal power unit to a great extent.

[0033] The present application also provides a thermal power unit operation device, equipment and computer-readable storage medium, which have the above-mentioned beneficial effects. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the embodiments of the present invention or the technical solutions of the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0035] Figure 1 A schematic diagram of a flow chart of a method for operating a thermal power unit provided in an embodiment of the present application;

[0036] Figure 2 A structural block diagram of a thermal power unit operation and management device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0037] During the actual operation of thermal power units, the temperature, air volume, etc. of the thermal power units need to be properly adjusted under different unit loads, different temperatures, different coal qualities, etc., so as to maximize the power generation power per unit mass of fuel, thereby reducing the coal consumption of the thermal power units to a certain extent and reducing the operating costs of the thermal power units.

[0038] However, at present, when adjusting the parameters that affect the power generation of thermal power units, such as the wind volume and temperature, they are often set based on human experience, which has no scientific theoretical basis and cannot maximize the use of fuel energy and improve the power generation efficiency of thermal power units.

[0039] In order to enable those skilled in the art to better understand the scheme of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific implementation methods. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0040] like Figure 1 As shown, Figure 1 A schematic flow chart of a method for operating a thermal power plant provided in an embodiment of the present application, wherein the method for operating a thermal power plant may include:

[0041] S11: Using the historical operating factors and the corresponding historical intermediate variables, a corresponding relationship model between the operating factors and the intermediate variables is obtained using the DDQN algorithm.

[0042] Among them, the operating factors may include but are not limited to any one of the air temperature, air pressure and air volume at the outlet of the coal mill, the opening of the hot air valve at the mill inlet, the instantaneous coal feed rate of the coal feeder, and the secondary air volume of the furnace; they mainly refer to the parameters that can be artificially controlled to control the coal combustion process when the thermal power unit is generating electricity.

[0043] Intermediate variables may include but are not limited to any one of the following: air preheater exhaust gas temperature, main steam temperature, main steam pressure, reheat steam temperature, condenser end difference, boiler combustion coal consumption, and power generation capacity; they mainly refer to the parameters of the coal combustion process of the thermal power unit.

[0044] It should be noted that during the operation of a thermal power unit, the coal needs to be first conveyed to the coal mill through a conveyor belt. After the coal mill grinds the coal, it blows the crushed coal powder into the furnace through primary hot air. The primary hot air is the hot air at the outlet of the coal mill. The air temperature, air pressure and air volume at the outlet of the coal mill affect the temperature of the coal powder entering the furnace and the amount of coal fed to a certain extent. In addition, the opening of the hot air valve at the mill inlet, that is, the opening of the inlet valve from the coal mill to the furnace, also affects the air volume and air pressure of the primary hot air to a certain extent.

[0045] The instantaneous coal feeding amount of the coal feeder refers to the mass of coal instantly transmitted by the conveyor belt to the coal mill. The instantaneous coal feeding amount of the coal feeder also directly affects the coal feeding amount from the coal mill outlet to the furnace. The secondary air volume of the furnace is the air volume that provides oxygen during the coal combustion process. It is generally cold air, which will take away the heat in the furnace to a certain extent. Therefore, the air volume also needs to be controlled within a reasonable range to avoid too much heat being taken away while providing sufficient oxygen.

[0046] Intermediate variables are parameters that characterize the power generation status of thermal power units to a certain extent and change under the influence of operating factors.

[0047] To this end, in this embodiment, the corresponding relationship model between the operation factors and the intermediate variables is obtained through the DDQN (Deep Reinforcement Learning with Double Q-learning) algorithm.

[0048] DDQN eliminates the problem of over-estimation by decoupling the selection of the target Q-value action and the calculation of the target Q-value. Therefore, compared with other learning algorithms, the DDQN algorithm can avoid the algorithm model obtained by learning from the local optimal result due to over-estimation, and ultimately make the obtained algorithm model more accurate.

[0049] When constructing a corresponding relationship model between operating factors and intermediate variables, the relevant data of historical operating factors and historical intermediate variables can be first extracted from the database; and then the relevant data of historical operating factors and historical intermediate variables can be standardized. For example, Lasso regression operation can be used to reduce the dimension of historical operating factors and historical intermediate variables, and then data clustering can be performed to reduce the number of historical operating factors and historical intermediate variables, so as to avoid local optimal and local transition fitting in the subsequent determination of the corresponding relationship model, and improve the accuracy of the corresponding relationship model obtained by learning the data of historical operating factors and historical intermediate variables after data processing using the DDQN algorithm.

[0050] S12: According to the boundary conditions of the current operation of the thermal power unit, the theoretical intermediate variables corresponding to the highest economic benefits of the thermal power unit under the boundary conditions are searched in a pre-created benchmark database.

[0051] The boundary conditions may include but are not limited to any one of the unit load, ambient temperature and coal quality data; the boundary conditions mainly refer to the restrictive conditions for the operation of thermal power units, such as the number and model of units, the quality of coal transported, etc.

[0052] Coal quality data mainly refers to the element content in the coal fed into the furnace, such as the carbon content and sulfur content per gram of coal; it also includes data such as the calorific value of coal.

[0053] Under different boundary conditions, the corresponding intermediate variables when the thermal power unit obtains the highest economic benefit are different. The thermal power unit obtains the highest economic benefit, which means that the coal consumption per unit of power generation is the least.

[0054] To this end, it is possible to collect multiple groups of historical intermediate variables generated during the operation of the thermal power unit and the coal consumption per unit power generation corresponding to each group of the historical intermediate variables;

[0055] The neural network training is carried out for the historical intermediate variables and the corresponding historical coal consumption per unit power under different boundary conditions, so as to determine the corresponding relationship between the intermediate variables and the coal consumption under different boundary conditions;

[0056] Under different boundary conditions determined based on this corresponding relationship, the intermediate variable with the lowest coal consumption is the theoretical intermediate variable corresponding to the highest economic benefit.

[0057] The theoretical intermediate variables corresponding to the highest economic benefits under different boundary conditions are stored in the benchmark database. During the operation of the thermal power unit, the corresponding theoretical intermediate variables are queried in the benchmark database through the current boundary conditions of the thermal power unit. Obviously, if the intermediate variables controlling the operation of the thermal power unit can reach the theoretical intermediate variables, the economic benefits of the thermal power unit can reach the highest.

[0058] S13: According to the theoretical intermediate variables and the corresponding relationship model, the theoretical operation factors corresponding to the theoretical intermediate variables are determined and output, so as to control the operation of the thermal power unit according to the theoretical operation factors.

[0059] To summarize, in this application, a more accurate correspondence model between operating factors and intermediate variables is obtained in advance through DDQN algorithm learning and training, and the theoretical intermediate variables corresponding to the highest economic benefits under the current operating state of the thermal power unit are determined through the benchmark database, and then the theoretical operating factors are determined using the corresponding relationship model and theoretical intermediate variables determined based on the DDQN algorithm. Therefore, the operation process of the thermal power unit can be controlled according to the theoretical operating factors, so that the intermediate variables in the operation process of the thermal power unit are equal to or close to the theoretical intermediate variables, which makes the economic benefits of the operation of the thermal power unit the highest, which is conducive to reducing the operating costs of the thermal power units, and then reducing the electricity costs of all industries.

[0060] Based on any of the above embodiments, after the operation of the thermal power unit is controlled based on the theoretical operating factor, the actual intermediate variable of the thermal power unit may not be completely the same as the theoretical intermediate variable. In order to obtain more accurate control of the operation of the thermal power unit, in an optional embodiment of the present application, it may further include:

[0061] Collect actual intermediate variables generated by controlling the thermal power unit according to multiple sets of theoretical operating factors within the period according to a predetermined period;

[0062] According to the actual intermediate variables and the corresponding theoretical operating factors, the DDQN algorithm is used to modify the corresponding relationship model.

[0063] The predetermined correspondence model is determined based on historical operating factors and corresponding historical intermediate variables. However, for different thermal power units, the correspondence model may also change with different operating processes and operating environments. Therefore, the correspondence model can be corrected and updated based on the actual operating factors and intermediate variables during the operation of the thermal power unit, further improving the accuracy of the correspondence model.

[0064] Similarly, for different boundary conditions in the benchmark database, the intermediate variables corresponding to the highest economic benefits of the thermal power unit may also have deviations. Therefore, in another optional embodiment of the present application, it may further include:

[0065] According to the preset period, the boundary conditions corresponding to the actual intermediate variables of the thermal power units within the period and the actual coal consumption per unit power generation are collected;

[0066] According to the actual intermediate variables and the corresponding actual coal consumption under different boundary conditions, the theoretical intermediate variables corresponding to the highest economic benefit in the benchmark database are updated.

[0067] When the corresponding relationship model and the theoretical intermediate variables corresponding to the highest economic benefit are updated according to a predetermined period, the same predetermined period or different periods may be used, and this is not limited in detail in the present application.

[0068] The following is an introduction to the thermal power unit operation and management device provided in an embodiment of the present invention. The thermal power unit operation and management device described below and the thermal power unit operation and management method described above can be referred to each other.

[0069] Figure 2 The structural block diagram of the thermal power unit operation device provided by the embodiment of the present invention is shown in FIG. Figure 2 The operation device of the thermal power unit may include:

[0070] A creation module 100 is used to obtain a corresponding relationship model between the operation factors and the intermediate variables by using the DDQN algorithm in advance through the historical operation factors and the corresponding historical intermediate variables;

[0071] For example, the operating factors may include but are not limited to any one of the air temperature, air pressure and air volume at the coal mill outlet, the opening of the hot air valve at the mill inlet, the instantaneous coal feed rate of the coal feeder, and the secondary air volume of the furnace; the intermediate variables may include but are not limited to any one of the air preheater exhaust temperature, the main steam temperature, the main steam pressure, the reheat steam temperature, the condenser end difference, the boiler combustion coal consumption, and the power generation capacity;

[0072] A search module 200 is used to search, according to the boundary conditions of the current operation of the thermal power unit, in a pre-created benchmark database for the theoretical intermediate variable corresponding to the maximum economic benefit of the thermal power unit under the boundary conditions;

[0073] The boundary conditions may include but are not limited to any one of unit load, ambient temperature and coal quality data;

[0074] The operation module 300 is used to determine and output the theoretical operation factor corresponding to the theoretical intermediate variable according to the theoretical intermediate variable and the corresponding relationship model, so as to control the operation of the thermal power unit according to the theoretical operation factor.

[0075] In an optional embodiment of the present application, it also includes a first correction module, which is used to control the actual intermediate variables generated by the thermal power unit according to multiple groups of the theoretical operating factors within a predetermined period acquisition period after determining and outputting the theoretical operating factors corresponding to the theoretical intermediate variables; and to correct the corresponding relationship model using the DDQN algorithm based on the actual intermediate variables and the corresponding theoretical operating factors.

[0076] In an optional embodiment of the present application, the creation module 100 is specifically used to collect historical operation factors and corresponding historical intermediate variables; perform data processing of Lasso regression and data clustering on the historical operation factors and the historical intermediate variables; and use the DDQN algorithm to learn the historical operation factors and the historical intermediate variables after data processing to obtain the corresponding relationship model.

[0077] In an optional embodiment of the present application, it also includes a learning and training module, which is used to pre-collect multiple groups of historical intermediate variables corresponding to the thermal power units and the historical coal consumption per unit power generation corresponding to each group of the historical intermediate variables; neural network training is performed on the historical intermediate variables and the corresponding historical coal consumption under different boundary conditions to obtain the corresponding relationship between the intermediate variables and the coal consumption under different boundary conditions; and the intermediate variable with the least coal consumption under each different boundary condition determined based on the corresponding relationship is the theoretical intermediate variable corresponding to the highest economic benefit.

[0078] In an optional embodiment of the present application, it also includes a second correction module for collecting boundary conditions corresponding to the actual intermediate variables of the thermal power unit within a preset period and the actual coal consumption per unit of power generation; according to the actual intermediate variables and the corresponding actual coal consumption under different boundary conditions, the theoretical intermediate variables corresponding to the highest economic benefit in the benchmark database are updated.

[0079] The thermal power unit operation and operating device of this embodiment is used to implement the aforementioned thermal power unit operation and operating method. Therefore, the specific implementation method of the thermal power unit operation and operating device can be found in the embodiment part of the thermal power unit operation and operating method in the previous text, and will not be repeated here.

[0080] The present application also provides an embodiment of a thermal power unit operation device, which may include:

[0081] Memory for storing computer programs;

[0082] A processor is used to implement the steps of any one of the methods for operating a thermal power unit when executing the computer program.

[0083] The steps of the thermal power unit operation method executed by the processor may include:

[0084] The corresponding relationship model between the operating factors and the intermediate variables is obtained in advance using the DDQN algorithm through the historical operating factors and the corresponding historical intermediate variables;

[0085] According to the boundary conditions of the current operation of the thermal power unit, searching in a pre-created benchmark database the theoretical intermediate variables corresponding to when the thermal power unit obtains the highest economic benefit under the boundary conditions;

[0086] According to the theoretical intermediate variable and the corresponding relationship model, the theoretical operating factor corresponding to the theoretical intermediate variable is determined and output, so as to control the operation of the thermal power unit according to the theoretical operating factor.

[0087] For example, the operating factors may include but are not limited to any one of the air temperature, air pressure and air volume at the coal mill outlet, the opening of the hot air valve at the mill inlet, the instantaneous coal feed rate of the coal feeder, and the secondary air volume of the furnace;

[0088] The intermediate variables may include but are not limited to any one of air preheater exhaust gas temperature, main steam temperature, main steam pressure, reheat steam temperature, condenser end difference, boiler combustion coal consumption, and power generation;

[0089] The boundary conditions may include but are not limited to any one of unit load, ambient temperature and coal quality data.

[0090] The thermal power unit operation device in this embodiment can use the corresponding relationship model between the operation factor and the intermediate variable determined in advance by the DDQN algorithm, combined with the theoretical intermediate variables corresponding to the highest operation efficiency of the current thermal power unit determined in advance, to determine the theoretical operation factor corresponding to the highest economic efficiency of the current thermal power unit operation, so as to control the operation of the thermal power unit according to the operation factor, so that the economic efficiency of the thermal power unit is maximized, and the power generation cost of the thermal power unit is reduced to a certain extent.

[0091] The present application also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the method for operating a thermal power unit as described in any one of the above items are implemented.

[0092] The computer-readable storage medium may include random access memory (RAM), memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disks, removable disks, CD-ROMs, or any other form of storage medium known in the technical field.

[0093] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply that there is any such actual relationship or order between these entities or operations. Moreover, the term "include", "comprise" or any other variant thereof is intended to cover non-exclusive inclusion, so that the process, method, article or equipment that includes a series of elements are inherent to the elements. In the absence of more restrictions, the elements limited by the sentence "comprise one..." do not exclude the presence of other identical elements in the process, method, article or equipment that includes the elements. In addition, the above-mentioned technical solution provided in the embodiment of the present application is consistent with the corresponding technical solution in the prior art in principle, and the part is not described in detail, so as not to repeat too much.

[0094] The principles and implementation methods of the present invention are described in this article using specific examples. The description of the above embodiments is only used to help understand the method and core ideas of the present invention. It should be pointed out that for ordinary technicians in this technical field, without departing from the principles of the present invention, several improvements and modifications can be made to the present invention, and these improvements and modifications also fall within the scope of protection of the claims of the present invention.

Claims

1. A method for operating a thermal power unit, characterized in that: include: The corresponding relationship model between the operating factors and the intermediate variables is obtained in advance by using the DDQN algorithm through the historical operating factors and the corresponding historical intermediate variables; wherein the operating factors include the wind temperature, wind pressure and air volume at the outlet of the coal mill, the opening of the hot air valve at the mill inlet, the instantaneous coal feed rate of the coal feeder, and the secondary air volume of the furnace; the intermediate variables include the exhaust temperature of the air preheater, the main steam temperature, the main steam pressure, the reheat steam temperature, the condenser end difference, the boiler combustion coal consumption, and the power generation power; According to the boundary conditions of the current operation of the thermal power unit, searching in a pre-created benchmark database the theoretical intermediate variables corresponding to the highest economic benefit of the thermal power unit under the boundary conditions; wherein the boundary conditions include unit load, ambient temperature and coal quality data; According to the theoretical intermediate variable and the corresponding relationship model, determining and outputting the theoretical operation factor corresponding to the theoretical intermediate variable, so as to control the operation of the thermal power unit according to the theoretical operation factor; The corresponding relationship model between the operating factors and the intermediate variables is obtained in advance using the DDQN algorithm through the historical operating factors and the corresponding historical intermediate variables, including: Collect historical operating factors and corresponding historical intermediate variables; Performing Lasso regression and data clustering on both the historical operation factors and the historical intermediate variables; The historical operation factors and the historical intermediate variables after data processing are learned using the DDQN algorithm to obtain the corresponding relationship model; The process of pre-creating theoretical intermediate variables corresponding to the highest economic benefits in the benchmark database includes: Pre-collecting multiple groups of historical intermediate variables corresponding to the thermal power unit and the historical coal consumption per unit power generation corresponding to each group of the historical intermediate variables; A neural network is trained for the historical intermediate variables and the corresponding historical coal consumption under different boundary conditions to obtain the corresponding relationship between the intermediate variables and the corresponding coal consumption under different boundary conditions, and based on the corresponding relationship, the intermediate variable with the minimum coal consumption under each different boundary condition is determined as the theoretical intermediate variable corresponding to the highest economic benefit; After determining and outputting the theoretical operation factors corresponding to the theoretical intermediate variables, the method further includes: Collecting actual intermediate variables generated by controlling the thermal power unit according to multiple groups of theoretical operating factors within a period of time according to a predetermined period; According to the actual intermediate variables and the corresponding theoretical operating factors, the corresponding relationship model is modified using the DDQN algorithm; After determining and outputting the theoretical operation factors corresponding to the theoretical intermediate variables, the method further includes: Collecting boundary conditions corresponding to actual intermediate variables of the thermal power unit within a period of time and actual coal consumption per unit power generation according to a preset period; According to the actual intermediate variables and the corresponding actual coal consumption under different boundary conditions, the theoretical intermediate variables corresponding to the highest economic benefit in the benchmark database are updated.

2. A thermal power unit operation device, characterized in that: include: A creation module is used to obtain the corresponding relationship model between the operation factors and the intermediate variables by using the DDQN algorithm in advance through the historical operation factors and the corresponding historical intermediate variables; wherein the operation factors include the wind temperature, wind pressure and air volume at the outlet of the coal mill, the opening of the hot air valve at the mill inlet, the instantaneous coal feed rate of the coal feeder, and the secondary air volume of the furnace; the intermediate variables include the exhaust temperature of the air preheater, the main steam temperature, the main steam pressure, the reheat steam temperature, the condenser end difference, the boiler combustion coal consumption, and the power generation power; A search module is used to search, according to the boundary conditions of the current operation of the thermal power unit, in a pre-created benchmark database for theoretical intermediate variables corresponding to the highest economic benefit of the thermal power unit under the boundary conditions; wherein the boundary conditions include unit load, ambient temperature and coal quality data; A calculation module, used for determining and outputting a theoretical operation factor corresponding to the theoretical intermediate variable according to the theoretical intermediate variable and the corresponding relationship model, so as to control the operation of the thermal power unit according to the theoretical operation factor; A creation module is specifically used to collect historical operation factors and corresponding historical intermediate variables; perform data processing of Lasso regression and data clustering on the historical operation factors and the historical intermediate variables; and use the DDQN algorithm to learn the historical operation factors and the historical intermediate variables after data processing to obtain the corresponding relationship model; It also includes a learning and training module, which is used to pre-collect multiple groups of historical intermediate variables corresponding to the thermal power units and the historical coal consumption per unit power generation corresponding to each group of the historical intermediate variables; neural network training is performed on the historical intermediate variables and the corresponding historical coal consumption under different boundary conditions to obtain the corresponding relationship between the intermediate variables and the corresponding coal consumption under different boundary conditions, and the intermediate variable with the minimum coal consumption under each different boundary condition determined based on the corresponding relationship is the theoretical intermediate variable corresponding to the highest economic benefit; It also includes a first correction module, which is used to control the actual intermediate variables generated by the thermal power unit according to multiple groups of the theoretical operation factors within a predetermined period acquisition period after determining and outputting the theoretical operation factors corresponding to the theoretical intermediate variables; and to correct the corresponding relationship model using a DDQN algorithm according to the actual intermediate variables and the corresponding theoretical operation factors; It also includes a second correction module for collecting boundary conditions corresponding to the actual intermediate variables of the thermal power unit within a preset period and the actual coal consumption per unit of power generation; according to the actual intermediate variables and the corresponding actual coal consumption under different boundary conditions, the theoretical intermediate variables corresponding to the highest economic benefit in the benchmark database are updated.

3. A thermal power unit operation device, characterized in that: include: Memory for storing computer programs; A processor is used to implement the steps of the thermal power unit operation method as claimed in claim 1 when executing the computer program.

4. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by the processor, the steps of the method for operating a thermal power unit as claimed in claim 1 are implemented.

Images