Internet-based intelligent thermal power plant production system and method

Abstract

The invention belongs to the technical field of artificial intelligence, and particularly relates to an intelligent thermal power plant production system and method based on the Internet. The system comprises a data acquisition module, a data analysis module, a fault prediction module and a safety monitoring module. The method comprises the following steps: collecting temperature and vibration data of thermal power generation equipment, and transmitting the data to a cloud server; analyzing the obtained temperature and vibration data of the thermal power generation equipment, and judging whether the equipment breaks down or not; establishing an equipment fault prediction model according to a judgment result; and real-time monitoring and early warning are carried out through an equipment fault prediction model, a maintenance plan is made for abnormal conditions in time, and the out-of-plan downtime is shortened. By means of monitoring and controlling the running state of the equipment in real time, predicting faults and carrying out maintenance planning, the out-of-plan downtime can be shortened, the reliability and stability of the equipment are improved, the thermal power generation efficiency is remarkably improved, and sustainable development is achieved.

Description

Technical Field

[0001] The present invention belongs to the field of artificial intelligence technology, and in particular relates to an Internet-based intelligent thermal power plant production system and method. Background Art

[0002] With the rapid development of my country's economy, intelligence and digitalization have penetrated into various industries and fields, and the power industry has increasingly become one of the important pillars of the national economy. As the main production force of the power industry, the efficiency, safety and reliability of thermal power plants are increasingly valued. Thermal power generation is a common way of energy production. The upgrade and development of the production system of intelligent thermal power plants will have a significant impact on the entire power industry.

[0003] However, traditional thermal power plants have some problems, including the emission of large amounts of greenhouse gases and pollutants such as carbon dioxide, sulfur dioxide and nitrogen oxides, which have a negative impact on the environment. In addition, the equipment is aging and difficult to maintain, posing certain safety risks. Summary of the invention

[0004] In view of the deficiencies in the above-mentioned prior art, the present invention provides an Internet-based intelligent thermal power plant production system and method, the purpose of which is to achieve the invention purpose of solving the problems raised in the above-mentioned background technology through real-time monitoring and control of equipment operating status and data analysis.

[0005] The technical solution adopted by the present invention to achieve the above-mentioned purpose is: An Internet-based intelligent thermal power plant production system comprises a data acquisition module, a data analysis module, a fault prediction module and a safety monitoring module; the data acquisition module: by deploying sensors and monitoring equipment on the thermal power generation equipment, the operation data of the thermal power generation equipment is collected in real time, the collected data is transmitted to a cloud server by using wireless communication technology, and a database is established on the cloud server for storing the collected operation data; the data analysis module: using a remote connection tool to connect to the cloud server, operating the server through a terminal window, obtaining the collected historical operation data, combining the analysis results of temperature data and vibration signal spectrum diagram, and judging whether the equipment has a fault; the fault prediction module: extracting time domain features from temperature data, extracting frequency domain features from the spectrum diagram of vibration signal data as input features, and establishing an equipment fault prediction model based on historical data and machine learning algorithms; the safety monitoring module: by real-time monitoring of the operation status and parameters of the equipment, real-time monitoring and analysis are carried out to judge whether there is an abnormal situation, and a maintenance plan is formulated according to the prediction results to reduce unplanned downtime.

[0006] Furthermore, the operating data of the thermal power generation equipment includes temperature and vibration data; the collected historical operating data includes temperature and vibration data; the operating status and parameters of the equipment include real-time collection of equipment data and transmission to a cloud server.

[0007] An Internet-based intelligent thermal power plant production method, comprising: Step 1. Collect temperature and vibration data of thermal power generation equipment and transmit them to the cloud server; Step 2: Analyze the acquired temperature and vibration data of the thermal power generation equipment to determine whether the equipment is faulty; Step 3. Establish an equipment failure prediction model based on the judgment results; Step 4. Use the equipment failure prediction model to conduct real-time monitoring and early warning, formulate maintenance plans for abnormal situations in a timely manner, and reduce unplanned downtime.

[0008] Furthermore, the step 1 of collecting the temperature and vibration data of the thermal power generation equipment and transmitting it to the cloud server is to deploy sensors and monitoring equipment on the thermal power generation equipment to collect the temperature and vibration data of the thermal power generation equipment in real time, use wireless communication technology to transmit the collected data to the cloud server, and establish a database on the cloud server to store the collected operation data; it includes the following steps: Step A1. Temperature data collection: Use a thermistor as a temperature sensor, install it in the high temperature area of ​​the turbine unit, and collect the temperature data of the thermal power generation equipment. The calculation formula is as follows: T 1= R 0×(1+ A × T + B × T 2 + C ×( T -100)× T 3 ) in, T 1 represents the temperature data of the high temperature area of ​​the turbine unit, R 0 is the resistance value of the thermistor at the reference temperature, A, B, C are the temperature coefficients of the thermistor, and T is the temperature of the thermistor; Step A2. Vibration data collection: Install the acceleration sensor on the generator to measure the vibration signal, convert the acceleration signal into a spectrum diagram through the Fourier transform method, and monitor the vibration of the equipment. The calculation formula is as follows:

[0009] Where x(n) is the discrete time series of the input signal,X ( k ) is the frequency of the output signal, N is the signal length, k is the frequency index, j is an imaginary unit, n is a time index, representing a time point in a discrete time series, and e is a natural constant.

[0010] Furthermore, in step 2, the temperature and vibration data of the thermal power generation equipment obtained by analyzing the analysis is used to determine whether the equipment is faulty; a remote connection tool is used to connect to a cloud server, and the server is operated through a terminal window to obtain the collected temperature and vibration data of historical operation, and the temperature data and the vibration signal spectrum analysis results are combined to determine whether the equipment is faulty, including the following steps: Step B1. Temperature data analysis: monitor the temperature data of the thermistor, monitor the temperature change of the device in real time, and set the temperature threshold range to determine whether the device has abnormal temperature. When the temperature exceeds the set range, an alarm is issued and fault diagnosis is performed; Step B2. Vibration signal analysis: Use an acceleration sensor to obtain vibration signal data, convert the time domain data into frequency domain data through Fourier transform, obtain a spectrum diagram, analyze the spectrum diagram, and determine whether there are abnormal frequency components in the spectrum diagram; when a frequency component inconsistent with the normal operation of the equipment appears, the equipment is faulty; Step B3. Make a judgment based on the analysis results of the temperature data and the vibration signal spectrum.

[0011] Furthermore, in step 3, according to the judgment result, an equipment failure prediction model is established; time domain features are extracted from the temperature data, and frequency domain features are extracted from the spectrum diagram of the vibration signal data, which are used as input features, and an equipment failure prediction model is established based on historical data and machine learning algorithms to achieve early warning of equipment failures, including the following steps: Step C1. Obtain historical operation data: divide the acquired historical operation data into a training set and a test set, use the training set to train the machine learning model, adjust parameters to optimize model performance, and evaluate the performance of the model on the test set; Step C2. Feature extraction: extracting time domain features from the temperature data and frequency domain features from the spectrum of the vibration signal data, and using them as input features, including the following steps: Step C201. Extracting time domain features from temperature data: The mean, standard deviation and maximum value in the temperature data are used as time domain features, which are expressed as ( T mean ,T std ,T max ); Step C202. Extract frequency domain features from vibration signal data: extract frequency components from the spectrum as frequency domain features, expressed as ( k 1, k 2…, k N ),in, k N is the value of the Nth frequency component in the spectrum; Step C3. Establish a prediction model: Combine the time domain features and frequency domain features as the input feature vector of the neural network, expressed as X=( T mean ,T std ,T max ,k 1, k 2…, k N ), a neural network algorithm is used to build a fault prediction model, and the calculation formula is as follows: Q = softmax ( W 2×Re LU ( W 1• X + b 1)+ b 2) in, Q represents the output of the neural network, X is the input feature vector, W 1 and b 1 is the weight and bias of the first layer of neural network, W 2 and b 2 is the weight and bias of the second layer of neural network, Re LU () is the activation function, softmax () is the activation function used for classification.

[0012] Furthermore, in step 4, the equipment failure prediction model is used to conduct real-time monitoring and early warning, and maintenance plans are formulated in time for abnormal situations to reduce unplanned downtime. This is achieved by real-time monitoring of the operating status and parameters of the equipment, including real-time collection of equipment data and transmission to a cloud server, real-time monitoring and analysis, determining whether there are abnormal situations, and formulating maintenance plans based on the prediction results to reduce unplanned downtime, including the following steps: Step D1. Maintenance plan formulation: Use the prediction model to predict equipment failures in the future, formulate a maintenance plan based on the prediction results, and maintain the equipment; Step D2. Real-time monitoring and early warning: Real-time monitoring of the operating status and parameters of the equipment, and real-time monitoring and analysis based on the equipment status and prediction model to determine whether there are abnormal conditions. When an abnormal condition is detected, an early warning notification is issued; Step D3. Data visualization: Design a data visualization interface to intuitively present the monitoring data in the form of charts, show the changing trends of key indicators, and quickly understand the equipment status.

[0013] Furthermore, the vibration signal analysis described in step B2: using an acceleration sensor to obtain vibration signal data, converting the time domain data into frequency domain data through Fourier transform, obtaining a spectrum diagram, analyzing the spectrum diagram, and determining whether there are abnormal frequency components in the spectrum diagram; when a frequency component inconsistent with the normal operating state of the equipment appears, the equipment is faulty; including the following steps: Step B201. Peak detection: Peak detection is performed by finding the local maximum value. Assume that the spectrum data obtained by Fourier transform is ( k 1, k 2…, k N ),in k N is the value of the Nth frequency component in the spectrum; Step B202. Find the local maximum: traverse the spectrum data and find the local maximum point that satisfies k i > k i-1 and k i > k i+1 The frequency point, k i in, k i is the value of the i-th frequency component in the spectrum graph, k i+1 is the value of the i+1th frequency component in the spectrum diagram; Step B203. Determine abnormal frequency components: Determine the peak value in the spectrum graph by comparing the value of each frequency component in the spectrum graph with its adjacent frequency components, and determine whether there are abnormal frequency components in the spectrum graph, including harmonics and resonant frequencies, based on the peak detection result; The step B3 combines the temperature data and the analysis results of the vibration signal spectrum to make a judgment, including: B301. When the temperature data is normal and there is no abnormal frequency component in the vibration signal spectrum, the equipment is operating normally; B302. When the temperature data is normal and there are abnormal frequency components in the vibration signal spectrum, there is a mechanical fault; B303. When the temperature data is abnormal and there is no abnormal frequency component in the vibration signal spectrum, there is a thermistor fault.

[0014] A computer device comprises a storage medium, a processor and a computer program stored on the storage medium and executable on the processor, wherein when the processor executes the computer program, the steps of any one of the Internet-based intelligent thermal power plant production methods are implemented.

[0015] A computer storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements any step of an Internet-based intelligent thermal power plant production method.

[0016] The present invention has the following beneficial effects and advantages: The intelligent thermal power plant production system uses modern information technology to intelligently manage and optimize the thermal power generation process. It improves the efficiency of thermal power generation and achieves sustainable development by real-time monitoring and control of equipment operating status, predicting faults and carrying out maintenance plans.

[0017] The present invention deploys sensors and monitoring equipment on thermal power generation equipment to collect operating data of thermal power generation equipment in real time, including temperature and vibration data, uses wireless communication technology to transmit the collected data to a cloud server, and establishes a database on the cloud server to store the collected operating data. A remote connection tool is used to connect to the cloud server to obtain the collected historical operating data, and combines the analysis results of the temperature data and the vibration signal spectrum diagram to determine whether the equipment fails. Based on historical data and machine learning algorithms, an equipment failure prediction model is established, and the operating status and parameters of the equipment are monitored in real time, including real-time collection of equipment data and transmission to the cloud server, real-time monitoring and analysis are performed, and a maintenance plan is formulated according to the prediction results to reduce unplanned downtime and improve the reliability and stability of the equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] 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 It is a block diagram of an Internet-based intelligent thermal power plant production system of the present invention; Figure 2 The present invention discloses an Internet-based production flow chart of an intelligent thermal power plant. DETAILED DESCRIPTION

[0019] In order to more clearly understand the above-mentioned objectives, 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.

[0020] 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.

[0021] Refer to the following Figure 1 and Figure 2 The technical solutions of some embodiments of the present invention are described.

[0022] Example 1

[0023] The present invention provides an embodiment, which is an intelligent thermal power plant production system based on the Internet, such as Figure 1 An Internet-based intelligent thermal power plant production system is shown, which specifically includes a data acquisition module, a data analysis module, a fault prediction module and a safety monitoring module.

[0024] The data acquisition module: by deploying sensors and monitoring equipment on the thermal power generation equipment, the operating data of the thermal power generation equipment, including temperature and vibration data, is collected in real time, the collected data is transmitted to the cloud server by using wireless communication technology, and a database is established on the cloud server to store the collected operating data.

[0025] The data analysis module uses a remote connection tool to connect to a cloud server and operates the server through a terminal window to obtain the collected historical operation data, including temperature and vibration data, and combines the analysis results of the temperature data and the vibration signal spectrum diagram to determine whether the equipment has a fault.

[0026] The fault prediction module extracts time domain features from temperature data and frequency domain features from the spectrum diagram of vibration signal data, uses them as input features, and establishes an equipment fault prediction model based on historical data and machine learning algorithms.

[0027] The safety monitoring module: monitors the operating status and parameters of the equipment in real time, including real-time collection of equipment data and transmission to the cloud server, conducts real-time monitoring and analysis, determines whether there are abnormal conditions, formulates maintenance plans based on the prediction results, and reduces unplanned downtime.

[0028] Example 2

[0029] The present invention provides an embodiment, which is an intelligent thermal power plant production method based on the Internet, such as Figure 2As shown, Figure 2 This is an Internet-based intelligent thermal power plant production flow chart of the present invention, which is implemented using an Internet-based intelligent thermal power plant production system described in Example 1.

[0030] An Internet-based intelligent thermal power plant production method, comprising: Step 1. Collect temperature and vibration data of thermal power generation equipment and transmit them to the cloud server.

[0031] The data acquisition module collects temperature and vibration data of the thermal power generation equipment in real time by deploying sensors and monitoring equipment on the thermal power generation equipment, transmits the collected data to the cloud server by using wireless communication technology, and establishes a database on the cloud server to store the collected operation data. The specific steps are as follows: Step A1. Temperature data collection: Use a thermistor as a temperature sensor, install it in the high temperature area of ​​the turbine unit, and collect the temperature data of the thermal power generation equipment. The specific calculation formula is as follows: T 1= R 0×(1+ A × T + B × T 2 + C ×( T -100)× T 3 ) in, T 1 represents the temperature data of the high temperature area of ​​the turbine unit, R 0 is the resistance value of the thermistor at the reference temperature, A, B, C are the temperature coefficients of the thermistor, and T is the temperature of the thermistor; Step A2. Vibration data collection: Install the acceleration sensor on the generator to measure the vibration signal, convert the acceleration signal into a spectrum diagram through the Fourier transform method, and monitor the vibration of the equipment. The specific calculation formula is as follows: , Where x(n) is the discrete time series of the input signal, X ( k ) is the frequency of the output signal, N is the signal length, k is the frequency index, j is an imaginary unit, n is a time index, representing a time point in a discrete time series, and e is a natural constant.

[0032] Step 2: Analyze the acquired temperature and vibration data of the thermal power generation equipment to determine whether the equipment is faulty.

[0033] The data analysis module uses a remote connection tool to connect to the cloud server and operates the server through a terminal window to obtain the collected historical operation data, including temperature and vibration data, and combines the analysis results of the temperature data and the vibration signal spectrum to determine whether the equipment is faulty. The specific steps are as follows: Step B1. Temperature data analysis: monitor the temperature data of the thermistor, monitor the temperature change of the device in real time, and set the temperature threshold range to determine whether the device has abnormal temperature. When the temperature exceeds the set range, an alarm is issued and fault diagnosis is performed; Step B2. Vibration signal analysis: Use an acceleration sensor to obtain vibration signal data, convert the time domain data into frequency domain data through Fourier transform, obtain a spectrum diagram, analyze the spectrum diagram, and determine whether there are abnormal frequency components in the spectrum diagram, including harmonics and resonant frequencies. When a frequency component inconsistent with the normal operation of the equipment appears, it indicates that the equipment is faulty, further comprising the following steps: Step B201. Peak detection: Peak detection is performed by finding the local maximum value. Assume that the spectrum data obtained by Fourier transform is ( k 1, k 2…, k N ),in k N Indicates the value of the Nth frequency component in the spectrum graph; Step B202. Find the local maximum: traverse the spectrum data and find the local maximum point that satisfies k i > k i-1 and k i > k i+1 The frequency point, k i in, k i is the value of the i-th frequency component in the spectrum graph, k i+1 Represents the value of the i+1th frequency component in the spectrum graph; Step B203. Determine abnormal frequency components: Determine the peak value in the spectrum graph by comparing the value of each frequency component in the spectrum graph with its adjacent frequency components, and determine whether there are abnormal frequency components in the spectrum graph, including harmonics and resonant frequencies, based on the peak detection result; Step B3. Based on the analysis results of the temperature data and the vibration signal spectrum, make the following judgments: B301. When the temperature data is normal and there is no abnormal frequency component in the vibration signal spectrum, the equipment is operating normally; B302. When the temperature data is normal and there are abnormal frequency components in the vibration signal spectrum, there is a mechanical fault; B303. When the temperature data is abnormal and there is no abnormal frequency component in the vibration signal spectrum, there is a thermistor fault.

[0034] Step 3. Based on the judgment results, establish an equipment failure prediction model.

[0035] The fault prediction module extracts time domain features from temperature data and frequency domain features from the spectrum of vibration signal data, uses them as input features, and establishes an equipment fault prediction model based on historical data and machine learning algorithms to achieve early warning of equipment faults. The specific steps are as follows: Step C1. Obtain historical operation data: divide the acquired historical operation data into a training set and a test set, use the training set to train the machine learning model, adjust parameters to optimize model performance, and evaluate the performance of the model on the test set; Step C2. Feature extraction: extracting time domain features from the temperature data and frequency domain features from the spectrum of the vibration signal data, taking them as input features, further comprising the following steps: Step C201. Extracting time domain features from temperature data: The mean, standard deviation and maximum value in the temperature data are used as time domain features, which are expressed as ( T mean ,T std ,T max ); Step C202. Extract frequency domain features from vibration signal data: extract frequency components from the spectrum as frequency domain features, expressed as ( k 1, k 2…, k N ),in, k N Indicates the value of the Nth frequency component in the spectrum graph; Step C3. Establish a prediction model: Combine the time domain features and frequency domain features as the input feature vector of the neural network, expressed as X=( T mean ,T std ,T max ,k 1, k 2…, k N ), use the neural network algorithm to build a fault prediction model, the specific calculation formula is as follows: Q = softmax ( W 2×Re LU ( W 1• X + b 1)+ b 2); in, Q represents the output of the neural network, X is the input feature vector, W 1 and b 1 is the weight and bias of the first layer of neural network, W 2 and b 2 is the weight and bias of the second layer of neural network, Re LU () is the activation function, softmax () is the activation function used for classification.

[0036] Step 4. Use the equipment failure prediction model to conduct real-time monitoring and early warning, formulate maintenance plans for abnormal situations in a timely manner, and reduce unplanned downtime.

[0037] The safety monitoring module monitors the operating status and parameters of the equipment in real time, including real-time collection of equipment data and transmission to the cloud server, performs real-time monitoring and analysis, determines whether there are abnormal conditions, formulates maintenance plans based on the prediction results, reduces unplanned downtime, and improves the reliability and stability of the equipment. The specific steps are as follows: Step D1. Maintenance plan formulation: Use the prediction model to predict equipment failures in the future, including the type of failure and the time of occurrence. According to the prediction results, formulate a maintenance plan and maintain the equipment; Step D2. Real-time monitoring and early warning: Real-time monitoring of the operating status and parameters of the equipment, including real-time collection of equipment data and transmission to the cloud server, real-time monitoring and analysis based on the equipment status and prediction model, to determine whether there are any abnormal conditions, and when abnormal conditions are detected, an early warning notification is issued to alert staff and take emergency measures; Step D3. Data visualization: Design a data visualization interface to intuitively present the monitoring data in the form of charts, show the changing trends of key indicators, and quickly understand the equipment status.

[0038] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[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 Internet-based intelligent thermal power plant production method described in Example 2 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 Internet-based intelligent thermal power plant production method described in Example 2 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 comprising 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. 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 solutions 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. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. An Internet-based intelligent thermal power plant production system, characterized by: It includes a data acquisition module, a data analysis module, a fault prediction module and a safety monitoring module; the data acquisition module: by deploying sensors and monitoring equipment on the thermal power generation equipment, the operation data of the thermal power generation equipment is collected in real time, and the collected data is transmitted to the cloud server by using wireless communication technology, and a database is established on the cloud server to store the collected operation data; the data analysis module: uses a remote connection tool to connect to the cloud server, operates the server through the terminal window, obtains the collected historical operation data, and combines the analysis results of the temperature data and the vibration signal spectrum diagram to determine whether the equipment has a fault; the fault prediction module: extracts time domain features from the temperature data, extracts frequency domain features from the spectrum diagram of the vibration signal data as input features, and establishes an equipment fault prediction model based on historical data and machine learning algorithms; the safety monitoring module: monitors the operation status and parameters of the equipment in real time, conducts real-time monitoring and analysis, determines whether there is an abnormal situation, formulates a maintenance plan based on the prediction results, and reduces unplanned downtime.

2. According to claim 1, an Internet-based intelligent thermal power plant production system is characterized in that: The operating data of the thermal power generation equipment includes temperature and vibration data; the collected historical operating data includes temperature and vibration data; the operating status and parameters of the equipment include real-time collection of equipment data and transmission to a cloud server.

3. An Internet-based intelligent thermal power plant production method, characterized by: include: Step 1. Collect temperature and vibration data of thermal power generation equipment and transmit them to the cloud server; Step 2: Analyze the acquired temperature and vibration data of the thermal power generation equipment to determine whether the equipment is faulty; Step 3. Establish an equipment failure prediction model based on the judgment results; Step 4. Use the equipment failure prediction model to conduct real-time monitoring and early warning, formulate maintenance plans for abnormal situations in a timely manner, and reduce unplanned downtime.

4. The Internet-based intelligent thermal power plant production method according to claim 3 is characterized in that: The step 1 of collecting the temperature and vibration data of the thermal power generation equipment and transmitting it to the cloud server is to deploy sensors and monitoring equipment on the thermal power generation equipment to collect the temperature and vibration data of the thermal power generation equipment in real time, use wireless communication technology to transmit the collected data to the cloud server, and establish a database on the cloud server to store the collected operation data; it includes the following steps: Step A1. Temperature data collection: Use a thermistor as a temperature sensor, install it in the high temperature area of ​​the turbine unit, and collect the temperature data of the thermal power generation equipment. The calculation formula is as follows: T 1= R 0×(1+ A × T + B × T 2 + C ×( T -100)× T 3 ) in, T 1 represents the temperature data of the high temperature area of ​​the turbine unit, R 0 is the resistance value of the thermistor at the reference temperature, A, B, C are the temperature coefficients of the thermistor, and T is the temperature of the thermistor; Step A2. Vibration data collection: Install the acceleration sensor on the generator to measure the vibration signal, convert the acceleration signal into a spectrum diagram through the Fourier transform method, and monitor the vibration of the equipment. The calculation formula is as follows: ， Where x(n) is the discrete time series of the input signal, X ( k ) is the frequency of the output signal, N is the signal length, k is the frequency index, j is an imaginary unit, n is a time index, representing a time point in a discrete time series, and e is a natural constant.

5. The Internet-based intelligent thermal power plant production method according to claim 3 is characterized in that: Step 2 analyzes the acquired temperature and vibration data of the thermal power generation equipment to determine whether the equipment is faulty; a remote connection tool is used to connect to the cloud server, and the server is operated through a terminal window to obtain the collected historical operating temperature and vibration data, and the analysis results of the temperature data and the vibration signal spectrum are combined to determine whether the equipment is faulty, including the following steps: Step B1. Temperature data analysis: monitor the temperature data of the thermistor, monitor the temperature change of the device in real time, and set the temperature threshold range to determine whether the device has abnormal temperature. When the temperature exceeds the set range, an alarm is issued and fault diagnosis is performed; Step B2. Vibration signal analysis: Use an acceleration sensor to obtain vibration signal data, convert the time domain data into frequency domain data through Fourier transform, obtain a spectrum diagram, analyze the spectrum diagram, and determine whether there are abnormal frequency components in the spectrum diagram; when a frequency component inconsistent with the normal operation of the equipment appears, the equipment is faulty; Step B3. Make a judgment based on the analysis results of the temperature data and the vibration signal spectrum.

6. The Internet-based intelligent thermal power plant production method according to claim 3 is characterized by: According to the judgment results, step 3 establishes an equipment failure prediction model; extracts time domain features from temperature data, extracts frequency domain features from the spectrum diagram of vibration signal data, uses them as input features, and establishes an equipment failure prediction model based on historical data and machine learning algorithms to achieve early warning of equipment failures, including the following steps: Step C1. Obtain historical operation data: divide the acquired historical operation data into a training set and a test set, use the training set to train the machine learning model, adjust parameters to optimize model performance, and evaluate the performance of the model on the test set; Step C2. Feature extraction: extracting time domain features from the temperature data and frequency domain features from the spectrum of the vibration signal data, and using them as input features, including the following steps: Step C201. Extracting time domain features from temperature data: The mean, standard deviation and maximum value in the temperature data are used as time domain features, which are expressed as ( T mean ,T std ,T max ); Step C202. Extract frequency domain features from vibration signal data: extract frequency components from the spectrum as frequency domain features, expressed as ( k 1, k 2…, k N ),in, k N is the value of the Nth frequency component in the spectrum; Step C3. Establish a prediction model: Combine the time domain features and frequency domain features as the input feature vector of the neural network, expressed as X=( T mean ,T std ,T max ,k 1, k 2…, k N ), a neural network algorithm is used to build a fault prediction model, and the calculation formula is as follows: Q = softmax ( W 2×Re LU ( W 1• X + b 1)+ b 2); in, Q represents the output of the neural network, X is the input feature vector, W 1 and b 1 is the weight and bias of the first layer of neural network, W 2 and b 2 is the weight and bias of the second layer of neural network, Re LU () is the activation function, softmax () is the activation function used for classification.

7. The Internet-based intelligent thermal power plant production method according to claim 3 is characterized by: In step 4, the equipment failure prediction model is used to conduct real-time monitoring and early warning, and maintenance plans are formulated in time for abnormal situations to reduce unplanned downtime. This is achieved by real-time monitoring of the equipment's operating status and parameters, including real-time collection of equipment data and transmission to a cloud server, real-time monitoring and analysis, determining whether there are abnormal situations, and formulating maintenance plans based on the prediction results to reduce unplanned downtime, including the following steps: Step D1. Maintenance plan formulation: Use the prediction model to predict equipment failures in the future, formulate a maintenance plan based on the prediction results, and maintain the equipment; Step D2. Real-time monitoring and early warning: Real-time monitoring of the operating status and parameters of the equipment, and real-time monitoring and analysis based on the equipment status and prediction model to determine whether there are abnormal conditions. When an abnormal condition is detected, an early warning notification is issued; Step D3. Data visualization: Design a data visualization interface to intuitively present the monitoring data in the form of charts, show the changing trends of key indicators, and quickly understand the equipment status.

8. The Internet-based intelligent thermal power plant production method according to claim 5 is characterized by: The vibration signal analysis described in step B2: using an acceleration sensor to obtain vibration signal data, converting the time domain data into frequency domain data through Fourier transform to obtain a spectrum diagram, analyzing the spectrum diagram, and determining whether there are abnormal frequency components in the spectrum diagram; When a frequency component inconsistent with the normal operation of the device appears, the device is faulty; including the following steps: Step B201. Peak detection: Peak detection is performed by finding the local maximum value. Assume that the spectrum data obtained by Fourier transform is ( k 1, k 2…, k N ),in k N is the value of the Nth frequency component in the spectrum; Step B202. Find the local maximum: traverse the spectrum data and find the local maximum point that satisfies k i > k i-1 and k i > k i+1 The frequency point, k i in, k i is the value of the i-th frequency component in the spectrum graph, k i+1 is the value of the i+1th frequency component in the spectrum diagram; Step B203. Determine abnormal frequency components: Determine the peak value in the spectrum graph by comparing the value of each frequency component in the spectrum graph with its adjacent frequency components, and determine whether there are abnormal frequency components in the spectrum graph, including harmonics and resonant frequencies, based on the peak detection result; The step B3 combines the temperature data and the analysis results of the vibration signal spectrum to make a judgment, including: B301. When the temperature data is normal and there is no abnormal frequency component in the vibration signal spectrum, the equipment is operating normally; B302. When the temperature data is normal and there are abnormal frequency components in the vibration signal spectrum, there is a mechanical fault; B303. When the temperature data is abnormal and there is no abnormal frequency component in the vibration signal spectrum, there is a thermistor fault.

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 processor implements the steps of an Internet-based intelligent thermal power plant production method as described in any one of claims 3 to 8.

10. A computer storage medium, characterized in that: The computer storage medium stores a computer program, which, when executed by a processor, implements the steps of an Internet-based intelligent thermal power plant production method as described in any one of claims 3 to 8.

Images