Water turbine speed regulation management method and system

Abstract

Embodiments of the present application provide a method and system for managing hydraulic turbine speed regulation. The method includes: obtaining current data of physical entities of a reservoir-type power plant; pre-processing the data of the physical entities of the reservoir-type power plant; obtaining data of physical entities of a turbine speed adjustment; obtaining a corresponding historical dataset of turbine speed adjustment based on the data of the physical entities of the turbine speed adjustment; pre-processing the historical dataset to obtain pre-processed data of the physical entities of the turbine speed adjustment; comparing the pre-processed data of the physical entities of the turbine speed adjustment with preset data to obtain a deviation rate; determining whether the deviation rate is equal to or greater than a preset deviation rate threshold; if the deviation rate is equal to or greater than the preset deviation rate threshold, generating correction information and correcting the data of the physical entities of the turbine speed adjustment based on the correction information; if the deviation rate is less than the preset deviation rate threshold, constructing a three-dimensional dynamic model using the pre-processed data of the physical entities of the turbine speed adjustment; and dynamically adjusting the speed of the turbine based on the three-dimensional dynamic model, thereby improving the accuracy of the turbine speed adjustment process.

Description

[Technical Field]

[0001] The present application relates to the field of water turbine speed regulation, and more particularly to a method and system for managing water turbine speed regulation. [Background technology]

[0002] Reservoir-type power plants are an environmentally friendly way to generate electricity by using a water turbine to convert the impulse force of water flow into power to supply a generator. As a key device in a reservoir-type power plant, the water turbine plays a vital role in the normal operation of the power plant. The turbine speed regulation system is one of the most important auxiliary control systems in a hydroelectric power plant unit. It includes a governor, a speed regulation cabinet, and a hydraulic device, and its operating quality directly affects the safety and stable operation of the hydroelectric power plant. Reducing the failure rate of the turbine speed regulation system is the most effective way to improve the operating reliability of the unit.

[0003] The safety management of the turbine speed regulation system in existing reservoir-type power plants is limited to data alone, and monitoring of the turbine speed regulation system is achieved through data analysis of real-time data. However, this management method is not intuitive and insufficient for overall control of the turbine speed regulation system. Furthermore, the existing safety management system cannot provide reference advice for the control of the turbine speed regulation system, has weak functionality, and no longer meets existing demands. Effective technical solutions to the above problems are urgently needed. Summary of the Invention [Problem to be solved by the invention]

[0004] The embodiments of the present application aim to provide a method and system for managing hydro turbine speed regulation, which constructs a three-dimensional dynamic model by creating data on the physical entities of hydro turbine speed regulation, realizes target management for hydro turbine speed regulation, allows operators to easily understand the overall layout and operating conditions of the hydro turbine in a reservoir-type power plant, and improves the technology for accurately controlling the hydro turbine speed regulation process. [Means for solving the problem]

[0005] An embodiment of the present application further provides a method for controlling water turbine speed regulation, comprising: Obtaining current reservoir power plant physical entity data, preprocessing the reservoir power plant physical entity data, and obtaining turbine speed adjustment physical entity data; According to the data of the physical entity of the turbine speed adjustment, obtain a corresponding historical dataset of the turbine speed adjustment, preprocess the historical dataset, and obtain preprocessed data of the physical entity of the turbine speed adjustment; Comparing the preprocessed turbine speed adjustment physical entity data with the preset data to obtain a deviation rate; determining whether the deviation rate is greater than or equal to a preset deviation rate threshold; If the deviation rate is equal to or greater than the preset deviation rate threshold, generating correction information and correcting the data of the physical entity of the turbine speed adjustment based on the correction information; If the deviation rate is less than a preset threshold, constructing a three-dimensional dynamic model by the preprocessed data of the physical entity of the turbine speed regulation; and dynamically adjusting speed for the turbine based on the three-dimensional dynamic model.

[0006] Optionally, in the method for managing turbine speed regulation described in the embodiments of the present application, obtaining a corresponding historical dataset of turbine speed regulation based on the data of the physical entity of turbine speed regulation, pre-processing the historical dataset, and obtaining the pre-processed data of the physical entity of turbine speed regulation can specifically include: Obtaining a historical data set of turbine speed adjustment, calculating a difference between the historical data set of turbine speed adjustment and an average value, and obtaining a data variance value; Analyzing the data dispersion value and a preset dispersion threshold to obtain a data dispersion degree; determining whether the data dispersion is greater than a preset dispersion threshold; If the dispersion degree is greater than a preset threshold, deleting the corresponding historical data of the turbine speed adjustment; generating processed turbine speed regulation physical entity data if the dispersion is equal to or less than the preset dispersion threshold.

[0007] Optionally, in the turbine speed regulation management method described in the embodiments of the present application, the preprocessed turbine speed regulation physical entity data includes turbine governor model number, installation location, quantity, rotation speed, power, current, voltage, opening, tank pressure, tank temperature, motor valve status, frequency swing, PID parameters, PLC control data, regulation mode, operation schedule, inspection schedule, control method, and fault data.

[0008] Optionally, in the method for managing the water turbine speed regulation described in the embodiments of the present application, when the deviation rate is less than a preset deviation rate threshold, constructing a three-dimensional dynamic model by the preprocessed data of the physical entities of the water turbine speed regulation, and dynamically adjusting the speed of the water turbine based on the three-dimensional dynamic model, specifically, Obtaining data of a physical entity of a turbine speed adjustment; extracting feature values ​​based on data of the physical entity of the turbine speed adjustment; Comparing the feature value with a preset feature threshold to calculate a feature similarity; determining whether the feature similarity is greater than or equal to a preset similarity threshold; If the similarity is equal to or greater than a preset threshold, determining that the data of the corresponding physical entity of the water turbine speed adjustment is static constant data; If the similarity is less than a preset threshold, determining that the data of the corresponding physical entity of the water turbine speed adjustment is dynamic variable data; and constructing a three-dimensional dynamic model based on the static constant data and the dynamic variable data.

[0009] As an option, in the water turbine speed regulation management method described in the embodiments of the present application, after constructing a three-dimensional dynamic model based on the static constant data and the dynamic variable data, further comprising: obtaining static constant data and dynamic variable data and generating a static validation set and a dynamic validation set; Inputting the static validation set into a 3D dynamic model to perform parameter training and obtain a static loss value of the 3D dynamic model; generating first feedback information when the static loss value is greater than a first loss threshold, and performing parameter adjustment on the three-dimensional dynamic model based on the first feedback information; inputting the dynamic validation set into a three-dimensional dynamic model to perform parameter training and obtain a dynamic loss value of the three-dimensional dynamic model; If the dynamic loss value is greater than a second loss threshold, generating second feedback information, and performing parameter adjustment on the three-dimensional dynamic model based on the second feedback information.

[0010] As an option, in the method for controlling the speed of a water turbine according to the embodiment of the present application, dynamically adjusting the speed of the water turbine based on the three-dimensional dynamic model may specifically include: Setting a plurality of water turbine detection points and acquiring current rotation speed information of each water turbine detection point; Comparing the current rotation speed information of the detection point with the preset rotation speed information to obtain a rotation speed deviation rate; Determining whether the rotation speed deviation rate is equal to or greater than a preset rotation speed deviation threshold value; If the rotation speed deviation is equal to or greater than the preset rotation speed deviation threshold, generating water turbine fault information, inputting a preset fault prediction model based on the water turbine fault information, and obtaining water turbine fault prediction information; If the rotation speed deviation is less than the preset threshold value, it is determined that the rotation of the water turbine is normal, and the real-time rotation speed data of each water turbine detection point is collectively saved.

[0011] In a second aspect, an embodiment of the present application provides a water turbine speed adjustment management system including a memory in which a program relating to a water turbine speed adjustment management method is stored and a processor, and when the program relating to the water turbine speed adjustment management method is executed by the processor, Obtaining current data of physical entities of the reservoir power plant, preprocessing the data of physical entities of the reservoir power plant, and obtaining data of physical entities of turbine speed adjustment; According to the data of the physical entity of the turbine speed adjustment, obtaining a corresponding historical dataset of the turbine speed adjustment, pre-processing the historical dataset, and obtaining pre-processed data of the physical entity of the turbine speed adjustment; comparing the preprocessed turbine speed adjustment physical entity data with the preset data to obtain a deviation rate; determining whether the deviation rate is greater than or equal to a preset deviation rate threshold; generating correction information when the deviation rate is equal to or greater than the preset deviation rate threshold, and correcting data of the physical entity of the turbine speed adjustment based on the correction information; If the deviation rate is less than the preset threshold, constructing a three-dimensional dynamic model by the preprocessed data of the physical entity of the turbine speed regulation; and dynamically adjusting speed for the turbine based on the three-dimensional dynamic model.

[0012] Optionally, in the turbine speed regulation management system described in the embodiments of the present application, the steps of obtaining a corresponding historical dataset of turbine speed regulation based on the data of the physical entity of the turbine speed regulation, pre-processing the historical dataset, and obtaining the pre-processed data of the physical entity of the turbine speed regulation can be specifically: obtaining a historical data set of turbine speed adjustments, calculating a difference between the historical data set of turbine speed adjustments and an average value, and obtaining a data variance value; analytically comparing the data dispersion value with a preset dispersion threshold to obtain a data dispersion degree; determining whether the data dispersion is greater than a preset dispersion threshold; If the dispersion degree is greater than the preset threshold, deleting the corresponding historical data of the turbine speed adjustment; If the degree of dispersion is equal to or less than the preset threshold, generating processed turbine speed regulation physical entity data.

[0013] Optionally, in the turbine speed regulation management system described in the embodiments of the present application, the preprocessed turbine speed regulation physical entity data includes turbine governor model number, installation location, quantity, rotation speed, power, current, voltage, opening, tank pressure, tank temperature, motor valve status, frequency swing, PID parameters, PLC control data, regulation mode, operation schedule, inspection schedule, control method, and fault data.

[0014] Optionally, in the water turbine speed regulation management system described in the embodiments of the present application, when the deviation rate is less than a preset deviation rate threshold, the step of constructing a three-dimensional dynamic model by the preprocessed data of the physical entities of water turbine speed regulation, and dynamically adjusting the speed of the water turbine based on the three-dimensional dynamic model can specifically include: obtaining data of a physical entity of the turbine speed adjustment, and extracting feature values ​​based on the data of the physical entity of the turbine speed adjustment; Comparing the feature values ​​with a preset feature threshold to calculate feature similarity; determining whether the feature similarity is greater than or equal to a preset similarity threshold; If the similarity is equal to or greater than a preset threshold, determining that the data of the corresponding physical entity of the water turbine speed adjustment is static constant data; If the similarity is less than a preset threshold, determining that the data of the corresponding physical entity of the water turbine speed adjustment is dynamic variable data; and constructing a three-dimensional dynamic model based on the static constant data and the dynamic variable data.

[0015] In view of the above, the embodiments of the present application provide a method and system for managing turbine speed regulation, which comprises: obtaining current data on the physical entities of a reservoir-type power plant; pre-processing the data on the physical entities of the reservoir-type power plant to obtain data on the physical entities of the turbine speed regulation; obtaining a corresponding historical dataset on the turbine speed regulation based on the data on the physical entities of the turbine speed regulation; pre-processing the historical dataset to obtain the pre-processed data on the physical entities of the turbine speed regulation; comparing the pre-processed data on the physical entities of the turbine speed regulation with preset data to obtain a deviation rate; determining whether the deviation rate is equal to or greater than a preset deviation rate threshold; if it is equal to or greater than the preset deviation rate threshold, generating correction information; correcting the data on the physical entities of the turbine speed regulation based on the correction information; if it is less than the preset deviation rate threshold, constructing a three-dimensional dynamic model using the pre-processed data on the physical entities of the turbine speed regulation. Constructing a three-dimensional dynamic model for managing turbine speed regulation enables targeted management of turbine speed regulation, allowing operators to easily grasp the overall layout and operating status of the turbines in the reservoir-type power plant and improving precise control over the turbine speed regulation process.

[0016] Other features and advantages of the present invention will be set forth in the following specification, and will be apparent from the description, may be inferred from the description, or may be obvious from the practice of the embodiments of the present invention. The objectives and other advantages of the present invention will be realized and obtained by the structure particularly pointed out in the written description, claims, and drawings.

[0017] In order to more clearly explain the technical solutions according to the embodiments of the present invention, the drawings necessary for describing the embodiments will be briefly described below. The drawings described below are merely illustrative of some embodiments of the present invention and do not limit the scope of the claims. It is clear that those skilled in the art can obtain drawings of other embodiments based on these drawings without any creative efforts. [Brief explanation of the drawings]

[0018] [Figure 1]FIG. 1 is a flowchart of a method for controlling the speed regulation of a water turbine provided by an embodiment of the present application. [Figure 2] FIG. 2 is a flowchart of the pre-processing of data of physical entities of turbine speed regulation in the turbine speed regulation management method provided by the embodiment of the present application. [Figure 3] FIG. 3 is a flowchart of constructing a three-dimensional dynamic model based on static constant data and dynamic variable data in the turbine speed regulation management method provided by the embodiment of the present application. [Figure 4] FIG. 4 is a schematic diagram showing the configuration of a water turbine speed adjustment management system provided by an embodiment of the present application. DETAILED DESCRIPTION OF THE INVENTION

[0019] Hereinafter, technical solutions in the embodiments of the present application will be described clearly and completely in conjunction with the drawings in the embodiments of the present application. However, it should be understood that the described embodiments are only a portion of the embodiments of the present application, and not all of the embodiments. Generally, the components of the embodiments of the present application described and illustrated in the drawings herein can be arranged and designed in different configurations. Therefore, the detailed description of the embodiments of the present application provided in the drawings merely represents selected embodiments of the present application and does not limit the scope of the claims of the present application. Other embodiments that can be obtained by a person skilled in the art based on the embodiments of the present application without requiring creative efforts also fall within the scope of protection of the present application.

[0020] It should be noted that in the following drawings, similar symbols and letters indicate similar elements, so that once an element is defined in one drawing, it does not need to be further defined and described in subsequent drawings. Also, in the description of this application, terms such as "first," "second," etc. are used merely for distinction, but should not be understood as expressing or implying relative importance.

[0021] Referring to FIG. 1, which is a flowchart of a turbine speed regulation control method according to some embodiments of the present application, the turbine speed regulation control method is used in an end device, Step S101: obtain current physical entity data of the reservoir-type power plant, perform preprocessing on the physical entity data of the reservoir-type power plant, and obtain physical entity data of the turbine speed adjustment; Step S102: obtaining a corresponding historical dataset of turbine speed adjustment based on the data of the physical entity of turbine speed adjustment, pre-processing the historical dataset, and obtaining pre-processed data of the physical entity of turbine speed adjustment; Step S103: comparing the pre-processed data of the physical entity of the turbine speed adjustment with the preset data to obtain a deviation rate; Step S104: determining whether the deviation rate is equal to or greater than a preset deviation rate threshold; If the deviation rate is equal to or greater than the preset threshold, generating correction information and correcting the data of the physical entity of the turbine speed adjustment based on the correction information; if the deviation rate is less than the preset threshold, constructing a three-dimensional dynamic model using the preprocessed data of the physical entity of the turbine speed adjustment and dynamically adjusting the speed of the turbine based on the three-dimensional dynamic model.

[0022] What we would like to explain is that by constructing a three-dimensional dynamic model, the speed of the turbine can be dynamically adjusted in real time, and if an error occurs in the turbine speed adjustment process, it can be corrected in real time, thereby ensuring the accuracy of the speed adjustment.

[0023] Referring to FIG. 2, which is a flowchart of the pre-processing of the physical entity data of the turbine speed regulation in the turbine speed regulation management method in some embodiments of the present application, according to the embodiments of the present invention, the steps of obtaining the corresponding historical data set of the turbine speed regulation based on the physical entity data of the turbine speed regulation, performing pre-processing on the historical data set, and obtaining the pre-processed physical entity data of the turbine speed regulation specifically include: Step S201: acquiring a historical data set of turbine speed adjustment, calculating a difference between the historical data set of turbine speed adjustment and an average value, and acquiring a data variance value; Step S202: analytically comparing the data dispersion value with a preset dispersion threshold to obtain a data dispersion degree; Step S203: determining whether the data dispersion is greater than a preset dispersion threshold; If the dispersion degree is greater than the preset threshold value, delete the corresponding turbine speed adjustment history data in step S204; If the dispersion degree is equal to or less than the preset threshold value, generating processed data of the physical entity of the turbine speed adjustment (S205).

[0024] What we would like to explain is that by performing decentralization processing on the data of the physical entity of turbine speed adjustment, data with high dispersion in the data set can be eliminated, and when constructing a three-dimensional dynamic model, the optimized data set can improve the accuracy of the model parameters and ensure the results of the model analysis.

[0025] According to an embodiment of the present application, the preprocessed data of the physical entity of the turbine speed regulation includes the turbine governor's part number, installation location, quantity, rotation speed, power, current, voltage, opening, tank pressure, tank temperature, motor valve status, frequency swing, PID parameters, PLC control data, regulation mode, operation schedule, inspection schedule, control method, and fault data.

[0026] What we want to explain is that by obtaining data on the physical entities of multi-dimensional turbine speed regulation, the speed regulation results can be made more reference-worthy, and when training the model, the trained model can output more accurate results.

[0027] Referring to FIG. 3, which is a flowchart of constructing a three-dimensional dynamic model based on static constant data and dynamic variable data in a method for managing hydraulic turbine speed regulation in some embodiments of the present application, according to an embodiment of the present invention, when the deviation rate is less than a preset deviation rate threshold, the steps of constructing a three-dimensional dynamic model based on the preprocessed data of the physical entities of hydraulic turbine speed regulation and dynamically adjusting the speed of the hydraulic turbine based on the three-dimensional dynamic model specifically include: Step S301: obtaining data of a physical entity of turbine speed regulation, and extracting feature values ​​based on the data of the physical entity of turbine speed regulation; Step S302: comparing the feature value with a preset feature threshold to calculate feature similarity; S303: determining whether the feature similarity is equal to or greater than a preset similarity threshold; Step S304: if the similarity is equal to or greater than the preset threshold, determine that the data of the corresponding physical entity of the turbine speed regulation is static constant data, and if the similarity is less than the preset threshold, determine that the data of the corresponding physical entity of the turbine speed regulation is dynamic variable data; and step S305 of constructing a three-dimensional dynamic model based on the static constant data and the dynamic variable data.

[0028] What we would like to explain is that by extracting features from the data of the physical entity of the turbine speed adjustment and separating the static data from the dynamic data, the separated dynamic data and static data can be used to construct a three-dimensional dynamic model for different cases, and the accuracy of the constructed three-dimensional dynamic model will be higher.

[0029] According to an embodiment of the present invention, after the step of constructing a three-dimensional dynamic model based on the static constant data and the dynamic variable data, obtaining static constant data and dynamic variable data and generating a static validation set and a dynamic validation set; Inputting the static validation set into a 3D dynamic model to perform parameter training and obtain a static loss value of the 3D dynamic model; generating first feedback information when the static loss value is greater than a first loss threshold, and performing parameter adjustment on the three-dimensional dynamic model based on the first feedback information; inputting the dynamic validation set into a three-dimensional dynamic model to perform parameter training and obtain a dynamic loss value of the three-dimensional dynamic model; If the dynamic loss value is greater than a second loss threshold, generating second feedback information, and performing parameter adjustment on the three-dimensional dynamic model based on the second feedback information.

[0030] What we would like to explain is that by extracting static and dynamic data from the data of the physical entity of turbine speed adjustment, it is possible to train a three-dimensional dynamic model (dynamic and static) with different data forms, thereby adjusting the model parameters with different data forms and improving the accuracy of the three-dimensional dynamic model.

[0031] According to an embodiment of the present invention, the step of dynamically adjusting the speed of the water turbine based on the three-dimensional dynamic model specifically includes: Setting a plurality of water turbine detection points and acquiring current rotation speed information of each water turbine detection point; Comparing the current rotation speed information of the detection point with the preset rotation speed information to obtain a rotation speed deviation rate; Determining whether the rotation speed deviation rate is equal to or greater than a preset rotation speed deviation threshold; If the rotation speed deviation is equal to or greater than the preset rotation speed deviation threshold, generating water turbine fault information, inputting a preset fault prediction model based on the water turbine fault information, and obtaining water turbine fault prediction information; If the rotation speed deviation is less than the preset threshold value, it is determined that the rotation of the water turbine is normal, and the real-time rotation speed data of each water turbine detection point is collectively saved.

[0032] What we would like to explain is that by setting the turbine detection point, it is possible to compare parameters at different positions on the shaft end when the turbine rotates, and the detection points at different positions can be used to determine the position deviation and rotational vibration information when the turbine rotates, so that defects and failures can be analyzed while the turbine is rotating, and as a result, it is possible to determine the failure of the turbine and provide the optimal solution to the failure.

[0033] According to an embodiment of the present invention, Obtaining a historical data set of the turbine governor and constructing a speed regulation control prediction model using the ROPN modeling method; A speed regulation fault diagnosis model is constructed using a deep learning algorithm, and a three-dimensional dynamic model of turbine speed regulation safety management is obtained after the prediction model is added; The method further includes receiving a three-dimensional dynamic model for turbine speed adjustment safety management after the addition of the predictive model transmitted from the predictive model construction unit, and performing safety management for the turbine speed adjustment parameters using the three-dimensional dynamic model for turbine speed adjustment safety management after the addition of the predictive model.

[0034] Specifically, the preprocessed governor real-time data is received, and the preprocessed governor real-time data is input into the speed regulation control prediction model and the speed regulation fault diagnosis model of the turbine speed regulation safety management three-dimensional dynamic model after the prediction model is added, and the corresponding speed regulation control method and speed regulation fault diagnosis result are obtained.

[0035] Referring to Fig. 4, which is a schematic diagram showing the configuration of a water turbine speed regulation management system in some embodiments of the present application, in a second aspect, the embodiments of the present application provide a water turbine speed regulation management system including a memory 41 in which a program relating to the water turbine speed regulation management method is stored, and a processor 42. When the program relating to the water turbine speed regulation management method is executed by the processor, Obtaining current data of physical entities of the reservoir power plant, preprocessing the data of physical entities of the reservoir power plant, and obtaining data of physical entities of turbine speed adjustment; According to the data of the physical entity of the turbine speed adjustment, obtaining a corresponding historical dataset of the turbine speed adjustment, pre-processing the historical dataset, and obtaining pre-processed data of the physical entity of the turbine speed adjustment; comparing the preprocessed turbine speed adjustment physical entity data with the preset data to obtain a deviation rate; determining whether the deviation rate is greater than or equal to a preset deviation rate threshold; generating correction information when the deviation rate is equal to or greater than the preset deviation rate threshold, and correcting data of the physical entity of the turbine speed adjustment based on the correction information; If the deviation rate is less than the preset threshold, constructing a three-dimensional dynamic model by the preprocessed data of the physical entities of the turbine speed regulation; and dynamically adjusting speed for the turbine based on the three-dimensional dynamic model.

[0036] What we would like to explain is that by constructing a three-dimensional dynamic model, the speed of the turbine can be dynamically adjusted in real time, and if an error occurs in the turbine speed adjustment process, it can be corrected in real time, thereby ensuring the accuracy of the speed adjustment.

[0037] According to an embodiment of the present invention, the steps of obtaining a corresponding historical dataset of turbine speed regulation based on the data of the physical entity of turbine speed regulation, pre-processing the historical dataset, and obtaining the pre-processed data of the physical entity of turbine speed regulation specifically include: Obtaining a historical data set of turbine speed adjustment, calculating a difference between the historical data set of turbine speed adjustment and an average value, and obtaining a data variance value; Analyzing the data dispersion value and a preset dispersion threshold to obtain a data dispersion degree; Determining whether the data dispersion is greater than a preset dispersion threshold; If the dispersion degree is greater than a preset threshold, deleting the corresponding historical data of the turbine speed adjustment; generating processed turbine speed regulation physical entity data if the dispersion is equal to or less than the preset dispersion threshold.

[0038] What we would like to explain is that by performing decentralization processing on the data of the physical entity of turbine speed adjustment, data with high dispersion in the data set can be eliminated, and when constructing a three-dimensional dynamic model, the optimized data set can improve the accuracy of the model parameters and ensure the results of the model analysis.

[0039] According to an embodiment of the present invention, the preprocessed data of the physical entity of the turbine speed regulation includes the turbine governor's part number, installation location, quantity, rotation speed, power, current, voltage, opening, tank pressure, tank temperature, motor valve status, frequency swing, PID parameters, PLC control data, regulation mode, operation schedule, inspection schedule, control method, and fault data.

[0040] What we want to explain is that by obtaining data on the physical entities of multi-dimensional turbine speed regulation, the speed regulation results can be made more reference-worthy, and when training the model, the trained model can output more accurate results.

[0041] According to an embodiment of the present invention, when the deviation rate is less than the preset deviation rate threshold, constructing a three-dimensional dynamic model according to the preprocessed data of the physical entity of the turbine speed adjustment, and dynamically adjusting the speed of the turbine according to the three-dimensional dynamic model, specifically: Obtaining data of a physical entity of a turbine speed adjustment; extracting feature values ​​based on data of the physical entity of the turbine speed adjustment; Comparing the feature value with a preset feature threshold to calculate a feature similarity; determining whether the feature similarity is greater than or equal to a preset similarity threshold; If the similarity is equal to or greater than a preset threshold, determining that the data of the corresponding physical entity of the water turbine speed adjustment is static constant data; If the characteristic threshold is less than the preset threshold, determining that the data of the corresponding turbine speed adjustment physical entity is dynamic variable data; and constructing a three-dimensional dynamic model based on the static constant data and the dynamic variable data.

[0042] What we would like to explain is that by extracting features from the data of the physical entity of the turbine speed adjustment and separating the static data from the dynamic data, the separated dynamic data and static data can be used to construct a three-dimensional dynamic model for different cases, and the accuracy of the constructed three-dimensional dynamic model will be higher.

[0043] According to an embodiment of the present invention, after the step of constructing a three-dimensional dynamic model based on the static constant data and the dynamic variable data, obtaining static constant data and dynamic variable data and generating a static validation set and a dynamic validation set; Inputting the static validation set into a 3D dynamic model to perform parameter training and obtain a static loss value of the 3D dynamic model; generating first feedback information when the static loss value is greater than a first loss threshold, and performing parameter adjustment on the three-dimensional dynamic model based on the first feedback information; inputting the dynamic validation set into a three-dimensional dynamic model to perform parameter training and obtain a dynamic loss value of the three-dimensional dynamic model; The method further includes generating second feedback information if the dynamic loss value is greater than a second loss threshold, and performing parameter adjustment on the three-dimensional dynamic model based on the second feedback information.

[0044] What we would like to explain is that by extracting static and dynamic data from the data of the physical entity of turbine speed adjustment, it is possible to train a three-dimensional dynamic model (dynamic and static) with different data forms, thereby adjusting the model parameters with different data forms and improving the accuracy of the three-dimensional dynamic model.

[0045] According to an embodiment of the present invention, the step of dynamically adjusting the speed of the water turbine based on the three-dimensional dynamic model specifically includes: Setting a plurality of water turbine detection points and acquiring current rotation speed information of each water turbine detection point; Comparing the current rotation speed information of the detection point with the preset rotation speed information to obtain a rotation speed deviation rate; Determining whether the rotation speed deviation rate is equal to or greater than a preset rotation speed deviation threshold; If the rotation speed deviation is equal to or greater than the preset rotation speed deviation threshold, generating water turbine fault information, inputting a preset fault prediction model based on the water turbine fault information, and obtaining water turbine fault prediction information; If the rotation speed deviation is less than the preset threshold value, it is determined that the rotation of the water turbine is normal, and the real-time rotation speed data of each water turbine detection point is collectively saved.

[0046] What we would like to explain is that by setting the turbine detection point, it is possible to compare parameters at different positions on the shaft end when the turbine rotates, and the detection points at different positions can be used to determine the position deviation and rotational vibration information when the turbine rotates, so that defects and failures can be analyzed while the turbine is rotating, and as a result, it is possible to determine the failure of the turbine and provide the optimal solution to the failure.

[0047] According to an embodiment of the present invention, Obtaining a historical data set of the turbine governor and constructing a speed regulation control prediction model using the ROPN modeling method; A speed regulation fault diagnosis model is constructed using a deep learning algorithm, and a three-dimensional dynamic model of turbine speed regulation safety management is obtained after the prediction model is added; The method further includes receiving a three-dimensional dynamic model for turbine speed adjustment safety management after the addition of the predictive model transmitted from the predictive model construction unit, and performing safety management for the turbine speed adjustment parameters using the three-dimensional dynamic model for turbine speed adjustment safety management after the addition of the predictive model.

[0048] Specifically, the preprocessed governor real-time data is received, and the preprocessed governor real-time data is input into the speed regulation control prediction model and the speed regulation fault diagnosis model of the turbine speed regulation safety management three-dimensional dynamic model after the prediction model is added, and the corresponding speed regulation control method and speed regulation fault diagnosis result are obtained.

[0049] The disclosed turbine speed regulation management method and system includes: acquiring current data on the physical entities of a reservoir-type power plant, pre-processing the data on the physical entities of the reservoir-type power plant, acquiring data on the physical entities of the turbine speed regulation, acquiring corresponding historical datasets on the turbine speed regulation based on the data on the physical entities of the turbine speed regulation, pre-processing the historical datasets, acquiring the pre-processed data on the physical entities of the turbine speed regulation, comparing the pre-processed data on the physical entities of the turbine speed regulation with preset data to obtain a deviation rate, determining whether the deviation rate is equal to or greater than a preset deviation rate threshold, generating correction information if the deviation rate is equal to or greater than the preset deviation rate threshold, correcting the data on the physical entities of the turbine speed regulation based on the correction information, and constructing a three-dimensional dynamic model using the pre-processed data on the physical entities of the turbine speed regulation if the deviation rate is less than the preset deviation rate threshold. The construction of the three-dimensional dynamic model for turbine speed regulation safety management realizes targeted management of turbine speed regulation, allowing operators to easily grasp the overall layout and operating status of the turbines in the reservoir-type power plant and improving precise control of the turbine speed regulation process.

[0050] It should be understood that the disclosed devices and methods in some embodiments provided in the present application may be implemented in other forms. The device embodiments described above are merely schematic, and for example, the division of units is merely a logical functional division. In actual implementation, the division may be implemented in other ways. For example, multiple units or components may be combined or integrated into another system, or some functions may be omitted or not implemented. Furthermore, the coupling or direct coupling or communication connection between the illustrated or described components may be an indirect coupling or communication connection via some interface, device, or unit, which may be electrical, mechanical, or other form.

[0051] The units described above as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, located in one location or distributed across multiple network units, and some or all of these units may be selected according to actual needs to achieve the objectives of the present embodiment.

[0052] Furthermore, the functional units in each embodiment of the present invention may all be integrated into one processing unit, each unit may exist separately as one unit, or two or more units may be integrated into one unit. The integrated units may be realized in the form of hardware, or in the form of a hardware and software functional unit.

[0053] Those skilled in the art should understand that all or part of the steps for realizing the method embodiments can be performed by hardware associated with program instructions, and the program is stored in a readable storage medium, and when the program is executed, it performs the steps comprising the method embodiments, and the storage medium is a medium capable of storing program code, such as a mobile storage device, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or a compact disk.

[0054] Alternatively, the integrated components of the present invention may be implemented in the form of software functional modules and stored in a readable storage medium when sold or used as an independent product. Based on this understanding, the technical aspects of the embodiments of the present invention, either essentially or in part making a contribution over the prior art, are embodied in the form of a software product. The software product is stored in a storage medium and includes some instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to execute all or part of the methods described in each embodiment of the present invention. The storage medium includes media capable of storing program code, such as a mobile storage device, a ROM, a RAM, a magnetic disk, and a compact disk.

Claims

1. A water turbine speed adjustment management method, comprising: Obtaining current reservoir power plant physical entity data, preprocessing the reservoir power plant physical entity data, and obtaining turbine speed adjustment physical entity data; According to the data of the physical entity of the turbine speed adjustment, obtain a corresponding historical dataset of the turbine speed adjustment, preprocess the historical dataset, and obtain preprocessed data of the physical entity of the turbine speed adjustment; Comparing the preprocessed turbine speed adjustment physical entity data with the preset data to obtain a deviation rate; determining whether the deviation rate is greater than or equal to a preset deviation rate threshold; If the deviation rate is equal to or greater than the preset deviation rate threshold, generating correction information and correcting the data of the physical entity of the turbine speed adjustment based on the correction information; If the deviation rate is less than a preset threshold, constructing a three-dimensional dynamic model by the preprocessed data of the physical entity of the turbine speed regulation; and dynamically adjusting speed for the turbine based on the three-dimensional dynamic model.

2. Specifically, obtaining a corresponding historical dataset of turbine speed adjustment based on the data of the physical entity of the turbine speed adjustment, pre-processing the historical dataset, and obtaining pre-processed data of the physical entity of the turbine speed adjustment includes: Obtaining a historical data set of turbine speed adjustment, calculating a difference between the historical data set of turbine speed adjustment and an average value, and obtaining a data variance value; Analyzing the data dispersion value and a preset dispersion threshold to obtain a data dispersion degree; determining whether the data dispersion is greater than a preset dispersion threshold; If the variance value is greater than a preset threshold, deleting the corresponding turbine speed adjustment history data; and generating processed turbine speed regulation physical entity data if the dispersion is less than a preset dispersion threshold.

3. The method for managing hydraulic turbine speed regulation according to claim 2, characterized in that the preprocessed data of physical entities of hydraulic turbine speed regulation includes hydraulic turbine governor model number, installation location, quantity, rotation speed, power, current, voltage, opening, tank pressure, tank temperature, motor valve status, frequency swing, PID parameters, PLC control data, regulation mode, operation schedule, inspection schedule, control method, and fault data.

4. Specifically, when the deviation rate is less than a preset deviation rate threshold, constructing a three-dimensional dynamic model according to the preprocessed data of the physical entity of the water turbine speed adjustment, and dynamically adjusting the speed of the water turbine according to the three-dimensional dynamic model. Obtaining data of a physical entity of a turbine speed adjustment; extracting feature values ​​based on data of the physical entity of the turbine speed adjustment; Comparing the feature value with a preset feature threshold to calculate a feature similarity; determining whether the feature similarity is greater than or equal to a preset similarity threshold; If the similarity is equal to or greater than a preset threshold, determining that the data of the corresponding physical entity of the water turbine speed adjustment is static constant data; If the similarity is less than a preset threshold, determining that the data of the corresponding physical entity of the water turbine speed adjustment is dynamic variable data; 4. The method for controlling water turbine speed regulation according to claim 3, further comprising: constructing a three-dimensional dynamic model based on the static constant data and the dynamic variable data.

5. After constructing a three-dimensional dynamic model based on the static constant data and the dynamic variable data, obtaining static constant data and dynamic variable data to obtain a static validation set and a dynamic validation set; Inputting the static validation set into a 3D dynamic model to perform parameter training and obtain a static loss value of the 3D dynamic model; generating first feedback information when the static loss value is greater than a first loss threshold, and performing parameter adjustment on the three-dimensional dynamic model based on the first feedback information; inputting the dynamic validation set into a three-dimensional dynamic model to perform parameter training and obtain a dynamic loss value of the three-dimensional dynamic model; The method for managing hydraulic turbine speed regulation according to claim 4, further comprising: generating second feedback information when the dynamic loss value is greater than a second loss threshold; and adjusting parameters of the three-dimensional dynamic model based on the second feedback information.

6. Dynamically adjusting the speed of the water turbine based on the three-dimensional dynamic model specifically includes: Setting a plurality of water turbine detection points and acquiring current rotation speed information of each water turbine detection point; Comparing the current rotation speed information of the detection point with the preset rotation speed information to obtain a rotation speed deviation rate; Determining whether the rotation speed deviation rate is equal to or greater than a preset rotation speed deviation threshold value; If the rotation speed deviation is equal to or greater than the preset rotation speed deviation threshold, generating water turbine fault information, inputting a preset fault prediction model based on the water turbine fault information, and obtaining water turbine fault prediction information; If the rotation speed deviation is less than a preset threshold value, the rotation of the turbine is determined to be normal, and the real-time rotation speed data of each turbine detection point is collectively saved.

7. A water turbine speed adjustment management system including a memory and a processor in which a program relating to a water turbine speed adjustment management method is stored, and when the program relating to the water turbine speed adjustment management method is executed by the processor, Obtaining current data of physical entities of the reservoir power plant, preprocessing the data of physical entities of the reservoir power plant, and obtaining data of physical entities of turbine speed adjustment; According to the data of the physical entity of the turbine speed adjustment, obtaining a corresponding historical dataset of the turbine speed adjustment, pre-processing the historical dataset, and obtaining pre-processed data of the physical entity of the turbine speed adjustment; comparing the preprocessed turbine speed adjustment physical entity data with the preset data to obtain a deviation rate; determining whether the deviation rate is greater than or equal to a preset deviation rate threshold; generating correction information when the deviation rate is equal to or greater than the preset deviation rate threshold, and correcting data of the physical entity of the turbine speed adjustment based on the correction information; If the deviation rate is less than the preset threshold, constructing a three-dimensional dynamic model by the preprocessed data of the physical entities of the turbine speed regulation; and dynamically adjusting the speed of the turbine based on the three-dimensional dynamic model.

8. The steps of obtaining a corresponding historical dataset of turbine speed regulation based on the data of the physical entity of the turbine speed regulation, pre-processing the historical dataset, and obtaining the pre-processed data of the physical entity of the turbine speed regulation specifically include: obtaining a historical data set of turbine speed adjustments, calculating a difference between the historical data set of turbine speed adjustments and an average value, and obtaining a data variance value; analytically comparing the data dispersion value with a preset dispersion threshold to obtain a data dispersion degree; determining whether the data dispersion is greater than a preset dispersion threshold; If the dispersion degree is greater than the preset threshold, deleting the corresponding historical data of the turbine speed adjustment; and generating processed turbine speed regulation physical entity data if the dispersion is equal to or less than a preset dispersion threshold.

9. The turbine speed regulation management system according to claim 8, wherein the preprocessed data of the physical entities of the turbine speed regulation includes turbine governor part number, installation location, quantity, rotation speed, power, current, voltage, opening, tank pressure, tank temperature, motor valve status, frequency swing, PID parameters, PLC control data, regulation mode, operation schedule, inspection schedule, control method, and fault data.

10. When the deviation rate is less than the preset deviation rate threshold, the step of constructing a three-dimensional dynamic model according to the preprocessed data of the physical entity of the water turbine speed adjustment, and dynamically adjusting the speed of the water turbine according to the three-dimensional dynamic model, specifically includes: obtaining data of a physical entity of a turbine speed regulation; extracting feature values ​​based on data of the physical entities of the turbine speed regulation; Comparing the feature values ​​with a preset feature threshold to calculate feature similarity; determining whether the feature similarity is greater than or equal to a preset similarity threshold; If the similarity is equal to or greater than a preset threshold, determining that the data of the corresponding physical entity of the water turbine speed adjustment is static constant data; If the similarity is less than a preset threshold, determining that the data of the corresponding physical entity of the water turbine speed adjustment is dynamic variable data; and constructing a three-dimensional dynamic model based on the static constant data and the dynamic variable data.

Images