A method and system for early warning of faults in the hydraulic system of a hydropower station governor

Abstract

This invention discloses a method and system for early warning of faults in the hydraulic pressure device of a hydropower station governor, relating to the field of hydropower station technology. The method includes: collecting data from various units using a data acquisition module; preprocessing the collected data using a data analysis module; obtaining predicted data from the preprocessed data through feature engineering and verifying the predicted data; and determining the operating status of the governor hydraulic pressure device based on the verification results. This method for early warning of faults in the hydraulic pressure device of a hydropower station governor introduces artificial intelligence technology into the field of governor hydraulic pressure device status monitoring. It utilizes an intelligent monitoring system to establish an online technical supervision index system for generator equipment, enabling real-time monitoring of relevant operating parameters of various components of the governor hydraulic pressure device. This allows for early prediction of the possibility of accidents, and ensures that operating personnel receive relevant early warning information before accidents occur, thus minimizing unplanned shutdowns of hydropower station units.

Description

Technical Field

[0001] This invention relates to the field of hydropower station technology, and in particular to a method and system for early warning of faults in the hydraulic device of a hydropower station governor. Background Technology

[0002] Currently, power generation companies urgently need to optimize production and combine it with scientific and efficient management methods to meet the requirements of safe and stable power production. To achieve this, it is necessary to ensure the normal operation of equipment, improve production efficiency, and reduce unnecessary equipment maintenance time. Therefore, it is imperative to use reliable equipment monitoring methods to improve the control of equipment operating status, strengthen the planning and targeting of equipment maintenance, and adopt a predictive maintenance management model.

[0003] Traditionally, equipment management has focused on preventative, predictive planned maintenance. However, with rapid industrial development, equipment maintenance management has gradually evolved towards condition-based maintenance. The essence of condition-based maintenance is to use advanced technologies to collect and analyze current and historical equipment data, making preliminary judgments to determine whether appropriate shutdowns for maintenance are necessary. Safely and effectively monitoring power equipment in real time and accurately obtaining fault information is crucial for the production and construction of power equipment.

[0004] Unplanned shutdowns of generating units can cause losses to the safe production and operational performance of hydropower stations. Unplanned shutdowns of large-capacity units may even affect the safe and stable operation of the power grid. Hydropower station generating units may experience unplanned shutdowns due to low oil pressure caused by governor hydraulic system malfunctions. To minimize the risk of such accidents causing unplanned shutdowns, it is crucial to detect potential problems as early as possible, and operating personnel should receive relevant information before such accidents occur, allowing more time for subsequent on-site handling.

[0005] For hydropower stations with "unmanned operation and minimal staffing," in order to avoid the aforementioned unplanned shutdowns of the hydropower station units as much as possible, the possibility of such accidents should be predicted as early as possible, and the operation and duty personnel should be able to receive relevant early warning information before such accidents occur.

[0006] Introducing artificial intelligence technology into the field of condition monitoring, and utilizing intelligent monitoring systems to establish an online technical supervision index system for generator sets, allows for real-time early warning of relevant equipment operating parameters. This system architecture explores technologies such as information collection, network transmission, and data processing to construct a closed-loop system encompassing perception, transmission, analysis, decision-making, and execution. This achieves the integration of physical and information technologies, enhancing the system's global reach, intelligence, and user-friendliness, thereby realizing the goal of real-time early warning for power equipment. This is also one of the future trends in the development of "smart power." Summary of the Invention

[0007] The purpose of this section is to summarize some aspects of the embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the abstract and title of this application to avoid obscuring the purpose of this section, the abstract and the title of the invention, and such simplifications or omissions should not be used to limit the scope of the present invention.

[0008] In view of the problems existing in the above and / or existing methods for early warning of faults in the hydraulic device of a hydropower station governor, the present invention is proposed.

[0009] Therefore, the problem to be solved by this invention is the problem of unplanned shutdown of hydropower station units due to low oil pressure caused by a fault in the governor oil pressure device.

[0010] To solve the above-mentioned technical problems, the present invention provides the following technical solution: a method for early warning of faults in the hydraulic pressure device of a hydropower station governor, comprising: collecting data from each unit using a data acquisition module; preprocessing the collected data using a data analysis module; obtaining predicted data from the preprocessed data through feature engineering, and verifying the predicted data; and determining the operating status of the hydraulic pressure device of the governor based on the verification results.

[0011] As a preferred embodiment of the fault early warning method for the hydropower station governor hydraulic device according to the present invention, the data of each unit includes a pressure tank pressure data acquisition unit, a pressure tank oil level data acquisition unit, a leak tank oil level data acquisition unit, and a return tank oil level data acquisition unit; the pressure tank pressure data acquisition unit is used to acquire the pressure data of the pressure tank in the hydropower generator governor hydraulic device; the pressure tank oil level data acquisition unit is used to acquire the oil level data of the pressure tank in the governor hydraulic device; the leak tank oil level data acquisition unit is used to acquire the oil level data of the leak tank in the governor hydraulic device; and the return tank oil level data acquisition unit is used to acquire the oil level data of the return tank in the governor hydraulic device.

[0012] As a preferred embodiment of the fault early warning method for the hydraulic device of the governor of a hydropower station according to the present invention, the preprocessing includes processing the collected pressure data of the pressure tank, the oil level data of the pressure tank, the oil level data of the leak tank and the oil level data of the return tank through piecewise linear interpolation to obtain preprocessed data. The data length of the preprocessed data is set, and the training dataset, the validation dataset and the test dataset are divided according to a time range length of 2:1:1.

[0013] As a preferred embodiment of the fault early warning method for the hydraulic device of a hydropower station governor according to the present invention, the predicted data includes: preprocessed data from the previous time period is used to predict the next predicted data through feature engineering; in the feature engineering, the data analysis module sets each collected preprocessed data into a window, performs rolling statistics on the window, and uses the summarized predicted data calculated from the values ​​in the rolling window as features in the subsequent predicted data; the feature engineering is expressed as:

[0014] feature_i=(x(i)×a i-i+1 +x(i-1)×a i-(i-1)+1 +...+x(i-n+1)×a i-(i-n+1)+1 ) / (a i-i+1 +a i-(i-1)+1 ...a i-(i-n+1)+1 )

[0015] Where feature_i is the predicted data at the i-th time point, x(i) is the preprocessed data at the i-th time point, i is the time point, n≤i≤m, a is the decay coefficient, data at earlier time points decay at an exponential rate, a is between 0 and 1, controlling the decay rate of data over time, a larger a value indicates faster decay; the verification of the predicted data includes verifying the predicted data using the Mann-Kendall trend test method, and sending the verification result data to the intelligent fault early warning module.

[0016] As a preferred embodiment of the fault early warning method for the hydraulic pressure device of a hydropower station governor according to the present invention, the method for determining the operating status of the hydraulic pressure device includes comparing the test result data with the normal operating status of the hydraulic pressure device. If the data changes are consistent with those during normal operation, the hydraulic pressure device is determined to be in normal operation. If the data changes are inconsistent with those during normal operation, the hydraulic pressure device is determined to be in abnormal operation, and a device fault early warning message is issued. The normal operating status includes the following: the oil pump starts at a set value of 5.8 MPa, and according to the normal operating data trend, the oil pump stops after 3 minutes, and the oil pressure of the hydraulic pressure device rises to the pump stop pressure of 6.3 MPa.

[0017] As a preferred embodiment of the fault early warning method for the hydropower station governor hydraulic device described in this invention, the normal operating state includes: when the oil pump of the governor hydraulic device is running, the oil in the return oil tank of the governor hydraulic device is drawn to the pressure oil tank of the governor hydraulic device, the oil level in the return oil tank of the governor hydraulic device drops, the oil level and pressure in the pressure oil tank of the governor hydraulic device rise, and the oil level in the leakage tank of the governor hydraulic device remains unchanged; when the automatic air replenishment valve of the governor hydraulic device is fully open, air is replenished to the pressure oil tank of the governor hydraulic device, the oil level in the pressure oil tank of the governor hydraulic device remains unchanged and the pressure rises, and the return oil level of the governor hydraulic device... When the oil level in the oil tank and the oil level in the leak tank of the governor hydraulic device remains unchanged, the oil in the pressure tank of the governor hydraulic device is discharged to the return tank of the governor hydraulic device, the oil level and pressure in the pressure tank of the governor hydraulic device decrease, the oil level in the return tank of the governor hydraulic device rises, and the oil level in the leak tank of the governor hydraulic device rises slightly. When the oil pump of the governor hydraulic device is running, the oil in the leak tank of the governor hydraulic device is pumped to the return tank of the governor hydraulic device, the oil level in the leak tank of the governor hydraulic device decreases, the oil level in the return tank of the governor hydraulic device rises, and the oil level and pressure in the pressure tank of the governor hydraulic device remain unchanged.

[0018] As a preferred embodiment of the fault early warning method for the hydropower station governor hydraulic device according to the present invention, the abnormal operating states include: when the governor hydraulic device's oil pump is running, the oil level in the governor hydraulic device's return oil tank remains unchanged, and the oil level and pressure in the governor hydraulic device's pressure oil tank remain unchanged, issuing a fault early warning message indicating blockage or leakage in the return oil pipeline; when the governor hydraulic device's oil pump is running, the oil level in the governor hydraulic device's return oil tank remains unchanged, but the oil level and pressure in the governor hydraulic device's pressure oil tank decrease, issuing a fault early warning message regarding the sealing of the pressure oil tank's oil supply pipeline and pump body; when the governor hydraulic device's oil pump is running, the oil level in the governor hydraulic device's return oil tank decreases, and the oil level and pressure in the governor hydraulic device's pressure oil tank decrease... If the pressure remains constant, a fault warning message is issued indicating a problem with the return oil line, return oil filter, or leakage. If the governor's hydraulic pump is running and the return oil level in the governor's hydraulic tank drops, or the pressure and level in the governor's hydraulic tank drop, a fault warning message is issued for the entire governor's hydraulic system. If the governor's leak pump is running and the leak tank level remains constant, or the return oil level remains constant, a fault warning message is issued regarding the leak pump's connection and sealing. If the governor's leak pump is running and the leak tank level drops, or the return oil level remains constant, a fault warning message is issued regarding a leaking oil line, connection, or leakage.

[0019] Another objective of this invention is to provide a system for a fault early warning method for the hydraulic device of a hydropower station governor, which can fully mobilize the fault early warning capability by constructing an early warning system.

[0020] To solve the above-mentioned technical problems, the present invention provides the following technical solution: a fault early warning system for a hydropower station governor hydraulic device, comprising a data acquisition module, a data analysis module, and an intelligent fault early warning module; the data acquisition module is used to collect operating data of various components within the governor hydraulic device; the data analysis module is used to preprocess the operating data of each component, and to predict the predicted data based on the preprocessed data, and then to perform data trend verification on the predicted data to obtain verification result data; the intelligent fault early warning module is used to determine whether the operating status of the governor hydraulic device is normal based on the verification result data obtained after data trend verification, and to issue a device fault early warning information when the governor hydraulic device is in an abnormal state.

[0021] A computer device includes a memory and a processor, the memory storing a computer program, characterized in that the processor executes the computer program to implement the steps of the above-described method for early warning of faults in the hydraulic pressure device of a hydropower station governor.

[0022] A computer-readable storage medium having a computer program stored thereon, characterized in that, when the computer program is executed by a processor, it implements the steps of the above-described method for early warning of faults in the hydraulic pressure device of a hydropower station governor.

[0023] The beneficial effects of this invention are as follows: The fault early warning method for the hydraulic governor device of a hydropower station provided by this invention introduces artificial intelligence technology into the field of condition monitoring of the hydraulic governor device. By using an intelligent monitoring system to establish an online technical supervision index system for generator equipment, it is possible to monitor the relevant operating parameters of each component of the hydraulic governor device in real time, predict the possibility of accidents in advance, and ensure that the operating personnel can receive relevant early warning information before the accident occurs, thereby avoiding unplanned shutdowns of hydropower station units as much as possible. Attached Figure Description

[0024] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. Wherein:

[0025] Figure 1 The above is an overall flowchart of a fault early warning method for a hydropower station governor hydraulic device provided in one embodiment of the present invention.

[0026] Figure 2 This is a trend diagram of the normal operation status of a fault early warning method for a hydropower station governor hydraulic device provided in the first embodiment of the present invention.

[0027] Figure 3 The diagram shows a structural diagram of a fault early warning system for a hydropower station governor hydraulic device, provided in the second embodiment of the present invention. Detailed Implementation

[0028] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0029] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0030] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that is mutually exclusive with other embodiments.

[0031] Example 1

[0032] Reference Figure 1 and Figure 2 The first embodiment of the present invention provides a method for early warning of faults in the hydraulic pressure device of a hydropower station governor, comprising: collecting data from each unit using a data acquisition module; preprocessing the collected data using a data analysis module; obtaining predicted data from the preprocessed data through feature engineering and verifying the predicted data; and determining the operating status of the hydraulic pressure device of the governor based on the verification results.

[0033] Furthermore, by introducing artificial intelligence technology into the field of governor hydraulic device status monitoring, and using an intelligent monitoring system to establish an online technical supervision index system for generator equipment, it is possible to monitor the relevant operating parameters of each component of the governor hydraulic device in real time, predict the possibility of accidents in advance, and ensure that the operating personnel can receive relevant early warning information before the accident occurs, thereby avoiding unplanned shutdowns of hydropower station units as much as possible.

[0034] The data acquisition module includes: a pressure tank pressure data acquisition unit, which is used to collect pressure data from the pressure tank in the hydraulic device of the hydro-generator speed governor, and send the obtained pressure data from the pressure tank to the data analysis module.

[0035] The oil level data acquisition unit for the pressure tank is used to collect the oil level data of the pressure tank in the governor's hydraulic device and send the obtained oil level data of the pressure tank to the data analysis module.

[0036] The oil level data acquisition unit for the oil leak tank is used to collect the oil level data of the oil leak tank in the governor hydraulic device and send the obtained oil level data of the oil leak tank to the data analysis module.

[0037] The return oil tank level data acquisition unit is used to collect the oil level data of the return oil tank in the governor hydraulic device and send the obtained return oil tank level data to the data analysis module.

[0038] Furthermore, the working principle of the governor hydraulic device is as follows: when the opening of the unit's guide vanes changes, the pressure oil tank provides hydraulic power to the unit's guide vanes. Most of the oil in the pressure oil tank is discharged to the return oil tank, and a small amount is discharged to the leakage oil tank. When the pressure in the pressure oil tank drops to 5.8 MPa, the hydraulic device's oil pump operates, drawing oil from the return oil tank to the pressure oil tank. When the pressure in the pressure oil tank reaches 6.3 MPa, the oil pump stops operating. When the pressure in the pressure oil tank drops to 6.1 MPa and the oil level in the pressure oil tank reaches 950 mm (AND relationship), the automatic air replenishment valve fully opens to replenish air to the pressure oil tank. After replenishing air to 6.3 MPa, the automatic air replenishment valve fully closes, stopping air replenishment. When the oil level in the leakage oil tank reaches 450 mm, the leakage oil pump operates, drawing oil from the leakage oil tank to the return oil tank. When the oil level in the leakage oil tank drops to 200 mm, the leakage oil pump stops operating.

[0039] like Figure 2 As shown, the oil pump starts at a set value of 5.8 MPa. Based on the normal operating data trend, it is predicted that the oil pump should stop after 3 minutes and the oil pressure of the hydraulic device should rise to the stop oil pressure of 6.3 MPa. However, the oil pump has been running for more than 3 minutes without stopping, and the oil pressure of the hydraulic device has not reached the predicted trend value of 6.3 MPa. Therefore, it is considered that the hydraulic device is in an abnormal operating state. It may be that the hydraulic device is leaking oil, or the oil pump is running dry or the oil pump efficiency is reduced.

[0040] The data analysis module processes the collected pressure data, oil level data, leakage tank oil level data, and return tank oil level data of the pressure tank using piecewise linear interpolation to obtain preprocessed data.

[0041] Since the start-stop accuracy of the oil pump is in seconds, while the relevant parameter data of the governor oil pressure device currently have two accuracy levels: 5 seconds and 30 seconds, due to the inconsistency in accuracy, in order to reduce the error in subsequent judgment, the data needs to be interpolated. Based on the characteristics of the data and the requirements for real-time calculation, this paper selects the piecewise linear interpolation method with small computational load and small interpolation error to align the data accuracy to seconds, which can improve the time accuracy.

[0042] The data analysis module also sets the data length of the preprocessed data, dividing the training dataset, validation dataset, and test dataset according to a 2:1:1 time range length.

[0043] The data analysis module also uses feature engineering to predict the next forecast data based on the preprocessed data from the previous time period.

[0044] Feature engineering is represented as:

[0045] feature_i=(x(i)×a i-i+1 +x(i-1)×a i-(i-1)+1 +...+x(i-n+1)×a i-(i-n+1)+1 ) / (a i-i+1 +a i-(i-1)+1 ...a i-(i-n+1)+1 )

[0046] Where feature_i is the predicted data at time point i, x(i) is the preprocessed data at time point i, i is the time point, n is the number of windows, and a is the decay coefficient. Data at earlier time points decay at an exponential rate. a is between 0 and 1 and controls the decay rate of data over time. A larger a value indicates faster decay.

[0047] The data analysis module also performs the Mann-Kendall trend test on the predicted data and sends the test results to the intelligent fault early warning module.

[0048] The Mann-Kendall trend test was used for this data trend test. This method is suitable for analyzing time series data with a continuous upward or downward trend. It does not require the data to meet the assumption of a specific distribution and is not affected by outliers, thus avoiding errors caused by abnormal data in the measurement data.

[0049] The intelligent fault early warning module compares the data of the governor hydraulic device under normal and abnormal operating conditions based on the inspection results. When the data changes are consistent with the data under normal operating conditions, it is determined that the governor hydraulic device is under normal operating conditions. When the data changes are inconsistent with the data under normal operating conditions, it is determined that the governor hydraulic device is under abnormal operating conditions, and a device fault early warning message is issued.

[0050] Furthermore, for hydropower stations with "unmanned operation and minimal staffing," the generating units may experience unplanned shutdowns due to low oil pressure caused by a fault in the governor's hydraulic system. To minimize the risk of such unplanned shutdowns, an intelligent fault early warning module can detect potential accidents early, and the on-duty personnel should be able to receive relevant information before the accident occurs, thus allowing more time for subsequent on-site handling.

[0051] When the governor hydraulic system is in normal operation, the operating states of each component are as follows: When the oil pump of the governor hydraulic system is running, it draws oil from the return oil tank to the pressure oil tank, causing the oil level in the return oil tank to drop, while the oil level and pressure in the pressure oil tank rise, and the oil level in the leakage tank remains unchanged. When the automatic air supply valve of the governor hydraulic system is fully open, it supplies air to the pressure oil tank, causing the oil level in the pressure oil tank to remain unchanged and the pressure to rise, while the oil levels in the return oil tank and the leakage tank remain unchanged. When the guide vane opening changes, it discharges oil from the pressure oil tank to the return oil tank, causing the oil level and pressure in the pressure oil tank to drop, the oil level in the return oil tank to rise, and the oil level in the leakage tank to rise slightly. When the oil leakage pump of the governor hydraulic device is running, it draws oil from the leakage tank of the governor hydraulic device to the return tank of the governor hydraulic device. The oil level in the leakage tank of the governor hydraulic device drops, the oil level in the return tank of the governor hydraulic device rises, and the oil level and pressure in the pressure tank of the governor hydraulic device remain unchanged.

[0052] When the governor hydraulic system is in an abnormal operating state, the operating status of each component is as follows: When the governor hydraulic pump is running, the oil level in the return oil tank remains unchanged, and the oil level and pressure in the pressure oil tank remain unchanged, issuing a fault warning message for blockage or leakage in the return oil pipeline; When the governor hydraulic pump is running, the oil level in the return oil tank remains unchanged, but the oil level and pressure in the pressure oil tank decrease, issuing a fault warning message for the oil supply pipeline and pump body sealing in the pressure oil tank; When the governor hydraulic pump is running, the oil level in the return oil tank decreases, but the oil level and pressure in the pressure oil tank remain unchanged, issuing a fault warning message for the return oil pipeline. 1. Fault warning information for return oil filter or leakage; 2. When the oil pump of the governor hydraulic device is running, if the oil level in the return oil tank of the governor hydraulic device drops, and the oil level and pressure in the pressure oil tank of the governor hydraulic device drop, a fault warning information for the entire governor hydraulic device will be issued; 3. When the leaking pump of the governor hydraulic device is running, if the oil level in the leaking oil tank of the governor hydraulic device remains unchanged, and the oil level in the return oil tank of the governor hydraulic device remains unchanged, a fault warning information for the connection and sealing of the leaking pump will be issued; 4. When the leaking pump of the governor hydraulic device is running, if the oil level in the leaking oil tank of the governor hydraulic device drops, and the oil level in the return oil tank of the governor hydraulic device remains unchanged, a fault warning information for leaking pipelines, connections, or leakage will be issued.

[0053] In feature engineering, the data analysis module sets each collected preprocessed data into a window and performs scrolling statistics on the window. The predicted data, which is the sum of the values ​​in the scrolling window, is included as a feature in the subsequent predicted data.

[0054] The selected data includes: the mean, variance, maximum, minimum, skewness, and kurtosis of the pressure in the governor hydraulic pressure device's pressure tank, the oil level in the pressure tank, the oil level in the leak tank, and the oil level in the return tank.

[0055] Example 2

[0056] Reference Figure 3 This is the second embodiment of the present invention, which differs from the previous embodiment in that it provides a fault early warning system for the hydraulic device of a hydropower station governor, including: a data acquisition module, a data analysis module and an intelligent fault early warning module.

[0057] The data acquisition module is used to collect operating data of various components within the governor's hydraulic system.

[0058] The data analysis module is used to preprocess the operating data of each component, make predictions based on the preprocessed data, and then perform data trend verification on the prediction data to obtain the verification results.

[0059] The intelligent fault early warning module is used to determine whether the operating status of the governor hydraulic device is normal based on the test results obtained after data trend verification. When the governor hydraulic device is in an abnormal state, it issues a device fault early warning message.

[0060] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0061] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0062] More specific examples of computer-readable media (a non-exhaustive list) include: electrical connections (electronic devices) having one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0063] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0064] Example 3

[0065] The third embodiment of the present invention differs from the first two embodiments in that it is used to verify and explain the technical effects adopted in the present invention, so as to verify the real effect of the method.

[0066] Currently, power generation companies urgently need to optimize production and combine it with scientific and efficient management methods to meet the requirements of safe and stable power production. To achieve this, it is necessary to ensure the normal operation of equipment, improve production efficiency, and reduce unnecessary equipment maintenance time. Therefore, it is imperative to use reliable equipment monitoring methods to improve the control of equipment operating status, strengthen the planning and targeting of equipment maintenance, and adopt a predictive maintenance management model.

[0067] Traditionally, equipment management has focused on preventative, predictive planned maintenance. However, with rapid industrial development, equipment maintenance management has gradually evolved towards condition-based maintenance. The essence of condition-based maintenance is to use advanced technologies to collect and analyze current and historical equipment data, making preliminary judgments to determine whether appropriate shutdowns for maintenance are necessary. Safely and effectively monitoring power equipment in real time and accurately obtaining fault information is crucial for the production and construction of power equipment.

[0068] Unplanned shutdowns of generating units can cause losses to the safe production and operational performance of hydropower stations. Unplanned shutdowns of large-capacity units may even affect the safe and stable operation of the power grid. Hydropower station generating units may experience unplanned shutdowns due to low oil pressure caused by governor hydraulic system malfunctions. To minimize the risk of such accidents causing unplanned shutdowns, it is crucial to detect potential problems as early as possible, and operating personnel should receive relevant information before such accidents occur, allowing more time for subsequent on-site handling.

[0069] Introducing artificial intelligence technology into the field of condition monitoring, and utilizing intelligent monitoring systems to establish an online technical supervision index system for generator sets, allows for real-time early warning of relevant equipment operating parameters. This system architecture explores technologies such as information collection, network transmission, and data processing to construct a closed-loop system encompassing perception, transmission, analysis, decision-making, and execution. This achieves the integration of physical and information technologies, enhancing the system's global reach, intelligence, and user-friendliness, thereby realizing the goal of real-time early warning for power equipment. This is also one of the future trends in the development of "smart power."

[0070] This embodiment utilizes both conventional methods and our invented method to simultaneously detect hydraulic device faults. The comparison results are shown in the table below:

[0071] Table 1 Comparison between traditional methods and our inventive methods

[0072] Determine the category Traditional methods Our invention method Time required to monitor faults 15min 20s Accuracy of accident prediction 81％ 92％ cost high Low

[0073] The above comparison results show that the time required for fault monitoring by our invention is 20 seconds, which is 880 seconds less than the 15 minutes of the traditional method. The accuracy of accident prediction by our invention is 92%, which is 11% higher than the 81% of the traditional method. The cost of our invention is much lower than that of the traditional method.

[0074] Our invention introduces artificial intelligence technology into the field of governor hydraulic device status monitoring. By using an intelligent monitoring system to establish an online technical supervision index system for generator set equipment, it can monitor the relevant operating parameters of each component of the governor hydraulic device in real time, predict the possibility of accidents in advance, and ensure that the operation and duty personnel can receive relevant early warning information before the accident occurs, thus avoiding unplanned shutdowns of hydropower station units as much as possible.

[0075] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A method for early warning of faults in the hydraulic system of a hydropower station governor, characterized in that: include, Data from each unit is collected using the data acquisition module; The collected data is preprocessed using the data analysis module; Preprocessed data is used to obtain predicted data through feature engineering, and the predicted data is then validated. Determine the operating status of the governor's hydraulic device based on the test results data; The data acquisition module includes a pressure tank pressure data acquisition unit, a pressure tank oil level data acquisition unit, an oil leakage tank oil level data acquisition unit, and an oil return tank oil level data acquisition unit. The oil pressure data acquisition unit is used to collect pressure data from the oil pressure tank in the hydraulic device of the governor of the hydro-generator set. The oil level data acquisition unit for the pressure tank is used to acquire the oil level data of the pressure tank in the governor's hydraulic device; The oil level data acquisition unit for the leaking tank is used to acquire the oil level data of the leaking tank in the governor hydraulic device. The oil level data acquisition unit for the return oil tank is used to acquire the oil level data of the return oil tank in the governor hydraulic device. The preprocessing includes processing the collected pressure data of the pressure tank, oil level data of the pressure tank, oil level data of the leak tank and oil level data of the return tank using piecewise linear interpolation to obtain preprocessed data. The data length of the preprocessed data is set, and the training dataset, validation dataset and test dataset are divided according to a time range length of 2:1:

1. The predicted data includes the predicted data for the next time obtained by using feature engineering to predict the preprocessed data from the previous time period. In feature engineering, the data analysis module sets each collected preprocessed data as a window, performs scrolling statistics on the window, and uses the summary statistics of the values ​​in the scrolling window as the features in the subsequent prediction data. The feature engineering is represented as follows: in, For the first Predicted data for each time point, For the first Preprocessed data at each time point For a point in time, For the number of windows, The attenuation coefficient is... Between 0 and 1; The verification of the predicted data includes performing the Mann-Kendall trend test on the predicted data and sending the verification results to the intelligent fault early warning module.

2. The method for early warning of faults in the hydraulic device of a hydropower station governor as described in claim 1, characterized in that: The determination of the operating status of the governor hydraulic device includes comparing the test result data with the normal operating status of the governor hydraulic device. If the data changes are consistent with those during normal operation, the governor hydraulic device is determined to be in normal operation. If the data changes are inconsistent with those during normal operation, the governor hydraulic device is determined to be in an abnormal operating state, and a device fault warning message is issued. The normal operating state includes the oil pump starting at a set value of 5.8 MPa, and according to the normal operating data trend, the oil pump stops after 3 minutes, and the oil pressure of the oil pressure device rises to the stop oil pressure of 6.3 MPa.

3. The method for early warning of faults in the hydraulic device of a hydropower station governor as described in claim 2, characterized in that: The normal operating state includes the following: when the oil pump of the governor hydraulic device is running, the oil in the return oil tank of the governor hydraulic device is drawn to the pressure oil tank of the governor hydraulic device, the oil level in the return oil tank of the governor hydraulic device drops, the oil level and pressure in the pressure oil tank of the governor hydraulic device rise, and the oil level in the leakage tank of the governor hydraulic device remains unchanged. When the automatic air replenishment valve of the governor hydraulic device is fully open, air is replenished to the pressure oil tank of the governor hydraulic device. The oil level in the pressure oil tank of the governor hydraulic device remains unchanged and the pressure increases. The oil levels in the return oil tank and the leakage oil tank of the governor hydraulic device remain unchanged. When the guide vane opening changes, the oil in the pressure tank of the governor hydraulic device is discharged to the return tank of the governor hydraulic device. The oil level and pressure in the pressure tank of the governor hydraulic device decrease, the oil level in the return tank of the governor hydraulic device increases, and the oil level in the leakage tank of the governor hydraulic device increases slightly. When the oil leakage pump of the governor hydraulic device is running, it draws oil from the leakage tank of the governor hydraulic device to the return tank of the governor hydraulic device. The oil level in the leakage tank of the governor hydraulic device drops, the oil level in the return tank of the governor hydraulic device rises, and the oil level and pressure in the pressure tank of the governor hydraulic device remain unchanged.

4. The method for early warning of faults in the hydraulic device of a hydropower station governor as described in claim 3, characterized in that: The abnormal operating conditions include: when the oil pump of the governor hydraulic device is running, the oil level in the return oil tank of the governor hydraulic device remains unchanged, the oil level and pressure in the pressure oil tank of the governor hydraulic device remain unchanged, and a fault warning message is issued indicating that the return oil pipeline is blocked or leaking. When the oil pump of the governor hydraulic device is running, the oil level in the return oil tank of the governor hydraulic device remains unchanged, while the oil level and pressure in the pressure oil tank of the governor hydraulic device drop, and a fault warning message is issued regarding the oil supply pipeline and pump body sealing of the pressure oil tank. When the oil pump of the governor hydraulic device is running, the oil level in the return oil tank of the governor hydraulic device drops, while the oil level and pressure in the pressure oil tank of the governor hydraulic device remain unchanged, and a fault warning message is issued regarding the return oil pipeline, return oil filter, or leakage. When the oil pump of the governor hydraulic device is running, the oil level in the return oil tank of the governor hydraulic device drops, and the oil level and pressure in the pressure oil tank of the governor hydraulic device drop, thus issuing a fault warning message for the entire governor hydraulic device. When the oil leakage pump of the governor hydraulic device is running, the oil level in the oil leakage tank of the governor hydraulic device remains unchanged, the oil level in the return tank of the governor hydraulic device remains unchanged, and a fault warning message for the connection and sealing status of the oil leakage pump is issued. When the oil pump of the governor hydraulic device is running, the oil level in the governor hydraulic device's oil leakage tank drops, while the oil level in the governor hydraulic device's return oil tank remains unchanged, and a fault warning message is issued indicating a leak in the oil pipeline, connection, or leakage.

5. A system employing a fault early warning method for a hydropower station governor hydraulic device as described in any one of claims 1 to 4, characterized in that: It includes a data acquisition module, a data analysis module, and an intelligent fault early warning module; The data acquisition module is used to collect the operating data of each component in the governor hydraulic device; The data analysis module is used to preprocess the operating data of each component, make predictions based on the preprocessed data to obtain predicted data, and then perform data trend verification on the predicted data to obtain the verification result data. The intelligent fault early warning module is used to determine whether the operating status of the governor hydraulic device is normal based on the test result data obtained after data trend verification. When the governor hydraulic device is in an abnormal state, it issues a device fault early warning message.

6. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, it implements the steps of the fault early warning method for the hydraulic device of the governor of a hydropower station as described in any one of claims 1 to 4.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, it implements the steps of the fault early warning method for the hydraulic device of the governor of a hydropower station as described in any one of claims 1 to 4.

Images