Water turbine speed regulation management method and system

Abstract

Embodiments of the present application provide a water turbine speed regulation management method and system. The method comprises: acquiring physical entity data of a current storage power station, and preprocessing the physical entity data of the storage power station to obtain water turbine speed regulation physical entity data; acquiring a corresponding water turbine speed regulation historical data set on the basis of the water turbine speed regulation physical entity data, and preprocessing the historical data set to obtain preprocessed water turbine speed regulation physical entity data; comparing the preprocessed water turbine speed regulation physical entity data with 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 greater than or equal to the preset deviation rate threshold, generating correction information, and correcting the water turbine speed regulation physical entity data on the basis of the correction information; and if the deviation rate is less than the preset deviation rate threshold, establishing a three-dimensional dynamic model by means of the preprocessed water turbine speed regulation physical entity data, and dynamically regulating the speed of a water turbine on the basis of the three-dimensional dynamic model. The accuracy of a water turbine speed regulation process is improved.

Description

A method and system for managing water turbine speed regulation Technical Field

[0001] The present application relates to the field of turbine speed regulation, and in particular, to a turbine speed regulation management method and system. Background Art

[0002] Pumped storage hydropower stations need to use turbines to convert the impact force of water flow into power to provide to generators. It is an environmentally friendly and clean way to obtain electricity. As an important equipment of pumped storage hydropower stations, turbines play a key role in the normal operation of pumped storage hydropower stations. The turbine speed control system is one of the very important auxiliary control systems of the hydro-generator set, including the speed governor, speed control cabinet and oil pressure device. The quality of its operation directly determines the safety and stable operation of the turbine unit. Reducing the failure rate of the turbine speed control system is the most effective means to improve the operational reliability of the unit.

[0003] The existing safety management of the turbine speed control system in the pumped storage hydropower station only stays at the data level. The turbine speed control system is monitored by analyzing real-time data. This management method is not intuitive enough and lacks overall control over the turbine speed control system. In addition, the existing safety management system cannot provide reference guidance for the control of the turbine speed control system. It has weak functionality and can no longer adapt to existing needs. In response to the above problems, effective technical solutions are urgently needed.

[0004] Summary of the Invention

[0005] The purpose of the embodiments of the present application is to provide a turbine speed regulation management method and system, which can achieve targeted management of turbine speed regulation by constructing a three-dimensional dynamic model based on the physical entity data of the turbine speed regulation, making it easier for staff to understand the overall layout and operating conditions of the turbines in the pumped storage hydropower station, and improving the technology for accurately controlling the turbine speed regulation process.

[0006] The present application also provides a method for managing turbine speed regulation, including:

[0007] Obtain the current physical entity data of the pumped storage hydropower station, pre-process the physical entity data of the pumped storage hydropower station, and obtain the physical entity data of the turbine speed regulation.

[0008] Acquire a corresponding turbine speed regulation historical data set according to the turbine speed regulation physical entity data; preprocess the historical data set to obtain preprocessed turbine speed regulation physical entity data;

[0009] Compare the pre-processed physical entity data of the turbine speed regulation with the preset data to obtain the deviation rate;

[0010] Determining whether the deviation rate is greater than or equal to a preset deviation rate threshold;

[0011] If it is greater than or equal to, then generate correction information, and correct the physical entity data of the turbine speed regulation according to the correction information;

[0012] If it is less than, a three-dimensional dynamic model is established by pre-processing the physical entity data of the turbine speed regulation;

[0013] The turbine is dynamically regulated based on the three-dimensional dynamic model.

[0014] Optionally, in the turbine speed regulation management method described in the embodiment of the present application, the step of obtaining a corresponding turbine speed regulation history data set based on the turbine speed regulation physical entity data and preprocessing the history data set to obtain preprocessed turbine speed regulation physical entity data is as follows:

[0015] Obtain a historical data set of turbine speed regulation, perform a difference calculation between the historical data set of turbine speed regulation and the average value, and obtain a discrete value of the data;

[0016] Analyze and compare the data discrete value with the preset discrete threshold to obtain the data discreteness;

[0017] Determining whether the data dispersion is greater than a preset dispersion threshold;

[0018] If it is greater than, the corresponding turbine speed regulation history data will be deleted;

[0019] If it is less than or equal to, the processed turbine speed regulation physical entity data is generated.

[0020] Optionally, in the turbine speed regulation management method described in the embodiment of the present application, the pre-processed turbine speed regulation physical entity data includes the model, installation location, quantity, speed, power, current, voltage, opening, oil tank pressure, oil tank temperature, electric valve status, frequency swing, PID parameters, PLC control data, adjustment mode, operation plan, maintenance plan, control scheme and fault data of the turbine speed governor.

[0021] Optionally, in the turbine speed regulation management method described in the embodiment of the present application, if is less than , a three-dimensional dynamic model is established by preprocessing the physical entity data of the turbine speed regulation, and the turbine is dynamically regulated according to the three-dimensional dynamic model, specifically:

[0022] Get the physical entity data of the turbine speed regulation,

[0023] Extract characteristic values ​​based on the physical entity data of the turbine speed regulation;

[0024] Compare the feature value with the preset feature threshold and calculate the feature similarity;

[0025] Determining whether the feature similarity is greater than or equal to a preset similarity threshold;

[0026] If it is greater than or equal to the preset similarity threshold, the corresponding turbine speed regulation physical entity data is determined to be static constant data;

[0027] If it is less than, the corresponding turbine speed regulation physical entity data is determined to be dynamic variable data;

[0028] Construct a three-dimensional dynamic model based on static constant data and dynamic variable data.

[0029] Optionally, in the turbine speed regulation management method described in the embodiment of the present application, after constructing the three-dimensional dynamic model according to the static constant data and the dynamic variable data, the method further includes:

[0030] Obtain static constant data and dynamic variable data to generate static verification sets and dynamic verification sets;

[0031] Input the static validation set into the 3D dynamic model for parameter training to obtain the static loss value of the 3D dynamic model;

[0032] When the static loss value is greater than a first loss threshold, first feedback information is generated, and parameters of the three-dimensional dynamic model are adjusted according to the first feedback information;

[0033] Input the dynamic verification set into the 3D dynamic model for parameter training to obtain the dynamic loss value of the 3D dynamic model;

[0034] When the dynamic loss value is greater than the second loss threshold, second feedback information is generated, and parameters of the three-dimensional dynamic model are adjusted according to the second feedback information.

[0035] Optionally, in the turbine speed regulation management method described in the embodiment of the present application, the dynamic speed regulation of the turbine according to the three-dimensional dynamic model is specifically:

[0036] Establish several turbine detection points and obtain the current speed information of each turbine detection point;

[0037] Compare the current speed information of the detection point with the preset speed information to obtain the speed deviation rate;

[0038] Determining whether the speed deviation rate is greater than or equal to a preset speed deviation threshold;

[0039] If it is greater than or equal to, turbine fault information is generated, and a preset fault prediction model is input according to the turbine fault information to obtain turbine fault prediction information;

[0040] If it is less than, it is determined that the turbine is rotating normally, and the real-time speed data of each turbine detection point is saved and summarized.

[0041] In a second aspect, an embodiment of the present application provides a turbine speed regulation management system, the system comprising: a memory and a processor, the memory comprising a program for a turbine speed regulation management method, the program for the turbine speed regulation management method being executed by the processor to implement the following steps:

[0042] Obtain the current physical entity data of the pumped storage hydropower station, pre-process the physical entity data of the pumped storage hydropower station, and obtain the physical entity data of the turbine speed regulation.

[0043] Acquire a corresponding turbine speed regulation historical data set according to the turbine speed regulation physical entity data; preprocess the historical data set to obtain preprocessed turbine speed regulation physical entity data;

[0044] Compare the pre-processed physical entity data of the turbine speed regulation with the preset data to obtain the deviation rate;

[0045] Determining whether the deviation rate is greater than or equal to a preset deviation rate threshold;

[0046] If it is greater than or equal to, then generate correction information, and correct the physical entity data of the turbine speed regulation according to the correction information;

[0047] If it is less than, a three-dimensional dynamic model is established by pre-processing the physical entity data of the turbine speed regulation;

[0048] The turbine is dynamically regulated based on the three-dimensional dynamic model.

[0049] Optionally, in the turbine speed regulation management system described in the embodiment of the present application, the step of obtaining a corresponding turbine speed regulation history data set based on the turbine speed regulation physical entity data and preprocessing the history data set to obtain preprocessed turbine speed regulation physical entity data is as follows:

[0050] Obtain a historical data set of turbine speed regulation, perform a difference calculation between the historical data set of turbine speed regulation and the average value, and obtain a discrete value of the data;

[0051] Analyze and compare the data discrete value with the preset discrete threshold to obtain the data discreteness;

[0052] Determining whether the data dispersion is greater than a preset dispersion threshold;

[0053] If it is greater than, the corresponding turbine speed regulation history data will be deleted;

[0054] If it is less than or equal to, the processed turbine speed regulation physical entity data is generated.

[0055] Optionally, in the turbine speed control management system described in the embodiment of the present application, the pre-processed turbine speed control physical entity data includes the model, installation location, quantity, speed, power, current, voltage, opening, oil tank pressure, oil tank temperature, electric valve status, frequency swing, PID parameters, PLC control data, adjustment mode, operation plan, maintenance plan, control scheme and fault data of the turbine speed governor.

[0056] Optionally, in the turbine speed regulation management system described in the embodiment of the present application, if is less than , a three-dimensional dynamic model is established by preprocessing the physical entity data of the turbine speed regulation, and the turbine is dynamically regulated according to the three-dimensional dynamic model, specifically:

[0057] Acquire physical entity data of the turbine speed regulation, and extract characteristic values ​​based on the physical entity data of the turbine speed regulation;

[0058] Compare the feature value with the preset feature threshold and calculate the feature similarity;

[0059] Determining whether the feature similarity is greater than or equal to a preset similarity threshold;

[0060] If it is greater than or equal to the preset similarity threshold, the corresponding turbine speed regulation physical entity data is determined to be static constant data;

[0061] If it is less than, the corresponding turbine speed regulation physical entity data is determined to be dynamic variable data;

[0062] Construct a three-dimensional dynamic model based on static constant data and dynamic variable data.

[0063] As can be seen from the above, the embodiment of the present application provides a turbine speed regulation management method and system, which obtains the physical entity data of the current pumped storage hydropower station, preprocesses the physical entity data of the pumped storage hydropower station, obtains turbine speed regulation physical entity data, and obtains the corresponding turbine speed regulation historical data set according to the turbine speed regulation physical entity data; preprocesses the historical data set to obtain preprocessed turbine speed regulation physical entity data; compares the preprocessed turbine speed regulation physical entity data with preset data to obtain a deviation rate; determines whether the deviation rate is greater than or equal to a preset deviation rate threshold; if greater than or equal to, generates correction information, and corrects the turbine speed regulation physical entity data according to the correction information; if less than, establishes a three-dimensional dynamic model through the preprocessed turbine speed regulation physical entity data; by constructing a three-dimensional dynamic model for full management of turbine speed regulation, targeted management of turbine speed regulation is achieved, which facilitates staff to understand the overall layout and operating conditions of the turbines of the pumped storage hydropower station, and improves the accurate control of the turbine speed regulation process.

[0064] Other features and advantages of the present application will be described in the following description, and the advantages of the present application can be inferred from the description or understood by practicing the embodiments of the present application. The objectives and other advantages of the present application can be achieved and obtained through the structures particularly pointed out in the written description, claims, and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments of the present application. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without creative work.

[0066] FIG1 is a flow chart of a turbine speed regulation management method provided by an embodiment of the present application;

[0067] FIG2 is a flow chart of the preprocessing of physical entity data of a turbine speed regulation method for a turbine speed regulation management method according to an embodiment of the present application;

[0068] FIG3 is a flow chart of constructing a three-dimensional dynamic model based on static constant data and dynamic variable data in a method for managing turbine speed regulation according to an embodiment of the present application;

[0069] FIG4 is a schematic structural diagram of a turbine speed regulation management system provided in an embodiment of the present application. DETAILED DESCRIPTION

[0070] The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. The components of the embodiments of the present application generally described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work fall within the scope of protection of the present application.

[0071] It should be noted that similar reference numerals and letters represent similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined or explained in subsequent drawings. At the same time, in the description of this application, the terms "first", "second", etc. are only used to distinguish the description and should not be understood as indicating or implying relative importance.

[0072] Please refer to Figure 1, which is a flow chart of a turbine speed regulation management method in some embodiments of the present application. The turbine speed regulation management method is used in a terminal device and includes the following steps:

[0073] S101, obtaining the physical entity data of the current pumped storage hydropower station, pre-processing the physical entity data of the pumped storage hydropower station, and obtaining the physical entity data of the turbine speed regulation.

[0074] S102, acquiring a corresponding turbine speed regulation historical data set based on the turbine speed regulation physical entity data; preprocessing the historical data set to obtain preprocessed turbine speed regulation physical entity data;

[0075] S103, comparing the pre-processed physical entity data of the turbine speed regulation with the preset data to obtain a deviation rate;

[0076] S104, determining whether the deviation rate is greater than or equal to a preset deviation rate threshold;

[0077] S105: If it is greater than or equal to, then generate correction information and correct the turbine speed regulation physical entity data according to the correction information; if it is less than, then establish a three-dimensional dynamic model by pre-processing the turbine speed regulation physical entity data and dynamically regulate the turbine speed according to the three-dimensional dynamic model.

[0078] It should be noted that by establishing a three-dimensional dynamic model, the turbine can be regulated in real time. At the same time, when errors occur during the turbine speed regulation process, they can be corrected in real time to ensure the accuracy of the speed regulation.

[0079] Please refer to Figure 2, which is a flow chart of preprocessing turbine speed control physical entity data in a turbine speed control management method according to some embodiments of the present application. According to an embodiment of the present invention, a corresponding turbine speed control historical data set is obtained based on the turbine speed control physical entity data; the historical data set is preprocessed to obtain preprocessed turbine speed control physical entity data, specifically:

[0080] S201, obtaining a historical data set of turbine speed regulation, performing a difference calculation between the historical data set of turbine speed regulation and an average value, and obtaining a data discrete value;

[0081] S202, analyzing and comparing the data discrete value with a preset discrete threshold value to obtain the data discreteness;

[0082] S203, determining whether the data dispersion is greater than a preset dispersion threshold;

[0083] S204, if it is greater than, deleting the corresponding turbine speed regulation history data;

[0084] S205: If it is less than or equal to, generate processed turbine speed regulation physical entity data.

[0085] It should be noted that by discretizing the physical data of the turbine speed regulating object, the data with large discretization in the data set can be eliminated, ensuring that when establishing a three-dimensional dynamic model, the optimized data set can improve the parameter accuracy of the model and improve the results of the model analysis.

[0086] According to an embodiment of the present invention, the pre-processed physical entity data of the turbine speed regulator includes the model, installation location, quantity, speed, power, current, voltage, opening, oil tank pressure, oil tank temperature, electric valve status, frequency swing, PID parameters, PLC control data, adjustment mode, operation plan, maintenance plan, control scheme and fault data of the turbine speed regulator.

[0087] It should be noted that by obtaining multi-dimensional physical entity data of turbine speed regulation, the speed regulation results can be made more referenceable. During the model training process, the output results of the trained model can be made more accurate.

[0088] Please refer to FIG3 , which is a flow chart of a method for managing turbine speed regulation in some embodiments of the present application, wherein a three-dimensional dynamic model is constructed based on static constant data and dynamic variable data. According to an embodiment of the present invention, if is less than , a three-dimensional dynamic model is established by pre-processing the physical entity data of the turbine speed regulation, and the turbine is dynamically regulated based on the three-dimensional dynamic model, specifically:

[0089] S301, obtaining physical entity data of a hydraulic turbine speed regulation, and extracting characteristic values ​​based on the physical entity data of the hydraulic turbine speed regulation;

[0090] S302, comparing the feature value with a preset feature threshold and calculating feature similarity;

[0091] S303, determining whether the feature similarity is greater than or equal to a preset similarity threshold;

[0092] S304: If the similarity is greater than or equal to a preset threshold, the corresponding hydraulic turbine speed regulation physical entity data is determined to be static constant data; if the similarity is less than, the corresponding hydraulic turbine speed regulation physical entity data is determined to be dynamic variable data;

[0093] S305: Construct a three-dimensional dynamic model based on the static constant data and the dynamic variable data.

[0094] It should be noted that by extracting features from the physical entity data of the turbine speed regulation and separating static data from dynamic data, the three-dimensional dynamic model is constructed under different circumstances through the separated dynamic data and static data, and the constructed three-dimensional dynamic model has higher accuracy.

[0095] According to an embodiment of the present invention, after constructing a three-dimensional dynamic model based on static constant data and dynamic variable data, the method further includes:

[0096] Obtain static constant data and dynamic variable data to generate static verification sets and dynamic verification sets;

[0097] Input the static validation set into the 3D dynamic model for parameter training to obtain the static loss value of the 3D dynamic model;

[0098] When the static loss value is greater than a first loss threshold, first feedback information is generated, and parameters of the three-dimensional dynamic model are adjusted according to the first feedback information;

[0099] Input the dynamic verification set into the 3D dynamic model for parameter training to obtain the dynamic loss value of the 3D dynamic model;

[0100] When the dynamic loss value is greater than the second loss threshold, second feedback information is generated, and parameters of the three-dimensional dynamic model are adjusted according to the second feedback information.

[0101] It should be noted that by extracting static and dynamic data from the physical entity data of the turbine speed regulation, the three-dimensional dynamic model under different data forms (dynamic and static) can be trained, thereby adjusting the model parameters under different data forms and improving the accuracy of the three-dimensional dynamic model.

[0102] According to an embodiment of the present invention, the dynamic speed regulation of the turbine is performed based on the three-dimensional dynamic model, specifically as follows:

[0103] Establish several turbine detection points and obtain the current speed information of each turbine detection point;

[0104] Compare the current speed information of the detection point with the preset speed information to obtain the speed deviation rate;

[0105] Determining whether the speed deviation rate is greater than or equal to a preset speed deviation threshold;

[0106] If it is greater than or equal to, turbine fault information is generated, and a preset fault prediction model is input according to the turbine fault information to obtain turbine fault prediction information;

[0107] If it is less than, it is determined that the turbine is rotating normally, and the real-time speed data of each turbine detection point is saved and summarized.

[0108] It should be noted that by establishing turbine detection points, parameter comparison at different positions of the shaft end during turbine rotation can be achieved. Detection points at different positions can determine the position deviation and rotational vibration information during turbine rotation, thereby analyzing defects or faults during turbine rotation, thereby determining turbine faults and providing the best solution to the fault.

[0109] According to an embodiment of the present invention, the method further includes: obtaining a historical data set of a speed governor of a hydraulic turbine, and constructing a speed control prediction model using a ROPN modeling method;

[0110] Using deep learning algorithms, a speed regulation fault diagnosis model was constructed, and a three-dimensional dynamic model for turbine speed regulation safety management was obtained after adding a prediction model.

[0111] The three-dimensional dynamic model for safety management of turbine speed regulation after adding the prediction model is received from the prediction model building unit, and the three-dimensional dynamic model for safety management of turbine speed regulation after adding the prediction model is used to safely manage turbine speed regulation parameters.

[0112] Specifically, the preprocessed real-time data of the speed governor is received, and the preprocessed real-time data of the speed governor is input into the speed control prediction model and speed fault diagnosis model of the turbine speed regulation safety management three-dimensional dynamic model after the prediction model is added to obtain the corresponding speed control scheme and speed fault diagnosis results.

[0113] Please refer to Figure 4, which is a schematic diagram of the structure of a turbine speed control management system in some embodiments of the present application. In a second aspect, the embodiments of the present application provide a turbine speed control management system 4, which includes: a memory 41 and a processor 42. The memory 41 includes a program for a turbine speed control management method. When the program is executed by the processor, the following steps are implemented:

[0114] Acquire the current physical entity data of the pumped storage hydropower station, pre-process the physical entity data of the pumped storage hydropower station, and obtain the physical entity data of the turbine speed regulation;

[0115] Acquire a corresponding turbine speed regulation historical data set according to the turbine speed regulation physical entity data; preprocess the historical data set to obtain preprocessed turbine speed regulation physical entity data;

[0116] Compare the pre-processed physical entity data of the turbine speed regulation with the preset data to obtain the deviation rate;

[0117] Determining whether the deviation rate is greater than or equal to a preset deviation rate threshold;

[0118] If it is greater than or equal to, then generate correction information, and correct the physical entity data of the turbine speed regulation according to the correction information;

[0119] If it is less than, a three-dimensional dynamic model is established by pre-processing the physical entity data of the turbine speed regulation;

[0120] The turbine is dynamically regulated based on the three-dimensional dynamic model.

[0121] It should be noted that by establishing a three-dimensional dynamic model, the turbine can be regulated in real time. At the same time, when errors occur during the turbine speed regulation process, they can be corrected in real time to ensure the accuracy of the speed regulation.

[0122] According to an embodiment of the present invention, a corresponding turbine speed regulation historical data set is obtained based on the turbine speed regulation physical entity data; the historical data set is preprocessed to obtain preprocessed turbine speed regulation physical entity data, specifically:

[0123] Obtain a historical data set of turbine speed regulation, perform a difference calculation between the historical data set of turbine speed regulation and the average value, and obtain a discrete value of the data;

[0124] Analyze and compare the data discrete value with the preset discrete threshold to obtain the data discreteness;

[0125] Determine whether the data dispersion is greater than a preset dispersion threshold;

[0126] If it is greater than, the corresponding turbine speed regulation history data will be deleted;

[0127] If it is less than or equal to, the processed turbine speed regulation physical entity data is generated.

[0128] It should be noted that by discretizing the physical data of the turbine speed regulating object, the data with large discretization in the data set can be eliminated, ensuring that when establishing a three-dimensional dynamic model, the optimized data set can improve the parameter accuracy of the model and improve the results of the model analysis.

[0129] According to an embodiment of the present invention, the pre-processed physical entity data of the turbine speed regulator includes the model, installation location, quantity, speed, power, current, voltage, opening, oil tank pressure, oil tank temperature, electric valve status, frequency swing, PID parameters, PLC control data, adjustment mode, operation plan, maintenance plan, control scheme and fault data of the turbine speed regulator.

[0130] It should be noted that by obtaining multi-dimensional physical entity data of turbine speed regulation, the speed regulation results can be made more referenceable. During the model training process, the output results of the trained model can be made more accurate.

[0131] According to an embodiment of the present invention, if , ...

[0132] Get the physical entity data of the turbine speed regulation,

[0133] Extract characteristic values ​​based on the physical entity data of the turbine speed regulation;

[0134] Compare the feature value with the preset feature threshold and calculate the feature similarity;

[0135] Determine whether the feature similarity is greater than or equal to a preset similarity threshold;

[0136] If it is greater than or equal to the preset similarity threshold, the corresponding turbine speed regulation physical entity data is determined to be static constant data;

[0137] If it is less than, the corresponding turbine speed regulation physical entity data is determined to be dynamic variable data;

[0138] Construct a three-dimensional dynamic model based on static constant data and dynamic variable data.

[0139] It should be noted that by extracting features from the physical entity data of the turbine speed regulation and separating static data from dynamic data, the three-dimensional dynamic model is constructed under different circumstances through the separated dynamic data and static data, and the constructed three-dimensional dynamic model has higher accuracy.

[0140] According to an embodiment of the present invention, after constructing a three-dimensional dynamic model based on static constant data and dynamic variable data, the method further includes:

[0141] Obtain static constant data and dynamic variable data to generate static verification sets and dynamic verification sets;

[0142] Input the static validation set into the 3D dynamic model for parameter training to obtain the static loss value of the 3D dynamic model;

[0143] When the static loss value is greater than a first loss threshold, first feedback information is generated, and parameters of the three-dimensional dynamic model are adjusted according to the first feedback information;

[0144] Input the dynamic verification set into the 3D dynamic model for parameter training to obtain the dynamic loss value of the 3D dynamic model;

[0145] When the dynamic loss value is greater than the second loss threshold, second feedback information is generated, and parameters of the three-dimensional dynamic model are adjusted according to the second feedback information.

[0146] It should be noted that by extracting static and dynamic data from the physical entity data of the turbine speed regulation, the three-dimensional dynamic model under different data forms (dynamic and static) can be trained, thereby adjusting the model parameters under different data forms and improving the accuracy of the three-dimensional dynamic model.

[0147] According to an embodiment of the present invention, the dynamic speed regulation of the turbine is performed based on the three-dimensional dynamic model, specifically as follows:

[0148] Establish several turbine detection points and obtain the current speed information of each turbine detection point;

[0149] Compare the current speed information of the detection point with the preset speed information to obtain the speed deviation rate;

[0150] Determining whether the speed deviation rate is greater than or equal to a preset speed deviation threshold;

[0151] If it is greater than or equal to, turbine fault information is generated, and a preset fault prediction model is input according to the turbine fault information to obtain turbine fault prediction information;

[0152] If it is less than, it is determined that the turbine is rotating normally, and the real-time speed data of each turbine detection point is saved and summarized.

[0153] It should be noted that by establishing turbine detection points, parameter comparison at different positions of the shaft end during turbine rotation can be achieved. Detection points at different positions can determine the position deviation and rotational vibration information during turbine rotation, thereby analyzing defects or faults during turbine rotation, thereby determining turbine faults and providing the best solution to the fault.

[0154] According to an embodiment of the present invention, the method further includes: obtaining a historical data set of a speed governor of a hydraulic turbine, and constructing a speed control prediction model using a ROPN modeling method;

[0155] Using deep learning algorithms, a speed regulation fault diagnosis model was constructed, and a three-dimensional dynamic model for turbine speed regulation safety management was obtained after adding a prediction model.

[0156] The three-dimensional dynamic model for safety management of turbine speed regulation after adding the prediction model is received from the prediction model building unit, and the three-dimensional dynamic model for safety management of turbine speed regulation after adding the prediction model is used to safely manage turbine speed regulation parameters.

[0157] Specifically, the preprocessed real-time data of the speed governor is received, and the preprocessed real-time data of the speed governor is input into the speed control prediction model and speed fault diagnosis model of the turbine speed regulation safety management three-dimensional dynamic model after the prediction model is added to obtain the corresponding speed control scheme and speed fault diagnosis results.

[0158] The present invention discloses a turbine speed regulation management method and system, which obtains physical entity data of the current pumped storage hydropower station, preprocesses the physical entity data of the pumped storage hydropower station to obtain turbine speed regulation physical entity data, and obtains a corresponding turbine speed regulation history data set according to the turbine speed regulation physical entity data; preprocesses the historical data set to obtain preprocessed turbine speed regulation physical entity data; compares the preprocessed turbine speed regulation physical entity data with preset data to obtain a deviation rate; determines whether the deviation rate is greater than or equal to a preset deviation rate threshold; if greater than or equal to, generates correction information, and corrects the turbine speed regulation physical entity data according to the correction information; if less than, establishes a three-dimensional dynamic model through the preprocessed turbine speed regulation physical entity data; by constructing a three-dimensional dynamic model for full management of turbine speed regulation, targeted management of turbine speed regulation is achieved, which makes it easier for staff to understand the overall layout and operating conditions of the turbines in the pumped storage hydropower station, and improves the accurate control of the turbine speed regulation process.

[0159] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of units is merely a logical function division. In actual implementation, there may be other division methods, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of devices or units can be electrical, mechanical or other forms.

[0160] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed across multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the scheme of this embodiment.

[0161] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0162] Those skilled in the art will understand that all or part of the steps of the above-mentioned method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a readable storage medium. When the program is executed, it executes the steps of the above-mentioned method embodiment; and the aforementioned storage medium includes: mobile storage devices, read-only memory (ROM), random access memory (RAM), magnetic disk or optical disk, etc. Various media that can store program codes.

[0163] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software functional module and sold or used as an independent product, it can also be stored in a readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium and includes a number of instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, magnetic disks or optical disks.

Claims

1. A method for managing water turbine speed regulation, characterized in that: include: Obtain the current physical entity data of the pumped storage hydropower station, pre-process the physical entity data of the pumped storage hydropower station, and obtain the physical entity data of the turbine speed regulation. According to the physical entity data of the hydraulic turbine speed regulation, a corresponding historical data set of hydraulic turbine speed regulation is obtained; the historical data set is preprocessed to obtain the physical entity data of the hydraulic turbine speed regulation after preprocessing; Compare the pre-processed physical entity data of the turbine speed regulation with the preset data to obtain the deviation rate; Determining whether the deviation rate is greater than or equal to a preset deviation rate threshold; If it is greater than or equal to, then generate correction information, and correct the physical entity data of the turbine speed regulation according to the correction information; If it is less than, a three-dimensional dynamic model is established by preprocessing the physical entity data of the turbine speed regulation; The turbine speed is dynamically regulated according to the three-dimensional dynamic model.

2. The turbine speed regulation management method according to claim 1, characterized in that: The method of obtaining a corresponding turbine speed regulation historical data set according to the turbine speed regulation physical entity data and preprocessing the historical data set to obtain the preprocessed turbine speed regulation physical entity data is as follows: Obtain a historical data set of turbine speed regulation, perform a difference calculation between the historical data set of turbine speed regulation and the average value, and obtain a discrete value of the data; Analyze and compare the data discrete value with the preset discrete threshold to obtain the data discreteness; Determining whether the data discreteness is greater than a preset discreteness threshold; If it is greater, the corresponding turbine speed regulation history data will be deleted; If it is less than or equal to, the processed turbine speed regulation physical entity data is generated.

3. The turbine speed regulation management method according to claim 2, characterized in that: The pre-processed turbine speed regulation physical entity data includes the model, installation location, quantity, speed, power, current, voltage, opening, oil tank pressure, oil tank temperature, electric valve status, frequency swing, PID parameters, PLC control data, regulation mode, operation plan, maintenance plan, control scheme and fault data of the turbine speed governor.

4. The turbine speed regulation management method according to claim 3, characterized in that: If the above value is less than , a three-dimensional dynamic model is established by preprocessing the physical entity data of the turbine speed regulation, and the turbine is dynamically regulated according to the three-dimensional dynamic model, specifically: Get the physical entity data of turbine speed regulation. Extract characteristic values ​​according to the physical entity data of turbine speed regulation; Compare the feature value with the preset feature threshold and calculate the feature similarity; Determining whether the feature similarity is greater than or equal to a preset similarity threshold; If it is greater than or equal to the preset similarity threshold, the corresponding turbine speed regulation physical entity data is determined to be static constant data; If it is less than, the corresponding turbine speed regulation physical entity data is determined to be dynamic variable data; Construct a three-dimensional dynamic model based on static constant data and dynamic variable data.

5. The method for managing water turbine speed regulation according to claim 4, characterized in that: After the three-dimensional dynamic model is constructed according to the static constant data and the dynamic variable data, the method further includes: Obtain static constant data and dynamic variable data to generate static verification sets and dynamic verification sets; Input the static verification set into the 3D dynamic model for parameter training to obtain the static loss value of the 3D dynamic model; When the static loss value is greater than a first loss threshold, first feedback information is generated, and parameters of the three-dimensional dynamic model are adjusted according to the first feedback information; The dynamic verification set is input into the three-dimensional dynamic model for parameter training to obtain the dynamic loss value of the three-dimensional dynamic model; When the dynamic loss value is greater than the second loss threshold, second feedback information is generated, and parameters of the three-dimensional dynamic model are adjusted according to the second feedback information.

6. The method for managing water turbine speed regulation according to claim 5, characterized in that: The dynamic speed regulation of the turbine according to the three-dimensional dynamic model is specifically as follows: Establish several turbine detection points and obtain the current speed information of each turbine detection point; Compare the current speed information of the detection point with the preset speed information to obtain the speed deviation rate; Determining whether the speed deviation rate is greater than or equal to a preset speed deviation threshold; If it is greater than or equal to, turbine fault information is generated, and a preset fault prediction model is input according to the turbine fault information to obtain turbine fault prediction information; If it is less than, it is determined that the turbine is rotating normally, and the real-time speed data of each turbine detection point is saved and summarized.

7. A turbine speed management system, characterized in that: The system comprises: a memory and a processor, wherein the memory comprises a program of a water turbine speed regulation management method, and when the program of the water turbine speed regulation management method is executed by the processor, the following steps are implemented: Obtain the current physical entity data of the pumped storage hydropower station, pre-process the physical entity data of the pumped storage hydropower station, and obtain the physical entity data of the turbine speed regulation. According to the physical entity data of the hydraulic turbine speed regulation, a corresponding historical data set of hydraulic turbine speed regulation is obtained; the historical data set is preprocessed to obtain the physical entity data of the hydraulic turbine speed regulation after preprocessing; Compare the pre-processed physical entity data of the turbine speed regulation with the preset data to obtain the deviation rate; Determining whether the deviation rate is greater than or equal to a preset deviation rate threshold; If it is greater than or equal to, then generate correction information, and correct the physical entity data of the turbine speed regulation according to the correction information; If it is less than, a three-dimensional dynamic model is established by preprocessing the physical entity data of the turbine speed regulation; The turbine speed is dynamically regulated according to the three-dimensional dynamic model.

8. The turbine speed regulation management system according to claim 7, characterized in that: The method of obtaining a corresponding turbine speed regulation historical data set according to the turbine speed regulation physical entity data and preprocessing the historical data set to obtain the preprocessed turbine speed regulation physical entity data is as follows: Obtain the historical data set of turbine speed regulation and compare it with the average value. Perform difference calculation to obtain the discrete value of the data; Analyze and compare the data discrete value with the preset discrete threshold to obtain the data discreteness; Determining whether the data discreteness is greater than a preset discreteness threshold; If it is greater, the corresponding turbine speed regulation history data will be deleted; If it is less than or equal to, the processed turbine speed regulation physical entity data is generated.

9. The turbine speed regulation management system according to claim 8, characterized in that: The pre-processed turbine speed regulation physical entity data includes the model, installation location, quantity, speed, power, current, voltage, opening, oil tank pressure, oil tank temperature, electric valve status, frequency swing, PID parameters, PLC control data, regulation mode, operation plan, maintenance plan, control scheme and fault data of the turbine speed governor.

10. The turbine speed management system according to claim 8, characterized in that: If the above value is less than , a three-dimensional dynamic model is established by preprocessing the physical entity data of the turbine speed regulation, and the turbine is dynamically regulated according to the three-dimensional dynamic model, specifically: Get the physical entity data of turbine speed regulation. Extract characteristic values ​​according to the physical entity data of turbine speed regulation; Compare the feature value with the preset feature threshold and calculate the feature similarity; Determining whether the feature similarity is greater than or equal to a preset similarity threshold; If it is greater than or equal to the preset similarity threshold, the corresponding turbine speed regulation physical entity data is determined to be static constant data; If it is less than, the corresponding turbine speed regulation physical entity data is determined to be dynamic variable data; Construct a three-dimensional dynamic model based on static constant data and dynamic variable data.

Images