Method and system for intelligently monitoring operation state of hydraulic power plant equipment

Abstract

The invention discloses a hydraulic power plant equipment operation state intelligent monitoring method and system, and the method comprises the steps: collecting operation data sets of various types of equipment of a hydraulic power plant, and carrying out the preprocessing, the operation data sets comprising temperature data, pressure data, vibration data, current data and voltage data; processing the operation data set to obtain a state reference value, and classifying the state reference value to obtain an equipment state classification result; processing the equipment state classification result to obtain a state response decision result; the normal prompt information is displayed through the display end, the operation data set is analyzed, and an analysis result is obtained and displayed; according to the method, the state reference value obtained by processing the operation data set of the hydraulic power plant equipment can directly reflect the current operation state of the equipment, so that the huge workload caused by analyzing and calculating the operation data of the equipment by workers is greatly reduced.

Description

Technical Field

[0001] This invention relates to the field of hydropower plant equipment monitoring technology, and in particular to an intelligent monitoring method and system for the operating status of hydropower plant equipment. Background Technology

[0002] As an important energy production unit, the stable operation of hydropower plants is crucial for ensuring power supply. Various equipment in hydropower plants, such as generators, turbines, and transformers, are susceptible to various factors during operation, which may lead to malfunctions or performance degradation.

[0003] Currently, traditional methods for monitoring equipment in hydropower plants mainly rely on manual inspections and simple sensor data collection, which suffers from problems such as incomplete monitoring, low accuracy, and inability to predict equipment failures in a timely manner. Manual inspections also have drawbacks such as long time intervals and the ease of missing inspections, making it difficult to grasp the real-time operating status of equipment.

[0004] Simple sensor data acquisition can only obtain limited information and cannot provide an in-depth analysis or accurate assessment of the overall operating status of the equipment. This often results in equipment malfunctions not being detected and addressed in a timely manner, thus affecting the normal production of hydropower plants and potentially even causing safety accidents.

[0005] Therefore, how to achieve comprehensive monitoring and accurate prediction of the operating status of hydropower plant equipment has become an urgent problem to be solved in the field of hydropower plant equipment management. Summary of the Invention

[0006] The main objective of this invention is to provide an intelligent monitoring method for the operating status of hydropower plant equipment.

[0007] Another objective of this invention is to propose an intelligent monitoring system for the operating status of hydropower plant equipment.

[0008] The third objective of this invention is to provide a computer device.

[0009] A fourth objective of this invention is to provide a non-transitory computer-readable storage medium.

[0010] To achieve the above objectives, a first aspect of the present invention provides a method for intelligent monitoring of the operating status of hydropower plant equipment, comprising: The operation datasets of various equipment in the hydropower plant are collected and preprocessed to obtain preprocessed operation datasets; wherein, the operation datasets include temperature data, pressure data, vibration data, current data, and voltage data; The preprocessed running dataset is processed to obtain state reference values, and the preprocessed running dataset is classified based on the state reference values ​​to obtain device state classification results; The equipment status classification results are processed accordingly to obtain the status response decision results; The system displays normal prompts and analyzes operational data based on status response decisions, then displays the analysis results.

[0011] In one embodiment of the present invention, the data collection of operational data from various types of equipment in a hydropower plant includes: Temperature data is obtained by installing temperature sensors to collect temperature values ​​from key parts of the equipment. Pressure data is obtained by installing pressure sensors to collect pressure values ​​inside the equipment or related pipelines. Vibration data is obtained by installing vibration sensors to collect values ​​such as vibration frequency and amplitude during equipment operation; By installing current transformers and voltage transformers, the current and voltage values ​​of the equipment are collected respectively, and the current data and voltage data are obtained.

[0012] In one embodiment of the present invention, processing the preprocessed running dataset includes: By substituting into the calculation formula: The equipment operation reference values ​​are obtained, where T is the temperature data, P is the pressure data, V is the vibration data, I is the current data, U is the voltage data, and a1, a2, a3, a4, and a5 are the corresponding weighting factors. The preset comprehensive threshold range (Z1, Z2) for normal equipment operation is set. When the equipment operation reference value is greater than Z1 and less than Z2, the value is 1, indicating that the equipment operation status is basically normal; when the equipment operation reference value is less than Z1 or greater than Z2, the value is 2, indicating that the equipment operation status may be abnormal. Collect M sets of historical feature vectors as a sample set, and divide the sample set into a 70%M training set, a 15%M test set, and a 15%M validation set. The historical feature vectors include various parameter combinations of the device under different operating conditions. A state classification model is established based on the sample set. Historical feature vectors are obtained from the training set. Normal data cluster N1, warning data cluster N2 and fault data cluster N3 are preset. Three data points are randomly selected in the training set as the first cluster center, representing normal data cluster N1, warning data cluster N2 and fault data cluster N3 respectively. By substituting into the calculation formula: d=∑i=1n(xil-xi2)2, the distance between data items is obtained. The distance between the data items in the training set and the normal data cluster N1, the early warning data cluster N2, and the fault data cluster N3 is calculated respectively. The data items are then assigned to the nearest data cluster to obtain three new data clusters as the second cluster center, where xil and xi2 are the coordinate values ​​of the data points and n is the number of sub-data items. Calculate the mean of the three new data clusters in the second cluster center, and use them as the new first cluster center for recalculation; Repeat this process until the preset number of iterations is reached to obtain the device status classification model. Input the currently collected feature vector into the device state classification model, and output the state reference value.

[0013] In one embodiment of the present invention, classifying the preprocessed running dataset includes: The device status threshold range (F1, F2) is preset. When the status reference value is less than F1, a normal signal is generated. When the status reference value is greater than F1 and less than F2, a warning signal is generated. When the status reference value is greater than F2, a fault signal is generated. Normal signals contain a set of fields representing that the equipment is operating normally; warning signals contain a set of fields representing that the equipment may be operating abnormally and requires attention; and fault signals contain a set of fields representing that the equipment is operating severely abnormally and requires immediate action. Normal signals, warning signals, and fault signals are packaged to obtain equipment status classification results.

[0014] In one embodiment of the present invention, the corresponding processing of the device status classification results includes: When the equipment status classification result is a normal signal, a normal prompt message is sent to the monitoring terminal through the communication unit to remind the staff that the equipment is operating normally and can be inspected and maintained as usual. When the equipment status classification result is a warning signal, a warning text message is sent to the staff's receiving end through the communication unit. The warning text message includes an explanation that the equipment's operating status may be abnormal, requiring the staff to immediately check and evaluate the equipment's operating data set, and adjust the equipment or take corresponding preventive measures based on the inspection results, such as adjusting the equipment's operating parameters or checking the equipment's lubrication. When the equipment status classification result is a fault signal, a fault SMS is sent to the staff's receiving end through the communication unit. The fault SMS includes an explanation of the serious abnormality in the equipment's operating status, requiring the staff to immediately carry out maintenance, adopt emergency measures, and formulate a maintenance plan. Package normal prompts, warning text messages, and fault text messages to obtain status response decision results.

[0015] In one embodiment of the present invention, the analysis of operational data includes: Preset data standard threshold interval groups, substitute the running dataset into the corresponding data standard threshold intervals for comparison, and output the normal state, abnormal state or fault state. When all results in the running dataset are normal, output a normal status. When one or more results in the running dataset are abnormal and the rest are normal, output an abnormal status. When one or more results in the running dataset are faulty and the rest are normal or abnormal, output a faulty status. The analysis results are obtained by packaging the normal state, abnormal state, and fault state.

[0016] To achieve the above objectives, a second aspect of the present invention provides an intelligent monitoring system for the operating status of hydropower plant equipment, comprising: The data acquisition and preprocessing module is used to acquire operational datasets of various equipment in the hydropower plant and preprocess them to obtain preprocessed operational datasets; wherein, the operational datasets include temperature data, pressure data, vibration data, current data, and voltage data; The data processing and classification module is used to process the preprocessed running dataset to obtain a state reference value, and classify the preprocessed running dataset based on the state reference value to obtain a device state classification result. The data status decision module is used to process the equipment status classification results to obtain the status response decision results. The data analysis and display module is used to display normal prompts through the display terminal, and to analyze and display the analysis results based on the status response decision.

[0017] The intelligent monitoring method and device for the operating status of hydropower plant equipment according to the present invention can realize multi-parameter intelligent fusion assessment and classification of the operating status of hydropower plant equipment, improve the real-time performance and accuracy of monitoring, reduce the workload of manual analysis, and enhance the ability to predict and respond to faults.

[0018] To achieve the above objectives, a third aspect of this application provides a computer device, including a processor and a memory; wherein the processor reads executable program code stored in the memory to run a program corresponding to the executable program code, so as to implement the intelligent monitoring method for the operating status of hydropower plant equipment as described in the first aspect embodiment.

[0019] To achieve the above objectives, the fourth aspect of this application proposes a non-transitory computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the intelligent monitoring method for the operating status of hydropower plant equipment as described in the first aspect embodiment.

[0020] In summary, the beneficial effects of the present invention are as follows: This invention, through processing data sets of hydropower plant equipment operation, provides status reference values ​​that directly reflect the current operating status of the equipment, significantly reducing the enormous workload for staff involved in analyzing and calculating equipment operation data. Processing the equipment status classification results yields status-based decision-making results that assist staff in quickly implementing highly targeted countermeasures based on different equipment operating states, greatly reducing the risks associated with equipment failures. Analyzing the operation dataset provides results that help staff quickly screen individual equipment operation data, avoiding safety hazards caused by untimely responses to exceeding limits in a single piece of equipment operation data. Overall, this invention has significant advantages such as strong equipment operation data processing capabilities, high decision-making support, and timely feedback on equipment operation status monitoring. Attached Figure Description

[0021] The above and / or additional aspects and advantages of the present invention will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein: Figure 1 A flowchart of an intelligent monitoring method for the operating status of hydropower plant equipment provided in an embodiment of the present invention; Figure 2 This is a structural diagram of the intelligent monitoring system for the operating status of hydropower plant equipment provided in an embodiment of the present invention; Figure 3 The computer device provided in the embodiments of the present invention. Detailed Implementation

[0022] It should be noted that, unless otherwise specified, the embodiments and features described in the present invention can be combined with each other. The present invention will now be described in detail with reference to the accompanying drawings and embodiments.

[0023] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0024] The following description, with reference to the accompanying drawings, describes an intelligent monitoring method and system for the operating status of hydropower plant equipment according to an embodiment of the present invention.

[0025] This embodiment provides a method for intelligent monitoring of the operating status of hydropower plant equipment. For example... Figure 1 As shown, the method includes the following steps: S101, Collect the operation data sets of various equipment in the hydropower plant and preprocess them to obtain preprocessed operation data sets; wherein, the operation data sets include temperature data, pressure data, vibration data, current data, and voltage data; S102, the preprocessed running dataset is processed to obtain a state reference value, and the preprocessed running dataset is classified based on the state reference value to obtain a device state classification result; S103, Process the equipment status classification results accordingly to obtain the status response decision results; S104 displays normal prompts through the display terminal, and analyzes and displays the analysis results based on the status response decision.

[0026] In one embodiment of the present invention, step one involves collecting operational datasets of various equipment in the hydropower plant and preprocessing them. The operational datasets include temperature data, pressure data, vibration data, current data, and voltage data. The specific method for collecting the operational datasets of various equipment in the hydropower plant is as follows: Temperature data is obtained by installing temperature sensors to collect temperature values ​​from key components of the equipment; temperature data is also obtained by collecting temperature values ​​from key components such as the generator stator windings and bearings. For example, for large generators, excessively high stator winding temperatures may accelerate insulation aging and affect the generator's service life. Pressure data is obtained by installing pressure sensors to collect pressure values ​​inside the equipment or related pipelines; pressure data is also obtained by installing pressure sensors to collect pressure values ​​from parts such as the turbine casing and draft tube. Abnormal changes in internal turbine pressure may reflect instability in the water flow or damage to the internal structure of the equipment. Vibration data is obtained by installing vibration sensors to collect values ​​such as vibration frequency and amplitude during equipment operation; abnormal equipment vibration may be caused by rotor imbalance, bearing wear, etc. By installing current transformers and voltage transformers, the current and voltage values ​​of the equipment are collected respectively to obtain current data and voltage data; abnormal fluctuations in current and voltage may affect the normal operation of the equipment or even cause malfunctions.

[0027] In one embodiment of the present invention, the running dataset is processed to obtain state reference values, and then classified to obtain device state classification results; the specific method for processing the running dataset is as follows: S1. By substituting into the calculation formula: Ppost=a1T+a2P+a3V+a4I+a5U, the equipment operation reference value is obtained, where T is the temperature data, P is the pressure data, V is the vibration data, I is the current data, U is the voltage data, and a1, a2, a3, a4, and a5 are the corresponding weighting factors. S2. The preset comprehensive threshold range (Z1, Z2) for normal equipment operation. When the equipment operation reference value is greater than Z1 and less than Z2, the value is 1, indicating that the equipment operation status is basically normal; when the equipment operation reference value is less than Z1 or greater than Z2, the value is 2, indicating that the equipment operation status may be abnormal. S3. Collect M sets of historical feature vectors as a sample set, and divide the sample set into a 70%M training set, a 15%M test set, and a 15%M validation set. The historical feature vectors include various parameter combinations of the device under different operating conditions. S4. Establish a state classification model based on the sample set, obtain historical feature vectors in the training set, and pre-define normal data cluster N1, early warning data cluster N2, and fault data cluster N3. In the training set, randomly select three data points as the first cluster centers, representing normal data cluster N1, early warning data cluster N2, and fault data cluster N3, respectively. S5. By substituting into the calculation formula: d = ∑i=1n(xil-xi2)2, the distance between data items is obtained. The distance between the data items in the training set and the normal data cluster N1, the early warning data cluster N2, and the fault data cluster N3 is calculated respectively. The data items are assigned to the nearest data cluster, resulting in three new data cluster sets as the second cluster center, where xil and xi2 are the coordinate values ​​of the data points, and n is the number of sub-data items. S6. Calculate the mean of the three new data clusters in the second cluster center respectively, and use them as the new first cluster center for recalculation; S7. Repeat S5 and S6 until the preset number of iterations is reached to obtain the device status classification model; S8. Input the currently collected feature vector into the device status classification model and output the status reference value. Specifically, the specific method for classifying the running dataset is as follows: T1. Preset device status threshold range (F1, F2). When the status reference value is less than F1, a normal signal is generated. When the status reference value is greater than F1 and less than F2, a warning signal is generated. When the status reference value is greater than F2, a fault signal is generated. T2. Normal signals contain a set of fields representing that the equipment is operating normally; warning signals contain a set of fields representing that the equipment may be operating abnormally and needs attention; and fault signals contain a set of fields representing that the equipment is operating severely abnormally and needs to be dealt with immediately. T3. Pack normal signals, warning signals and fault signals to obtain equipment status classification results.

[0028] In one embodiment of the present invention, step three involves processing the equipment state classification results to obtain state response decision results; the specific method for processing the equipment state classification results is as follows: Q1. When the equipment status classification result is a normal signal, a normal prompt message is sent to the monitoring terminal through the communication unit to remind the staff that the equipment is operating normally and can be inspected and maintained as usual. Q2. When the equipment status classification result is a warning signal, a warning text message is sent to the staff's receiving end through the communication unit. The warning text message includes an explanation that the equipment operating status may be abnormal, requiring the staff to immediately check and evaluate the equipment's operating data set, and adjust the equipment or take corresponding preventive measures based on the inspection results, such as adjusting the equipment's operating parameters or checking the equipment's lubrication. Q3. When the equipment status classification result is a fault signal, a fault SMS message is sent to the staff's receiving end through the communication unit. The fault SMS message includes an explanation that the equipment's operating status is seriously abnormal, requiring the staff to immediately carry out maintenance, adopt emergency measures, and formulate a maintenance plan. Q4. Package normal prompts, warning text messages, and fault text messages to obtain status response decision results.

[0029] In one embodiment of the present invention, step four involves displaying normal prompt information via a display terminal, analyzing the running dataset, and obtaining and displaying the analysis results. The specific method for analyzing the running dataset is as follows: P1. Preset data standard threshold interval group. Substitute the running dataset into the corresponding data standard threshold interval for comparison and output the normal state, abnormal state or fault state. P2. When all results in the running dataset are normal, output a normal status. When one or more results in the running dataset are abnormal and the rest are normal, output an abnormal status. When one or more results in the running dataset are faulty and the rest are normal or abnormal, output a faulty status. P3. Pack the normal state, abnormal state, and fault state to obtain the analysis results.

[0030] In a specific embodiment, suppose that the operating status of a turbine in a hydropower plant is monitored, and the following set of operating data is collected, as shown in Table 1: Table 1

[0031] In one embodiment of the present invention, data acquisition and preprocessing are performed by installing temperature sensors, pressure sensors, vibration sensors, current transformers, and voltage transformers at key parts of the turbine to obtain the aforementioned operational data. Preprocessing is assumed to have been completed to ensure the accuracy and usability of the data.

[0032] Furthermore, calculate and categorize the equipment's operating reference values: 1. Assume weighting factors a1=0.2, a2=0.15, a3=0.3, a4=0.2, a5=0.15. Calculate the equipment operating reference value using the formula Ppost=alT+a2P+a3V+a4I+a5U: Ppost=0.2×45+0.15×3.2+0.3×5.0+0.2×120+0.15×10=9+0.48+1.5+24+1.5=36.48.

[0033] 2. The preset comprehensive threshold range for normal equipment operation is (Z1, Z2) = (20, 50). Since 20 < 36.48 < 50, the value is 1, indicating that the equipment is basically operating normally.

[0034] 3. Assume that M=100 sets of historical feature vectors have been collected and divided into training set (70 sets), test set (15 sets), and validation set (15 sets).

[0035] 4. Establish a state classification model based on the sample set: Pre-defined normal data cluster N1, early warning data cluster N2, and fault data cluster N3 are used. Three data points are randomly selected from the training set as the center of the first cluster.

[0036] The distance between the data items in the training set and the cluster centers is calculated according to the formula d=∑i=1n(xil-xi2)2, and the data items are assigned to the nearest cluster to obtain a new data cluster set as the second cluster center.

[0037] Calculate the mean of the new data cluster set at the second cluster center, and use it as the new first cluster center to calculate again. Repeat this process until the preset number of iterations is reached to obtain the device status classification model.

[0038] 5. Input the currently collected feature vector (45, 3.2, 5.0, 120, 10) into the device status classification model, and output the status reference value (assuming the output result is consistent with the previous calculation, which means it is basically normal).

[0039] 6. A preset equipment status threshold range (F1, F2) = (30, 40) is established. Since 30 < 36.48 < 40, a warning signal is generated. Normal signal fields include "Equipment is running smoothly, all parameters are normal," warning signal fields include "Some equipment parameters are approaching critical values, close monitoring is required," and fault signal fields include "Equipment parameters are severely out of control, immediate shutdown and maintenance are required." The resulting equipment status classification is then packaged into warning signals.

[0040] Furthermore, generate state-response decision results: Since the equipment status classification result is an early warning signal, an early warning text message is sent to the staff receiver via the communication unit: "The turbine's operating status may be abnormal; some equipment parameters are approaching critical values ​​and require close monitoring. Please immediately check and evaluate the equipment operation dataset, and adjust the equipment or take corresponding preventive measures based on the inspection results, such as checking the equipment lubrication and adjusting operating parameters." This early warning text message is packaged to obtain the status response decision.

[0041] Further, analyze the running dataset and display the results: 1. Preset data standard threshold range groups: Temperature data standard threshold range (30, 50)℃, 45℃ is within this range and is considered a normal result. Pressure data standard threshold range (2.5, 3.5)MPa, 3.2MPa is within this range and is considered a normal result.

[0042] The standard threshold range for vibration data is (2,6) mm / s. 5.0 mm / s is within this range and is considered a normal result.

[0043] The current data falls within the standard threshold range of (100, 150) A. 120 A is within this range and is considered a normal result.

[0044] The standard threshold range for voltage data is (9, 11) kV. 10 kV is within this range, which is considered a normal result.

[0045] 2. Since all operational data are normal, the output is in a normal state. The normal state is packaged and displayed as normal on the dashboard. The dashboard also displays a normal notification message (if any); however, this is a warning signal, so no normal notification message is displayed.

[0046] The method described in this invention enables intelligent multi-parameter fusion assessment and classification of the operating status of hydropower plant equipment, improving the real-time performance and accuracy of monitoring, reducing the workload of manual analysis, and enhancing fault early warning and response decision-making capabilities. By processing the hydropower plant equipment operating dataset, the obtained status reference values ​​can directly reflect the current operating status of the equipment, significantly reducing the enormous workload of staff in analyzing and calculating equipment operating data.

[0047] This invention also provides an intelligent monitoring system 10 for the operating status of hydropower plant equipment, such as... Figure 2 As shown, the system 10 includes: The data acquisition and preprocessing module 100 is used to acquire the operation dataset of various equipment in the hydropower plant and preprocess it to obtain a preprocessed operation dataset; wherein, the operation dataset includes temperature data, pressure data, vibration data, current data, and voltage data; The data processing and classification module 200 is used to process the preprocessed running dataset to obtain a state reference value, and classify the preprocessed running dataset based on the state reference value to obtain a device state classification result; The data status decision module 300 is used to process the equipment status classification results to obtain the status response decision results. The data analysis and display module 400 is used to display normal prompt information through the display terminal, and to analyze and display the analysis results based on the status response decision results of the running data.

[0048] The intelligent monitoring system for the operating status of hydropower plant equipment in this embodiment of the invention can realize multi-parameter intelligent fusion assessment and classification of the operating status of hydropower plant equipment, improve the real-time performance and accuracy of monitoring, reduce the workload of manual analysis, and enhance the ability to predict and respond to faults.

[0049] To implement the methods of the above embodiments, the present invention also provides a computer device, such as... Figure 3 As shown, the computer device 600 includes a memory 601 and a processor 602; wherein, the processor 602 reads executable program code stored in the memory 601 to run a program corresponding to the executable program code, so as to implement the various steps of the method described above.

[0050] To implement the above embodiments, this application also proposes a non-transitory computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the method described in the foregoing embodiments.

[0051] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

[0052] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0053] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this invention, "a plurality of" means at least two, such as two, three, etc., unless otherwise explicitly specified.

Claims

1. A method for intelligent monitoring of the operating status of hydropower plant equipment, characterized in that, Specifically, it includes the following: The operation datasets of various equipment in the hydropower plant are collected and preprocessed to obtain preprocessed operation datasets; wherein, the operation datasets include temperature data, pressure data, vibration data, current data, and voltage data; The preprocessed running dataset is processed to obtain state reference values, and the preprocessed running dataset is classified based on the state reference values ​​to obtain device state classification results; The equipment status classification results are processed accordingly to obtain the status response decision results; The system displays normal prompts and analyzes operational data based on status response decisions, then displays the analysis results.

2. The intelligent monitoring method for the operating status of hydropower plant equipment according to claim 1, characterized in that, Collect operational datasets for various equipment in the hydropower plant, including: Temperature data is obtained by installing temperature sensors to collect temperature values ​​from key parts of the equipment. Pressure data is obtained by installing pressure sensors to collect pressure values ​​inside the equipment or related pipelines. Vibration data is obtained by installing vibration sensors to collect values ​​such as vibration frequency and amplitude during equipment operation; By installing current transformers and voltage transformers, the current and voltage values ​​of the equipment are collected respectively, and the current data and voltage data are obtained.

3. The intelligent monitoring method for the operating status of hydropower plant equipment according to claim 1, characterized in that, The preprocessed run dataset is processed, including: By substituting into the calculation formula: The equipment operation reference values ​​are obtained, where T is the temperature data, P is the pressure data, V is the vibration data, I is the current data, U is the voltage data, and a1, a2, a3, a4, and a5 are the corresponding weighting factors. The preset comprehensive threshold range (Z1, Z2) for normal equipment operation is set. When the equipment operation reference value is greater than Z1 and less than Z2, the value is 1, indicating that the equipment operation status is basically normal; when the equipment operation reference value is less than Z1 or greater than Z2, the value is 2, indicating that the equipment operation status may be abnormal. Collect M sets of historical feature vectors as a sample set, and divide the sample set into a 70%M training set, a 15%M test set, and a 15%M validation set. The historical feature vectors include various parameter combinations of the device under different operating conditions. A state classification model is established based on the sample set. Historical feature vectors are obtained from the training set. Normal data cluster N1, warning data cluster N2 and fault data cluster N3 are preset. Three data points are randomly selected in the training set as the first cluster center, representing normal data cluster N1, warning data cluster N2 and fault data cluster N3 respectively. By substituting into the calculation formula: d=∑i=1n(xil-xi2)2, the distance between data items is obtained. The distance between the data items in the training set and the normal data cluster N1, the early warning data cluster N2, and the fault data cluster N3 is calculated respectively. The data items are then assigned to the nearest data cluster to obtain three new data clusters as the second cluster center, where xil and xi2 are the coordinate values ​​of the data points and n is the number of sub-data items. Calculate the mean of the three new data clusters in the second cluster center, and use them as the new first cluster center for recalculation; Repeat this process until the preset number of iterations is reached to obtain the device status classification model. Input the currently collected feature vector into the device state classification model, and output the state reference value.

4. The intelligent monitoring method for the operating status of hydropower plant equipment according to claim 1, characterized in that, The preprocessed run datasets are categorized as follows: The device status threshold range (F1, F2) is preset. When the status reference value is less than F1, a normal signal is generated. When the status reference value is greater than F1 and less than F2, a warning signal is generated. When the status reference value is greater than F2, a fault signal is generated. Normal signals contain a set of fields representing that the equipment is operating normally; warning signals contain a set of fields representing that the equipment may be operating abnormally and requires attention; and fault signals contain a set of fields representing that the equipment is operating severely abnormally and requires immediate action. Normal signals, warning signals, and fault signals are packaged to obtain equipment status classification results.

5. The intelligent monitoring method for the operating status of hydropower plant equipment according to claim 1, characterized in that, The corresponding processing of equipment status classification results includes: When the equipment status classification result is a normal signal, a normal prompt message is sent to the monitoring terminal through the communication unit to remind the staff that the equipment is operating normally and can be inspected and maintained as usual. When the equipment status classification result is a warning signal, a warning text message is sent to the staff's receiving end through the communication unit. The warning text message includes an explanation that the equipment's operating status may be abnormal, requiring the staff to immediately check and evaluate the equipment's operating data set, and adjust the equipment or take corresponding preventive measures based on the inspection results, such as adjusting the equipment's operating parameters or checking the equipment's lubrication. When the equipment status classification result is a fault signal, a fault SMS is sent to the staff's receiving end through the communication unit. The fault SMS includes an explanation of the serious abnormality in the equipment's operating status, requiring the staff to immediately carry out maintenance, adopt emergency measures, and formulate a maintenance plan. Package normal prompts, warning text messages, and fault text messages to obtain status response decision results.

6. The intelligent monitoring method for the operating status of hydropower plant equipment according to claim 1, characterized in that, Analyze the operational data, including: Preset data standard threshold interval groups, substitute the running dataset into the corresponding data standard threshold intervals for comparison, and output the normal state, abnormal state or fault state. When all results in the running dataset are normal, output a normal status. When one or more results in the running dataset are abnormal and the rest are normal, output an abnormal status. When one or more results in the running dataset are faulty and the rest are normal or abnormal, output a faulty status. The analysis results are obtained by packaging the normal state, abnormal state, and fault state.

7. An intelligent monitoring system for the operating status of hydropower plant equipment, characterized in that, Specifically, it includes: The data acquisition and preprocessing module is used to acquire operational datasets of various equipment in the hydropower plant and preprocess them to obtain preprocessed operational datasets; wherein, the operational datasets include temperature data, pressure data, vibration data, current data, and voltage data; The data processing and classification module is used to process the preprocessed running dataset to obtain a state reference value, and classify the preprocessed running dataset based on the state reference value to obtain a device state classification result. The data status decision module is used to process the equipment status classification results to obtain the status response decision results. The data analysis and display module is used to display normal prompts through the display terminal, and to analyze and display the analysis results based on the status response decision.

8. A computer device, characterized in that, Including processor and memory; The processor reads the executable program code stored in the memory to run the program corresponding to the executable program code, so as to implement the intelligent monitoring and analysis method for the cylinder valve operating status as described in any one of claims 1-6.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by the processor, the program implements the intelligent monitoring and analysis method for the operating status of cylinder valves as described in any one of claims 1-6.

Images