Pumped storage power station transient safety monitoring method and device, storage medium and product

Abstract

The invention relates to the technical field of pumped storage power stations, and discloses a pumped storage power station transient safety monitoring method, a pumped storage power station transient safety monitoring device, a storage medium and a product. The requirement of real-time simulation in the transient process is met; the cavitation volume fraction is obtained through three-dimensional simulation, and the influence of the volume of gas generated by cavitation on the compressibility of the water body is determined. Further, the influence degree of working condition parameters on the wave velocity is determined in combination with sensitivity analysis, and physical mapping logic is provided for a wave velocity prediction model; and a high-precision mapping model of the working condition parameters and the wave velocity is constructed by utilizing a machine learning algorithm, so that rapid prediction of the wave velocity is realized, the calculated amount of traditional cross-scale simulation is reduced, and the real-time performance is improved. Furthermore, when cavitation occurs, dynamic monitoring of transient safety of the pumped storage power station is realized through fusion of the wave velocity prediction model and one-dimensional transient simulation.

Description

Technical Field

[0001] The present invention relates to the technical field of pumped storage power stations, and in particular to a method, device, storage medium and product for transient safety monitoring of pumped storage power stations. Background Art

[0002] To meet grid regulation needs, pumped-storage power stations need to frequently start and stop units and switch operating modes. The risk of transient safe operation of power stations increases significantly during their frequent participation in grid regulation tasks. In particular, given the current trend toward high-head, high-speed unit designs, the risk of cavitation in high-speed pump-turbines during operation is significantly increased. Cavitation not only causes significant pressure fluctuations, but also, after cavitation occurs, the increase in local gas volume in the flow field changes the compressibility of the local water body, resulting in a decrease in the wave velocity in the flow field. If not corrected, the minimum tailwater inlet pressure calculated for the transient process of the pumped-storage power station may not be accurately predicted, leading to the risk of water column separation. This is not conducive to the safe control of pumped-storage power stations participating in grid regulation during frequent transient processes.

[0003] Currently, preliminary transient performance analysis of pumped-storage power plants faces the following limitations: First, existing monitoring methods lack the ability to account for the presence of gas in water transmission and power generation systems. Second, during the design phase, cavitation analysis of pumped-storage units and transient simulation analysis of pumped-storage power plants are conducted separately. Traditional transient analysis methods use system-level simulations at the second-scale, while cavitation two-phase flow analysis operates at the microsecond scale. This cross-scale coupled simulation is difficult to implement and results in a significant increase in computational complexity. This can lead to inaccurate predictions for some operating conditions. Summary of the Invention

[0004] In view of this, the present invention provides a method, device, storage medium and product for transient safety monitoring of a pumped storage power station to solve the problems related to the limitations of existing methods for transient performance analysis of pumped storage power stations.

[0005] In a first aspect, the present invention provides a method for transient safety monitoring of a pumped storage power station, the method comprising:

[0006] Obtain a historical parameter dataset of the water transmission system and a historical parameter dataset of the unit operating conditions of the pumped-storage power station to be monitored; establish a one-dimensional hydraulic system transient simulation analysis model and a three-dimensional pump-turbine simulation analysis model of the pumped-storage power station to be monitored based on the historical parameter dataset of the water transmission system, wherein the output of the one-dimensional hydraulic system transient simulation analysis model is the boundary condition of the three-dimensional pump-turbine simulation analysis model; based on the historical parameter dataset of the unit operating conditions, use the three-dimensional pump-turbine simulation analysis model to perform three-dimensional cavitation two-phase flow simulation, and determine the sensitivity relationship between the operating condition parameters and the wave velocity; based on the historical parameter dataset of the unit operating conditions and the sensitivity relationship, establish a target wave velocity prediction model; when cavitation occurs in the pump-turbine in the pumped-storage power station to be monitored, use the target wave velocity prediction model and the one-dimensional hydraulic system transient simulation analysis model to perform transient simulation and determine the transient safety monitoring results of the pumped-storage power station to be monitored.

[0007] The transient safety monitoring method for a pumped-storage power station provided by the present invention ensures that the model parameters are consistent with the actual operating conditions of the power station by obtaining a historical parameter data set of the water transmission system and a historical parameter data set of the unit operating conditions of the pumped-storage power station to be monitored, thereby avoiding the disconnection between the simulation model and the actual operating conditions due to data loss, ensuring the accuracy of transient analysis from the source, and solving the problem of prediction deviation caused by incomplete data in traditional methods. Furthermore, the output of the one-dimensional model is used as the boundary condition of the three-dimensional cavitation simulation, so that the three-dimensional simulation is closer to the actual working conditions, solving the coupling difficulty problem caused by the independent analysis of the two in traditional methods. Furthermore, through the coupling of the one-dimensional and three-dimensional models, a cross-scale association between the macro-hydraulic system and the micro-cavitation simulation is achieved, avoiding the surge in computational complexity caused by directly performing a full three-dimensional transient simulation, and meeting the demand for real-time simulation in the transient process while ensuring the accuracy of the cavitation analysis. Furthermore, the cavitation volume fraction is obtained through three-dimensional simulation, clarifying the influence of the volume of gas generated by cavitation on the compressibility of the water body, solving the problem that the existing monitoring methods cannot take the presence of gas into account. Furthermore, sensitivity analysis was combined to determine the degree of influence of operating parameters on wave velocity, providing a physical mapping logic for the wave velocity prediction model, addressing the drawback of traditional methods that fail to consider the impact of cavitation on wave velocity. Furthermore, a high-precision mapping model between operating parameters and wave velocity was constructed using a machine learning algorithm, enabling rapid prediction of wave velocity, reducing the computational complexity of traditional cross-scale simulations and improving real-time performance. Furthermore, when cavitation occurs, the wave velocity changes caused by cavitation can be corrected by integrating the wave velocity prediction model with one-dimensional transient simulation, enabling transient simulation and dynamic monitoring of the transient safety of pumped-storage power stations.

[0008] In an optional embodiment, obtaining a historical parameter data set of operating conditions of a unit of a pumped storage power station to be monitored includes:

[0009] Obtain an initial parameter data set of the unit operating condition of the pumped storage power station to be monitored; obtain multiple maximum values ​​and multiple minimum values ​​of multiple parameters in the initial parameter data set of the unit operating condition; and determine a historical parameter data set of the unit operating condition in the initial parameter data set of the unit operating condition based on the multiple maximum values ​​and the multiple minimum values.

[0010] The transient safety monitoring method for pumped-storage power plants provided by this invention uses extreme values ​​to define parameter boundaries, ensuring that subsequent simulation calculations cover extreme operating conditions such as high and low loads. This addresses the uneven data distribution problem inherent in traditional methods. Furthermore, the generated historical parameter dataset for unit operating conditions meets the sample size requirements for three-dimensional cavitation simulation and wave velocity model training, avoiding errors in cavitation volume calculations caused by insufficient data.

[0011] In an optional embodiment, based on a historical parameter data set of the unit's operating conditions, a three-dimensional cavitation two-phase flow simulation is performed using a three-dimensional simulation analysis model of a pump-turbine, and the sensitivity relationship between the operating condition parameters and the wave velocity is determined, including:

[0012] Based on the historical parameter dataset of the unit's operating conditions, a three-dimensional cavitation two-phase flow simulation was performed using a three-dimensional simulation analysis model of a pump-turbine to obtain multiple cavitation volume fractions for different operating conditions. Based on these multiple cavitation volume fractions, multiple historical wave velocity values ​​were calculated. Finally, a sensitivity relationship was determined based on the historical parameter dataset of the unit's operating conditions and multiple historical wave velocity values.

[0013] The transient safety monitoring method for pumped storage power stations provided by the present invention quantifies the degree of cavitation (cavitation volume fraction) under different operating conditions through three-dimensional simulation, clarifies the impact of the volume of gas generated by cavitation on the compressibility of the water body, and solves the defect that existing monitoring methods cannot take into account the presence of gas. Furthermore, the wave velocity value is calculated based on the cavitation volume fraction, so that the wave velocity parameters can reflect the actual flow field characteristics, solving the problem of inaccurate tailwater pipe pressure prediction caused by uncorrected wave velocity in traditional transient analysis. Furthermore, by determining the sensitivity relationship, the weight of the influence of operating parameters (such as pressure and guide vane opening) on ​​the wave velocity is quantified, thereby providing support for the subsequent reduction of model input redundancy.

[0014] In an optional embodiment, multiple historical wave velocity values ​​are calculated based on multiple cavitation volume fractions, including: calculating multiple equivalent elastic moduli based on the multiple cavitation volume fractions; and obtaining multiple historical wave velocity values ​​based on the multiple equivalent elastic moduli through water hammer wave velocity relationship calculation.

[0015] The transient safety monitoring method for pumped-storage power stations proposed in this paper quantifies the changes in water compressibility caused by cavitation by considering the effects of cavitation gases on water elasticity and calculating the equivalent elastic modulus, ensuring the scientific accuracy of subsequent wave velocity corrections. Furthermore, the cavitation effect is converted into a wave velocity correction value, and the wave velocity is derived using the water hammer wave velocity relationship. This allows the wave velocity parameters in one-dimensional transient simulations to accurately reflect the cavitation state, avoiding the risk of water column separation caused by wave velocity miscalculation.

[0016] In an optional embodiment, a target wave speed prediction model is established based on a historical parameter data set of unit operating conditions and sensitivity relationships, including:

[0017] Based on the historical parameter data set and sensitivity relationship of the unit operating conditions, an initial wave speed prediction model is constructed using a machine learning algorithm. When the initial wave speed prediction model does not meet the training requirements, the back propagation algorithm is used to adjust the preset weight matrix and preset bias value in the initial wave speed prediction model and iterative training is performed until the target wave speed prediction model that meets the training requirements is obtained.

[0018] The transient safety monitoring method for pumped-storage power stations proposed in this paper, by establishing an initial wave velocity prediction model, can transform the complex cavitation-wave velocity relationship into a rapidly applicable computational model, addressing the computational complexity of traditional cross-scale simulations. Furthermore, by adjusting the weight matrix and bias values ​​and iteratively training the model, the model's prediction accuracy and generalization capabilities are improved across the full range of operating conditions, ensuring the accuracy of wave velocity predictions during cavitation.

[0019] In an optional embodiment, when cavitation occurs in a pump-turbine in a pumped-storage power station to be monitored, a transient simulation is performed using a target wave velocity prediction model and a one-dimensional hydraulic system transient simulation analysis model to determine a transient safety monitoring result of the pumped-storage power station to be monitored, including:

[0020] When cavitation occurs in the pump-turbine, the real-time parameter data set and the real-time operation boundary data set of the unit operating conditions of the pumped-storage power station to be monitored are obtained; the real-time parameter data set of the unit operating conditions are input into the target wave velocity prediction model to obtain multiple target wave velocity values; the real-time operation boundary data set and the multiple target wave velocity values ​​are input into the one-dimensional hydraulic system transient simulation analysis model to obtain transient simulation results; based on the transient simulation results, it is judged whether the pumped-storage power station to be monitored meets the preset safety requirements and the transient safety monitoring results are determined.

[0021] The transient safety monitoring method for a pumped-storage power station provided by the present invention ensures that the transient simulation data is consistent with the real-time operating status of the power station by collecting the current operating parameters and the one-dimensional model boundary conditions in real time when cavitation occurs in the pump-turbine, thereby improving the timeliness and accuracy of the simulation results. Furthermore, the wave velocity is quickly predicted based on the real-time operating parameters, and the wave velocity parameters under the influence of cavitation are dynamically updated, so that the one-dimensional simulation can reflect the current cavitation state, solving the problem of transient monitoring lag in the prior art. Furthermore, the updated wave velocity and real-time operating data are integrated into the one-dimensional model, realizing accurate simulation of the current transient process. Furthermore, the transient simulation results can be used to further determine whether the pumped-storage power station to be monitored meets the preset safety requirements, realizing transient safety monitoring of the water transmission system, pump-turbine and other systems in the pumped-storage power station to be monitored, and making up for the functional deficiencies of existing monitoring methods.

[0022] In an optional embodiment, the method further includes: when the transient safety monitoring result shows that the pumped storage power station to be monitored does not meet the preset safety requirements, issuing a safety warning based on the transient simulation result.

[0023] The transient safety monitoring method for pumped-storage power stations provided by the present invention can provide timely safety warnings for operating conditions that do not meet preset safety requirements, help operating personnel respond quickly, avoid equipment damage or system failures, and improve the safety control capabilities of pumped-storage power stations when they frequently participate in grid regulation.

[0024] In a second aspect, the present invention provides a transient safety monitoring device for a pumped storage power station, the device comprising:

[0025] An acquisition module is used to obtain a historical parameter data set of the water transmission system and a historical parameter data set of the unit operating conditions of the pumped-storage power station to be monitored; a first establishment module is used to establish a one-dimensional hydraulic system transient simulation analysis model and a three-dimensional simulation analysis model of the pump-turbine of the pumped-storage power station to be monitored based on the historical parameter data set of the water transmission system, wherein the output of the one-dimensional hydraulic system transient simulation analysis model is the boundary condition of the three-dimensional simulation analysis model of the pump-turbine; a first simulation determination module is used to perform a three-dimensional cavitation two-phase flow simulation based on the historical parameter data set of the unit operating conditions using the three-dimensional simulation analysis model of the pump-turbine, and determine the sensitivity relationship between the operating condition parameters and the wave velocity; a second establishment module is used to establish a target wave velocity prediction model based on the historical parameter data set of the unit operating conditions and the sensitivity relationship; a second simulation determination module is used to perform a transient simulation using the target wave velocity prediction model and the one-dimensional hydraulic system transient simulation analysis model when cavitation occurs in the pump-turbine in the pumped-storage power station to be monitored, and determine the transient safety monitoring results of the pumped-storage power station to be monitored.

[0026] In a third aspect, the present invention provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the method for transient safety monitoring of a pumped storage power station according to the first aspect or any corresponding embodiment thereof.

[0027] In a fourth aspect, the present invention provides a computer program product comprising computer instructions for causing a computer to execute the method for transient safety monitoring of a pumped storage power station according to the first aspect or any corresponding embodiment thereof. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the specific embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0029] Figure 1 1 is a flow chart of a method for transient safety monitoring of a pumped storage power station according to an embodiment of the present invention;

[0030] Figure 2 is a flow chart of another method for transient safety monitoring of a pumped storage power station according to an embodiment of the present invention;

[0031] Figure 3 is a flow chart of another method for transient safety monitoring of a pumped storage power station according to an embodiment of the present invention;

[0032] Figure 4 2 is a structural block diagram of a transient safety monitoring device for a pumped storage power station according to an embodiment of the present invention;

[0033] Figure 5 Schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0034] To make the purpose, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making creative efforts shall fall within the scope of protection of the present invention.

[0035] An embodiment of the present invention provides a method for transient safety monitoring of a pumped storage power station, which realizes cross-scale association between macro-hydraulic system and micro-cavitation simulation through coupling of a three-dimensional model. At the same time, the cavitation volume fraction is obtained through three-dimensional simulation and a high-precision mapping model of operating parameters and wave velocity is constructed in combination with sensitivity analysis, thereby realizing rapid prediction of wave velocity, reducing the computational complexity of traditional cross-scale simulation, and improving real-time performance. Furthermore, when cavitation occurs, by integrating the wave velocity prediction model with the one-dimensional transient simulation, the wave velocity changes caused by cavitation can be corrected, and then transient simulation can be performed, thereby realizing dynamic monitoring of the transient safety of the pumped storage power station.

[0036] According to an embodiment of the present invention, an embodiment of a method for transient safety monitoring of a pumped storage power station is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0037] In this embodiment, a method for transient safety monitoring of a pumped storage power station is provided, which can be used in electronic devices such as computers, mobile phones, tablet computers, etc. Figure 1 FIG. 1 is a flow chart of a method for transient safety monitoring of a pumped storage power station according to an embodiment of the present invention. Figure 1 As shown, the process includes the following steps:

[0038] Step S101: Acquire a historical parameter dataset of the water delivery system and a historical parameter dataset of the unit operating conditions of the pumped storage power station to be monitored.

[0039] Among them, the water transmission system historical parameter dataset represents a set of historical operating parameters related to the pumped storage power station water transmission system, which can include parameters such as the water levels of the upper and lower reservoirs, the area, impedance, and elevation of the upstream and downstream gate wells, the elevation, length, wave velocity, and diameter of the water diversion tunnel, the area, impedance, and elevation of the surge tank, the elevation, length, diameter, and wave velocity of the water diversion penstock, the elevation, length, diameter, and wave velocity of the tailwater straight cone section and the remaining elbow diffusion section, the elevation, length, diameter, and wave velocity of the tailwater penstock, and the guide vane closing pattern.

[0040] Furthermore, the historical parameter data set of the unit operating condition represents the set of operating condition parameters generated by the pumped storage power station unit during the historical operation process, which may include the unit inlet pressure P in , outlet pressure P out , guide vane opening α, power N, speed and other parameters.

[0041] Step S102 : establishing a one-dimensional hydraulic system transient simulation analysis model and a three-dimensional pump-turbine simulation analysis model of the pumped-storage power station to be monitored based on the historical parameter data set of the water transmission system.

[0042] Among them, the output of the one-dimensional hydraulic system transient simulation analysis model (volute inlet and draft tube outlet pressure, unit speed, and flow) can be used as the boundary conditions of the three-dimensional simulation analysis model of the pump-turbine; the cavitation volume of the three-dimensional simulation analysis model of the pump-turbine can be used to calculate the wave velocity value of the one-dimensional hydraulic system transient simulation analysis model.

[0043] Furthermore, the one-dimensional hydraulic system transient simulation analysis model represents a model based on one-dimensional pipeline theory that simplifies the water supply system into a combination of several pipeline sections. By solving the water hammer wave equation, it simulates the dynamic changes of hydraulic system parameters such as pressure, flow, and speed during transient processes such as unit startup and shutdown and operating mode conversion in the pumped storage power station. This model includes all hydraulic components that pass water between the upper and lower reservoirs of the power station. Specifically, it includes the water levels of the upper and lower reservoirs; the area, impedance, and elevation of the upstream and downstream gate wells; the elevation, length, wave velocity, and diameter of the water diversion tunnel; the area, impedance, and elevation of the surge tank; the elevation, length, diameter, and wave velocity of the water diversion penstock; the rated value and initial operating value of the turbine; the elevation, length, diameter, and wave velocity of the tailwater pipe's straight cone section and the remaining elbow diffuser section; the elevation, length, diameter, and wave velocity of the tailwater penstock; and the guide vane closing pattern.

[0044] Furthermore, the three-dimensional simulation analysis model of the pump-turbine represents a model that performs three-dimensional modeling of the flow components (volute, guide vanes, runner, and tailwater pipe) of the pump-turbine based on computational fluid dynamics (CFD) to simulate the cavitation two-phase flow (water-air mixed flow) phenomenon in the flow field.

[0045] Specifically, the water supply system can be simplified into a one-dimensional pipeline network. Then, based on the water hammer equation and the continuity equation, the transient process of water flow in the pipeline, such as pressure fluctuations and flow changes, can be simulated, and a one-dimensional hydraulic system transient simulation analysis model can be established.

[0046] The tailwater pipe can be divided into two parts: the straight cone section and the remaining elbow section and diffusion section. The wave velocity of each section can be calculated separately to reflect the different effects of cavitation on different pipe sections.

[0047] Furthermore, the input of the one-dimensional hydraulic system transient simulation analysis model is the real-time upstream and downstream water levels of the power station and the specific operating instructions of the unit (including guide vane opening, power, etc.). The output of the model is parameters such as pressure along the flow channel and unit speed. Special position extreme value outputs can also be set, such as the maximum pressure at the volute inlet, the minimum pressure at the tailwater pipe inlet, the maximum speed of the unit, and other power station transient process design parameters.

[0048] Furthermore, a 3D simulation analysis model for a pump-turbine can be created based on the flow path dimensions of the volute, fixed guide vanes, movable guide vanes, runner, and draft tube. The 3D draft tube model is also divided into two parts: the straight cone section and the remaining elbow section and diffuser section.

[0049] Further, the input of the three-dimensional simulation analysis model of the pump-turbine is the boundary conditions such as the volute inlet pressure, the draft tube outlet pressure, the unit speed and the flow rate output by the one-dimensional model, and the output is the cavitation volume fraction under different working conditions.

[0050] In step S103, based on the historical parameter data set of the unit operating condition, the three-dimensional cavitation two-phase flow simulation is performed by using the three-dimensional simulation analysis model of the pump-turbine, and the sensitivity relationship between the operating condition parameters and the wave speed is determined.

[0051] Specifically, the inlet pressure, outlet pressure, guide vane opening and other operating condition parameters can be extracted from the historical parameter data set of the unit operating condition as the input conditions of the three-dimensional simulation model.

[0052] Further, the established three-dimensional simulation analysis model of the pump-turbine can be used to carry out simulation calculation under different conditions.

[0053] Further, the sensitivity relationship between the operating condition parameters and the wave speed can be further determined according to the simulation calculation results.

[0054] In step S104, based on the historical parameter data set of the unit operating condition and the sensitivity relationship, a target wave speed prediction model is established.

[0055] The target wave speed prediction model represents a mathematical model reflecting the high-precision mapping relationship between the operating condition parameters (such as inlet and outlet pressure, guide vane opening, power, etc.) of the pumped storage power station unit and the draft tube wave speed, which is constructed based on machine learning or deep learning algorithm.

[0056] Specifically, by analyzing the sensitivity relationship between the operating condition parameters and the wave speed, the key parameters (such as inlet and outlet pressure, guide vane opening, etc.) that significantly affect the wave speed can be screened out, and the secondary parameters can be eliminated, so as to determine the core input variables of the target wave speed prediction model, reduce the redundant dimensions of the model, improve the prediction efficiency and accuracy of the model, and ensure that the model can accurately reflect the influence of the operating condition parameter change on the wave speed.

[0057] Further, the model is trained according to the screened key parameters and the corresponding target wave speed prediction model is established.

[0058] In step S105, when cavitation occurs in the pump-turbine of the to-be-monitored pumped storage power station, the target wave speed prediction model and the one-dimensional hydraulic system transient simulation analysis model are used for transient simulation to determine the transient safety monitoring result of the to-be-monitored pumped storage power station.

[0059] Specifically, the power plant's cavitation noise or vibration monitoring system (e.g., sensors) can be used to determine in real time whether cavitation is occurring in the pump-turbine. If cavitation signals are detected (e.g., abnormal noise or vibration amplitude exceeding a threshold), transient simulation is performed using a target wave velocity prediction model and a one-dimensional hydraulic system transient simulation analysis model.

[0060] Furthermore, the transient safety status of the pumped storage power station to be monitored, ie, the transient safety monitoring result, can be further determined based on the transient simulation result.

[0061] The transient safety monitoring method for a pumped-storage power station provided in this embodiment ensures that the model parameters are consistent with the actual operating conditions of the power station by obtaining a historical parameter data set of the water transmission system and a historical parameter data set of the unit operating conditions of the pumped-storage power station to be monitored, thereby avoiding the disconnection between the simulation model and the actual operating conditions due to data loss, ensuring the accuracy of transient analysis from the source, and solving the problem of prediction deviation caused by incomplete data in traditional methods. Furthermore, the output of the one-dimensional model is used as the boundary condition of the three-dimensional cavitation simulation, making the three-dimensional simulation closer to the actual operating conditions, solving the coupling difficulty caused by the independent analysis of the two in traditional methods. Furthermore, through the coupling of the one-dimensional and three-dimensional models, a cross-scale association between the macro-hydraulic system and the micro-cavitation simulation is achieved, avoiding the surge in computational complexity caused by directly performing a full three-dimensional transient simulation, and meeting the requirements of real-time simulation during the transient process while ensuring the accuracy of the cavitation analysis. Furthermore, the cavitation volume fraction is obtained through three-dimensional simulation, clarifying the impact of the volume of gas generated by cavitation on the compressibility of the water body, solving the problem that existing monitoring methods cannot take into account the presence of gas. Furthermore, sensitivity analysis was combined to determine the degree of influence of operating parameters on wave velocity, providing a physical mapping logic for the wave velocity prediction model, addressing the drawback of traditional methods that fail to consider the impact of cavitation on wave velocity. Furthermore, a high-precision mapping model between operating parameters and wave velocity was constructed using a machine learning algorithm, enabling rapid prediction of wave velocity, reducing the computational complexity of traditional cross-scale simulations and improving real-time performance. Furthermore, when cavitation occurs, the wave velocity changes caused by cavitation can be corrected by integrating the wave velocity prediction model with one-dimensional transient simulation, enabling transient simulation and dynamic monitoring of the transient safety of pumped-storage power stations.

[0062] In this embodiment, a method for transient safety monitoring of a pumped storage power station is provided, which can be used in electronic devices such as computers, mobile phones, tablet computers, etc. Figure 2 FIG. 1 is a flow chart of a method for transient safety monitoring of a pumped storage power station according to an embodiment of the present invention. Figure 2 As shown, the process includes the following steps:

[0063] Step S201: Acquire a historical parameter data set of the water delivery system and a historical parameter data set of the unit operating conditions of the pumped storage power station to be monitored.

[0064] The historical parameter data set of the unit operating conditions can be obtained through the following steps:

[0065] Step a1: obtaining an initial parameter data set of the operating conditions of the units of the pumped storage power station to be monitored.

[0066] Step a2: obtaining multiple maximum values ​​and multiple minimum values ​​of multiple parameters in the initial parameter data set of the unit operating condition.

[0067] Step a3: determining a historical parameter data set of the unit operating condition in the initial parameter data set of the unit operating condition according to the multiple maximum values ​​and the multiple minimum values.

[0068] Specifically, the operating parameters of the unit under different operating conditions can be collected from the monitoring system or historical operation database of the pumped storage power station to form an initial parameter data set, which may include key parameters reflecting the operating status of the unit, such as the unit inlet pressure (Pin), outlet pressure (Pout), guide vane opening, power (N), and speed.

[0069] Furthermore, a statistical analysis is performed on each parameter in the initial data set (such as inlet pressure, guide vane opening, etc.), and its maximum (Max) and minimum (Min) values ​​in historical operation are calculated.

[0070] Furthermore, the value range boundary of each parameter can be determined by calculating the maximum and minimum values.

[0071] Furthermore, based on the maximum and minimum values ​​of each parameter, a historical parameter data set covering the entire operating range can be screened or generated from the initial data set.

[0072] In some optional embodiments, the screening criteria are: the training data generated for each parameter is no less than 30 to ensure sufficient sample size; the values ​​of each parameter must be independent and evenly cover its extreme value range (such as sampling at equal intervals within the pressure extreme value range) to avoid data concentration in specific working conditions.

[0073] Step S202: Based on the historical parameter data set of the water transmission system, a one-dimensional hydraulic system transient simulation analysis model and a three-dimensional simulation analysis model of the pump-turbine to be monitored are established. Figure 1 Step S102 of the illustrated embodiment will not be described in detail here.

[0074] Step S203 , based on the historical parameter data set of the unit operating condition, a three-dimensional cavitation two-phase flow simulation is performed using a three-dimensional simulation analysis model of a pump-turbine, and a sensitivity relationship between the operating condition parameters and the wave velocity is determined.

[0075] Specifically, the above step S203 includes:

[0076] Step S2031 : Based on the historical parameter data set of the unit operating conditions, a three-dimensional cavitation two-phase flow simulation is performed using a three-dimensional simulation analysis model of a pump-turbine to obtain multiple cavitation volume fractions under different operating conditions.

[0077] Specifically, operating parameters such as inlet pressure, outlet pressure, and guide vane opening can be extracted from the historical parameter data set of the unit's operating conditions and used as input conditions for the three-dimensional simulation analysis model of the pump-turbine.

[0078] Furthermore, the three-dimensional simulation analysis model of the pump-turbine is used to carry out simulation calculations for different working conditions.

[0079] Furthermore, by solving the two-phase flow control equations and cavitation models (such as the Rayleigh-Plesset equation), the mixed flow of water and bubbles in the flow field can be simulated, and the bubble volume ratio in the tailwater pipe under different working conditions, that is, the cavitation volume fraction, can be calculated.

[0080] Through the above process, the effect of gas generated by cavitation on the compressibility of water was considered and the degree of cavitation was quantified.

[0081] Step S2032: Calculate multiple historical wave velocity values ​​according to the multiple cavitation volume fractions.

[0082] Specifically, based on the calculated multiple cavitation volume fractions, the wave velocity values ​​of the straight cone section of the draft tube under different working conditions, that is, multiple historical wave velocity values, can be further calculated.

[0083] In some optional implementations, the above step S2032 includes:

[0084] Step b1: Calculate multiple equivalent elastic moduli based on multiple cavitation volume fractions.

[0085] Step b2: Based on multiple equivalent elastic moduli, multiple historical wave velocity values ​​are obtained through calculation using a water hammer wave velocity relationship.

[0086] The equivalent elastic modulus is a physical quantity used to characterize the elastic properties of water under the influence of cavitation. Specifically, when cavitation occurs during the operation of a pump-turbine in a pumped-storage power station, the local increase in gas volume in the flow field changes the compressibility of the water. The equivalent elastic modulus quantifies the impact of this change on the elasticity of the water by incorporating the cavitation volume fraction (the proportion of air bubbles in the water volume) into its calculations.

[0087] Specifically, the equivalent elastic modulus can be calculated using the following equation (1):

[0088]

[0089] Where: K effrepresents the equivalent elastic modulus; f represents the cavitation volume fraction; K represents the bulk elastic modulus of water; γ represents the specific heat ratio of gas; and P represents the absolute pressure of the computational domain.

[0090] Furthermore, the wave velocity value can be calculated based on the water hammer wave velocity relationship, as shown in the following relationship (2):

[0091]

[0092] Where: a represents the wave velocity; ρ represents the density of water; E represents the elastic modulus of the pipe wall material; D represents the inner diameter of the pipe; e represents the thickness of the pipe; C1 = 1-v 2 , represents the pipeline constraint coefficient, and v represents the Poisson's ratio.

[0093] Step S2033: determining a sensitivity relationship based on the historical parameter data set of the unit operating conditions and a plurality of historical wave velocity values.

[0094] Specifically, the historical operating parameters (such as inlet and outlet pressures, guide vane opening, and power) in the unit operating condition historical parameter data set are matched one by one with the calculated wave velocity values, and sensitivity analysis methods (such as correlation coefficient and gradient analysis) are used for analysis to determine the sensitivity relationship between the operating condition parameters and the wave velocity.

[0095] Step S204: establishing a target wave speed prediction model based on the historical parameter data set and sensitivity relationship of the unit operating conditions.

[0096] Specifically, the above step S204 includes:

[0097] Step S2041: Based on the historical parameter data set and sensitivity relationship of the unit operating conditions, an initial wave speed prediction model is constructed using a machine learning algorithm.

[0098] Specifically, the sensitivity relationship can be used to screen out the key parameter set X that has a significant impact on the wave speed from the historical parameter data set of the unit operating conditions and construct the input layer matrix, as shown in the following relationship (3):

[0099]

[0100] Where: Indicates the filtered historical operating parameters of the mth group of units.

[0101] Furthermore, the filtered key parameter set X can be used as model input, and intelligent algorithms such as machine learning algorithms or deep learning can be used to construct a prediction model for unit operating parameters such as inlet and outlet pressures, guide vane opening, power and wave speed, namely the initial wave speed prediction model.

[0102] Furthermore, the output of the model is the wave velocity value α, as shown in the following equation (4):

[0103] α=σ(WX+b) (4)

[0104] Where: W represents the weight matrix, which can determine the contribution weight of different input signals to the result and is the core learnable parameter responsible for feature conversion, as shown in the following relationship (5):

[0105]

[0106] Furthermore, each value in W can be automatically optimized through training data, ultimately enabling the model to accurately predict the target physical quantity, such as wave speed, from the input operating parameters (such as pressure and guide vane opening).

[0107] Furthermore, b represents a bias, which is used to determine the difficulty of neuron activation.

[0108] Step S2042: When the initial wave speed prediction model does not meet the training requirements, the preset weight matrix and the preset bias value in the initial wave speed prediction model are adjusted using the back propagation algorithm and iterative training is performed until a target wave speed prediction model that meets the training requirements is obtained.

[0109] Specifically, when the initial wave speed prediction model does not meet the training requirements, the back propagation algorithm can be used to adjust the preset weight matrix W and the preset bias value b in the initial wave speed prediction model, and then through repeated iterative training, until the target wave speed prediction model that meets the training requirements is obtained.

[0110] Step S205: When cavitation occurs in the pump-turbine of the pumped storage power station to be monitored, a transient simulation is performed using the target wave velocity prediction model and the one-dimensional hydraulic system transient simulation analysis model to determine the transient safety monitoring results of the pumped storage power station to be monitored. Figure 1 Step S105 of the illustrated embodiment will not be described in detail here.

[0111] The transient safety monitoring method for a pumped storage power station provided in this embodiment defines parameter boundaries by using extreme values, ensuring that subsequent simulation calculations can cover extreme operating conditions such as high load and low load, thereby solving the problem of uneven data distribution in traditional methods. Furthermore, the generated historical parameter data set for the unit's operating conditions meets the sample size requirements for three-dimensional cavitation simulation and wave velocity model training, avoiding deviations in cavitation volume calculations due to insufficient data. Furthermore, by considering the impact of cavitation gas on the elasticity of the water body and calculating the equivalent elastic modulus, the changes in the compressibility of the water body caused by cavitation are quantified, ensuring the scientific nature of subsequent wave velocity corrections. Furthermore, the cavitation effect is converted into a wave velocity correction value, and the wave velocity is derived through the water hammer wave velocity relationship, so that the wave velocity parameters in the one-dimensional transient simulation can accurately reflect the cavitation state, avoiding the risk of water column separation due to errors in wave velocity calculation. Furthermore, the wave velocity value is calculated based on the cavitation volume fraction, so that the wave velocity parameters can reflect the actual flow field characteristics, solving the problem of inaccurate tailwater pipe pressure prediction caused by uncorrected wave velocity in traditional transient analysis. Furthermore, by determining the sensitivity relationship, the influence weights of operating parameters (such as pressure and guide vane opening) on ​​wave velocity were quantified, which provided support for the subsequent reduction of model input redundancy.

[0112] In this embodiment, a method for transient safety monitoring of a pumped storage power station is provided, which can be used in electronic devices such as computers, mobile phones, tablet computers, etc. Figure 3 FIG. 1 is a flow chart of a method for transient safety monitoring of a pumped storage power station according to an embodiment of the present invention. Figure 3 As shown, the process includes the following steps:

[0113] Step S301: Obtain the historical parameter data set of the water transmission system and the historical parameter data set of the unit operating condition of the pumped storage power station to be monitored. Figure 2 Step S201 of the illustrated embodiment will not be described in detail here.

[0114] Step S302: Based on the historical parameter data set of the water transmission system, a one-dimensional hydraulic system transient simulation analysis model and a three-dimensional simulation analysis model of the pump-turbine to be monitored are established. Figure 1 Step S102 of the illustrated embodiment will not be described in detail here.

[0115] Step S303: Based on the historical parameter data set of the unit's operating conditions, a three-dimensional cavitation two-phase flow simulation is performed using the pump-turbine three-dimensional simulation analysis model, and the sensitivity relationship between the operating condition parameters and the wave velocity is determined. Figure 2 Step S203 of the illustrated embodiment will not be described in detail here.

[0116] Step S304: Based on the historical parameter data set and sensitivity relationship of the unit operating conditions, a target wave speed prediction model is established. Figure 2Step S204 of the illustrated embodiment, which will not be described here again.

[0117] Step S305, when cavitation occurs in the water pump turbine in the to-be-monitored pumped storage power station, a transient simulation is performed using a target wave speed prediction model and a one-dimensional hydraulic system transient simulation analysis model to determine the transient safety monitoring result of the to-be-monitored pumped storage power station.

[0118] Specifically, step S305 includes:

[0119] Step S3051, when cavitation occurs in the water pump turbine, a set of real-time operating condition parameter data and a set of real-time operating boundary data of the to-be-monitored pumped storage power station are obtained.

[0120] The set of real-time operating condition parameter data represents a set of parameters reflecting the current operating state and working characteristics of the unit during the operation of the pumped storage power station, which are collected in real time by various sensors.

[0121] Further, the set of real-time operating boundary data represents a set of various data reflecting the operating environment and system boundary conditions of the pumped storage power station, which are collected in real time and can directly affect the hydraulic characteristics and operating state of the power station. It can include data reflecting the upstream water level, downstream water level, unit speed, and other boundary conditions of the real-time operation of the pumped storage power station.

[0122] Step S3052, the set of real-time operating condition parameter data is input into the target wave speed prediction model to obtain a plurality of target wave speed values.

[0123] Specifically, the set of real-time operating condition parameter data obtained is input into the trained target wave speed prediction model, and the wave speed values of the draft tube corresponding to different operating conditions, i.e. a plurality of target wave speed values, can be calculated.

[0124] Step S3053, the set of real-time operating boundary data and the plurality of target wave speed values are input into the one-dimensional hydraulic system transient simulation analysis model to obtain a transient simulation result.

[0125] Specifically, the set of real-time operating boundary data and the plurality of target wave speed values obtained are input into the established one-dimensional hydraulic system transient simulation analysis model, and the hydraulic transient process under cavitation state is simulated.

[0126] Further, through simulation, the one-dimensional hydraulic system transient simulation analysis model can output a corresponding transient simulation result.

[0127] For example, the transient simulation result can include the transient pressure distribution of the pressure pipeline, the unit speed fluctuation curve, the water flow state at the guide vane, etc.

[0128] Step S3054: Based on the transient simulation results, determine whether the pumped storage power station to be monitored meets the preset safety requirements and determine the transient safety monitoring results.

[0129] Specifically, based on the transient simulation results obtained, safety can be judged from different dimensions, for example, whether the maximum volute inlet pressure, the minimum draft tube inlet pressure, and the maximum unit speed design limits are exceeded.

[0130] Further, if it is exceeded, it is determined that the preset safety requirement is not met; if it is not exceeded, it is determined that the preset safety requirement is met.

[0131] Furthermore, if the preset safety requirements are not met, a safety warning can be issued based on the transient simulation results.

[0132] The transient safety monitoring method for a pumped-storage power station provided in this embodiment ensures that transient simulation data is consistent with the power station's real-time operating status by real-time acquisition of current operating parameters and one-dimensional model boundary conditions when cavitation occurs in the pump-turbine, thereby improving the timeliness and accuracy of the simulation results. Furthermore, the method rapidly predicts wave velocity based on real-time operating parameters and dynamically updates the wave velocity parameters under the influence of cavitation, enabling the one-dimensional simulation to reflect the current cavitation state, resolving the issue of transient monitoring lag in the prior art. Furthermore, the updated wave velocity and real-time operating data are integrated into the one-dimensional model, enabling accurate simulation of the current transient process. Furthermore, the transient simulation results can be used to further determine whether the monitored pumped-storage power station meets preset safety requirements, enabling transient safety monitoring of systems such as the water delivery system and pump-turbines within the monitored pumped-storage power station, thus addressing the functional deficiencies of existing monitoring methods. Furthermore, timely safety warnings are issued for operating conditions that do not meet preset safety requirements, enabling operators to respond quickly, avoiding equipment damage or system failures, and improving the safety control capabilities of pumped-storage power stations when they frequently participate in grid regulation.

[0133] In this embodiment, a pumped storage power station transient safety monitoring device is also provided, which is used to implement the above-mentioned embodiments and preferred embodiments. The details that have been described will not be repeated here. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, implementation using hardware, or a combination of software and hardware, is also possible and contemplated.

[0134] This embodiment provides a transient safety monitoring device for a pumped storage power station, such as Figure 4 As shown, the device includes:

[0135] The acquisition module 401 is used to acquire a historical parameter data set of the water delivery system and a historical parameter data set of the unit operating conditions of the pumped storage power station to be monitored.

[0136] The first establishment module 402 is used to establish a one-dimensional hydraulic system transient simulation analysis model and a three-dimensional simulation analysis model of the pump-turbine of the pump-storage power station to be monitored based on the historical parameter data set of the water transmission system, wherein the output of the one-dimensional hydraulic system transient simulation analysis model is the boundary condition of the three-dimensional simulation analysis model of the pump-turbine.

[0137] The first simulation determination module 403 is used to perform three-dimensional cavitation two-phase flow simulation based on the historical parameter data set of the unit operating condition using the three-dimensional simulation analysis model of the pump-turbine and determine the sensitivity relationship between the operating condition parameters and the wave velocity.

[0138] The second establishing module 404 is used to establish a target wave speed prediction model based on the historical parameter data set and sensitivity relationship of the unit operating conditions.

[0139] The second simulation determination module 405 is used to perform transient simulation and determine the transient safety monitoring result of the pumped storage power station to be monitored using the target wave velocity prediction model and the one-dimensional hydraulic system transient simulation analysis model when cavitation occurs in the pump turbine in the pumped storage power station to be monitored.

[0140] In some optional implementations, the acquisition module 401 includes:

[0141] The first acquisition submodule is used to obtain an initial parameter data set of the operating conditions of the units of the pumped storage power station to be monitored.

[0142] The second acquisition submodule is used to obtain multiple maximum values ​​and multiple minimum values ​​of multiple parameters in the initial parameter data set of the unit operating condition.

[0143] The determination submodule is used to determine the unit operating condition historical parameter data set in the unit operating condition initial parameter data set based on multiple maximum values ​​and multiple minimum values.

[0144] In some optional implementations, the first simulation determination module 403 includes:

[0145] The simulation submodule is used to perform three-dimensional cavitation two-phase flow simulation based on the historical parameter data set of the unit operating conditions and use the three-dimensional simulation analysis model of the pump-turbine to obtain multiple cavitation volume fractions under different operating conditions.

[0146] The calculation submodule is used to calculate multiple historical wave velocity values ​​according to multiple cavitation volume fractions.

[0147] The determination submodule is used to determine the sensitivity relationship based on the historical parameter data set of the unit operating conditions and multiple historical wave speed values.

[0148] In some optional implementations, the calculation submodule includes:

[0149] The first calculation unit is configured to calculate a plurality of equivalent elastic moduli according to a plurality of cavitation volume fractions.

[0150] The second calculation unit is used to obtain multiple historical wave velocity values ​​based on multiple equivalent elastic moduli and through a water hammer wave velocity relationship.

[0151] In some optional implementations, the second establishing module 404 includes:

[0152] A submodule is constructed to build an initial wave speed prediction model using a machine learning algorithm based on the historical parameter data set and sensitivity relationship of the unit operating conditions.

[0153] The iterative submodule is used to adjust the preset weight matrix and preset bias value in the initial wave speed prediction model using the back propagation algorithm and iteratively train when the initial wave speed prediction model does not meet the training requirements until a target wave speed prediction model that meets the training requirements is obtained.

[0154] In some optional implementations, the second simulation determination module 405 includes:

[0155] The third acquisition submodule is used to obtain the real-time parameter data set and the real-time operation boundary data set of the unit operating conditions of the pumped storage power station to be monitored when cavitation occurs in the pump turbine.

[0156] The first input submodule is used to input the real-time parameter data set of the unit operation condition into the target wave speed prediction model to obtain multiple target wave speed values.

[0157] The second input submodule is used to input the real-time operation boundary data set and multiple target wave velocity values ​​into the one-dimensional hydraulic system transient simulation analysis model to obtain transient simulation results.

[0158] The judgment and determination submodule is used to judge whether the pumped storage power station to be monitored meets the preset safety requirements and determine the transient safety monitoring results based on the transient simulation results.

[0159] In some optional embodiments, the device further comprises:

[0160] The early warning module is used to issue a safety warning based on the transient simulation results when the transient safety monitoring result shows that the pumped storage power station to be monitored does not meet the preset safety requirements.

[0161] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0162] The transient safety monitoring device of the pumped storage power station in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0163] The embodiment of the present invention also provides a computer device having the above Figure 4 The transient safety monitoring device of the pumped storage power station shown.

[0164] See also Figure 5 , Figure 5 is a structural diagram of a computer device provided by an optional embodiment of the present invention, such as Figure 5 As shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components utilize different buses to communicate with each other and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the computer device, including instructions stored in or on the memory to display the graphical information of a GUI on an external input / output device (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories. Equally, multiple computer devices can be connected, and each device provides part of the necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 5 A processor 10 is taken as an example.

[0165] The processor 10 may be a central processing unit, a network processor, or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit, a programmable logic device, or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic, or any combination thereof.

[0166] The memory 20 stores instructions that can be executed by at least one processor 10, so as to enable at least one processor 10 to execute the method shown in the above embodiment.

[0167] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and application programs required for at least one function; the data storage area may store data created based on the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely located relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0168] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid-state drive; the memory 20 may also include a combination of the above types of memory.

[0169] The computer device further includes a communication interface 30 for the computer device to communicate with other devices or a communication network.

[0170] The embodiment of the present invention also provides a computer-readable storage medium. The above-mentioned method according to the embodiment of the present invention can be implemented in hardware, firmware, or implemented as a computer code that can be recorded in a storage medium, or implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and downloaded through a network and will be stored in a local storage medium, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state drive, etc.; further, the storage medium can also include a combination of the above-mentioned types of memory. It can be understood that a computer, a processor, a microprocessor controller or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor or hardware, the method shown in the above embodiment is implemented.

[0171] A portion of the present invention may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present invention through the operation of the computer. Those skilled in the art should understand that the form in which the computer program instruction exists in a computer-readable medium includes, but is not limited to, a source file, an executable file, an installation package file, etc. Accordingly, the way in which the computer program instruction is executed by the computer includes, but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Here, the computer-readable medium may be any available computer-readable storage medium or communication medium that can be accessed by the computer.

[0172] Although the embodiments of the present invention have been described with reference to the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention. Such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A method for transient safety monitoring of a pumped storage power station, characterized in that: The method comprises: Obtain a historical parameter dataset of the water transmission system and a historical parameter dataset of the unit operating conditions of the pumped storage power station to be monitored; Based on the water transmission system historical parameter data set, a one-dimensional hydraulic system transient simulation analysis model and a three-dimensional pump-turbine simulation analysis model of the pumped-storage power station to be monitored are established, wherein the output of the one-dimensional hydraulic system transient simulation analysis model serves as the boundary conditions of the three-dimensional pump-turbine simulation analysis model; Based on the historical parameter data set of the unit's operating conditions, a three-dimensional cavitation two-phase flow simulation is performed using the pump-turbine three-dimensional simulation analysis model, and a sensitivity relationship between the operating condition parameters and the wave velocity is determined; Establishing a target wave speed prediction model based on the historical parameter data set of the unit operating conditions and the sensitivity relationship; When cavitation occurs in the pump-turbine of the pumped-storage power station to be monitored, transient simulation is performed using the target wave velocity prediction model and the one-dimensional hydraulic system transient simulation analysis model to determine the transient safety monitoring result of the pumped-storage power station to be monitored.

2. The method according to claim 1, characterized in that Obtain the historical parameter data set of the unit operating conditions of the pumped storage power station to be monitored, including: Obtaining an initial parameter data set of the operating conditions of the units of the pumped-storage power station to be monitored; Acquire multiple maximum values ​​and multiple minimum values ​​of multiple parameters in the initial parameter data set of the unit operating condition; The unit operating condition historical parameter data set is determined in the unit operating condition initial parameter data set according to the multiple maximum values ​​and the multiple minimum values.

3. The method according to claim 1, characterized in that Based on the historical parameter data set of the unit's operating conditions, a three-dimensional cavitation two-phase flow simulation is performed using the pump-turbine three-dimensional simulation analysis model, and the sensitivity relationship between the operating condition parameters and the wave velocity is determined, including: Based on the historical parameter data set of the unit's operating conditions, a three-dimensional cavitation two-phase flow simulation is performed using the pump-turbine three-dimensional simulation analysis model to obtain multiple cavitation volume fractions under different operating conditions; Calculating a plurality of historical wave velocity values ​​according to the plurality of cavitation volume fractions; The sensitivity relationship is determined based on the historical parameter data set of the unit operating condition and the multiple historical wave velocity values.

4. The method according to claim 3, characterized in that Calculating a plurality of historical wave velocity values ​​according to the plurality of cavitation volume fractions includes: calculating a plurality of equivalent elastic moduli according to the plurality of cavitation volume fractions; Based on the multiple equivalent elastic moduli, the multiple historical wave velocity values ​​are obtained through calculation using a water hammer wave velocity relationship.

5. The method according to claim 1, wherein Based on the historical parameter data set of the unit operating condition and the sensitivity relationship, a target wave speed prediction model is established, including: Based on the historical parameter data set of the unit operating conditions and the sensitivity relationship, an initial wave velocity prediction model is constructed using a machine learning algorithm; When the initial wave speed prediction model does not meet the training requirements, the preset weight matrix and the preset bias value in the initial wave speed prediction model are adjusted using a back propagation algorithm and iterative training is performed until the target wave speed prediction model that meets the training requirements is obtained.

6. The method according to claim 1, characterized in that When cavitation occurs in the pump-turbine of the pumped-storage power station to be monitored, transient simulation is performed using the target wave velocity prediction model and the one-dimensional hydraulic system transient simulation analysis model to determine the transient safety monitoring result of the pumped-storage power station to be monitored, including: When cavitation occurs in the pump-turbine, a real-time parameter data set and a real-time operation boundary data set of the unit operating conditions of the pumped-storage power station to be monitored are obtained; Inputting the real-time parameter data set of the unit operating condition into the target wave speed prediction model to obtain multiple target wave speed values; Inputting the real-time operation boundary data set and the multiple target wave velocity values ​​into the one-dimensional hydraulic system transient simulation analysis model to obtain a transient simulation result; According to the transient simulation results, it is judged whether the pumped storage power station to be monitored meets the preset safety requirements and the transient safety monitoring results are determined.

7. The method according to claim 6, characterized in that The method further comprises: When the transient safety monitoring result indicates that the pumped storage power station to be monitored does not meet the preset safety requirements, a safety warning is issued based on the transient simulation result.

8. A transient safety monitoring device for a pumped storage power station, characterized in that: The device comprises: An acquisition module is used to obtain a historical parameter data set of the water transmission system and a historical parameter data set of the unit operating conditions of the pumped storage power station to be monitored; A first establishment module is configured to establish a one-dimensional hydraulic system transient simulation analysis model and a three-dimensional pump-turbine simulation analysis model of the pumped-storage power station to be monitored based on the historical parameter data set of the water transmission system, wherein the output of the one-dimensional hydraulic system transient simulation analysis model serves as the boundary condition of the three-dimensional pump-turbine simulation analysis model; a first simulation determination module, configured to perform a three-dimensional cavitation two-phase flow simulation based on a historical parameter data set of the unit's operating conditions and using the three-dimensional simulation analysis model of the pump-turbine, and determine a sensitivity relationship between the operating condition parameters and the wave velocity; A second establishing module is used to establish a target wave speed prediction model based on the historical parameter data set of the unit operating condition and the sensitivity relationship; The second simulation determination module is used to perform transient simulation and determine the transient safety monitoring result of the pumped storage power station to be monitored using the target wave velocity prediction model and the one-dimensional hydraulic system transient simulation analysis model when cavitation occurs in the pump turbine in the pumped storage power station to be monitored.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the method for transient safety monitoring of a pumped-storage power station according to any one of claims 1 to 7.

10. A computer program product, characterized in that The method comprises computer instructions for causing a computer to execute the method for transient safety monitoring of a pumped storage power station according to any one of claims 1 to 7.

Images