Cluster remote real-time state monitoring and fault diagnosis method and platform

Abstract

The invention discloses a cluster remote real-time state monitoring and fault diagnosis method and platform, and belongs to the technical field of thermal power. The method solves the problem that the existing method is poor in machine group judgment accuracy, analyzes the collected operation data through the data processing center, extracts the characteristics of the operation data and compares the characteristics with the fault database, so that the fault type and position of the thermal power plant equipment can be judged, and meanwhile, the fault judgment accuracy of the thermal power plant equipment is improved. By performing trend analysis on the historical operation data and constructing the fault prediction model based on the historical operation data, the fault of the thermal power plant equipment can be predicted, and through the above process, the operation state of the thermal power plant equipment can be monitored in real time and the fault can be accurately diagnosed. According to the device, the fault early warning can be given out when a fault is found, and the response of the worker to the fault early warning is monitored in real time, so that the timely response of the worker to the fault early warning is improved.

Description

Technical Field

[0001] The present invention relates to the field of thermal power technology, and in particular to a remote real-time status monitoring and fault diagnosis method and platform for a cluster of machines. Background Art

[0002] With the rapid development of social economy, thermal power plants play an important role in energy supply. However, due to the high temperature, high pressure and complex mechanical equipment in the operation process of thermal power plants, various faults are prone to occur, affecting their normal operation and safety. Thermal power plants are in urgent need of a reliable monitoring and fault warning method to ensure the stable operation and safety of thermal power plants. However, the traditional equipment operation status monitoring and fault diagnosis method is often based on regular inspections. The accuracy of this method is poor and the cause of the fault cannot be determined; therefore, it does not meet the existing needs. In this regard, we propose a remote real-time status monitoring and fault diagnosis method and platform for the fleet. Summary of the invention

[0003] The purpose of the present invention is to provide a remote real-time status monitoring and fault diagnosis method and platform for a cluster of machines. The collected operating data is analyzed by a data processing center, and the characteristics of the operating data are extracted and compared with a fault database, so that the fault type and location of the thermal power plant equipment can be determined. At the same time, by performing trend analysis on historical operating data and building a fault prediction model based on historical operating data, the fault of the thermal power plant equipment can be predicted so that the staff can take preventive measures. When a fault is found, a fault warning will be issued, and the staff's response to the fault warning will be monitored in real time to improve the staff's timely response to the fault warning, thereby solving the problems raised in the above-mentioned background technology.

[0004] To achieve the above object, the present invention provides the following technical solution: a remote real-time status monitoring and fault diagnosis method for a cluster, comprising the following steps:

[0005] Sensors installed on thermal power plant equipment can collect real-time operating data of thermal power plant equipment, including temperature, humidity, pressure, vibration, current and voltage of the equipment;

[0006] The collected operation data of thermal power plant equipment is transmitted to the data processing center through wired or wireless communication, and the data processing center processes and analyzes the received operation data of thermal power plant equipment in real time;

[0007] The data processing center pre-processes the operation data, including removing outliers, filtering and standardization. After processing, the operation data is displayed in the form of visual charts;

[0008] The data processing center analyzes the pre-processed operation data, establishes a fault database for thermal power plant equipment, extracts features from the real-time collected operation data, and compares it with the fault database to determine the fault type and location of the thermal power plant equipment;

[0009] By establishing a historical database of thermal power plant equipment, trend analysis is performed on the data in the historical database. At the same time, a fault prediction model is constructed using the data in the historical database. The fault prediction model is used to predict faults on the real-time collected operating data.

[0010] Based on the above analysis results, if there is a fault problem in the thermal power plant equipment, a fault warning will be issued, and the staff's response to the fault warning will be monitored in real time.

[0011] Furthermore, sensors are installed at monitoring positions corresponding to the thermal power plant equipment. The sensors include temperature and humidity sensors, pressure sensors, vibration sensors, current sensors and voltage sensors. Through the installed sensors, the temperature and humidity, pressure, vibration, current and voltage operating data of the thermal power plant equipment are collected in real time.

[0012] Furthermore, the transmission of the operation data specifically includes the following steps:

[0013] Summarize the operation data collected by sensors;

[0014] Transmitting the aggregated operating data by wired or wireless communication;

[0015] The operation data is transmitted in parallel, and the operation data is transmitted in groups on multiple parallel channels at the same time;

[0016] The operation data is transmitted to the data processing center for real-time processing and analysis through wired or wireless communication and parallel transmission.

[0017] Furthermore, the collected operation data is transmitted by wired or wireless communication, the wired communication method includes Ethernet or serial port line, and the wireless communication method includes Wi-Fi or Bluetooth or LoRa.

[0018] Furthermore, the data processing center is used to process and analyze the received equipment operation data in real time, and is also used to establish and manage equipment ledgers. By establishing equipment ledgers, basic information, operating status, fault records and maintenance records of thermal power plant equipment are recorded in detail.

[0019] Furthermore, a fault database of thermal power plant equipment is established, which specifically includes the following steps:

[0020] Collect fault case data of thermal power plant equipment. Each fault case data includes equipment information, fault name, fault phenomenon, fault cause analysis and conclusion, and maintenance process steps and requirements;

[0021] The collected data is sorted and classified according to equipment type and fault phenomenon, and then a fault database of thermal power plant equipment is established;

[0022] After completing the above steps, feature extraction is performed on the real-time collected operation data;

[0023] The extracted features are compared with the fault database to diagnose the faults of thermal power plant equipment;

[0024] Among them, feature extraction uses time domain analysis, frequency domain analysis, and time-frequency analysis, specifically:

[0025] Time domain analysis: The characteristics of the operating data are characterized by calculating statistics such as mean and variance. The characteristics reflect the working status, fault type and degree of the thermal power plant equipment.

[0026] Frequency domain analysis: The operating data is converted from the time domain to the frequency domain through the Fourier transform method, the frequency characteristics of the operating data are analyzed, and the fault type and degree are identified.

[0027] Time-frequency analysis: Analyze the characteristics of operating data in two dimensions: time and frequency, capture the frequency distribution of operating data at different times, and indicate the status of thermal power plant equipment at different times.

[0028] Furthermore, the data in the historical database is used for trend analysis and fault prediction, which specifically includes the following steps:

[0029] Collect a large amount of historical operation data of thermal power plant equipment and establish a historical database based on the collected historical operation data;

[0030] Use time series analysis to conduct trend analysis on historical operation data. By conducting time series analysis on historical operation data of thermal power plant equipment, the law and trend of the change of thermal power plant equipment status over time are obtained;

[0031] At the same time, a machine learning model is selected based on historical operation data, including decision tree, random forest or support vector machine, to build a fault prediction model;

[0032] Extract features from historical operation data and construct a training set with the extracted features;

[0033] Use the constructed training set to train the fault prediction model and learn the features and patterns in the historical operation data;

[0034] Deploy the trained fault prediction model to actual applications, and use the fault prediction model to predict faults based on real-time collected operating data;

[0035] If the operating status of the thermal power plant equipment is in line with expectations, it is determined that there is no fault problem with the thermal power plant equipment;

[0036] If there is a fault problem in the thermal power plant equipment, it is determined that there is a fault problem in the thermal power plant equipment and a fault warning is issued.

[0037] Furthermore, fault warning is in the form of SMS notification. After receiving the SMS notification, the staff sends the known warning information to the data processing center. The staff is evaluated according to the feedback time of the known warning information. The feedback time is divided into 0-1min, 1-2min and more than 2min, specifically:

[0038] 0-1min means timely feedback from staff;

[0039] 1-2min means the staff’s feedback is slow;

[0040] More than 2 minutes means that the staff's feedback is not timely;

[0041] Among them, the staff members whose feedback time is 1-2 minutes will be counted. When the feedback time of the staff members is 1-2 minutes and the number of feedbacks in this feedback time period exceeds five times, the staff members will be evaluated as untimely in giving feedback. The staff members who are evaluated as untimely in giving feedback will be warned.

[0042] A remote real-time status monitoring and fault diagnosis platform for a cluster of machines is used to implement a remote real-time status monitoring and fault diagnosis method for a cluster of machines, including:

[0043] Data acquisition module for:

[0044] The installed sensors collect real-time operating data of thermal power plant equipment, including temperature, humidity, pressure, vibration, current and voltage of the equipment;

[0045] Data transmission module for:

[0046] Transmit the collected operation data to the data processing center through wired or wireless communication;

[0047] Data processing centre for:

[0048] Process and analyze the received thermal power plant equipment operation data in real time, establish and manage equipment records, diagnose and predict thermal power plant equipment failures through analysis, and issue early warnings when failures occur;

[0049] The data processing center includes:

[0050] Data processing module for:

[0051] Preprocess the operating data, including removing outliers, filtering and standardizing, and display them in the form of visual charts after processing;

[0052] Equipment ledger module, used for:

[0053] Establish equipment records and record in detail the basic information, operating status, fault records and maintenance records of thermal power plant equipment;

[0054] Data analysis module for:

[0055] Collect fault case data of thermal power plant equipment to establish a fault database, extract features from real-time collected operating data, and compare the extracted features with the fault database to perform fault diagnosis on thermal power plant equipment;

[0056] Use time series analysis to analyze the trend of historical operation data and obtain the law and trend of equipment status changes over time in thermal power plants;

[0057] Build and train a fault prediction model based on historical operation data, and use the trained fault prediction model to predict faults on real-time collected operation data;

[0058] Fault warning module, used for:

[0059] Based on the above analysis results, if there is a fault in the thermal power plant equipment, a fault warning will be sent to the staff via SMS notification.

[0060] Furthermore, the fault warning module includes:

[0061] Early warning response monitoring module, used for:

[0062] After the staff receives the SMS notification, the feedback time for the staff to send the known warning information to the data processing center is monitored;

[0063] Response evaluation module, used to:

[0064] Evaluate staff response speed based on monitoring feedback duration;

[0065] Staff warning module for:

[0066] Issue warnings to staff members who are evaluated as not providing timely feedback.

[0067] Compared with the prior art, the present invention has the following beneficial effects:

[0068] 1. The present invention collects the operating data of thermal power plant equipment in real time through the installed sensors, and then removes outliers, filters and standardizes the received operating data of thermal power plant equipment through the data processing center. Then, the processed operating data is analyzed. First, by extracting the characteristics of the operating data and comparing it with the fault database, the fault type and location of the thermal power plant equipment can be determined. Secondly, by performing trend analysis on the historical operating data, the law and trend of the change of the status of the thermal power plant equipment over time can be obtained, so that the fault of the thermal power plant equipment can be predicted. Finally, a fault prediction model is constructed based on the historical operating data, which can further predict the fault of the thermal power plant equipment. Through the above process, the operating status of the thermal power plant equipment can be monitored in real time and the fault can be accurately diagnosed, which not only makes it convenient for the staff to understand the operating status of the equipment, but also improves the diagnostic accuracy of the thermal power plant equipment fault, so that the staff can take relevant preventive measures in time.

[0069] 2. After analyzing the operating data, if there is a fault in the thermal power plant equipment, the present invention will send a fault warning to the staff through SMS notification, monitor the feedback time of the staff sending the known warning information to the data processing center, and evaluate the response speed of the staff according to the monitoring feedback time, and issue a warning to the staff who are evaluated as not giving timely feedback, so as to supervise the speed at which the staff responds to the warning, so as to ensure that the staff can respond to the fault warning in time. BRIEF DESCRIPTION OF THE DRAWINGS

[0070] Figure 1 It is a flow chart of the method for remote real-time status monitoring and fault diagnosis of a cluster of machines of the present invention;

[0071] Figure 2 It is a structural schematic diagram of the remote real-time status monitoring and fault diagnosis platform of a cluster of machines of the present invention. DETAILED DESCRIPTION

[0072] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0073] In order to solve the problem that the existing thermal power plant equipment operation status monitoring and fault diagnosis methods are often based on regular inspections, which have poor accuracy in fault judgment and cannot determine the cause of the fault, please refer to Figure 1-Figure 2 , this embodiment provides the following technical solutions:

[0074] A remote real-time status monitoring and fault diagnosis method for a cluster of machines comprises the following steps:

[0075] Sensors installed on thermal power plant equipment can collect real-time operating data of thermal power plant equipment, including temperature, humidity, pressure, vibration, current and voltage of the equipment;

[0076] The collected operation data of thermal power plant equipment is transmitted to the data processing center through wired or wireless communication, and the data processing center processes and analyzes the received operation data of thermal power plant equipment in real time;

[0077] The data processing center pre-processes the operation data, including removing outliers, filtering and standardization. After processing, the operation data is displayed in the form of visual charts;

[0078] The data processing center analyzes the pre-processed operation data, establishes a fault database for thermal power plant equipment, extracts features from the real-time collected operation data, and compares it with the fault database to determine the fault type and location of the thermal power plant equipment;

[0079] By establishing a historical database of thermal power plant equipment, trend analysis is performed on the data in the historical database. At the same time, a fault prediction model is constructed using the data in the historical database. The fault prediction model is used to predict faults on the real-time collected operating data.

[0080] Based on the above analysis results, if there is a fault problem in the thermal power plant equipment, a fault warning will be issued, and the staff's response to the fault warning will be monitored in real time.

[0081] The sensors are installed at the corresponding monitoring positions of the thermal power plant equipment. The sensors include temperature and humidity sensors, pressure sensors, vibration sensors, current sensors and voltage sensors. Through the installed sensors, the temperature and humidity, pressure, vibration, current and voltage operating data of the thermal power plant equipment are collected in real time.

[0082] The technical effects of the above contents are as follows: various operating data of thermal power plant equipment can be collected by using sensors, the collected operating data can reflect the operating status of the thermal power plant equipment, and the collected operating data is the basis for subsequent data analysis. The operating data can be used to diagnose faults of thermal power plant equipment.

[0083] The transmission of operation data specifically includes the following steps:

[0084] Summarize the operation data collected by sensors;

[0085] Transmitting the aggregated operating data by wired or wireless communication;

[0086] The operation data is transmitted in parallel, and the operation data is transmitted in groups on multiple parallel channels at the same time;

[0087] The operation data is transmitted to the data processing center for real-time processing and analysis through wired or wireless communication and parallel transmission.

[0088] The technical effects of the above content are as follows: the collected operating data needs to be summarized before transmission in order to improve the efficiency of data transmission, and the data transmission adopts wired or wireless communication methods, and the operating data is transmitted in a parallel transmission manner. Parallel transmission allows multiple groups of operating data to be transmitted simultaneously on different channels. By dividing the operating data into multiple groups and transmitting them simultaneously on multiple independent and parallel channels, the operating data transmission speed and efficiency can be greatly improved. Since multiple groups of operating data can be transmitted simultaneously, the transmission time is greatly shortened, thereby ensuring the timeliness of the operating data.

[0089] It should be noted that the collected operation data is transmitted by wired or wireless communication. Wired communication methods include Ethernet or serial port lines, and wireless communication methods include Wi-Fi, Bluetooth or LoRa. The communication method can be selected according to the communication rate, communication distance, communication protocol, installation flexibility, work efficiency and environmental requirements, so as to make the operation data transmission more flexible.

[0090] The data processing center is used to process and analyze the received equipment operation data in real time, and is also used to establish and manage equipment ledgers. By establishing equipment ledgers, the basic information, operating status, fault records and maintenance records of thermal power plant equipment are recorded in detail.

[0091] Establishing a fault database for thermal power plant equipment includes the following steps:

[0092] Collect fault case data of thermal power plant equipment. Each fault case data includes equipment information, fault name, fault phenomenon, fault cause analysis and conclusion, and maintenance process steps and requirements;

[0093] The collected data is sorted and classified according to equipment type and fault phenomenon, and then a fault database of thermal power plant equipment is established;

[0094] After completing the above steps, feature extraction is performed on the real-time collected operation data;

[0095] The extracted features are compared with the fault database to diagnose the faults of thermal power plant equipment;

[0096] Among them, feature extraction uses time domain analysis, frequency domain analysis, and time-frequency analysis, specifically:

[0097] Time domain analysis: The characteristics of the operating data are characterized by calculating statistics such as mean and variance. The characteristics reflect the working status, fault type and degree of the thermal power plant equipment.

[0098] Frequency domain analysis: The operating data is converted from the time domain to the frequency domain through the Fourier transform method, the frequency characteristics of the operating data are analyzed, and the fault type and degree are identified.

[0099] Time-frequency analysis: Analyze the characteristics of operating data in two dimensions: time and frequency, capture the frequency distribution of operating data at different times, and indicate the status of thermal power plant equipment at different times.

[0100] The technical effects of the above content are as follows: after receiving the operating data, the data processing center pre-processes the operating data. By removing outliers, filtering and standardizing, outliers in the operating data can be eliminated, noise can be reduced and standardized to ensure the consistency and reliability of the operating data, thereby improving the quality of the operating data, and then improving the efficiency and accuracy of subsequent analysis. Then, the processed operating data is subjected to feature extraction using methods such as time domain analysis, frequency domain analysis and time-frequency analysis, so that the extracted features can be compared with the data in the previously established fault database, so that the fault type and location of the thermal power plant equipment can be determined, thereby realizing the diagnosis of the thermal power plant equipment.

[0101] Using the data in the historical database to perform trend analysis and fault prediction includes the following steps:

[0102] Collect a large amount of historical operation data of thermal power plant equipment and establish a historical database based on the collected historical operation data;

[0103] Use time series analysis to conduct trend analysis on historical operation data. By conducting time series analysis on historical operation data of thermal power plant equipment, the law and trend of the change of thermal power plant equipment status over time are obtained;

[0104] At the same time, a machine learning model is selected based on historical operation data, including decision tree, random forest or support vector machine, to build a fault prediction model;

[0105] Extract features from historical operation data and construct a training set with the extracted features;

[0106] Use the constructed training set to train the fault prediction model and learn the features and patterns in the historical operation data;

[0107] Deploy the trained fault prediction model to actual applications, and use the fault prediction model to predict faults based on real-time collected operating data;

[0108] If the operating status of the thermal power plant equipment is in line with expectations, it is determined that there is no fault problem with the thermal power plant equipment;

[0109] If there is a fault problem in the thermal power plant equipment, it is determined that there is a fault problem in the thermal power plant equipment and a fault warning is issued.

[0110] The technical effects of the above content are as follows: by collecting a large amount of historical operating data of thermal power plant equipment, a historical database can be established, and by using time series analysis to perform trend analysis on the historical operating data, the laws and trends of how the status of thermal power plant equipment changes over time can be obtained, so that the failure of thermal power plant equipment can be predicted. Based on the historical operating data, a fault prediction model can be constructed. By extracting features from the historical operating data, the extracted features can be constructed into a training set to train the fault prediction model. The trained fault prediction model will be deployed in practice to predict failures of the real-time collected operating data, so as to further predict the failures of thermal power plant equipment. Through the above process, the failures of thermal power plant equipment can be accurately diagnosed and predicted, thereby improving the diagnostic accuracy of thermal power plant equipment failures, so that the staff can take corresponding measures for the thermal power plant equipment according to the diagnosis and prediction results.

[0111] Fault warnings are in the form of SMS notifications. After receiving the SMS notifications, the staff will send the known warning information to the data processing center. The staff will be evaluated based on the feedback time of the known warning information. The feedback time is divided into 0-1min, 1-2min and more than 2min, specifically:

[0112] 0-1min means timely feedback from staff;

[0113] 1-2min means the staff’s feedback is slow;

[0114] More than 2 minutes means that the staff's feedback is not timely;

[0115] Among them, the staff members whose feedback time is 1-2 minutes will be counted. When the feedback time of the staff members is 1-2 minutes and the number of feedbacks in this feedback time period exceeds five times, the staff members will be evaluated as untimely in giving feedback. The staff members who are evaluated as untimely in giving feedback will be warned.

[0116] The technical effects of the above content are as follows: when there is a fault in the equipment of a thermal power plant, a fault warning will be sent to the staff via SMS notification. By monitoring the feedback time of the staff sending the known warning information to the data processing center, and evaluating the staff's response speed based on the monitoring feedback time, the speed at which the staff responds to the warning can be supervised to ensure that the staff can respond to the fault warning in time.

[0117] A remote real-time status monitoring and fault diagnosis platform for a cluster of machines is used to implement a remote real-time status monitoring and fault diagnosis method for a cluster of machines, comprising:

[0118] Data acquisition module for:

[0119] The installed sensors collect real-time operating data of thermal power plant equipment, including temperature, humidity, pressure, vibration, current and voltage of the equipment;

[0120] Data transmission module for:

[0121] Transmit the collected operation data to the data processing center through wired or wireless communication;

[0122] Data processing centre for:

[0123] Process and analyze the received thermal power plant equipment operation data in real time, establish and manage equipment records, diagnose and predict thermal power plant equipment failures through analysis, and issue early warnings when failures occur;

[0124] The data processing center includes:

[0125] Data processing module for:

[0126] Preprocess the operating data, including removing outliers, filtering and standardizing, and display them in the form of visual charts after processing;

[0127] Equipment ledger module, used for:

[0128] Establish equipment records and record in detail the basic information, operating status, fault records and maintenance records of thermal power plant equipment;

[0129] Data analysis module for:

[0130] Collect fault case data of thermal power plant equipment to establish a fault database, extract features from real-time collected operating data, and compare the extracted features with the fault database to perform fault diagnosis on thermal power plant equipment;

[0131] Use time series analysis to analyze the trend of historical operation data and obtain the law and trend of equipment status changes over time in thermal power plants;

[0132] Build and train a fault prediction model based on historical operation data, and use the trained fault prediction model to predict faults on real-time collected operation data;

[0133] Fault warning module, used for:

[0134] Based on the above analysis results, if there is a fault in the thermal power plant equipment, a fault warning will be sent to the staff via SMS notification.

[0135] The technical effects of the above contents are as follows: the remote real-time status monitoring and fault diagnosis platform of the cluster can realize the remote real-time status monitoring and fault diagnosis method of the cluster through the data acquisition module, the data transmission module and the data processing center. The data acquisition module can collect the temperature, humidity, pressure, vibration, current and voltage and other operating data of the thermal power plant equipment in real time through the installed sensors. The data transmission module transmits the collected operating data to the data processing center through wired or wireless communication, so that the data processing center can process and analyze the received thermal power plant equipment operating data in real time, thereby realizing the diagnosis and prediction of the faults of the thermal power plant equipment, and issuing early warnings in case of faults, so that the staff can deal with the faults in time.

[0136] Fault warning module, including:

[0137] Early warning response monitoring module, used for:

[0138] After the staff receives the SMS notification, the feedback time for the staff to send the known warning information to the data processing center is monitored;

[0139] Response evaluation module, used to:

[0140] Evaluate staff response speed based on monitoring feedback duration;

[0141] Staff warning module for:

[0142] Issue warnings to staff members who are evaluated as not providing timely feedback.

[0143] The technical effects of the above content are as follows: when there is a fault in the equipment of a thermal power plant, a fault warning will be issued. The fault warning is sent to the staff in the form of a text message notification. After receiving the text message notification, the staff needs to send the warning known information to the data processing center. The warning known information is sent to make it clear that the staff has received the fault warning and will handle the fault. By monitoring the feedback time of the staff sending the warning known information to the data processing center, the staff is evaluated according to the feedback time of the warning known information, and the monitored feedback time is compared with the pre-established standards to determine whether the monitoring feedback time belongs to 0-1min, 1-2min and 2mi n, so as to evaluate the response speed of the staff. If it is more than 2 minutes, the staff is not timely in responding and needs to be warned immediately. If it is 1-2 minutes, the staff will not be warned immediately. However, if the staff has five feedback times in 1-2 minutes, it will also be evaluated as untimely feedback. At this time, the staff will be warned. The speed of the staff's response to the warning is monitored to ensure that the staff can respond to the fault warning in time. This is very important for maintaining the efficiency and reliability of the platform, especially when a quick response is required in the event of a fault.

[0144] Working principle: The installed sensors can collect the operating data of thermal power plant equipment such as temperature, humidity, pressure, vibration, current and voltage in real time. The data processing center will then remove outliers, filter and standardize the received operating data of thermal power plant equipment to improve the quality of operating data, so as to improve the efficiency and accuracy of subsequent analysis. Then, the processed operating data will be analyzed. First, by extracting the characteristics of the operating data and comparing it with the fault database, the fault type and location of the thermal power plant equipment can be determined. Secondly, by performing trend analysis on the historical operating data, the law and trend of the change of the status of the thermal power plant equipment over time can be obtained, so as to predict the failure of the thermal power plant equipment. Finally, a fault prediction model is constructed based on the historical operating data, which can further predict the failure of the thermal power plant equipment. The above process can monitor the operating status of the thermal power plant equipment in real time and accurately diagnose faults, which not only makes it easier for staff to understand the operating status of the equipment, but also improves the diagnostic accuracy of thermal power plant equipment faults, so that staff can take relevant preventive measures in a timely manner. When there is a fault in the thermal power plant equipment, a fault warning will be issued. The fault warning is sent to the staff in the form of a text message notification. After receiving the text message notification, the staff needs to send the warning known information to the data processing center, monitor the feedback time for the staff to send the warning known information to the data processing center, and evaluate the response speed of the staff based on the monitoring feedback time. Warnings are issued to staff who are evaluated as untimely feedback, so that the speed at which the staff responds to the warning can be supervised to ensure that the staff can respond to the fault warning in a timely manner.

[0145] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0146] While the embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that many changes, modifications, substitutions and variations can be made to the embodiments without departing from the principles and spirit of the invention.

Claims

1. A remote real-time status monitoring and fault diagnosis method for a cluster, characterized in that: The following steps are involved: Sensors installed on thermal power plant equipment can collect real-time operating data of thermal power plant equipment, including temperature, humidity, pressure, vibration, current and voltage of the equipment; The collected operation data of thermal power plant equipment is transmitted to the data processing center through wired or wireless communication, and the data processing center processes and analyzes the received operation data of thermal power plant equipment in real time; The data processing center pre-processes the operation data, including removing outliers, filtering and standardization. After processing, the operation data is displayed in the form of visual charts; The data processing center analyzes the pre-processed operation data, establishes a fault database for thermal power plant equipment, extracts features from the real-time collected operation data, and compares it with the fault database to determine the fault type and location of the thermal power plant equipment; By establishing a historical database of thermal power plant equipment, trend analysis is performed on the data in the historical database. At the same time, a fault prediction model is constructed using the data in the historical database. The fault prediction model is used to predict faults on the real-time collected operating data. Based on the above analysis results, if there is a fault problem in the thermal power plant equipment, a fault warning will be issued, and the staff's response to the fault warning will be monitored in real time.

2. A method for remote real-time status monitoring and fault diagnosis of a cluster according to claim 1, characterized in that: The sensors are installed at the corresponding monitoring positions of the thermal power plant equipment. The sensors include temperature and humidity sensors, pressure sensors, vibration sensors, current sensors and voltage sensors. Through the installed sensors, the temperature and humidity, pressure, vibration, current and voltage operating data of the thermal power plant equipment are collected in real time.

3. A cluster remote real-time status monitoring and fault diagnosis method according to claim 1, characterized in that: The transmission of operation data specifically includes the following steps: Summarize the operation data collected by sensors; Transmitting the aggregated operating data by wired or wireless communication; The operation data is transmitted in parallel, and the operation data is transmitted in groups on multiple parallel channels at the same time; The operation data is transmitted to the data processing center for real-time processing and analysis through wired or wireless communication and parallel transmission.

4. A method for remote real-time status monitoring and fault diagnosis of a cluster of machines according to claim 3, characterized in that: The collected operation data is transmitted by wired or wireless communication. The wired communication method includes Ethernet or serial port line, and the wireless communication method includes Wi-Fi or Bluetooth or LoRa.

5. The method for remote real-time status monitoring and fault diagnosis of a cluster of machines according to claim 1, characterized in that: The data processing center is used to process and analyze the received equipment operation data in real time, and is also used to establish and manage equipment ledgers. By establishing equipment ledgers, basic information, operating status, fault records and maintenance records of thermal power plant equipment are recorded in detail.

6. A cluster remote real-time status monitoring and fault diagnosis method according to claim 1, characterized in that: Establishing a fault database for thermal power plant equipment includes the following steps: Collect fault case data of thermal power plant equipment. Each fault case data includes equipment information, fault name, fault phenomenon, fault cause analysis and conclusion, and maintenance process steps and requirements; The collected data are sorted and classified according to equipment type and fault phenomenon, and then a fault database of thermal power plant equipment is established; After completing the above steps, feature extraction is performed on the real-time collected operation data; The extracted features are compared with the fault database to diagnose the faults of thermal power plant equipment; Among them, feature extraction uses time domain analysis, frequency domain analysis, and time-frequency analysis, specifically: Time domain analysis: The characteristics of the operating data are characterized by calculating the mean and variance statistics. The characteristics reflect the working status, fault type and degree of the thermal power plant equipment. Frequency domain analysis: The operating data is converted from the time domain to the frequency domain through the Fourier transform method, the frequency characteristics of the operating data are analyzed, and the fault type and degree are identified. Time-frequency analysis: Analyze the characteristics of operating data in two dimensions: time and frequency, capture the frequency distribution of operating data at different times, and indicate the status of thermal power plant equipment at different times.

7. The method for remote real-time status monitoring and fault diagnosis of a cluster of machines according to claim 1, characterized in that: Using the data in the historical database to perform trend analysis and fault prediction includes the following steps: Collect a large amount of historical operation data of thermal power plant equipment and establish a historical database based on the collected historical operation data; Use time series analysis to conduct trend analysis on historical operation data. By conducting time series analysis on historical operation data of thermal power plant equipment, the law and trend of the change of thermal power plant equipment status over time are obtained; At the same time, a machine learning model is selected based on historical operation data, including decision tree, random forest or support vector machine, to build a fault prediction model; Extract features from historical operation data and construct a training set with the extracted features; Use the constructed training set to train the fault prediction model and learn the features and patterns in the historical operation data; Deploy the trained fault prediction model to actual applications, and use the fault prediction model to predict faults based on real-time collected operating data; If the operating status of the thermal power plant equipment is in line with expectations, it is determined that there is no fault problem with the thermal power plant equipment; If there is a fault problem in the thermal power plant equipment, it is determined that there is a fault problem in the thermal power plant equipment and a fault warning is issued.

8. The method for remote real-time status monitoring and fault diagnosis of a cluster of machines according to claim 1, characterized in that: Fault warnings are in the form of SMS notifications. After receiving the SMS notifications, the staff will send the known warning information to the data processing center. The staff will be evaluated based on the feedback time of the known warning information. The feedback time is divided into 0-1min, 1-2min and more than 2min, specifically: 0-1min means timely feedback from staff; 1-2min means the staff’s feedback is slow; More than 2 minutes means that the staff's feedback is not timely; Among them, the staff members whose feedback time is 1-2 minutes will be counted. When the feedback time of the staff members is 1-2 minutes and the number of feedbacks in this feedback time period exceeds five times, the staff members will be evaluated as untimely in giving feedback. The staff members who are evaluated as untimely in giving feedback will be warned.

9. A remote real-time status monitoring and fault diagnosis platform for a cluster, used to implement the remote real-time status monitoring and fault diagnosis method for a cluster as claimed in any one of claims 1 to 8, characterized in that: include: Data acquisition module for: The installed sensors collect real-time operating data of thermal power plant equipment, including temperature, humidity, pressure, vibration, current and voltage of the equipment; Data transmission module for: Transmit the collected operation data to the data processing center through wired or wireless communication; Data processing centre for: Process and analyze the received thermal power plant equipment operation data in real time, establish and manage equipment records, diagnose and predict thermal power plant equipment failures through analysis, and issue early warnings when failures occur; The data processing center includes: Data processing module for: Preprocess the operating data, including removing outliers, filtering and standardizing, and display them in the form of visual charts after processing; Equipment ledger module, used for: Establish equipment records and record in detail the basic information, operating status, fault records and maintenance records of thermal power plant equipment; Data analysis module for: Collect fault case data of thermal power plant equipment to establish a fault database, extract features from real-time collected operating data, and compare the extracted features with the fault database to perform fault diagnosis on thermal power plant equipment; Use time series analysis to analyze the trend of historical operation data and obtain the law and trend of equipment status changes over time in thermal power plants; Build and train a fault prediction model based on historical operation data, and use the trained fault prediction model to predict faults on real-time collected operation data; Fault warning module, used for: Based on the analysis results, if there is a fault in the thermal power plant equipment, a fault warning will be sent to the staff via SMS notification.

10. A remote real-time status monitoring and fault diagnosis platform for a cluster of machines according to claim 9, characterized in that: The fault warning module comprises: Early warning response monitoring module, used for: After the staff receives the SMS notification, the feedback time for the staff to send the known warning information to the data processing center is monitored; Response evaluation module, used to: Evaluate staff response speed based on monitoring feedback duration; Staff warning module for: Issue warnings to staff members who are evaluated as not providing timely feedback.

Images