Efficient thermal power plant production process control system and method

Abstract

The invention belongs to the technical field of industrial automation, and particularly relates to an efficient thermal power plant production process control system and method. The method comprises the steps that a temperature sensor, a pressure sensor and coal consumption instrument equipment are installed to collect original key parameter data of temperature, pressure and coal consumption in real time, the original key parameter data are processed and stored, the accuracy and reliability of the data can be guaranteed, adverse effects of data missing on follow-up analysis and decision making are avoided, and the accuracy and reliability of the data are improved. A linear regression model is established to describe the technological process of the thermal power plant, guidance and support are provided for technological optimization and improvement, the technological process of the thermal power plant is described based on the linear regression model to execute an optimal control strategy, a decision tree is utilized to construct a control strategy model, the efficiency and performance of the technological process are improved, data can be organized and managed more finely, and the method is suitable for popularization and application. Key parameter data in the control system and actuator output are adjusted, a visual interface is created, and a user is allowed to control the key parameter data of the process control system.

Description

Technical Field

[0001] The invention belongs to the technical field of industrial automation, and in particular relates to an efficient production process control system and method for a thermal power plant. Background Art

[0002] Process control systems play a key role in thermal power plants. They can monitor, control and optimize the production processes of the combustion subsystem, boiler subsystem and turbine subsystem to ensure the normal operation and production efficiency of the thermal power plant.

[0003] At present, the production process control system of thermal power plants has problems such as inaccurate, inconsistent, incomplete data and unsafe storage, low intelligence level and management efficiency, bottlenecks in data analysis and prediction, and difficulty in managing process control systems. Users are unable to understand and explain the basis of each control decision node. The monitoring and control capabilities of the production process control system of thermal power plants are insufficient, the information display is not intuitive, and there is a lack of alarm functions. As a result, the existing thermal power plant process control system has low production efficiency and many unsafe hidden dangers, which need to be solved urgently. Summary of the invention

[0004] In view of the shortcomings of the above-mentioned prior art, the present invention provides an efficient thermal power plant production process control system and method. Its purpose is to achieve data accuracy and reliability, help users to comprehensively monitor and manage process control systems, improve operational efficiency, reduce risks, timely discover and handle potential problems, and ensure the stable operation of the system.

[0005] The technical solution adopted by the present invention to achieve the above-mentioned purpose is: An efficient thermal power plant production process control method comprises the following steps: S101. Install temperature sensors, pressure sensors and coal consumption meter equipment to collect original key parameter data of temperature, pressure and coal consumption in real time, and use them as input of the process control system. Use minimum-maximum normalization to reduce the original key parameter data to a specified range, map them to the same scale, use the Z-score algorithm to convert the process control data set into a standard normal distribution with zero mean and unit standard deviation, and selectively connect the standardized process control data set to the cloud for cloud storage and local database; S102. Connect the cloud and local databases and extract the characteristic variables of the data in the standardized process control data set, select the characteristic variables related to the process of the thermal power plant through the Pearson correlation coefficient, establish a linear regression model to describe the process of the thermal power plant, use the least squares algorithm to fit the coefficients of the linear regression model, and analyze the relationship between each subsystem, distribution and correlation of the pre-production situation; S103. Describe the optimal control strategy for the process execution of the thermal power plant based on the linear regression model, build a control strategy model using a decision tree, and adjust key parameter data and actuator output in the control system; S104. Create a visual interface and allow users to control key parameter data of the process control system, provide authorization management and allow authorized users to remotely control the process control system through the visual interface.

[0006] Furthermore, the installation of temperature sensors, pressure sensors and coal consumption meter equipment described in S101 is implemented by using a collection and processing module, and the original key parameter data of temperature, pressure and coal consumption are collected in real time as input of the process control system. The process control system includes: a combustion subsystem, a boiler subsystem and a turbine subsystem, and the process control system and the central control room are connected through an API interface. The original key parameter data is checked to see if it exceeds the reasonable range measured by the temperature sensor, the pressure sensor and the coal consumption meter equipment, and the preliminary data items are prepared. The missing values ​​are filled in with the preliminary data items, and the original key parameter data is reduced to the specified range using minimum-maximum normalization and mapped to the same scale. The minimum-maximum normalization formula is: ; Among them, Q represents the normalized key parameter data, P Represents the original key parameter data, P min Indicates the minimum value of the original key parameter data, P max Indicates the maximum value of the original key parameter data; Identify sources of normalized critical parameter data for integration and correlation into process control data sets.

[0007] Furthermore, the process control data set described in S101 is collated by the central control room and used to standardize the data in the process control data set with naming rules and unit definition differences. The standardization scales the data in the process control data set so that its value range falls within the range of [-1,1] centered on 0, eliminates the dimension and unit differences between the values, and uses the Z-score algorithm to convert the process control data set into a standard normal distribution with zero mean and unit standard deviation. The formula is: ; Where Z represents the standardized process control data set, ψ represents the process control data set, μ represents the mean value of the data in the process control data set, and σ represents the standard deviation of the data in the process control data set; Selectively store standardized process control data sets in the cloud and local databases; The cloud storage has redundancy and backup mechanisms, and the local database allows full control over the standardized process control data set.

[0008] Furthermore, the step of connecting the cloud and the local database and extracting characteristic variables of the data in the standardized process control data set in S102 is to use the extraction modeling module to connect the cloud and the local database and extract characteristic variables of the data in the standardized process control data set, including: the mean of the temperature key parameter data, the mean of the pressure key parameter data, and the mean of the coal consumption key parameter data, and select characteristic variables related to the process control data set and the process of the thermal power plant through the Pearson correlation coefficient; The specific formula of Pearson correlation coefficient is: ; Among them, r represents the Pearson coefficient, cov(x,y) represents the covariance of the process control data set x and the thermal power plant process y, The sign represents the multiplication sign, and Sd(x) and Sd(y) represent the standard deviation values ​​of the process control data set x and the process y of the thermal power plant; The value range of the Pearson correlation coefficient is between -1 and 1. The closer its absolute value is to 1, the stronger the correlation is, and the closer it is to 0, the weaker the correlation is. The process control data set is divided into a training set, a validation set, and a test set. 70% of the process control data set is used as a training set, 20% of the process control data set is used as a validation set, and 10% of the process control data set is used as a test set. A linear regression model is established to describe the process of the thermal power plant, and the relationship, distribution, and correlation of the pre-production conditions of each subsystem are analyzed. The coefficients of the linear regression model are fitted using the least squares algorithm. The specific formula of least squares method is: ; Among them, α represents the estimated value of the coefficient of the linear regression model, X It means that each row is a feature vector of a process control data set and each column corresponds to a matrix of feature variables. Y represents a vector containing the target variable values ​​of the process control data set, T represents the transpose of the matrix, X´ T Indicates transpose.

[0009] Furthermore, the optimal control strategy for describing the process of the thermal power plant based on the linear regression model in S103 is to describe the process of the thermal power plant based on the linear regression model through the control strategy module and to construct the control strategy model using the decision tree, including: The key parameter data representing the characteristic variable is selected as the root node of the decision tree, and the process control data set is divided into different process control data subsets. For each non-leaf node, the control strategy selected by the best feature in the key parameter data is selected for splitting. The smaller the Gini index of the non-leaf node is, the lower the impurity of the judgment node is, and the more optimal the control strategy category represented by the feature is. According to the selected best feature, the current node is split into multiple child nodes, where each child node corresponds to a different process control data subset under the feature value, and the selection and splitting steps are repeated until the process control data set represented by the node corresponding to the feature belongs to the optimal control strategy, and the category is marked, and the key parameter data and actuator output in the control system are adjusted.

[0010] Furthermore, the creation of a visualization interface as described in S104 and allowing the user to control the key parameter data of the process control system is implemented by a visualization module, including: the adjustment amount of temperature, pressure and coal consumption, using a line graph to display the trend changes of the key parameter data of temperature and pressure through the time dimension, using a ring graph to display the proportion of temperature and pressure in the combustion subsystem and the proportion of the working environment of the boiler subsystem and the turbine subsystem, using a thermal map to display the key parameter data of temperature and pressure, and performing thermal marking to display the key parameter data of temperature in the working environment of different subsystems through the depth of color and the density of the marking points, providing authorization management and allowing authorized users to remotely control the process control system through the visualization interface, and when an abnormal situation occurs in the process control system, promptly issuing an alarm to the user, and displaying the error information and location on the visualization interface.

[0011] An efficient thermal power plant production process control system, comprising: The collection and processing module is used to install temperature sensors, pressure sensors and coal consumption meter equipment to collect the original key parameter data of temperature, pressure and coal consumption in real time, and use it as the input of the process control system. The original key parameter data is reduced to a specified range using minimum-maximum normalization, mapped to the same scale, and the process control data set is converted into a standard normal distribution with zero mean and unit standard deviation using the Z-score algorithm. The standardized process control data set is selectively connected to the cloud for cloud storage and local database; The extraction modeling module is used to connect to the cloud and local databases and extract the characteristic variables of the data in the standardized process control data set. The characteristic variables related to the process control data set and the thermal power plant process are selected through the Pearson correlation coefficient. A linear regression model is established to describe the process of the thermal power plant. The coefficients of the linear regression model are fitted using the least squares algorithm to analyze the relationship between each subsystem, the distribution and the correlation of the pre-production situation. The control strategy module is used to describe the process of thermal power plants based on the linear regression model to execute the optimal control strategy, build the control strategy model using the decision tree, and adjust the key parameter data and actuator output in the control system; The visualization module is used to create a visualization interface and allow users to control key parameter data of the process control system, provide authorization management and allow authorized users to remotely control the process control system through the visualization interface.

[0012] Furthermore, the control system is used to implement any of the steps of an efficient thermal power plant production process control method.

[0013] A computer device comprises a storage medium, a processor and a computer program stored on the storage medium and executable on the processor, wherein the processor implements any one of the steps of an efficient thermal power plant production process control method when executing the computer program.

[0014] A computer storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of any one of the methods for efficiently controlling a thermal power plant production process.

[0015] The present invention has the following beneficial effects and advantages: The present invention connects the process control system and the central control room through the API interface to process and store the original key parameter data, which can ensure the accuracy and reliability of the data, avoid the adverse effects of data loss on subsequent analysis and decision-making, ensure redundant backup and full controllability of the data, and meet the needs of storage structure, backup strategy and data migration. The characteristic variables of the mean value of the key parameter data are helpful to describe the characteristics and trends of the process control data set. The coefficient estimate of the linear regression model is calculated by the least squares algorithm to reveal the influence of each characteristic variable on the target variable, which is helpful to deeply analyze the relationship between each subsystem in the process of the thermal power plant, predict the correlation of the situation, and provide guidance and support for process optimization and improvement. Based on the linear regression model Describe the process of thermal power plants to implement the optimal control strategy, improve the efficiency and performance of the process, help to organize and manage data more finely, achieve the optimal control effect, create a visual interface and display the trend of key parameter data over time through a line chart, help users to timely observe the system status and change trend, use a ring chart to display the proportion of temperature and pressure in different subsystems, and intuitively present the proportion and distribution of each part in the whole. The temperature key parameter data of the working environment of different subsystems is displayed through the depth of color and the density of marking points, which helps users quickly understand the system status, helps users to comprehensively monitor and manage process control systems, improve operational efficiency, reduce risks, and promptly deal with potential problems to ensure stable system operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The above and / or additional aspects and advantages of the present invention will become apparent and easily understood from the description of the embodiments in conjunction with the following drawings, in which: Figure 1 is a flow chart of the method of the present invention; Figure 2 It is a system structure block diagram of the present invention. DETAILED DESCRIPTION

[0017] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present invention and the features in the embodiments can be combined with each other without conflict.

[0018] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.

[0019] Refer to the following Figure 1 and Figure 2 The technical solutions of some embodiments of the present invention are described.

[0020] Example 1

[0021] The present invention provides an embodiment, which is an efficient production process control method for a thermal power plant. Figure 1 As shown, Figure 1 It is a flow chart of the method of the present invention.

[0022] An efficient thermal power plant production process control method specifically comprises the following steps: S101. Install temperature sensors, pressure sensors and coal consumption meter equipment to collect original key parameter data of temperature, pressure and coal consumption in real time and use them as input of the process control system. Reduce the original key parameter data to a specified range using minimum-maximum normalization and map them to the same scale. Use the Z-score algorithm to convert the process control data set into a standard normal distribution with zero mean and unit standard deviation. Selectively connect the standardized process control data set to the cloud for cloud storage and local database; The installation of temperature sensors, pressure sensors and coal consumption meter equipment is realized by using a collection and processing module, and the original key parameter data of temperature, pressure and coal consumption are collected in real time and used as input of the process control system, wherein the process control system includes: a combustion subsystem, a boiler subsystem and a steam turbine subsystem, and the process control system and the central control room are connected through an API interface. The original key parameter data is checked to see whether it exceeds the reasonable range measured by the temperature sensor, the pressure sensor and the coal consumption meter equipment, and a preliminary data item is prepared, and the missing value is filled by the preliminary data item, and the original key parameter data is reduced to a specified range by using minimum-maximum normalization and mapped to the same scale. The minimum-maximum normalization formula is: ; Among them, Q represents the normalized key parameter data, P Represents the original key parameter data, P min Indicates the minimum value of the original key parameter data, P max Indicates the maximum value of the original key parameter data.

[0023] Identify sources of normalized critical parameter data for integration and correlation into process control data sets.

[0024] The process control data set is collated by the central control room and is used to standardize the data in the process control data set that have naming rules and unit definition differences. The standardization scales the data in the process control data set so that its value range falls within the range of [-1,1] centered on 0, eliminates the dimension and unit differences between the values, and uses the Z-score algorithm to convert the process control data set into a standard normal distribution with zero mean and unit standard deviation. The specific formula is: ; Where Z represents the standardized process control data set, ψ represents the process control data set, μ represents the data mean in the process control data set, and σ represents the data standard deviation in the process control data set.

[0025] The standardized process control data sets are selectively stored in the cloud and local database.

[0026] The cloud storage has redundancy and backup mechanisms, and the local database allows full control of the standardized process control data set. The cloud storage includes: storage structure, backup strategy and data migration.

[0027] S102. Connect the cloud and local databases and extract the characteristic variables of the data in the standardized process control data set, select the characteristic variables related to the process of the thermal power plant through the Pearson correlation coefficient, establish a linear regression model to describe the process of the thermal power plant, use the least squares algorithm to fit the coefficients of the linear regression model, and analyze the relationship between each subsystem, distribution and correlation of the pre-production situation; The method of connecting the cloud and the local database and extracting the characteristic variables of the data in the standardized process control data set is to use the extraction modeling module to connect the cloud and the local database and extract the characteristic variables of the data in the standardized process control data set, including: the mean of the temperature key parameter data, the mean of the pressure key parameter data and the mean of the coal consumption key parameter data, and select the characteristic variables related to the process control data set and the thermal power plant process through the Pearson correlation coefficient.

[0028] The specific formula of the Pearson correlation coefficient is: ; Among them, r represents the Pearson coefficient, cov(x,y) represents the covariance of the process control data set x and the thermal power plant process y, The sign represents the multiplication sign, and Sd(x) and Sd(y) represent the standard deviation values ​​of the process control data set x and the thermal power plant process y.

[0029] The value range of the Pearson correlation coefficient is between -1 and 1. The closer the absolute value is to 1, the stronger the correlation is, and the closer it is to 0, the weaker the correlation is. The process control data set is divided into training set, validation set and test set, of which 70% of the process control data set is used as training set, 20% of the process control data set is used as validation set, and 10% of the process control data set is used as test set. A linear regression model is established to describe the process of the thermal power plant, and the relationship, distribution and correlation of the pre-production conditions among the subsystems are analyzed. The coefficients of the linear regression model are fitted using the least squares algorithm.

[0030] The specific formula of the least squares method is: ; Among them, α represents the estimated value of the coefficient of the linear regression model, X It means that each row is a feature vector of a process control data set and each column corresponds to a matrix of feature variables. Y represents a vector containing the target variable values ​​of the process control data set, T represents the transpose of the matrix, X´ T Indicates transpose.

[0031] S103. Describe the optimal control strategy for the process execution of the thermal power plant based on the linear regression model, build a control strategy model using a decision tree, and adjust key parameter data and actuator output in the control system; The optimal control strategy for describing the process of the thermal power plant based on the linear regression model is to describe the process of the thermal power plant based on the linear regression model through the control strategy module to execute the optimal control strategy, and to construct the control strategy model using a decision tree, including: The key parameter data representing the characteristic variable is selected as the root node of the decision tree, and the process control data set is divided into different process control data subsets. For each non-leaf node, the control strategy selected by the best feature in the key parameter data is split. The smaller the Gini index of the non-leaf node is, the lower the impurity of the node is judged to be, and the control strategy category represented by the feature is more optimal. The current node is split into multiple child nodes according to the selected best feature, where each child node corresponds to a different process control data subset under the feature value. The selection and splitting steps are repeated until the process control data set represented by the node corresponding to the feature belongs to the optimal control strategy and is marked as a category, and the key parameter data and actuator output in the control system are adjusted.

[0032] S104. Create a visual interface and allow users to control key parameter data of the process control system, provide authorization management and allow authorized users to remotely control the process control system through the visual interface.

[0033] The creation of a visualization interface and allowing the user to control the key parameter data of the process control system is achieved by a visualization module, including: the adjustment amount of temperature, pressure and coal consumption, using a line graph to display the trend changes of the key parameter data of temperature and pressure through the time dimension, using a ring graph to display the proportion of temperature and pressure in the combustion subsystem and the proportion of the working environment of the boiler subsystem and the turbine subsystem, using a thermal map to display the key parameter data of temperature and pressure, and performing thermal marking to display the key parameter data of temperature in the working environment of different subsystems through the depth of color and the density of the marking points, providing authorization management and allowing authorized users to remotely control the process control system through the visualization interface, and when an abnormal situation occurs in the process control system, an alarm is promptly issued to the user and the corresponding error information and location are displayed on the visualization interface.

[0034] Example 2

[0035] The present invention also provides an embodiment, which is an efficient thermal power plant production process control system. Figure 2 As shown, Figure 2 It is a system structure block diagram of the present invention.

[0036] An efficient production process control system for a thermal power plant, specifically comprising: a collection and processing module, an extraction and modeling module, a control strategy module and a visualization module; Among them, the temperature sensor, pressure sensor and coal consumption instrument equipment are connected to the collection and processing module, the collection and processing module is connected to the extraction and modeling module, the extraction and modeling module is connected to the control strategy module, and the control strategy module is connected to the visualization module; the central control room and the process control system are also connected to the collection and processing module, the linear regression model is connected to the extraction and modeling module. The control strategy module is connected to the control strategy model, and the control strategy model is connected to the optimal control strategy module.

[0037] Collection and processing module: Install temperature sensors, pressure sensors and coal consumption meter equipment to collect original key parameter data of temperature, pressure and coal consumption in real time, and connect the process control system and the central control room through the API interface to process and store the original key parameter data; Extraction modeling module: extract characteristic variables of data in the standardized process control data set, establish a linear regression model to describe the process of the thermal power plant, and analyze the relationship, distribution and correlation of pre-production conditions among various subsystems; Control strategy module: describes the optimal control strategy for the process of thermal power plants based on the linear regression model, builds the control strategy model using the decision tree, and adjusts the key parameter data and actuator output in the control system; Visualization module: creates a visualization interface and allows users to control key parameter data of the process control system, provides authorization management and allows authorized users to remotely control the process control system through the visualization interface.

[0038] The efficient thermal power plant production process control system is used to implement the steps of an efficient thermal power plant production process control method as described in Example 1.

[0039] Example 3

[0040] Based on the same inventive concept, an embodiment of the present invention further provides a computer device, including a storage medium, a processor, and a computer program stored on the storage medium and executable on the processor. When the processor executes the computer program, the steps of an efficient thermal power plant production process control method described in Example 1 are implemented.

[0041] Example 4

[0042] Based on the same inventive concept, an embodiment of the present invention further provides a computer storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of an efficient thermal power plant production process control method described in Example 1 are implemented.

[0043] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0044] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0045] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0046] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0047] 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 above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents, and any modifications or equivalent replacements that do not depart from the spirit and scope of the present invention should be covered within the scope of protection of the present invention.

Claims

1. An efficient thermal power plant production process control method, characterized by: include: S101. Install temperature sensors, pressure sensors and coal consumption meter equipment to collect original key parameter data of temperature, pressure and coal consumption in real time, and use them as input of the process control system. Use minimum-maximum normalization to reduce the original key parameter data to the specified range, map them to the same scale, use the Z-score algorithm to convert the process control data set into a standard normal distribution with zero mean and unit standard deviation, and selectively connect the standardized process control data set to the cloud for cloud storage and local database; S102. Connect to the cloud and local database and extract the characteristic variables of the data in the standardized process control data set, select the characteristic variables related to the process of the process control data set and the process of the thermal power plant through the Pearson correlation coefficient, establish a linear regression model to describe the process of the thermal power plant, use the least squares algorithm to fit the coefficients of the linear regression model, and analyze the relationship, distribution and pre-situation correlation between each subsystem; S103. Describe the optimal control strategy for the process execution of the thermal power plant based on the linear regression model, use the decision tree to build the control strategy model, and adjust the key parameter data and actuator output in the control system; S104. Create a visual interface and allow users to control the key parameter data of the process control system, provide authorization management and allow authorized users to remotely control the process control system through the visual interface.

2. The efficient thermal power plant production process control method according to claim 1 is characterized in that: The installation of temperature sensors, pressure sensors and coal consumption meter equipment described in S101 is realized by using the collection and processing module, and the original key parameter data of temperature, pressure and coal consumption are collected in real time as the input of the process control system. The process control system includes: a combustion subsystem, a boiler subsystem and a steam turbine subsystem, and the process control system and the central control room are connected through an API interface. The original key parameter data is checked to see if it exceeds the reasonable range measured by the temperature sensor, the pressure sensor and the coal consumption meter equipment, and the preliminary data items are prepared. The missing values ​​are filled with the preliminary data items, and the original key parameter data is reduced to the specified range by using the minimum-maximum normalization and mapped to the same scale. The minimum-maximum normalization formula is: ； Among them, Q represents the normalized key parameter data, P Represents the original key parameter data, P min Indicates the minimum value of the original key parameter data, P max Indicates the maximum value of the original key parameter data; identifies the source of the normalized key parameter data for integration and association into the process control data set.

3. The efficient thermal power plant production process control method according to claim 1 is characterized in that: The process control data set described in S101 is collated by the central control room and is used to standardize the data in the process control data set that has naming rules and unit definition differences. Standardization scales the data in the process control data set so that its value range falls within the range of [-1,1] centered on 0, eliminates the dimension and unit differences between the values, and uses the Z-score algorithm to convert the process control data set into a standard normal distribution with zero mean and unit standard deviation. The formula is: ； Where Z represents the standardized process control data set, ψ represents the process control data set, μ represents the mean value of the data in the process control data set, and σ represents the standard deviation of the data in the process control data set; Selectively store standardized process control data sets in the cloud and local databases; The cloud storage has redundancy and backup mechanisms, and the local database allows full control over the standardized process control data set.

4. The efficient thermal power plant production process control method according to claim 1 is characterized in that: The step of connecting the cloud and the local database and extracting characteristic variables of the data in the standardized process control data set in S102 is to use the extraction modeling module to connect the cloud and the local database and extract characteristic variables of the data in the standardized process control data set, including: the mean of the temperature key parameter data, the mean of the pressure key parameter data, and the mean of the coal consumption key parameter data, and select characteristic variables related to the process control data set and the process of the thermal power plant through the Pearson correlation coefficient; The specific formula of Pearson correlation coefficient is: ； Among them, r represents the Pearson coefficient, cov(x,y) represents the covariance of the process control data set x and the thermal power plant process y, The sign represents the multiplication sign, and Sd(x) and Sd(y) represent the standard deviation values ​​of the process control data set x and the process y of the thermal power plant; The value range of the Pearson correlation coefficient is between -1 and 1. The closer its absolute value is to 1, the stronger the correlation is, and the closer it is to 0, the weaker the correlation is. The process control data set is divided into a training set, a validation set, and a test set. 70% of the process control data set is used as a training set, 20% of the process control data set is used as a validation set, and 10% of the process control data set is used as a test set. A linear regression model is established to describe the process of the thermal power plant, and the relationship, distribution, and correlation of the pre-production conditions of each subsystem are analyzed. The coefficients of the linear regression model are fitted using the least squares algorithm. The specific formula of least squares method is: ； Among them, α represents the estimated value of the coefficient of the linear regression model, X It means that each row is a feature vector of a process control data set and each column corresponds to a matrix of feature variables. Y represents a vector containing the target variable values ​​of the process control data set, T represents the transpose of the matrix, X´ T Indicates transpose.

5. The efficient thermal power plant production process control method according to claim 1 is characterized by: In S103, the optimal control strategy for the process of the thermal power plant is described based on the linear regression model, which is to describe the optimal control strategy for the process of the thermal power plant based on the linear regression model through the control strategy module, and to construct the control strategy model using a decision tree, including: The key parameter data representing the characteristic variable is selected as the root node of the decision tree, and the process control data set is divided into different process control data subsets. For each non-leaf node, the control strategy selected by the best feature in the key parameter data is selected for splitting. The smaller the Gini index of the non-leaf node is, the lower the impurity of the judgment node is, and the more optimal the control strategy category represented by the feature is. According to the selected best feature, the current node is split into multiple child nodes, where each child node corresponds to a different process control data subset under the feature value, and the selection and splitting steps are repeated until the process control data set represented by the node corresponding to the feature belongs to the optimal control strategy, and the category is marked, and the key parameter data and actuator output in the control system are adjusted.

6. The efficient thermal power plant production process control method according to claim 1 is characterized by: The creation of a visualization interface as described in S104 and allowing the user to control the key parameter data of the process control system is implemented by a visualization module, including: the adjustment amount of temperature, pressure and coal consumption, using a line graph to display the trend changes of the key parameter data of temperature and pressure through the time dimension, using a ring graph to display the proportion of temperature and pressure in the combustion subsystem and the proportion of the working environment of the boiler subsystem and the turbine subsystem, using a thermal map to display the key parameter data of temperature and pressure, and performing thermal marking to display the key parameter data of temperature in the working environment of different subsystems through the depth of color and the density of the marking points, providing authorization management and allowing authorized users to remotely control the process control system through a visualization interface, and when an abnormal situation occurs in the process control system, promptly issuing an alarm to the user, and displaying the error information and location on the visualization interface.

7. An efficient thermal power plant production process control system, characterized by: include: The collection and processing module is used to install temperature sensors, pressure sensors and coal consumption meter equipment to collect the original key parameter data of temperature, pressure and coal consumption in real time, and use it as the input of the process control system. The original key parameter data is reduced to a specified range using minimum-maximum normalization, mapped to the same scale, and the process control data set is converted into a standard normal distribution with zero mean and unit standard deviation using the Z-score algorithm. The standardized process control data set is selectively connected to the cloud for cloud storage and local database; The extraction modeling module is used to connect to the cloud and local databases and extract the characteristic variables of the data in the standardized process control data set. The characteristic variables related to the process control data set and the thermal power plant process are selected through the Pearson correlation coefficient. A linear regression model is established to describe the process of the thermal power plant. The coefficients of the linear regression model are fitted using the least squares algorithm to analyze the relationship between each subsystem, the distribution and the correlation of the pre-production situation. The control strategy module is used to describe the process of thermal power plants based on the linear regression model to execute the optimal control strategy, build the control strategy model using the decision tree, and adjust the key parameter data and actuator output in the control system; The visualization module is used to create a visualization interface and allow users to control key parameter data of the process control system, provide authorization management and allow authorized users to remotely control the process control system through the visualization interface.

8. The efficient thermal power plant production process control system according to claim 7 is characterized by: The control system is used to implement the steps of an efficient thermal power plant production process control method as described in any one of claims 2-6.

9. A computer device comprising a storage medium, a processor, and a computer program stored in the storage medium and executable on the processor, characterized in that: When the processor executes the computer program, the steps of an efficient thermal power plant production process control method as described in any one of claims 1 to 6 are implemented.

10. A computer storage medium, characterized in that: The computer storage medium stores a computer program, and when the computer program is executed by a processor, the steps of an efficient thermal power plant production process control method as described in any one of claims 1 to 6 are implemented.

Images