Intelligent power plant comprehensive monitoring and management system based on electric power Internet of Things

Abstract

The invention discloses an intelligent power plant comprehensive monitoring and management system based on the electric power Internet of Things, and relates to the technical field of monitoring and control. Internet of Things monitoring equipment is deployed in a power plant area needing to be monitored and managed, and a monitoring network is constructed based on the deployed Internet of Things monitoring equipment; meanwhile, historical monitoring data in the power plant area is collected, the collected historical monitoring data is processed in a data processing mode after collection is completed, and the processed historical monitoring data is analyzed in a data analysis mode; after the analysis is completed, based on analyzed historical monitoring data, a comprehensive monitoring management prediction model is constructed through a digital twinborn mode, finally, monitoring data in the power plant area are collected in real time, prediction is carried out through the comprehensive monitoring management prediction model, and meanwhile comprehensive monitoring management is carried out on the power plant area based on the comprehensive monitoring management prediction data. And the accuracy of comprehensive monitoring management of the power plant is improved.

Description

Technical Field

[0001] This invention relates to the field of monitoring and control technology, specifically to a smart power plant integrated monitoring and management system based on the Internet of Things for power. Background Technology

[0002] Currently, although major power generation companies have piloted and defined smart power plants, their equipment fault diagnosis and maintenance techniques are relatively weak, making it difficult to detect potential equipment problems in a timely and accurate manner.

[0003] The prior art, such as the invention patent application with publication number CN103984333A, discloses a power plant monitoring and management system, the method of which includes: a data input device for receiving basic information data of the power plant entered by the user; a three-dimensional model building device for generating a three-dimensional power plant model based on the basic information data of the power plant and a pre-stored model; a terminal information acquisition device for collecting terminal information within the power plant; and a monitoring and management device for generating power plant monitoring and management data based on the terminal information and the three-dimensional power plant model.

[0004] As can be seen from the above solutions, the current integrated monitoring and management of power plants mainly focuses on the collection and location of information about the power plant, but lacks the monitoring and control of the power plant equipment, which has certain limitations. Summary of the Invention

[0005] The purpose of this invention is to provide a smart power plant integrated monitoring and management system based on the Internet of Things for power, which solves the problems existing in the background technology.

[0006] To solve the above-mentioned technical problems, the present invention adopts the following technical solution: The present invention provides a smart power plant integrated monitoring and management system for the Internet of Things, specifically including the following steps: S1. Deploy IoT monitoring devices in the power plant area where monitoring and management are required, and build a monitoring network based on the deployed IoT monitoring devices; S2. Collect historical monitoring data within the power plant area based on the constructed monitoring network; The historical monitoring data includes power equipment temperature data and power equipment operating vibration data; S3. The collected historical monitoring data is processed using data processing methods to obtain processed historical monitoring data; S4. Analyze the processed historical monitoring data using data analysis methods to obtain the analyzed historical monitoring data; S41. Analyze the temperature data of power equipment in the processed historical monitoring data through data analysis to obtain the analyzed temperature data of power equipment. S42. Analyze the vibration data of power equipment operation in the processed historical monitoring data through data analysis to obtain the analyzed vibration data of power equipment operation. S43. Based on the analyzed power equipment operating vibration data and analyzed power equipment temperature data, establish a fault tree and perform fusion analysis to obtain the analyzed historical monitoring data. S5. Based on the analyzed historical monitoring data, construct a comprehensive monitoring and management prediction model using digital twin technology; S6. Collect monitoring data within the power plant area in real time and input it into the constructed comprehensive monitoring and management prediction model to obtain comprehensive monitoring and management prediction data. At the same time, perform comprehensive monitoring and management of the power plant area based on the comprehensive monitoring and management prediction data.

[0007] Preferably, the deployment of IoT monitoring equipment within the power plant area requiring monitoring and management, and the construction of a monitoring network based on the deployed IoT monitoring equipment, includes the following steps: S11. Divide the power plant area that needs to be monitored and managed into monitoring nodes and sections, and deploy IoT monitoring devices at each node. The center of the power plant area is set as the origin of the coordinate system, and the horizontal direction of the power plant area is set as the X-axis of the three-dimensional coordinate system, the vertical direction as the Y-axis of the three-dimensional coordinate system, and the vertical direction as the Z-axis of the three-dimensional coordinate system. At the same time, the division interval is set based on the X-axis and Y-axis in the three-dimensional coordinate system, and the power plant area is divided into various segments based on the set division interval. Each segment is numbered, and the center point of each segment is set as a monitoring node. IoT monitoring devices are deployed at each monitoring node. S12. Collect and save the coordinate location information of the corresponding IoT monitoring devices, establish an aggregated local area network, and deploy them. The coordinate position information of each node is collected based on the established three-dimensional coordinate system, and an aggregated local area network is established based on the collected coordinate position information. Configure the aggregated local area network to consist of a tuple It means that, among them This indicates the establishment of an aggregated local area network. Indicates the section number, Indicates the coordinate location information of the section. This indicates the coordinate location information of the monitoring node.

[0008] Preferably, the collection of historical monitoring data within the power plant area based on the constructed monitoring network includes the following steps: Set the data collection interval and summarize the collected historical monitoring data based on the set data collection interval; Set the historical monitoring data set at different data collection intervals as , This represents the historical monitoring data collected within the i-th data collection interval. Indicates the number of data collection intervals; The collected historical monitoring data are summarized to obtain a historical monitoring data matrix. .

[0009] Preferably, the step of processing the collected historical monitoring data to obtain processed historical monitoring data includes the following steps: The standards for setting historical monitoring data include: power equipment temperature data, power equipment operating vibration data, and timestamps; Based on the historical monitoring data standard, the historical monitoring data collected is traversed and collected. When missing data is detected, the historical monitoring data containing the missing data is located. Meanwhile, the average value of the two sets of historical monitoring data adjacent to the missing data is calculated by linear interpolation, and the missing data is supplemented based on the calculated average value. After the data is completed, the supplemented historical monitoring data is obtained by summarizing it. The dimensions of the supplemented historical monitoring data were removed through data transformation. The temperature data and vibration data of power equipment in the supplemented historical monitoring data will be converted into numerical data. The converted historical monitoring data is obtained by summarizing the numerical data. The converted historical monitoring data is standardized using data standardization methods; The standardized calculation formula is as follows: ; in, This represents the minimum value in the converted historical monitoring data. This represents the maximum value in the converted historical monitoring data. This represents the s-th transformed historical monitoring data. This represents the s-th historical monitoring data after standardization; Standardized historical monitoring data is defined as processed historical monitoring data.

[0010] Preferably, the step of analyzing the temperature data of power equipment in the processed historical monitoring data through data analysis to obtain the analyzed temperature data of power equipment includes the following steps: Setting Data Window Functions The average value and standard deviation of the temperature data of the power equipment are calculated based on the set data window function. in, Indicates time interval, Indicates the first Temperature data of power equipment collected at each time point data window. The data window function represents time t. This represents the temperature data of the power equipment collected in the data window at time point t; The formulas for calculating the average and standard deviation of temperature data for electrical equipment are shown below; ; ; in, This represents the average temperature data of electrical equipment over time t. This represents the standard deviation of electrical equipment temperature data with respect to time t; A temperature sensitivity factor is set, and abnormal temperature conditions of power equipment are determined based on the average value and standard deviation of the calculated temperature data of power equipment. Abnormal temperature conditions of power equipment ; in, Indicates the temperature sensitivity factor. This indicates abnormal temperature conditions in electrical equipment. The abnormal temperature condition of the power equipment is set as the analyzed temperature data of the power equipment.

[0011] Preferably, the step of analyzing the vibration data of power equipment operation in the processed historical monitoring data through data analysis to obtain the analyzed vibration data of power equipment operation includes the following steps: Calculate the vibration data of the power equipment during operation and set the threshold for the vibration data of the power equipment during operation; ; in, Indicates the mass of the rotating part. Indicates rotational speed. Represents gravitational acceleration. Indicates eccentricity. This represents the collected vibration data from the operation of power equipment; The collected vibration data of the power equipment operation is transformed by wavelet transform coefficients, and the cumulative vibration energy value is determined based on the energy accumulation algorithm after the transformation is completed. The wavelet transform is shown below: ; in, For scaling variables, For translation variables, Describes the wavelet transform function. Represent real numbers, This represents the vibration data of the power equipment after wavelet transform. The formula for calculating the cumulative value of vibration energy is as follows: ; in, This represents the cumulative value of vibration energy. Indicates a time interval; Set a threshold for the cumulative vibration energy value, which is set as the threshold for vibration data of power equipment operation; The threshold for the vibration data of the power equipment operation is set as the vibration data of the power equipment operation after analysis.

[0012] Preferably, the step of establishing a fault tree and performing fusion analysis based on the analyzed power equipment operating vibration data and analyzed power equipment temperature data to obtain the analyzed historical monitoring data includes the following steps: Define fault tree rule functions ,in, This refers to a specific data point from the collected historical monitoring data. Fault tree rules are established based on the analyzed vibration data and temperature data of the power equipment, as shown below; ; in, This represents the maximum value of the analyzed power equipment temperature data. This represents the minimum value of the analyzed power equipment temperature data. This represents the maximum value of the analyzed power equipment operating vibration data. This represents the minimum value of the analyzed power equipment operating vibration data; Define the fault tree rule hysteresis function; The fault tree rule hysteresis function is shown below: ; in, Represents the fault tree rule hysteresis function. This indicates the duration for which a specific data item in the historical monitoring data was collected; Indicates the hysteresis threshold; The fault tree is obtained by summarizing the fault tree rules and the fault tree rule hysteresis function; Fault Tree ; in, Represents a fault tree. The output of the fault tree represents the analyzed historical monitoring data.

[0013] Preferably, the step of constructing a comprehensive monitoring and management prediction model based on analyzed historical monitoring data using a digital twin approach includes the following steps: S51. Summary and collection of historical monitoring data matrix Summarize the control action set within the power plant area ,in This represents the q-th control action within the power plant area; S52, Based on historical monitoring data matrix The initial probability is calculated from the control action set within the power plant area and the analyzed historical monitoring data, and the one-step state transition probability is also calculated. The one-step state transition probability is calculated as follows: ; in, This is the probability distribution for a one-step state transition. Historical monitoring data Historical monitoring data is obtained after processing and analyzing control actions within the power plant area. The probability, This represents the historical monitoring data collected by the first monitoring node within the first data collection interval within the power plant area. This represents the historical monitoring data collected by the first monitoring node within the j-th data collection interval within the power plant area. This indicates the analyzed historical monitoring data. ; S53. Calculate multi-step state transition probabilities based on one-step state transition probabilities; S54. Based on the historical monitoring data matrix after output prediction, the control action corresponding to each historical monitoring data and the probability of executing the corresponding control action, construct a comprehensive monitoring and management prediction model.

[0014] Preferably, the real-time acquisition of monitoring data within the power plant area and the input of the real-time acquired monitoring data into the constructed comprehensive monitoring and management prediction model to obtain comprehensive monitoring and management prediction data includes the following steps: The real-time collected monitoring data is input into the constructed comprehensive monitoring and management prediction model to obtain all prediction results and corresponding probabilities in the next interval of the real-time collected monitoring data. Fault results are removed from all prediction results, and the control action corresponding to the prediction result with the highest probability is selected to carry out comprehensive monitoring and management of the power plant area.

[0015] The present invention also provides a smart power plant integrated monitoring and management system for the Internet of Things of power, comprising: a data acquisition module, a data processing module, a data analysis module, a data prediction module, and a monitoring and management module; The data acquisition module is used to collect monitoring data from various IoT monitoring devices within the power plant area in real time. The data processing module is used to process the real-time collected monitoring data to obtain processed monitoring data; The data analysis module is used to analyze the processed monitoring data to obtain the analyzed monitoring data; The data prediction module is used to establish a comprehensive monitoring and management prediction model based on the analyzed monitoring data. The monitoring and management module is used to perform comprehensive monitoring and management of the power plant area based on the prediction data of the comprehensive monitoring and management prediction model.

[0016] The beneficial effects of this invention are as follows: (1) This invention deploys IoT monitoring devices in the power plant area that needs to be monitored and managed, and builds a monitoring network based on the deployed IoT monitoring devices. At the same time, it collects historical monitoring data in the power plant area. After collection, the collected historical monitoring data is processed by data processing and analyzed by data analysis. After analysis, a comprehensive monitoring and management prediction model is built based on the analyzed historical monitoring data through digital twin. Finally, the monitoring data in the power plant area is collected in real time and predicted by the comprehensive monitoring and management prediction model. At the same time, the power plant area is comprehensively monitored and managed based on the comprehensive monitoring and management prediction data, which improves the accuracy of comprehensive monitoring and management of the power plant.

[0017] (2) This invention sets historical monitoring data standards and traverses the collected monitoring data based on the set historical monitoring data standards. After the traversal is completed, missing data is filled in. After the filling is completed, the dimensions of the monitoring data are removed by data transformation and standardized, thereby improving the effectiveness of data processing.

[0018] (3) This invention improves the stability of power plant monitoring and management by analyzing the temperature data and vibration data of power equipment in the processed historical monitoring data respectively, and by constructing a fault tree for fusion analysis.

[0019] (4) This invention improves the real-time performance of power plant monitoring by summarizing monitoring data, control actions within the power plant area and analyzing historical monitoring data to calculate the possible states of each device. Attached Figure Description

[0020] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 This is a schematic diagram of the process of the smart power plant integrated monitoring and management system of the power Internet of Things of the present invention. Detailed Implementation

[0022] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0023] In a specific embodiment of the present invention, Reference Figure 1 As shown, this invention provides a smart power plant integrated monitoring and management system based on the Internet of Things for power, comprising: S1. Deploy IoT monitoring devices in the power plant area where monitoring and management are required, and build a monitoring network based on the deployed IoT monitoring devices; S2. Collect historical monitoring data within the power plant area based on the constructed monitoring network; The historical monitoring data includes power equipment temperature data and power equipment operating vibration data; S3. The collected historical monitoring data is processed using data processing methods to obtain processed historical monitoring data; S4. Analyze the processed historical monitoring data using data analysis methods to obtain the analyzed historical monitoring data; S41. Analyze the temperature data of power equipment in the processed historical monitoring data through data analysis to obtain the analyzed temperature data of power equipment. S42. Analyze the vibration data of power equipment operation in the processed historical monitoring data through data analysis to obtain the analyzed vibration data of power equipment operation. S43. Based on the analyzed power equipment operating vibration data and analyzed power equipment temperature data, establish a fault tree and perform fusion analysis to obtain the analyzed historical monitoring data. S5. Based on the analyzed historical monitoring data, construct a comprehensive monitoring and management prediction model using digital twin technology; S6. Collect monitoring data within the power plant area in real time and input it into the constructed comprehensive monitoring and management prediction model to obtain comprehensive monitoring and management prediction data. At the same time, perform comprehensive monitoring and management of the power plant area based on the comprehensive monitoring and management prediction data. Furthermore, referring to Figure 1 As shown, deploying IoT monitoring devices in the power plant area requiring monitoring and management, and building a monitoring network based on the deployed IoT monitoring devices, includes the following steps: S11. Divide the power plant area that needs to be monitored and managed into monitoring nodes and sections, and deploy IoT monitoring devices at each node. The center of the power plant area is set as the origin of the coordinate system, and the horizontal direction of the power plant area is set as the X-axis of the three-dimensional coordinate system, the vertical direction as the Y-axis of the three-dimensional coordinate system, and the vertical direction as the Z-axis of the three-dimensional coordinate system. At the same time, the division interval is set based on the X-axis and Y-axis in the three-dimensional coordinate system, and the power plant area is divided into various segments based on the set division interval. Furthermore, the divided sections are numbered, and the center point of each section is set as a monitoring node, and IoT monitoring devices are deployed at each monitoring node. S12. Collect and save the coordinate location information of the corresponding IoT monitoring devices, establish an aggregated local area network, and deploy them. The coordinate position information of each node is collected based on the established three-dimensional coordinate system, and an aggregated local area network is established based on the collected coordinate position information. Furthermore, the aggregated local area network is configured to consist of a tuple. It means that, among them This indicates the establishment of an aggregated local area network. Indicates the section number, Indicates the coordinate location information of the section. This indicates the coordinate location information of the monitoring node; Furthermore, referring to Figure 1 As shown, collecting historical monitoring data within the power plant area based on the constructed monitoring network includes the following steps: Set the data collection interval and summarize the collected historical monitoring data based on the set data collection interval; Set the historical monitoring data set at different data collection intervals as , This represents the historical monitoring data collected within the i-th data collection interval. Indicates the number of data collection intervals; Furthermore, the collected historical monitoring data are aggregated to obtain a historical monitoring data matrix. As shown below: ; in, Indicates the time within the j-th data collection interval. Historical monitoring data collected by each monitoring node; Furthermore, referring to Figure 1 As shown, the collected historical monitoring data is processed using data processing methods to obtain the processed historical monitoring data, including the following steps: The standards for setting historical monitoring data include: power equipment temperature data, power equipment operating vibration data, and timestamps; Based on the historical monitoring data standard, the historical monitoring data collected is traversed and collected. When missing data is detected, the historical monitoring data containing the missing data is located. Meanwhile, the average value of the two sets of historical monitoring data adjacent to the missing data is calculated by linear interpolation, and the missing data is supplemented based on the calculated average value. After the data is completed, the supplemented historical monitoring data is obtained by summarizing it. The dimensions of the supplemented historical monitoring data were removed through data transformation. The temperature data and vibration data of power equipment in the supplemented historical monitoring data will be converted into numerical data. The converted historical monitoring data is obtained by summarizing the numerical data. The converted historical monitoring data is standardized using data standardization methods; The standardized calculation formula is as follows: ; in, This represents the minimum value in the converted historical monitoring data. This represents the maximum value in the converted historical monitoring data. This represents the s-th transformed historical monitoring data. This represents the s-th historical monitoring data after standardization; Furthermore, the standardized historical monitoring data is defined as the processed historical monitoring data; Furthermore, referring to Figure 1 As shown, the temperature data of power equipment in the processed historical monitoring data is analyzed using data analysis methods. The analyzed temperature data of power equipment includes the following steps: Setting Data Window Functions The average value and standard deviation of the temperature data of the power equipment are calculated based on the set data window function. in, Indicates time interval, Indicates the first Temperature data of power equipment collected at each time point data window. The data window function represents time t. This represents the temperature data of the power equipment collected in the data window at time point t; The formulas for calculating the average and standard deviation of temperature data for electrical equipment are shown below; ; ; in, This represents the average temperature data of electrical equipment over time t. This represents the standard deviation of electrical equipment temperature data with respect to time t; A temperature sensitivity factor is set, and abnormal temperature conditions of power equipment are determined based on the average value and standard deviation of the calculated temperature data of power equipment. Abnormal temperature conditions of power equipment ; in, Indicates the temperature sensitivity factor. This indicates abnormal temperature conditions in electrical equipment. The abnormal temperature condition of the power equipment is set as the analyzed temperature data of the power equipment. Furthermore, referring to Figure 1 As shown, the analysis of power equipment vibration data from processed historical monitoring data is performed using data analysis methods. The resulting analyzed power equipment vibration data includes the following steps: Calculate the vibration data of the power equipment during operation and set the threshold for the vibration data of the power equipment during operation; ; in, Indicates the mass of the rotating part. Indicates rotational speed. Represents gravitational acceleration. Indicates eccentricity. This represents the collected vibration data from the operation of power equipment; The collected vibration data of the power equipment operation is transformed by wavelet transform coefficients, and the cumulative vibration energy value is determined based on the energy accumulation algorithm after the transformation is completed. The wavelet transform is shown below: ; in, For scaling variables, For translation variables, Describes the wavelet transform function. Represent real numbers, This represents the vibration data of the power equipment after wavelet transform. The formula for calculating the cumulative value of vibration energy is as follows: ; in, This represents the cumulative value of vibration energy. Indicates a time interval; Set a threshold for the cumulative vibration energy value, which is set as the threshold for vibration data of power equipment operation; Furthermore, the threshold for the vibration data of the power equipment operation is set as the analyzed vibration data of the power equipment operation; Furthermore, referring to Figure 1 As shown, the fault tree is established and fused based on the analyzed power equipment operating vibration data and analyzed power equipment temperature data to obtain the analyzed historical monitoring data, including the following steps: Define fault tree rule functions ,in, This refers to a specific data point from the collected historical monitoring data. Furthermore, fault tree rules are established based on the analyzed power equipment operating vibration data and analyzed power equipment temperature data, as shown below; ; in, This represents the maximum value of the analyzed power equipment temperature data. This represents the minimum value of the analyzed power equipment temperature data. This represents the maximum value of the analyzed power equipment operating vibration data. This represents the minimum value of the analyzed power equipment operating vibration data; Furthermore, define the fault tree rule hysteresis function; The fault tree rule hysteresis function is shown below: ; in, Represents the fault tree rule hysteresis function. This indicates the duration for which a specific data item in the historical monitoring data was collected; Indicates the hysteresis threshold; Furthermore, the fault tree is obtained by summarizing the fault tree rules and the fault tree rule hysteresis function; Fault Tree ; in, Represents a fault tree. The output of the fault tree represents the analyzed historical monitoring data; Furthermore, referring to Figure 1 As shown, based on the analyzed historical monitoring data, the construction of a comprehensive monitoring and management prediction model using digital twin technology includes the following steps: S51. Summary and collection of historical monitoring data matrix Summarize the control action set within the power plant area ,in This represents the q-th control action within the power plant area; S52, Based on historical monitoring data matrix The initial probability is calculated from the control action set within the power plant area and the analyzed historical monitoring data, and the one-step state transition probability is also calculated. The one-step state transition probability is calculated as follows: ; in, This is the probability distribution for a one-step state transition. Historical monitoring data Historical monitoring data is obtained after processing and analyzing control actions within the power plant area. The probability, This represents the historical monitoring data collected by the first monitoring node within the first data collection interval within the power plant area. This represents the historical monitoring data collected by the first monitoring node within the j-th data collection interval within the power plant area. This indicates the analyzed historical monitoring data. ; S53. Calculate multi-step state transition probabilities based on one-step state transition probabilities; S54. Construct a comprehensive monitoring and management prediction model based on the historical monitoring data matrix after output prediction, the control action corresponding to each historical monitoring data, and the probability of executing the corresponding control action; Furthermore, referring to Figure 1 As shown, real-time monitoring data is collected within the power plant area, and this collected data is input into the constructed integrated monitoring and management prediction model to obtain integrated monitoring and management prediction data. The process includes the following steps: The real-time collected monitoring data is input into the constructed comprehensive monitoring and management prediction model to obtain all prediction results and corresponding probabilities in the next interval of the real-time collected monitoring data. Fault results are removed from all prediction results, and the control action corresponding to the prediction result with the highest probability is selected to carry out comprehensive monitoring and management of the power plant area. In one specific embodiment, the smart power plant integrated monitoring and management system of the power Internet of Things further includes: a data acquisition module, a data processing module, a data analysis module, a data prediction module, and a monitoring and management module; The data acquisition module is used to collect monitoring data from various IoT monitoring devices within the power plant area in real time. The data processing module is used to process the real-time collected monitoring data to obtain processed monitoring data; The data analysis module is used to analyze the processed monitoring data to obtain the analyzed monitoring data; The data prediction module is used to establish a comprehensive monitoring and management prediction model based on the analyzed monitoring data. The monitoring and management module is used to perform comprehensive monitoring and management of the power plant area based on the prediction data of the comprehensive monitoring and management prediction model.

[0024] It should be noted that The above content is merely an example and illustration of the concept of the present invention. Those skilled in the art can make various modifications or additions to the specific embodiments described, or use similar methods to replace them, as long as they do not deviate from the concept of the invention or exceed the scope defined by the present invention, and all such modifications and additions should fall within the protection scope of the present invention.

Claims

1. A smart power plant integrated monitoring and management system based on the Internet of Things for power, characterized in that, Includes the following steps: S1. Deploy IoT monitoring devices in the power plant area where monitoring and management are required, and build a monitoring network based on the deployed IoT monitoring devices; S2. Collect historical monitoring data within the power plant area based on the constructed monitoring network; The historical monitoring data includes power equipment temperature data and power equipment operating vibration data; S3. The collected historical monitoring data is processed using data processing methods to obtain processed historical monitoring data; S4. Analyze the processed historical monitoring data using data analysis methods to obtain the analyzed historical monitoring data, including the following steps; S41. Analyze the temperature data of power equipment in the processed historical monitoring data through data analysis to obtain the analyzed temperature data of power equipment. S42. Analyze the vibration data of power equipment operation in the processed historical monitoring data through data analysis to obtain the analyzed vibration data of power equipment operation. S43. Based on the analyzed power equipment operating vibration data and analyzed power equipment temperature data, establish a fault tree and perform fusion analysis to obtain the analyzed historical monitoring data. S5. Based on the analyzed historical monitoring data, construct a comprehensive monitoring and management prediction model using digital twin technology; S6. Collect monitoring data within the power plant area in real time and input it into the constructed comprehensive monitoring and management prediction model to obtain comprehensive monitoring and management prediction data. At the same time, perform comprehensive monitoring and management of the power plant area based on the comprehensive monitoring and management prediction data.

2. The smart power plant integrated monitoring and management system for the Internet of Things in power according to claim 1, characterized in that, The process of deploying IoT monitoring equipment within the power plant area requiring monitoring and management, and constructing a monitoring network based on the deployed IoT monitoring equipment, includes the following steps: S11. Divide the power plant area that needs to be monitored and managed into monitoring nodes and sections, and deploy IoT monitoring devices at each node. The center of the power plant area is set as the origin of the coordinate system, and the horizontal direction of the power plant area is set as the X-axis of the three-dimensional coordinate system, the vertical direction as the Y-axis of the three-dimensional coordinate system, and the vertical direction as the Z-axis of the three-dimensional coordinate system. At the same time, the division interval is set based on the X-axis and Y-axis in the three-dimensional coordinate system, and the power plant area is divided into various segments based on the set division interval. Each segment is numbered, and the center point of each segment is set as a monitoring node. IoT monitoring devices are deployed at each monitoring node. S12. Collect and save the coordinate location information of the corresponding IoT monitoring devices, establish an aggregated local area network, and deploy them. The coordinate position information of each node is collected based on the established three-dimensional coordinate system, and an aggregated local area network is established based on the collected coordinate position information. Configure the aggregated local area network to consist of a tuple It means that, among them This indicates the establishment of an aggregated local area network. Indicates the section number, Indicates the coordinate location information of the section. This indicates the coordinate location information of the monitoring node.

3. The smart power plant integrated monitoring and management system for the Internet of Things in power according to claim 1, characterized in that, The collection of historical monitoring data within the power plant area based on the constructed monitoring network includes the following steps: Set the data collection interval and summarize the collected historical monitoring data based on the set data collection interval; Set the historical monitoring data set at different data collection intervals as , This represents the historical monitoring data collected within the i-th data collection interval. Indicates the number of data collection intervals; The collected historical monitoring data are summarized to obtain a historical monitoring data matrix. .

4. The smart power plant integrated monitoring and management system for the Internet of Things in power according to claim 1, characterized in that, The process of processing the collected historical monitoring data to obtain processed historical monitoring data includes the following steps: The standards for setting historical monitoring data include: power equipment temperature data, power equipment operating vibration data, and timestamps; Based on the historical monitoring data standard, the historical monitoring data collected is traversed and collected. When missing data is detected, the historical monitoring data containing the missing data is located. Meanwhile, the average value of the two sets of historical monitoring data adjacent to the missing data is calculated by linear interpolation, and the missing data is supplemented based on the calculated average value. After the data is completed, the supplemented historical monitoring data is obtained by summarizing it. The dimensions of the supplemented historical monitoring data were removed through data transformation. The temperature data and vibration data of power equipment in the supplemented historical monitoring data will be converted into numerical data. The converted historical monitoring data is obtained by summarizing the numerical data. The converted historical monitoring data is standardized using data standardization methods; The standardized calculation formula is as follows: ； in, This represents the minimum value in the converted historical monitoring data. This represents the maximum value in the converted historical monitoring data. This represents the s-th transformed historical monitoring data. This represents the s-th historical monitoring data after standardization; Standardized historical monitoring data is defined as processed historical monitoring data.

5. The smart power plant integrated monitoring and management system for the Internet of Things in power according to claim 1, characterized in that, The process of analyzing the temperature data of power equipment in the processed historical monitoring data to obtain the analyzed temperature data of power equipment includes the following steps: Setting Data Window Functions The average value and standard deviation of the temperature data of the power equipment are calculated based on the set data window function. in, Indicates time interval, Indicates the first Temperature data of power equipment collected at each time point data window. The data window function represents time t. This represents the temperature data of the power equipment collected in the data window at time point t; The formulas for calculating the average and standard deviation of temperature data for electrical equipment are shown below; ； ； in, This represents the average temperature data of electrical equipment over time t. This represents the standard deviation of electrical equipment temperature data with respect to time t; A temperature sensitivity factor is set, and abnormal temperature conditions of power equipment are determined based on the average value and standard deviation of the calculated temperature data of power equipment. Abnormal temperature conditions of power equipment ; in, Indicates the temperature sensitivity factor. This indicates abnormal temperature conditions in electrical equipment. The abnormal temperature condition of the power equipment is set as the analyzed temperature data of the power equipment.

6. The smart power plant integrated monitoring and management system for the Internet of Things in power according to claim 1, characterized in that, The process of analyzing the vibration data of power equipment operation in the processed historical monitoring data to obtain the analyzed vibration data of power equipment operation includes the following steps: Calculate the vibration data of the power equipment during operation and set the threshold for the vibration data of the power equipment during operation; ； in, Indicates the mass of the rotating part. Indicates rotational speed. Represents gravitational acceleration. Indicates eccentricity. This represents the collected vibration data from the operation of power equipment; The collected vibration data of the power equipment operation is transformed by wavelet transform coefficients, and the cumulative vibration energy value is determined based on the energy accumulation algorithm after the transformation is completed. The wavelet transform is shown below: ； in, For scaling variables, For translation variables, Describes the wavelet transform function. Represent real numbers, This represents the vibration data of the power equipment after wavelet transform. The formula for calculating the cumulative value of vibration energy is as follows: ； in, This represents the cumulative value of vibration energy. Indicates a time interval; Set a threshold for the cumulative vibration energy value, which is set as the threshold for vibration data of power equipment operation; The threshold for the vibration data of the power equipment operation is set as the vibration data of the power equipment operation after analysis.

7. The smart power plant integrated monitoring and management system for the Internet of Things in power according to claim 1, characterized in that, The process of establishing a fault tree and performing fusion analysis based on the analyzed power equipment operating vibration data and analyzed power equipment temperature data to obtain the analyzed historical monitoring data includes the following steps: Define fault tree rule functions ,in, This refers to a specific data point from the collected historical monitoring data. Fault tree rules are established based on the analyzed vibration data and temperature data of the power equipment, as shown below; ； in, This represents the maximum value of the analyzed power equipment temperature data. This represents the minimum value of the analyzed power equipment temperature data. This represents the maximum value of the analyzed power equipment operating vibration data. This represents the minimum value of the analyzed power equipment operating vibration data; Define the fault tree rule hysteresis function; The fault tree rule hysteresis function is shown below: ； in, Represents the fault tree rule hysteresis function. This indicates the duration for which a specific data item in the historical monitoring data was collected; Indicates the hysteresis threshold; The fault tree is obtained by summarizing the fault tree rules and the fault tree rule hysteresis function; Fault Tree ; in, Represents a fault tree. The output of the fault tree represents the analyzed historical monitoring data.

8. The smart power plant integrated monitoring and management system for the Internet of Things in power according to claim 1, characterized in that, The process of constructing a comprehensive monitoring and management prediction model based on analyzed historical monitoring data using a digital twin approach includes the following steps: S51. Summary and collection of historical monitoring data matrix Summarize the control action set within the power plant area ,in This represents the q-th control action within the power plant area; S52, Based on historical monitoring data matrix The initial probability is calculated from the control action set within the power plant area and the analyzed historical monitoring data, and the one-step state transition probability is also calculated. The one-step state transition probability is calculated as follows: ； in, This is the probability distribution for a one-step state transition. Historical monitoring data Historical monitoring data is obtained after processing and analyzing control actions within the power plant area. The probability, This represents the historical monitoring data collected by the first monitoring node within the first data collection interval within the power plant area. This represents the historical monitoring data collected by the first monitoring node within the j-th data collection interval within the power plant area. This indicates the analyzed historical monitoring data. ; S53. Calculate multi-step state transition probabilities based on one-step state transition probabilities; S54. Based on the historical monitoring data matrix after output prediction, the control action corresponding to each historical monitoring data and the probability of executing the corresponding control action, construct a comprehensive monitoring and management prediction model.

9. A smart power plant integrated monitoring and management system for the Internet of Things in the power industry according to claim 1, characterized in that, The process of collecting real-time monitoring data within the power plant area and inputting this data into the constructed integrated monitoring and management prediction model to obtain integrated monitoring and management prediction data includes the following steps: The real-time collected monitoring data is input into the constructed comprehensive monitoring and management prediction model to obtain all prediction results and corresponding probabilities in the next interval of the real-time collected monitoring data. Fault results are removed from all prediction results, and the control action corresponding to the prediction result with the highest probability is selected to carry out comprehensive monitoring and management of the power plant area.

10. A smart power plant integrated monitoring and management system for the Internet of Things of power as described in claims 1-9, characterized in that, Also includes: The system includes a data acquisition module, a data processing module, a data analysis module, a data prediction module, and a monitoring and management module. The data acquisition module is used to collect monitoring data from various IoT monitoring devices within the power plant area in real time. The data processing module is used to process the real-time collected monitoring data to obtain processed monitoring data; The data analysis module is used to analyze the processed monitoring data to obtain the analyzed monitoring data; The data prediction module is used to establish a comprehensive monitoring and management prediction model based on the analyzed monitoring data. The monitoring and management module is used to perform comprehensive monitoring and management of the power plant area based on the prediction data of the comprehensive monitoring and management prediction model.

Images