Method, device and equipment for monitoring pressure steel pipe of water delivery system of pumped storage power station

Through transient simulation analysis and stress prediction model, combined with linear cumulative damage theory, the stress and damage of pressure steel pipes in pumped storage power stations is monitored in real time, and the problem of inability to effectively monitor the strength changes and cumulative damage of steel pipes in the transient process in the existing technology is solved. , improves safety and stability.

CN118586323BActive Publication Date: 2024-11-12THREE GORGES GROUP IND DEVELOPMENT (BEIJING) CO LTD +1
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411089437.7
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-08-09
Publication Date
2024-11-12
Estimated Expiration
2044-08-09

AI Technical Summary

Technical Problem

The prior art cannot effectively monitor and analyze the strength changes and accumulated damage of the pressure steel pipes in the pumped storage power station during the transient process, resulting in safety hazards.

Method used

Using pre-constructed transient simulation analysis model and stress prediction model, simulation calculation and stress prediction are carried out through operation data, combined with linear accumulated damage theory and rain flow counting method, the stress and damage of pressure steel pipes are monitored in real time, and scientific, safe and stable operation are provided. in accordance with.

Benefits of technology

It improves accurate monitoring of the operating status of pressure steel pipes, ensures the safety and stability of the pumped storage power station, and extends the service life of the equipment.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118586323B_ABST
    Figure CN118586323B_ABST
Patent Text Reader

Abstract

The present invention relates to the technical field of pumped storage power stations, and specifically to a method, device and equipment for monitoring penstocks in a water delivery system of a pumped storage power station. The method comprises: based on the operation data of the pumped storage power station, using a pre-built transient simulation analysis model to simulate and calculate all transient operating conditions of the power station to obtain pressure data; calculating the stress on the penstock based on the pressure data; using the operation data and stress training to obtain a stress prediction model; inputting the real-time operation data of the pumped storage power station into the stress prediction model to obtain stress data at various positions of the penstock; when the relationship between the collected stress data at a preset position of the penstock and the predicted stress data meets the preset conditions, using the linear cumulative damage theory and the rain flow counting method to determine the damage data of the penstock; monitoring the penstock according to the damage data and the predicted stress data. Provide a basis for on-site staff to more accurately grasp the actual operating status of the penstock of the power station.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of pumped storage power stations, and in particular to a method, device and equipment for monitoring pressure steel pipes of a water delivery system of a pumped storage power station. Background Art

[0002] In order to respond to the grid regulation needs, pumped storage power stations (hereinafter referred to as pumped storage power stations) need to frequently experience transient processes such as unit start-up and shutdown and operating condition conversion. The high-pressure pipelines of pumped storage power stations not only have higher internal water pressure than conventional power stations, but also the pressure pipelines are subject to higher dynamic water pressure due to the frequent unit operating condition conversion. In this process, the water supply system of the power station may produce a significant increase in water pressure and a sharp change in flow, which may lead to accidents such as pipeline rupture. At present, there are more studies on the pressure changes and speed changes of the water supply system during load shedding, but less attention has been paid to the influence of transient hydraulic instability on the strength changes of the pressure steel pipe. In order to ensure safety during operation, it is necessary to monitor the strength changes and cumulative damage of the pressure steel pipes of pumped storage power stations.

[0003] At present, the monitoring and analysis of the pressure steel pipes of pumped storage power stations cannot fully meet the on-site needs. There are mainly the following limitations: First, the existing monitoring methods do not have the monitoring and analysis function of the pressure steel pipe stress. Second, the transient analysis in the design stage only verifies the dangerous working conditions, and does not fully consider the cumulative damage to the structure caused by the transient process under various long-term changing working conditions on site. Summary of the invention

[0004] In view of this, the present invention provides a method, device and equipment for monitoring the pressure steel pipe of the water delivery system of a pumped storage power station to solve the problem of lack of monitoring of the pressure steel pipe of the pumped storage power station in the prior art.

[0005] In a first aspect, the present invention provides a method for monitoring penstocks in a water delivery system of a pumped-storage power station, the method comprising: based on the operating data of the pumped-storage power station, using a pre-constructed transient simulation analysis model to simulate and calculate all transient operating conditions of the power station to obtain pressure data of the penstock; calculating the stress on the penstock based on the pressure data; using the operating data and stress to train a preset network model to obtain a stress prediction model; inputting the real-time operating data of the pumped-storage power station into the stress prediction model to predict stress data at various positions of the penstock; when the relationship between the collected stress data at the preset position of the penstock and the predicted stress data meets a preset condition, based on the predicted stress data, using the linear cumulative damage theory and the rain flow counting method to determine the damage data of the penstock; and monitoring the penstock according to the damage data and the predicted stress data.

[0006] The method for monitoring the pressure steel pipe of the water delivery system of a pumped storage power station provided by the embodiment of the present invention obtains the operation data of the pumped storage power station, performs simulation analysis and calculation based on a pre-built transient simulation analysis model, obtains pressure data, obtains stress data based on the pressure data, and uses the stress data and operation data to train and construct a stress prediction model, uses the stress data predicted by the stress prediction model, and determines the damage data of the pressure steel pipe based on the linear cumulative damage theory and the rain flow counting method, so as to monitor each position of the pressure steel pipe. Therefore, the method provides a basis for on-site staff to more accurately grasp the actual operation status of the power station pressure steel pipe.

[0007] In an optional embodiment, the method also includes: when the relationship between the collected stress data of a preset position of the pressure steel pipe and the predicted stress data does not meet the preset conditions, using a pre-built transient simulation analysis model to re-simulate the current operating conditions of the power station to obtain new pressure data of the pressure steel pipe; re-training the stress prediction model based on the new stress calculated based on the new pressure data of the pressure steel pipe to obtain a new stress prediction model.

[0008] In this embodiment, when the predicted stress data and the collected stress data do not meet the preset conditions, the model training is performed again to ensure the accuracy of the stress data in the stress prediction model, thereby further improving the accuracy of monitoring.

[0009] In an optional embodiment, based on the predicted stress data, the damage data of the pressure steel pipe is determined using the linear cumulative damage theory and the rain flow counting method, including: based on the predicted stress data, using the rain flow counting method to statistically calculate the stress spectrum of the pressure steel pipe; according to the linear cumulative damage theory, combining the stress spectrum and the fatigue curve to determine the total damage of the pressure steel pipe; according to the stress spectrum and the fatigue curve, determine the fatigue life at each stress level; and calculate the remaining safe service life of the pressure steel pipe based on the total damage.

[0010] In this embodiment, the rain flow counting method is used to count the stress spectrum of the pressure steel pipe; according to the linear cumulative damage theory, the total damage of the pressure steel pipe, that is, the cumulative damage, is calculated in combination with the stress spectrum, providing a scientific basis for the commissioning, safe and stable operation and maintenance of the pumped storage power station.

[0011] In an optional embodiment, the pressure steel pipe is monitored based on damage data and predicted stress data, including: comparing the maximum stress in the predicted stress data with an alarm threshold, and obtaining an alarm signal when the maximum stress exceeds the alarm threshold, and the alarm threshold is a preset multiple of the yield strength of the steel; comparing the total damage in the damage data with a preset damage threshold, and obtaining a fatigue detection signal when the total damage exceeds the preset damage threshold.

[0012] In this embodiment, the operating status of the pressure steel pipe in the pumped storage power station is monitored through stress warning and damage warning, thereby ensuring the safety and stability of the pumped storage power station.

[0013] In an optional embodiment, the transient simulation analysis model is pre-constructed in the following manner: a group of partial differential equations is established for the water body running in the pressurized pipeline of the pumped storage power station based on the conservation of mass and conservation of motion; a transient simulation analysis model is established based on the group of partial differential equations and the hydraulic components passing water between the upper and lower reservoirs.

[0014] In this embodiment, a transient simulation analysis model is constructed by combining a group of partial differential equations established by combining mass conservation and motion conservation and hydraulic components, thereby providing a basis for pressure analysis of a pumped storage power station.

[0015] In an optional embodiment, the method further includes: obtaining operating data corresponding to a preset working condition; inputting the operating data into a stress prediction model to obtain the stress of the preset working condition; and analyzing the preset working condition based on the stress of the preset working condition.

[0016] In this embodiment, the constructed stress prediction model can also realize off-line prediction of stress, thereby facilitating off-line analysis of different working conditions.

[0017] In a second aspect, the present invention provides a device for monitoring penstocks in a water delivery system of a pumped-storage power station, the device comprising: a simulation module, for simulating and calculating all transient operating conditions of the power station based on the operating data of the pumped-storage power station using a pre-built transient simulation analysis model to obtain pressure data of the penstock; a stress calculation module, for calculating the stress on the penstock based on the pressure data; a model training module, for training a preset network model using operating data and stress to obtain a stress prediction model; a prediction module, for inputting the real-time operating data of the pumped-storage power station into the stress prediction model to predict stress data at various positions of the penstock; a damage determination module, for determining the damage data of the penstock based on the predicted stress data using a linear cumulative damage theory and a rain flow counting method when the relationship between the collected stress data at a preset position of the penstock and the predicted stress data meets a preset condition; and a monitoring module, for monitoring the penstock based on the damage data and the predicted stress data.

[0018] In a third aspect, the present invention provides a computer device, comprising: a memory and a processor, the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the method for monitoring pressure steel pipes of a water transmission system of a pumped-storage power station according to the first aspect or any corresponding embodiment thereof by executing the computer instructions.

[0019] In a fourth 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 monitoring pressure steel pipes in a water transfer system of a pumped-storage power station according to the first aspect or any corresponding embodiment thereof. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0021] Figure 1 1 is a flow chart of a method for monitoring a pressure steel pipe of a water delivery system of a pumped storage power station according to an embodiment of the present invention;

[0022] Figure 2 It is a flow chart of another method for monitoring the pressure steel pipe of the water delivery system of a pumped storage power station according to an embodiment of the present invention;

[0023] Figure 3 is a structural block diagram of a device for monitoring a pressure steel pipe of a water delivery system of a pumped storage power station according to an embodiment of the present invention;

[0024] Figure 4 It is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0025] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the 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 creative work are within the scope of protection of the present invention.

[0026] According to an embodiment of the present invention, an embodiment of a method for monitoring pressure steel pipes in a water delivery system 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.

[0027] In this embodiment, a method for monitoring the pressure steel pipe of the water delivery system of a pumped storage power station is provided, which can be used for electronic devices such as computers, mobile phones, tablet computers, etc. Figure 1FIG. 1 is a flow chart of a method for monitoring a pressure steel pipe of a water delivery system of a pumped storage power station according to an embodiment of the present invention. Figure 1 As shown, the process includes the following steps:

[0028] Step S101, based on the operation data of the pumped storage power station, a pre-built transient simulation analysis model is used to simulate and calculate all transient conditions of the power station to obtain the pressure data of the penstock. The operation data may include the operation parameters of the pumped storage power station at historical moments. For example, the upstream water level , downstream water level , guide vane opening y, unit speed n, flow rate Q, etc. The operating parameters can be obtained from the monitoring system of the pumped storage power station through the branch line communication method, wherein the pumped storage power station uses the electric energy during the low power load to pump water to the upper reservoir, and then releases water to the lower reservoir for power generation during the peak power load period. At the same time, there are also multiple hydraulic components between the upper reservoir and the lower reservoir. Therefore, at present, multiple monitoring systems are set up at multiple locations for the pumped storage power station to obtain the operating data of each location. Therefore, the monitoring data of multiple monitoring systems can be obtained through the branch line communication method, that is, the data of multiple monitoring systems are sent separately, which effectively avoids interference and confusion. At the same time, the branch line can also improve the communication efficiency and reliability of the equipment and shorten the data transmission time.

[0029] The transient simulation analysis model can be pre-built using transient simulation software in related technologies. The specific construction method can be implemented by referring to related technologies and will not be described in detail here. , downstream water level , guide vane opening y, unit speed n and flow rate Q are input into the pre-built transient simulation analysis model for simulation analysis and calculation. At the same time, in order to improve the accuracy of the simulation analysis, basic parameters such as water wave velocity and roughness can also be determined according to the pipeline material type, and these basic parameters are also input into the pre-built transient simulation analysis model.

[0030] Among them, when performing simulation calculations, all transient operating conditions of the power station can be simulated and calculated so that the stress prediction model constructed subsequently can predict the stress of all operating conditions. The transient operating conditions of the power station include transient operating conditions such as power generation startup, power generation shutdown, pumping startup, and pumping shutdown. Through the simulation calculation of the transient simulation analysis model, the pressure data of each position of the pressure steel pipe under various transient conditions can be obtained. The pressure data obtained by simulation calculation and the corresponding operation data can be saved in the Transcond database.

[0031] Step S102, calculating the stress of the penstock based on the pressure data. Specifically, the pressure data calculated by simulation analysis includes the water pressure in the penstock, and the stress of the penstock can be calculated based on the pressure. For example, when the pressure data is the water pressure in the end of the penstock, the calculated pressure is the stress in the end of the penstock, i.e., the radial compressive stress, which can be understood as the stress caused in the pipe wall by the water pressure in the end of the penstock.

[0032] The radial compressive stress can be calculated using the following formula:

[0033]

[0034] in: is the radial compressive stress, P is the internal water pressure calculated in transient state, D is the pipe diameter, Represents the pipe wall thickness. For example, the diameter of a power station's pressure pipe is 5m, and the pipe wall thickness is 70mm. The maximum water pressure value during the transition process is 8.05MPa, so the stress on the pipe at this time is =287.5Mpa.

[0035] In addition to the radial compressive stress at the end of the penstock, the stress at other positions of the penstock can also be calculated through the pressure data at other positions of the penstock in the pressure data, thereby obtaining the stress data at various positions of the penstock.

[0036] Step S103, using the operation data and stress to train the preset network model to obtain a stress prediction model. Specifically, in order to predict the stress at each position of the pressure steel pipe, this embodiment uses the operation data stored in the database and the stress data at each position as training data to train the preset network model to obtain a stress prediction model. The stress prediction module can predict stress based on relevant operation data.

[0037] Specifically, the preset network model can be a neural network or a machine learning regression prediction convolutional network. After determining the adopted network model, the operating parameters and corresponding radial compressive stress stored in the database can be used to train the model, such as using the upstream water level , downstream water level , guide vane opening y, unit speed n, flow rate Q and radial compressive stress Constitute the training data, then based on the training data, the model can be expressed as , that is, use the operating parameters to predict stress. In the training process, let:

[0038]

[0039]

[0040] Find:

[0041] ,

[0042] This gives the parameters in the model w and b.

[0043] Step S104, input the real-time operation data of the pumped storage power station into the stress prediction model, and predict the stress data of each position of the pressure steel pipe. Specifically, since the stress prediction model is predicted by the operation data and the stress data of each position, the real-time operation data of the pumped storage power station is input into the stress prediction model, and the stress data of each position of the pressure steel pipe can be obtained.

[0044] Step S105, when the relationship between the collected stress data of a preset position of the pressure steel pipe and the predicted stress data meets the preset conditions, the damage data of the pressure steel pipe is determined based on the predicted stress data by using the linear cumulative damage theory and the rain flow counting method; specifically, the collected stress data may be the stress data of a certain position of the pressure steel pipe, which may be obtained by a sensor or other means, and the collected stress data is compared with the predicted stress data of the position. When the relationship between the two meets the preset conditions, it indicates that the predicted stress data is available, and therefore the damage data of the pressure steel pipe may be determined by using the linear cumulative damage theory and the rain flow counting method according to the predicted stress data of each position.

[0045] Step S106, monitoring the penstock according to the damage data and the predicted stress data. Specifically, during real-time monitoring, it can be determined whether to overhaul or replace the penstock by analyzing the damage data and the stress data at each position of the penstock.

[0046] The method for monitoring the pressure steel pipe of the water delivery system of a pumped storage power station provided by the embodiment of the present invention obtains the operation data of the pumped storage power station, performs simulation analysis and calculation based on a pre-built transient simulation analysis model, obtains pressure data, obtains stress data based on the pressure data, and uses the stress data and operation data to train and construct a stress prediction model, uses the stress data predicted by the stress prediction model, and determines the damage data of the pressure steel pipe based on the linear cumulative damage theory and the rain flow counting method, so as to monitor each position of the pressure steel pipe. Therefore, the method provides a basis for on-site staff to more accurately grasp the actual operation status of the power station pressure steel pipe.

[0047] In this embodiment, a method for monitoring the pressure steel pipe of a water delivery system of a pumped storage power station is provided, and the process includes the following steps:

[0048] Step S201: Based on the operation data of the pumped storage power station, a pre-built transient simulation analysis model is used to simulate and calculate all transient conditions of the power station to obtain the pressure data of the penstock. Figure 1 Step S101 of the illustrated embodiment will not be described in detail here.

[0049] Step S202, calculate the stress of the pressure pipe based on the pressure data. Figure 1 Step S102 of the illustrated embodiment will not be described in detail here.

[0050] Step S203, using the operation data and stress training preset network model to obtain a stress prediction model; see Figure 1 Step S103 of the illustrated embodiment will not be described in detail here.

[0051] Step S204: Input the real-time operation data of the pumped storage power station into the stress prediction model to predict the stress data of each position of the pressure steel pipe. Figure 1 Step S104 of the illustrated embodiment will not be described in detail here.

[0052] Step S205: When the relationship between the collected stress data of the preset position of the penstock and the predicted stress data meets the preset condition, the damage data of the penstock is determined by using the linear cumulative damage theory and the rain flow counting method based on the predicted stress data; see Figure 1 Step S105 of the illustrated embodiment will not be described in detail here.

[0053] Step S206: monitor the pressure steel pipe according to the damage data and the predicted stress data. Figure 1 Step S106 of the illustrated embodiment will not be described in detail here.

[0054] Step S207, when the relationship between the collected stress data of the preset position of the pressure steel pipe and the predicted stress data does not meet the preset conditions, the pre-built transient simulation analysis model is used to re-simulate the current operating conditions of the power station to obtain new pressure data of the pressure steel pipe; the stress prediction model is re-trained based on the new stress calculated based on the new pressure data of the pressure steel pipe to obtain a new stress prediction model.

[0055] Specifically, when the relationship between the collected stress data of a certain position of the pressure steel pipe and the predicted stress data of the same position does not meet the preset conditions, such as the difference between the two stress data is greater than the preset value, it means that the stress prediction result for the current working condition of the pumped storage power station is inaccurate. At this time, the operating data of the current working condition can be re-input into the pre-built transient simulation analysis model for simulation to obtain new pressure data, and then the stress data and operating data calculated by the new pressure data are used to retrain the stress prediction model, that is, the stress prediction model is calibrated, such as using the current working condition (y, n, Q, , ) Calibrate the parameters in the stress prediction model and save the calibrated model in the stress database Transcond.

[0056]

[0057] Step S208, obtaining operating data corresponding to a preset working condition; inputting the operating data into a stress prediction model to obtain the stress of the preset working condition; and analyzing the preset working condition based on the stress of the preset working condition.

[0058] Specifically, the stress prediction model can also be used to realize offline prediction of stress. For example, for certain working conditions, it is uncertain whether the stress generated during the operation of the working condition will damage the pressure steel pipe. In this case, the operating data corresponding to the working condition can be input into the stress prediction model to obtain the stress data corresponding to the working condition. Then, the working condition can be analyzed based on the stress data.

[0059] In this embodiment, a method for monitoring a pressure steel pipe of a water delivery system of a pumped storage power station is provided, and the method comprises the following steps:

[0060] Step S301, based on the operation data of the pumped storage power station, a pre-built transient simulation analysis model is used to simulate and calculate all transient operating conditions of the power station to obtain pressure data of the penstock.

[0061] Specifically, the transient simulation analysis model is constructed in the following way:

[0062] Step S2021, based on the conservation of mass and the conservation of motion, a group of partial differential equations is established for the running water body in the pressurized pipeline of the pumped storage power station; specifically, when it is necessary to monitor a pumped storage power station, a transient simulation analysis model can be pre-established for the power station so as to perform transient simulation analysis calculations on the power station. When establishing a transient simulation analysis model, a group of partial differential equations can be established for the power station to be monitored based on the conservation of mass and the conservation of motion of the moving water body in the pressurized pipeline that changes with time, wherein the conservation of mass is used to describe the conservation of the mass of the water body, and the conservation of momentum is used to describe the conservation of the momentum of the water body. The group of partial differential equations established based on the conservation of mass and the conservation of momentum can describe the movement law of the water body. Therefore, after the transient simulation analysis model is established based on the group of partial differential equations, the model can be solved to obtain various properties and parameters of the water flow.

[0063] Step S2022, establish a transient simulation analysis model based on the partial differential equations and the hydraulic components passing water between the upper and lower reservoirs. Wherein, when establishing the transient simulation analysis model, in addition to using the partial differential equations, it is also necessary to add all the hydraulic components passing water between the upper and lower reservoirs. In this embodiment, the hydraulic components specifically include the upper reservoir, the upstream gate well, the water diversion tunnel, the pressure regulating well, the water diversion pressure steel pipe, the unit, the tailwater pressure steel pipe, the gate well, the lower reservoir, the guide vane closing law, etc. It should be noted that the model can be constructed based on the transient analysis software in the relevant technology, and the specific construction process can be implemented with reference to the relevant technology, which will not be repeated here.

[0064] Step S302, calculate the stress of the pressure steel pipe based on the pressure data; see Figure 1 Step S102 of the illustrated embodiment will not be described in detail here.

[0065] Step S303, using the operation data and stress training preset network model to obtain a stress prediction model; see Figure 1 Step S103 of the illustrated embodiment will not be described in detail here.

[0066] Step S304: Input the real-time operation data of the pumped storage power station into the stress prediction model to predict the stress data of each position of the pressure steel pipe. Figure 1 Step S104 of the illustrated embodiment will not be described in detail here.

[0067] Step S305, when the relationship between the collected stress data of the preset position of the pressure steel pipe and the predicted stress data meets the preset conditions, the damage data of the pressure steel pipe is determined based on the predicted stress data using the linear cumulative damage theory and the rain flow counting method.

[0068] Specifically, the above step S305 includes:

[0069] Step S3051, based on the predicted stress data, the stress spectrum of the pressure steel pipe is statistically analyzed by the rain flow counting method; specifically, the stress data of each position of the pressure steel pipe predicted by the stress prediction model can be used to calculate the stress spectrum of the pressure steel pipe by the rain flow counting method. The rain flow counting method is a statistical method that rotates the strain-time history data record by 90 degrees and counts the data record in cycles, so that the radial compressive stress stored in the database in chronological order can be counted by the rain flow counting method to obtain the corresponding stress spectrum.

[0070] Step S3052, determining the total damage of the pressure steel pipe according to the linear cumulative damage theory combined with the stress spectrum and fatigue curve.

[0071] Step S3053, determining the fatigue life at each stress level according to the stress spectrum and the fatigue curve.

[0072] Step S3054, calculating the remaining safe service life of the pressure steel pipe according to the total damage.

[0073] Among them, Miner's linear cumulative damage theory means that fatigue damage can be linearly accumulated under cyclic stress, and each cyclic stress is independent of each other. When the accumulated damage reaches a certain value, the equipment fails. The fatigue curve is the SN curve. The SN curve uses the fatigue strength of the standard specimen of the material as the ordinate and the logarithm of the fatigue life as the abscissa to represent the relationship between the fatigue strength and fatigue life of the standard specimen under certain cyclic characteristics.

[0074] According to the stress spectrum, each stress level and cycle number can be obtained, and by comparing the SN curve, the fatigue life corresponding to the cycle number can be obtained, that is, the fatigue life under each stress level. The number of fatigue failure cycles under the action of Damage caused by Therefore, the total damage caused by m different stress cycles can be expressed as follows:

[0075]

[0076] Where: D is the total damage degree under load; m is different stress levels; is the number of cycles at each stress level; is the fatigue life under each stress level. The damage degree of the pressure steel pipe under the field stress-time history can be obtained from the above formula.

[0077] Therefore, according to the above analysis, the fatigue life corresponding to each stress level can be expressed as , and the remaining safe service life corresponding to the total damage can be combined with Determine by taking the inverse of the total damage.

[0078] Step S306: monitoring the pressure steel pipe according to the damage data and the predicted stress data.

[0079] Specifically, the above step S306 includes:

[0080] Step S3061, compare the maximum stress in the predicted stress data with the alarm threshold. When the maximum stress exceeds the alarm threshold, an alarm signal is obtained. The alarm threshold is a preset multiple of the steel yield strength. Specifically, the alarm threshold can be two-thirds of the steel yield strength. For example, if the pressure steel pipe strength is 800MPa and the yield strength is 690MPa, the maximum stress that the pressure steel pipe bears in engineering use should be less than 2 / 3 of the yield strength, that is, the allowable stress of 800Mpa high-strength steel should not exceed 460Mpa. =460Mpa, in actual operation Mpa outputs alarm information: the pressure steel pipe stress exceeds the maximum stress.

[0081] Step S3062, compare the total damage in the damage data with the preset damage threshold, and obtain a fatigue detection signal when the total damage exceeds the preset damage threshold. Specifically, the preset damage threshold can be determined according to actual conditions, for example, it can be 0.8, and when the total damage reaches 0.8, an alarm is issued to remind the staff to pay attention to the fatigue damage of the pressure steel pipe and to conduct on-site inspection.

[0082] As a specific application example of the embodiment of the present invention, Figure 2 As shown in the figure, the monitoring method of the pressure steel pipe of the water delivery system of the pumped storage power station can be realized by the following process:

[0083] 1. Establish a transient simulation analysis model of the hydraulic system based on power station parameters.

[0084] The pumped storage power station operation data, i.e., power station parameters, including the upstream water level of the power station in real time are obtained from the pumped storage power station monitoring system through branch line communication , downstream water level , guide vane opening y, unit speed n, flow rate Q, output power P. For the selected power station, a partial differential equation group is established based on the mass conservation and motion conservation of the moving water body in the pressurized pipeline over time, and a transient simulation analysis model of the hydraulic system is established: the model includes all hydraulic components that pass water between the upper and lower reservoirs. Specifically, it includes the upper reservoir, upstream gate well, water diversion tunnel, surge well, water diversion pressure pipe, unit, tailwater pressure pipe, gate well, lower reservoir, guide vane closing law, etc.

[0085] 2. Calculate the transient process penstock water pressure for all power station operating conditions.

[0086] According to the actual operation data input in step 1, the required boundary conditions include the upstream water level , downstream water level , guide vane opening y, unit speed n, and flow rate Q, etc. In addition, it is necessary to determine basic parameters such as water wave velocity and roughness according to the type of pipeline material (penstock or concrete pipe). Real-time transient calculation is performed by manually or automatically triggering the program to obtain the penstock water pressure calculated by the simulation method, including the maximum water pressure at the end.

[0087] 3. Calculate the stress based on the water pressure of the penstock.

[0088] Since the end of the penstock is subject to the greatest internal water pressure, the maximum internal water pressure at the end of the penstock calculated by transient simulation in step 2 is Calculate the stress at the end of the penstock, and add the calculated result of the stress, i.e. radial compressive stress, to the transient database Transcond of the corresponding working condition. The stress caused by the water pressure in the penstock, i.e. radial compressive stress, is calculated using the following formula:

[0089]

[0090] in: is the radial compressive stress, P is the internal water pressure calculated in transient state, D is the pipe diameter, Represents the pipe wall thickness. For example, the diameter of a power station's pressure pipe is 5m, and the pipe wall thickness is 70mm. The maximum water pressure value during the transition process is 8.05MPa, so the stress on the pipe at this time is =287.5Mpa.

[0091] In addition to the above-mentioned radial compressive stress, the stress data at various positions of the pressure pipe can also be obtained based on the pressure data obtained by simulation.

[0092] 4. Use intelligent algorithms such as machine learning to build a stress prediction model between transient conditions and stress.

[0093] Retrieve the operation data and pressure data in the transient calculation database Transcond to build a training set such as (y, n, Q, , , ), train the neural network or machine learning regression prediction convolution network, and obtain a prediction model for calculating the stress of the pressure steel pipe using the working condition parameters in the transient calculation database. This process can be achieved by the following formula:

[0094] ;

[0095] make:

[0096]

[0097]

[0098] Find:

[0099] ,

[0100] 5. Collect on-site working condition data and obtain the stress at each position of the pressure steel pipe based on the stress prediction model.

[0101] Specifically, the collected current operation data of the pumped storage power station is input into the stress prediction model to obtain the stress data of each position of the pressure steel pipe.

[0102] 6. Determine whether the error between the predicted stress data and the actual stress data collected at a certain location is within a preset range, such as 10%. When the error between the two exceeds 10%, add the current working condition to the training working condition, re-simulate and calculate, and re-train the stress prediction model.

[0103] 7. When the error is within the preset range, the stress spectrum is statistically analyzed based on the rain flow counting method in combination with the SN curve of the penstock material, and the cumulative damage and remaining safe service life of the penstock are calculated.

[0104] Specifically, according to Miner's linear cumulative damage theory, the stress spectrum of the pressure steel pipe is statistically analyzed by the rain flow counting method. The number of fatigue failure cycles under the action of Damage caused by express.

[0105] According to the stress spectrum, the stress levels and cycle times are obtained, and the damage caused by m different stress cycles can be expressed by the following formula:

[0106]

[0107] Where: D is the total damage degree under load, i.e., cumulative loss; m is different stress levels; is the number of cycles at each stress level; is the fatigue life under each stress level. The above formula can be used to obtain the damage degree of the pressure steel pipe under the field stress-time history. At the same time, the corresponding remaining safe service life can also be determined based on the accumulated damage.

[0108] 8. Make stress alarm according to the maximum stress and cumulative loss, and use stress prediction model for offline prediction.

[0109] First, the maximum stress exceeding warning threshold of the pressure steel pipe is determined based on the predicted stress, and the maximum tensile stress of the pressure steel pipe in the project is It should be less than 2 / 3 of the yield strength of the steel material. Therefore, 2 / 3 of the yield strength of the steel pipe is used as the alarm threshold in this system. ,like Then an alarm is issued.

[0110] For example, if the strength of the pressure steel pipe is 800MPa, the yield strength is 690MPa. According to the maximum allowable stress of the pressure steel pipe in engineering use, it should be less than 2 / 3 of the yield strength, that is, the allowable stress of 800Mpa high-strength steel should not exceed 460Mpa. =460Mpa, in actual operation Mpa, then the alarm information is output that the pressure steel pipe stress exceeds the maximum allowable stress.

[0111] Afterwards, monitoring can also be carried out based on the cumulative damage value. For example, when the damage degree D reaches 0.8, an alarm will be issued to pay attention to fatigue damage of the pressure steel pipe, and on-site inspection should be carried out during maintenance.

[0112] For the constructed stress prediction model, for example, the working conditions are manually input offline according to the pressure steel pipe stress prediction model, the stress on the pressure steel pipe is predicted and the result is displayed, thereby realizing the offline stress prediction function.

[0113] In this embodiment, a device for monitoring the pressure steel pipe of the water delivery system of a pumped storage power station is also provided, and the device is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0114] This embodiment provides a monitoring device for the pressure steel pipe of the water delivery system of a pumped storage power station. Figure 3 As shown, including:

[0115] The simulation module 31 is used to simulate and calculate all transient operating conditions of the power station based on the operation data of the pumped storage power station using a pre-built transient simulation analysis model to obtain the pressure data of the penstock;

[0116] A stress calculation module 32, used for calculating the stress of the pressure pipe based on the pressure data;

[0117] A model training module 33 is used to train a preset network model using operation data and stress to obtain a stress prediction model;

[0118] The prediction module 34 is used to input the real-time operation data of the pumped storage power station into the stress prediction model to predict the stress data of each position of the pressure steel pipe;

[0119] A damage determination module 35 is used to determine the damage data of the pressure steel pipe by using the linear cumulative damage theory and the rain flow counting method based on the predicted stress data when the relationship between the collected stress data of the preset position of the pressure steel pipe and the predicted stress data meets the preset conditions;

[0120] The monitoring module 36 is used to monitor the pressure steel pipe according to the damage data and the predicted stress data.

[0121] In an optional embodiment, the device also includes: a retraining module, which is specifically used to use a pre-built transient simulation analysis model to re-simulate and calculate the current operating conditions of the power station when the relationship between the collected stress data at a preset position of the pressure steel pipe and the predicted stress data does not meet the preset conditions to obtain new pressure data of the pressure steel pipe; and retrain the stress prediction model based on the new stress calculated based on the new pressure data of the pressure steel pipe to obtain a new stress prediction model.

[0122] In an optional embodiment, the damage determination module is specifically used to: based on the predicted stress data, use the rain flow counting method to statistically calculate the stress spectrum of the pressure steel pipe; according to the linear cumulative damage theory, combine the stress spectrum and the fatigue curve to determine the total damage of the pressure steel pipe; determine the fatigue life at each stress level based on the stress spectrum and the fatigue curve; calculate the remaining safe service life of the pressure steel pipe based on the total damage.

[0123] In an optional embodiment, the monitoring module is specifically used to: compare the maximum stress in the predicted stress data with the alarm threshold, and when the maximum stress exceeds the alarm threshold, obtain an alarm signal, and the alarm threshold is a preset multiple of the yield strength of the steel; compare the total damage in the damage data with the preset damage threshold, and when the total damage exceeds the preset damage threshold, obtain a fatigue detection signal.

[0124] In an optional embodiment, the transient simulation analysis model is pre-constructed in the following manner: a group of partial differential equations is established for the water body running in the pressurized pipeline of the pumped storage power station based on the conservation of mass and conservation of motion; a transient simulation analysis model is established based on the group of partial differential equations and the hydraulic components passing water between the upper and lower reservoirs.

[0125] In an optional embodiment, the device also includes: an offline prediction module, which is specifically used to obtain operating data corresponding to a preset working condition; input the operating data into a stress prediction model to obtain the stress of the preset working condition; and analyze the preset working condition based on the stress of the preset working condition.

[0126] The further functional description of each of the above modules is the same as that of the above corresponding embodiments and will not be repeated here.

[0127] The embodiment of the present invention also provides a computer device having the above Figure 3 The shown device is a pressure steel pipe monitoring device for the water delivery system of a pumped storage power station.

[0128] See also Figure 4 , Figure 4 is a schematic diagram of the structure of a computer device provided by an optional embodiment of the present invention, such as Figure 4 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 are connected to each other using different buses for communication, 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 the 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 and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 4 A processor 10 is taken as an example.

[0129] 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 a dedicated 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.

[0130] The memory 20 stores instructions executable by at least one processor 10, so that at least one processor 10 executes the method shown in the above embodiment.

[0131] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created by the use of a computer device based on the presentation of a small program landing page, 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 arranged 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.

[0132] 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.

[0133] The computer device further comprises a communication interface 30 for the computer device to communicate with other devices or a communication network.

[0134] The embodiment of the present invention also provides a computer-readable storage medium. The method according to the embodiment of the present invention can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through a network download, 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 hard disk, etc.; further, the storage medium can also include a combination of the above types of memories. 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.

[0135] A part 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 existence of the computer program instruction in a computer-readable medium includes, but is not limited to, a source file, an executable file, an installation package file, etc., and 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 accessible to the computer.

[0136] Although the embodiments of the present invention have been described in conjunction with 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, and such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A method for monitoring penstocks in a water delivery system of a pumped storage power station, characterized in that: The method comprises: Based on the operation data of the pumped storage power station, a pre-built transient simulation analysis model is used to simulate and calculate all transient conditions of the power station to obtain the pressure data of the penstock; Calculating the stress of the pressure steel pipe based on the pressure data; The operation data and the preset network model of stress training are used to obtain a stress prediction model; Inputting the real-time operation data of the pumped storage power station into the stress prediction model to predict the stress data of each position of the pressure steel pipe; When the relationship between the collected stress data at the preset position of the penstock and the predicted stress data meets the preset conditions, the damage data of the penstock is determined by using the linear cumulative damage theory and the rain flow counting method based on the predicted stress data; Monitoring the pressure steel pipe according to the damage data and the predicted stress data; When the relationship between the collected stress data of the preset position of the penstock and the predicted stress data does not meet the preset conditions, the pre-built transient simulation analysis model is used to re-simulate the current working conditions of the power station to obtain new pressure data of the penstock; The stress prediction model is retrained based on the new stress calculated based on the pressure data of the new penstock to obtain a new stress prediction model.

2. The method according to claim 1, characterized in that Based on the predicted stress data, the linear cumulative damage theory and rain flow counting method are used to determine the damage data of the pressure steel pipe, including: Based on the predicted stress data, the stress spectrum of the pressure steel pipe is statistically analyzed using the rain flow counting method; According to the linear cumulative damage theory, the total damage of the pressure steel pipe is determined in combination with the stress spectrum and the fatigue curve; Determine the fatigue life at each stress level according to the stress spectrum and the fatigue curve; The remaining safe service life of the pressure steel pipe is calculated based on the total damage.

3. The method according to claim 2, characterized in that The penstock is monitored according to the damage data and the predicted stress data, including: Comparing the maximum stress in the predicted stress data with an alarm threshold, and obtaining an alarm signal when the maximum stress exceeds the alarm threshold, wherein the alarm threshold is a preset multiple of the yield strength of the steel; The total damage in the damage data is compared with a preset damage threshold, and when the total damage exceeds the preset damage threshold, a fatigue detection signal is obtained.

4. The method according to claim 1, characterized in that: The transient simulation analysis model is pre-built in the following way: Based on the conservation of mass and motion, a group of partial differential equations is established for the water body running in the pressurized pipeline of the pumped storage power station; A transient simulation analysis model is established based on the partial differential equations and the hydraulic components passing water between the upper and lower reservoirs.

5. The method according to claim 1, characterized in that The method further comprises: Obtain the operating data corresponding to the preset working conditions; Based on the operation data input into the stress prediction model, the stress of the preset working condition is obtained; The preset working condition is analyzed based on the stress of the preset working condition.

6. A monitoring device for pressure steel pipes in a water delivery system of a pumped storage power station, characterized in that: The device comprises: The simulation module is used to simulate and calculate all transient conditions of the power station based on the operating data of the pumped storage power station using a pre-built transient simulation analysis model to obtain the pressure data of the penstock; A stress calculation module, used for calculating the stress of the pressure pipe based on the pressure data; A model training module, used to use the operating data and stress training preset network model to obtain a stress prediction model; A prediction module, used to input the real-time operation data of the pumped storage power station into the stress prediction model, and predict the stress data of each position of the pressure steel pipe; A damage determination module is used to determine the damage data of the pressure steel pipe by using the linear cumulative damage theory and the rain flow counting method based on the predicted stress data when the relationship between the collected stress data at the preset position of the pressure steel pipe and the predicted stress data meets the preset conditions; A monitoring module, used for monitoring the pressure steel pipe according to the damage data and the predicted stress data; The device also includes: a retraining module, which is specifically used to use a pre-built transient simulation analysis model to re-simulate and calculate the current working conditions of the power station when the relationship between the collected stress data at the preset position of the pressure steel pipe and the predicted stress data does not meet the preset conditions, so as to obtain new pressure data of the pressure steel pipe; and re-train the stress prediction model based on the new stress calculated based on the new pressure data of the pressure steel pipe to obtain a new stress prediction model.

7. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the method for monitoring the pressure steel pipe of the water transmission system of a pumped storage power station according to any one of claims 1 to 5 by executing the computer instructions.

8. 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 monitoring the pressure steel pipe of the water delivery system of a pumped-storage power station according to any one of claims 1 to 5.

9. A computer program product, characterized in that It comprises computer instructions, and the computer instructions are used to enable a computer to execute the method for monitoring the pressure steel pipe of the water delivery system of a pumped storage power station according to any one of claims 1 to 5.