Coal-fired power plant intelligent operation control method and system based on AI
Through the intelligent operation control method of coal-fired power stations based on AI, and the prediction model is used to optimize the control strategy, the problem of insufficient adaptability of traditional control methods in complex and harsh environments is solved, operating efficiency and safety are improved, and energy consumption and emissions are reduced.
Patent Information
- Application Number
- CN202410801797.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-06-20
- Publication Date
- 2024-11-08
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The traditional coal-fired power station control method relies on manual operation and fixed parameters, and cannot effectively adapt to complex and harsh operating environments, resulting in low operating efficiency, high energy consumption and high emissions.
Using the intelligent operation control method of coal-fired power stations based on AI, we use the intelligent operation control method to obtain historical operation data, establish a prediction model, determine the predicted boiler efficiency and nitrogen oxide emission concentration, compare it with the target value to determine the intelligent operation mode, and optimize the control strategy.
It improves the operating efficiency of coal-fired power plants, reduces energy consumption and emissions, enhances safety, stability and reliability, and is suitable for complex and harsh environments.
Smart Images

Figure CN118915429A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of coal-fired power plant operation control, and in particular to an AI-based intelligent operation control method and system for a coal-fired power plant. Background Art
[0002] Coal-fired power plants are important energy supply bases, but traditional operation and control methods have certain limitations. At present, the control of coal-fired power plants mainly focuses on the optimization of control strategy configuration based on traditional DCS, as well as the external optimization method using industrial computers and PLCs. The control strategy configuration optimization based on traditional DCS is mainly completed by traditional algorithm modules represented by PID, or mainly relies on manual operation and fixed parameter control strategies. There are certain limitations. Its adaptability to complex and harsh operating environments such as mixed coal combustion, ash accumulation and coking is poor, and it is impossible to fundamentally improve the operation and control performance of coal-fired power plants. Therefore, there is an urgent need for an AI-based intelligent operation and control method and system for coal-fired power plants to improve the operating efficiency of coal-fired power plants and reduce energy consumption and emissions. Summary of the invention
[0003] The purpose of the present invention is to provide an AI-based intelligent operation control method and system for coal-fired power plants, so as to solve the problem that traditional coal-fired power plant control mainly relies on manual operation and fixed parameter control strategies or traditional algorithm modules to adapt to complex and harsh operating environments such as mixed coal combustion, ash accumulation and coking, and has poor adaptability, and cannot fundamentally improve the operation control performance of coal-fired power plants.
[0004] The present invention provides an AI-based intelligent operation control method for a coal-fired power plant, comprising:
[0005] Acquire historical operation data of the coal-fired power plant, and process the historical operation data to obtain key influencing parameter data of the coal-fired power plant;
[0006] Establishing a coal-fired power plant prediction model based on the key influencing parameter data;
[0007] Acquire real-time operation data of the coal-fired power plant, and determine a predicted boiler efficiency and a predicted nitrogen oxide emission concentration of the coal-fired power plant based on the coal-fired power plant prediction model;
[0008] The predicted boiler efficiency is compared with the target boiler efficiency, the predicted nitrogen oxide emission concentration is compared with the target nitrogen oxide emission concentration, and the intelligent operation mode of the coal-fired power plant is obtained according to the comparison results.
[0009] In some embodiments of the present application, the historical operation data is processed to obtain key influencing parameter data of the coal-fired power plant, including:
[0010] Filtering and processing the historical operation data to obtain processed historical operation data;
[0011] The boiler efficiency and nitrogen oxide emission concentration in the processed historical operation data are set as dependent variables, and the historical operation data other than the boiler efficiency and nitrogen oxide emission concentration in the processed historical operation data are set as independent variables;
[0012] The key influencing parameters of the coal-fired power plant are determined according to the influence degree between the independent variable and the dependent variable, and the key influencing parameter data of the coal-fired power plant are obtained.
[0013] In some embodiments of the present application, filtering and processing the historical operation data to obtain processed historical operation data includes:
[0014] Preset data types;
[0015] Filtering the historical operation data according to the data type, and retaining the historical operation data corresponding to the data type;
[0016] Perform missing value processing on the retained historical operation data. If there are missing values in the historical operation data, delete the missing values together with other data at the time corresponding to the missing values;
[0017] The historical operating data after the missing value processing is standardized according to the standardization rules, and the processed historical operating data is obtained.
[0018] In some embodiments of the present application, determining the key influencing parameters of the coal-fired power plant according to the influence between the independent variable and the dependent variable includes:
[0019] Get the individual influence between each independent variable and the dependent variable;
[0020] Comparing the individual influence degree with the preset influence degree, and determining whether the historical operation data corresponding to the independent variable is a key influence parameter according to the comparison result;
[0021] If the comparison result is within an acceptable range, it is determined that the historical operation data corresponding to the independent variable is a key influencing parameter;
[0022] If the comparison result is not within the acceptable range, it is determined that the historical operation data corresponding to the independent variable is not a key influencing parameter;
[0023] The step of comparing the individual influence with the preset influence includes:
[0024] Determining a ratio between the individual influence degree and the preset influence degree;
[0025] If the ratio is greater than or equal to 1, it is determined that the comparison result is within an acceptable range;
[0026] If the ratio is less than 1, it is determined that the comparison result is not within an acceptable range.
[0027] In some embodiments of the present application, the calculation method of the individual influence degree is:
[0028]
[0029] Among them, P represents the individual influence, α represents the influence factor of the independent variable on the dependent variable, and Z t+1 Represents the data corresponding to the independent variable at time t+1, Z t Represents the data corresponding to the independent variable at time t, Y t+1 Represents the data corresponding to the dependent variable at time t+1, Y t It represents the data corresponding to the dependent variable at time t, and T represents the calculation period of the individual influence.
[0030] In some embodiments of the present application, a coal-fired power plant prediction model is established according to the key influencing parameter data, including:
[0031] Dividing the key influencing parameter data into a training data set and a test data set;
[0032] Constructing a coal-fired power plant operation model, and training the coal-fired power plant operation model according to the training data set to obtain a trained coal-fired power plant operation model;
[0033] The trained coal-fired power plant operation model is tested according to the test data set, and a coal-fired power plant prediction model is measured.
[0034] In some embodiments of the present application, the predicted boiler efficiency is compared with the target boiler efficiency, the predicted nitrogen oxide emission concentration is compared with the target nitrogen oxide emission concentration, and the intelligent operation mode of the coal-fired power plant is obtained according to the comparison results, including:
[0035] determining a first ratio between the predicted boiler efficiency and the target boiler efficiency, and determining a second ratio between the predicted nitrogen oxide emission concentration and the target nitrogen oxide emission concentration;
[0036] If the first ratio is within a first comparison acceptance interval, and the second ratio is within a second comparison acceptance interval, it is determined that the current operation mode of the coal-fired power plant does not need to be optimized;
[0037] If the first ratio is not within the first comparison acceptance interval and the second ratio is not within the second comparison acceptance interval, it is determined that the current operation mode of the coal-fired power plant needs to be optimized, and an intelligent operation mode of the coal-fired power plant is obtained based on the first ratio and the second ratio.
[0038] In some embodiments of the present application, the first contrast acceptance interval is (0.95, 1.1), and the second contrast acceptance interval is (0.9, 1.05).
[0039] In some embodiments of the present application, obtaining a smart operation mode of a coal-fired power plant according to the first ratio and the second ratio includes:
[0040] If the first ratio is less than 1, a first difference between the first ratio and a minimum value of the first comparison acceptance interval is determined; if the first ratio is greater than 1, a first difference between the first ratio and a maximum value of the first comparison acceptance interval is determined;
[0041] If the second ratio is less than 1, determining a second difference between the second ratio and a minimum value of the second comparison acceptance interval; if the second ratio is greater than 1, determining a second difference between the second ratio and a maximum value of the second comparison acceptance interval;
[0042] An optimization control method for the coal-fired power plant is determined according to the first difference and the second difference.
[0043] The present invention also discloses an AI-based intelligent operation control system for a coal-fired power plant, comprising:
[0044] A data acquisition module, wherein the data acquisition module is used to acquire historical operation data of the coal-fired power plant and real-time operation data of the coal-fired power plant;
[0045] A data processing module, the data processing module is used to process the historical operation data to obtain key influencing parameter data of the coal-fired power plant;
[0046] A model building module, the model building module is used to establish a coal-fired power plant prediction model according to the key influencing parameter data;
[0047] A prediction module, the prediction module is used to determine the predicted boiler efficiency and predicted nitrogen oxide emission concentration of the coal-fired power plant based on the coal-fired power plant prediction model;
[0048] A control module is used to compare the predicted boiler efficiency with the target boiler efficiency, and to compare the predicted nitrogen oxide emission concentration with the target nitrogen oxide emission concentration, and to obtain an intelligent operation mode of the coal-fired power plant according to the comparison results.
[0049] The present invention provides an AI-based intelligent operation control method for a coal-fired power plant, comprising: acquiring historical operation data of the coal-fired power plant, and processing the historical operation data to obtain key influencing parameter data of the coal-fired power plant; establishing a coal-fired power plant prediction model according to the key influencing parameter data; acquiring real-time operation data of the coal-fired power plant, and determining a predicted boiler efficiency and a predicted nitrogen oxide emission concentration of the coal-fired power plant based on the coal-fired power plant prediction model; comparing the predicted boiler efficiency with a target boiler efficiency, and comparing the predicted nitrogen oxide emission concentration with a target nitrogen oxide emission concentration, and obtaining an intelligent operation mode of the coal-fired power plant according to the comparison results.
[0050] The present invention establishes a prediction model for a coal-fired power plant, determines the predicted boiler efficiency and predicted nitrogen oxide emission concentration of the coal-fired power plant according to the real-time operation data of the coal-fired power plant, and compares them with the target boiler efficiency and target nitrogen oxide emission concentration to determine the intelligent operation mode of the coal-fired power plant. The present invention can effectively improve the operation efficiency of the coal-fired power plant, reduce energy consumption and emissions, and is applicable to complex and harsh operating environments, improving the safety, stability and reliability of the coal-fired power plant.
[0051] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS
[0052] Figure 1 This is a flow chart of an AI-based intelligent operation control method for a coal-fired power plant according to the present invention;
[0053] Figure 2 This is a functional block diagram of an AI-based intelligent operation control system for a coal-fired power plant according to the present invention. DETAILED DESCRIPTION
[0054] The technical solution of the present invention is further described below through the accompanying drawings and embodiments.
[0055] It should be noted that the following detailed descriptions are illustrative and intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same general meanings as those commonly understood by those skilled in the art to which the present invention belongs.
[0056] It should be noted that the terms used here are only for describing specific embodiments and are not intended to limit exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprise" and / or "include" are used in this specification, they indicate the presence of features, steps, operations, devices, components and / or combinations thereof, without excluding other elements or objects. The "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. The orientation or position relationship indicated by terms such as "upper", "lower", "left", "right", "front", "back", "vertical", "horizontal", "side", "bottom" and the like is based on the orientation or position relationship shown in the drawings. It is only a relationship word determined for the convenience of describing the structural relationship of each component or element of the present invention, not specifically referring to any component or element in the invention, and cannot be understood as a limitation on the invention. Terms such as "fixed connection", "connected", "connected" and the like should be understood in a broad sense, indicating that it can be fixedly connected, integrally connected or detachably connected; it can be directly connected or indirectly connected through an intermediate medium. For relevant scientific research or technical personnel in this field, the specific meanings of the above terms in the present invention can be determined according to specific circumstances, and they should not be understood as limitations on the present invention.
[0057] Example
[0058] The present invention provides an AI-based intelligent operation control method for a coal-fired power plant, such as Figure 1 As shown, including:
[0059] S1, acquiring historical operation data of a coal-fired power plant, and processing the historical operation data to obtain key influencing parameter data of the coal-fired power plant.
[0060] S2, establishing a coal-fired power plant prediction model based on the key influencing parameter data.
[0061] S3, acquiring real-time operation data of the coal-fired power plant, and determining the predicted boiler efficiency and predicted nitrogen oxide emission concentration of the coal-fired power plant based on the coal-fired power plant prediction model.
[0062] S4, comparing the predicted boiler efficiency with the target boiler efficiency, comparing the predicted nitrogen oxide emission concentration with the target nitrogen oxide emission concentration, and obtaining the intelligent operation mode of the coal-fired power plant according to the comparison results.
[0063] The present invention establishes a prediction model for a coal-fired power plant, determines the predicted boiler efficiency and predicted nitrogen oxide emission concentration of the coal-fired power plant according to the real-time operation data of the coal-fired power plant, and compares them with the target boiler efficiency and target nitrogen oxide emission concentration to determine the intelligent operation mode of the coal-fired power plant. The present invention can effectively improve the operation efficiency of the coal-fired power plant, reduce energy consumption and emissions, and is applicable to complex and harsh operating environments, improving the safety, stability and reliability of the coal-fired power plant.
[0064] In some embodiments of the present application, the historical operation data is processed to obtain key influencing parameter data of the coal-fired power plant, including:
[0065] The historical operation data is filtered and processed to obtain processed historical operation data.
[0066] The boiler efficiency and nitrogen oxide emission concentration in the processed historical operation data are set as dependent variables, and the historical operation data other than the boiler efficiency and nitrogen oxide emission concentration in the processed historical operation data are set as independent variables.
[0067] The key influencing parameters of the coal-fired power plant are determined according to the influence degree between the independent variable and the dependent variable, and the key influencing parameter data of the coal-fired power plant are obtained.
[0068] In this embodiment, the independent variables in the historical operation data can be the quality of the coal entering the furnace, the feed water temperature of each coal grinding amount, the feed water flow, the main steam flow, the main steam pressure, the reheat steam flow, the reheat steam pressure, the primary air damper opening, the secondary air damper opening, the oxygen content at the furnace outlet, the inlet air temperature, the burner swing angle, the air preheater leakage coefficient, etc.
[0069] In some embodiments of the present application, filtering and processing the historical operation data to obtain processed historical operation data includes:
[0070] Preset data types.
[0071] The historical operation data is filtered according to the data type, and the historical operation data corresponding to the data type is retained.
[0072] The retained historical operation data is processed for missing values. If there are missing values in the historical operation data, the missing values and other data at the time corresponding to the missing values are deleted together.
[0073] The historical operating data after the missing value processing is standardized according to the standardization rules, and the processed historical operating data is obtained.
[0074] In this embodiment, the required data types are preset in advance, the historical operation data are filtered according to the preset data types, and the historical operation data corresponding to the required data types are retained. The historical operation data after the missing value processing is standardized to unify the units of the historical operation data so that the units of all data are basic units.
[0075] In some embodiments of the present application, determining the key influencing parameters of the coal-fired power plant according to the influence between the independent variable and the dependent variable includes:
[0076] Get the individual influence of each independent variable on the dependent variable.
[0077] The individual influence degree is compared with a preset influence degree, and whether the historical operation data corresponding to the independent variable is a key influence parameter is determined according to the comparison result.
[0078] If the comparison result is within an acceptable range, it is determined that the historical operating data corresponding to the independent variable is a key influencing parameter.
[0079] If the comparison result is not within the acceptable range, it is determined that the historical operating data corresponding to the independent variable is not a key influencing parameter.
[0080] The step of comparing the individual influence with the preset influence includes:
[0081] A ratio between the individual influence degree and the preset influence degree is determined.
[0082] If the ratio is greater than or equal to 1, it is determined that the comparison result is within an acceptable range.
[0083] If the ratio is less than 1, it is determined that the comparison result is not within an acceptable range.
[0084] In this embodiment, the influence of each independent variable is calculated separately with the dependent variable to determine the individual influence, and whether the change of each independent variable is related to the dependent variable is determined. If the individual influence is greater than or equal to the preset influence, that is, the ratio is greater than or equal to 1, and the comparison result is within the acceptable range, it can be determined that the corresponding independent variable is a key influencing parameter and needs to be retained. If the individual influence is less than the preset influence, that is, the ratio is less than 1, and the comparison result is not within the acceptable range, it can be determined that the corresponding independent variable is not a key influencing parameter and does not need to be retained.
[0085] In some embodiments of the present application, the calculation method of the individual influence degree is:
[0086]
[0087] Among them, P represents the individual influence, α represents the influence factor of the independent variable on the dependent variable, and Z t+1 Represents the data corresponding to the independent variable at time t+1, Z t Represents the data corresponding to the independent variable at time t, Y t+1 Represents the data corresponding to the dependent variable at time t+1, Y t It represents the data corresponding to the dependent variable at time t, and T represents the calculation period of the individual influence.
[0088] In some embodiments of the present application, a coal-fired power plant prediction model is established according to the key influencing parameter data, including:
[0089] The key influencing parameter data are divided into a training data set and a test data set.
[0090] A coal-fired power plant operation model is constructed, and the coal-fired power plant operation model is trained according to the training data set to obtain a trained coal-fired power plant operation model.
[0091] The trained coal-fired power plant operation model is tested according to the test data set, and a coal-fired power plant prediction model is measured.
[0092] In this embodiment, the key influencing parameter data is divided, 90% of which is divided into a training data set, which is used as a data sample for the training model. 10% is divided into a test data set. If the same data is directly used to verify the trained model, the problem of the model cannot be found. By randomly dividing, 10% of the key influencing parameter data is used as known data to perform reverse verification of the model, and it can be verified whether the trained model meets the requirements. If it meets the requirements, it means that the model trained by the training data set can be used to predict the actual situation. On the contrary, if it does not meet the requirements, it means that there is a problem with the model and it needs to be retrained, and then the retrained model is tested.
[0093] The coal-fired power plant operation model is constructed by computer. The obtained training data set is input into the neural network model and trained in the server to obtain a status prediction model of the power plant related facilities.
[0094] In some embodiments of the present application, the predicted boiler efficiency is compared with the target boiler efficiency, the predicted nitrogen oxide emission concentration is compared with the target nitrogen oxide emission concentration, and the intelligent operation mode of the coal-fired power plant is obtained according to the comparison results, including:
[0095] A first ratio between the predicted boiler efficiency and the target boiler efficiency is determined, and a second ratio between the predicted nitrogen oxide emission concentration and the target nitrogen oxide emission concentration is determined.
[0096] If the first ratio is within a first comparison acceptance interval, and the second ratio is within a second comparison acceptance interval, it is determined that the current operation mode of the coal-fired power plant does not need to be optimized.
[0097] If the first ratio is not within the first comparison acceptance interval and the second ratio is not within the second comparison acceptance interval, it is determined that the current operation mode of the coal-fired power plant needs to be optimized, and an intelligent operation mode of the coal-fired power plant is obtained based on the first ratio and the second ratio.
[0098] In some embodiments of the present application, the first contrast acceptance interval is (0.95, 1.1), and the second contrast acceptance interval is (0.9, 1.05).
[0099] In some embodiments of the present application, obtaining a smart operation mode of a coal-fired power plant according to the first ratio and the second ratio includes:
[0100] If the first ratio is less than 1, a first difference between the first ratio and a minimum value of the first comparison acceptance interval is determined; if the first ratio is greater than 1, a first difference between the first ratio and a maximum value of the first comparison acceptance interval is determined.
[0101] If the second ratio is less than 1, a second difference between the second ratio and the minimum value of the second comparison acceptance interval is determined; if the second ratio is greater than 1, a second difference between the second ratio and the maximum value of the second comparison acceptance interval is determined.
[0102] An optimization control method for the coal-fired power plant is determined according to the first difference and the second difference.
[0103] The present invention also discloses an AI-based intelligent operation control system for a coal-fired power plant using the above method, such as Figure 2 As shown, including:
[0104] A data acquisition module is used to acquire historical operation data of the coal-fired power plant and real-time operation data of the coal-fired power plant.
[0105] A data processing module is used to process the historical operation data to obtain key influencing parameter data of the coal-fired power plant.
[0106] A model building module is used to build a coal-fired power plant prediction model based on the key influencing parameter data.
[0107] A prediction module is used to determine the predicted boiler efficiency and predicted nitrogen oxide emission concentration of the coal-fired power plant based on the coal-fired power plant prediction model.
[0108] A control module is used to compare the predicted boiler efficiency with the target boiler efficiency, and to compare the predicted nitrogen oxide emission concentration with the target nitrogen oxide emission concentration, and to obtain an intelligent operation mode of the coal-fired power plant according to the comparison results.
[0109] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that they can still modify or replace the technical solution of the present invention with equivalents, and these modifications or equivalent replacements cannot cause the modified technical solution to deviate from the spirit and scope of the technical solution of the present invention.
[0110] The system provided in the above embodiment is only illustrated by the division of the above functional modules. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the modules or steps in the embodiments of the present invention can be decomposed or combined. For example, the modules in the above embodiment can be combined into one module, or further divided into multiple sub-modules to complete all or part of the functions described above. The names of the modules and steps involved in the embodiments of the present invention are only for distinguishing the modules or steps, and are not regarded as improper limitations of the present invention.
[0111] Those skilled in the art should be able to appreciate that the modules and method steps of each example described in conjunction with the embodiments disclosed herein can be implemented with electronic hardware, computer software or a combination of the two, and the programs corresponding to the software modules and method steps can be placed in random access memory (RAM), internal 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. In order to clearly illustrate the interchangeability of electronic hardware and software, the composition and steps of each example have been generally described in the above description according to the function. Whether these functions are performed in electronic hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.
Claims
1. An AI-based intelligent operation control method for a coal-fired power plant, characterized in that: include: Acquire historical operation data of the coal-fired power plant, and process the historical operation data to obtain key influencing parameter data of the coal-fired power plant; Establishing a coal-fired power plant prediction model based on the key influencing parameter data; Acquire real-time operation data of the coal-fired power plant, and determine a predicted boiler efficiency and a predicted nitrogen oxide emission concentration of the coal-fired power plant based on the coal-fired power plant prediction model; The predicted boiler efficiency is compared with the target boiler efficiency, the predicted nitrogen oxide emission concentration is compared with the target nitrogen oxide emission concentration, and the intelligent operation mode of the coal-fired power plant is obtained according to the comparison results.
2. The AI-based intelligent operation control method for a coal-fired power plant according to claim 1 is characterized in that: The historical operation data is processed to obtain key influencing parameter data of the coal-fired power plant, including: Filtering and processing the historical operation data to obtain processed historical operation data; The boiler efficiency and nitrogen oxide emission concentration in the processed historical operation data are set as dependent variables, and the historical operation data other than the boiler efficiency and nitrogen oxide emission concentration in the processed historical operation data are set as independent variables; The key influencing parameters of the coal-fired power plant are determined according to the influence degree between the independent variable and the dependent variable, and the key influencing parameter data of the coal-fired power plant are obtained.
3. The AI-based intelligent operation control method for a coal-fired power plant according to claim 2 is characterized in that: The historical operation data is filtered and processed to obtain processed historical operation data, including: Preset data types; Filtering the historical operation data according to the data type, and retaining the historical operation data corresponding to the data type; Perform missing value processing on the retained historical operation data. If there are missing values in the historical operation data, delete the missing values together with other data at the time corresponding to the missing values; The historical operating data after the missing value processing is standardized according to the standardization rules, and the processed historical operating data is obtained.
4. The AI-based intelligent operation control method for a coal-fired power plant according to claim 2 is characterized in that: The key influencing parameters of the coal-fired power plant are determined according to the influence between the independent variables and the dependent variables, including: Get the individual influence between each independent variable and the dependent variable; Comparing the individual influence degree with the preset influence degree, and determining whether the historical operation data corresponding to the independent variable is a key influence parameter according to the comparison result; If the comparison result is within an acceptable range, it is determined that the historical operation data corresponding to the independent variable is a key influencing parameter; If the comparison result is not within the acceptable range, it is determined that the historical operation data corresponding to the independent variable is not a key influencing parameter; The step of comparing the individual influence with the preset influence includes: Determining a ratio between the individual influence degree and the preset influence degree; If the ratio is greater than or equal to 1, it is determined that the comparison result is within an acceptable range; If the ratio is less than 1, it is determined that the comparison result is not within an acceptable range.
5. The AI-based intelligent operation control method for a coal-fired power plant according to claim 4 is characterized in that: The calculation method of the individual influence is: Among them, P represents the individual influence, α represents the influence factor of the independent variable on the dependent variable, and Z t+1 Represents the data corresponding to the independent variable at time t+1, Z t Represents the data corresponding to the independent variable at time t, Y t+1 Represents the data corresponding to the dependent variable at time t+1, Y t It represents the data corresponding to the dependent variable at time t, and T represents the calculation period of the individual influence.
6. The AI-based intelligent operation control method for a coal-fired power plant according to claim 1 is characterized in that: A coal-fired power plant prediction model is established based on the key influencing parameter data, including: Dividing the key influencing parameter data into a training data set and a test data set; Constructing a coal-fired power plant operation model, and training the coal-fired power plant operation model according to the training data set to obtain a trained coal-fired power plant operation model; The trained coal-fired power plant operation model is tested according to the test data set, and a coal-fired power plant prediction model is measured.
7. The AI-based intelligent operation control method for a coal-fired power plant according to claim 1 is characterized in that: The predicted boiler efficiency is compared with the target boiler efficiency, and the predicted nitrogen oxide emission concentration is compared with the target nitrogen oxide emission concentration. According to the comparison results, the intelligent operation mode of the coal-fired power plant is obtained, including: determining a first ratio between the predicted boiler efficiency and the target boiler efficiency, and determining a second ratio between the predicted nitrogen oxide emission concentration and the target nitrogen oxide emission concentration; If the first ratio is within a first comparison acceptance interval, and the second ratio is within a second comparison acceptance interval, it is determined that the current operation mode of the coal-fired power plant does not need to be optimized; If the first ratio is not within the first comparison acceptance interval and the second ratio is not within the second comparison acceptance interval, it is determined that the current operation mode of the coal-fired power plant needs to be optimized, and an intelligent operation mode of the coal-fired power plant is obtained based on the first ratio and the second ratio.
8. The AI-based intelligent operation control method for a coal-fired power plant according to claim 7 is characterized in that: The first contrast acceptance interval is (0.95, 1.1), and the second contrast acceptance interval is (0.9, 1.05).
9. The AI-based intelligent operation control method for a coal-fired power plant according to claim 7, characterized in that: The intelligent operation mode of the coal-fired power plant is obtained according to the first ratio and the second ratio, including: If the first ratio is less than 1, a first difference between the first ratio and a minimum value of the first comparison acceptance interval is determined; if the first ratio is greater than 1, a first difference between the first ratio and a maximum value of the first comparison acceptance interval is determined; If the second ratio is less than 1, determining a second difference between the second ratio and a minimum value of the second comparison acceptance interval; if the second ratio is greater than 1, determining a second difference between the second ratio and a maximum value of the second comparison acceptance interval; An optimization control method for the coal-fired power plant is determined according to the first difference and the second difference.
10. An AI-based intelligent operation control system for a coal-fired power plant, characterized in that: include: A data acquisition module, wherein the data acquisition module is used to acquire historical operation data of the coal-fired power plant and real-time operation data of the coal-fired power plant; A data processing module, the data processing module is used to process the historical operation data to obtain key influencing parameter data of the coal-fired power plant; A model building module, the model building module is used to establish a coal-fired power plant prediction model according to the key influencing parameter data; A prediction module, the prediction module is used to determine the predicted boiler efficiency and predicted nitrogen oxide emission concentration of the coal-fired power plant based on the coal-fired power plant prediction model; A control module is used to compare the predicted boiler efficiency with the target boiler efficiency, and to compare the predicted nitrogen oxide emission concentration with the target nitrogen oxide emission concentration, and to obtain an intelligent operation mode of the coal-fired power plant according to the comparison results.
