Automatic control method and device for hydropower station

Abstract

The invention relates to an automatic control method and device for a hydropower station. The method comprises the following steps: acquiring state parameters of the hydropower station; wherein the state parameters comprise a space parameter, a water level parameter, a ground parameter, a water bottom parameter, an air parameter, a wind speed parameter and an environment parameter; analyzing and predicting the state parameters; an ecological control model is constructed, the ecological control model is established based on a CNN algorithm and is obtained through data set training, and the data set comprises the state parameters and the corresponding control modes; and inputting the predicted state parameters into the ecological control model, obtaining a corresponding control mode, and carrying out automatic control on the hydropower station. According to the invention, comprehensive, multi-dimensional and multi-level joint defense and joint control of automatic management and control of the hydropower station and construction of an intelligent platform of remote management can be realized.

Description

Technical Field

[0001] The present invention relates to the technical field of hydropower station automation control, and in particular to a hydropower station automation control method and device. Background Art

[0002] With the vigorous development of power grid expansion and transformation projects, traditional hydropower station automation control methods can no longer solve the contradiction between the increasingly complex environment around hydropower stations, the continuous gathering of people, the increasing real-time, precision, and systematic requirements of control, and the shortage of hydropower station technology and management personnel and relatively backward equipment. Adding multiple sensors, providing intelligent control devices, coordinating multiple management methods, forming an effective closed-loop control mechanism (method and control structure), building an intelligent management and control platform and architecture design, effectively realizing the construction of AI intelligent water conservancy and intelligent hydropower stations, reducing labor costs, and achieving the comprehensive control goals of intelligent, systematic, precise, energy-saving, and environmentally friendly power stations. Summary of the invention

[0003] The purpose of the present invention is to provide a method and device for automated control of a hydropower station to solve the problems existing in the above-mentioned prior art, and to utilize the intelligent control system of the hydropower station to complete the local deployment of the control interface and method, the B / S control architecture and control method, the configuration of the SERVER control platform method, the intelligent monitoring and deep intelligent control architecture and closed-loop control method, the provision of intelligent AI control computing power, the intelligent distributed management and control decision-making method and decision-making management application, and the real-time monitoring of the operating status of the power station, and finally realize the comprehensive and multi-dimensional automated management and control of the hydropower station, multi-extreme joint prevention and control, and remote management of the intelligent platform.

[0004] To achieve the above object, the present invention provides the following solutions:

[0005] A method for automatic control of a hydropower station comprises: autonomously controlling a switch quantity and an automatic adjustment control unit of a frequency conversion control system through a cloud autonomous control system and a local gateway control system according to changes in state parameters of the hydropower station, thereby realizing a control system optimization method under an AI large model.

[0006] Obtaining state parameters of the hydropower station; wherein the state parameters include: space parameters, water level parameters, ground parameters, bottom parameters, air parameters, wind speed parameters, and environmental parameters;

[0007] Analyzing and predicting the state parameters;

[0008] Constructing an ecological control model, wherein the ecological control model is established based on a CNN algorithm and is obtained by training using a data set, wherein the data set includes: the state parameters and corresponding control methods;

[0009] The predicted state parameters are input into the ecological control model to obtain the corresponding control method and perform automatic control on the hydropower station.

[0010] Optionally, predicting the state parameter includes:

[0011] Monitor and analyze water flow status, flow width, control algorithm optimization, water pump control water volume regulation, control water flow control valve, realize water flow and flow rate control, conduct estimated flow analysis and prediction for different control flows and river widths, form data analysis and data statistics, and use AI computing power to effectively predict water flow and monitor fluid temperature, status, and floating data.

[0012] Optionally, constructing the ecological control model includes:

[0013] Establish a water ecological standard control model, implement a training model library, automatically identify multiple states, and obtain the state parameters and corresponding control methods;

[0014] Based on the state parameters and the corresponding control methods, construct the data set;

[0015] The CNN model is trained using the data set to obtain the ecological control model, and the training algorithm is used to perform autonomous model optimization.

[0016] Optionally, analyzing the state parameter includes:

[0017] Effectively analyze and manage the status parameters of the hydropower station, establish a multi-dimensional data analysis model, establish ground data and aerial data, propose effective data analysis methods, establish data model standard parameter analysis management, implement prefabricated models, count data for more than 10 days, conduct effective superposition budgeting and analysis, repeat superposition, and effectively enter the next model superposition budget, realizing the stage of continuous work and continuous model training.

[0018] Optionally, establish a longitudinal echelon data model, conduct data and data fluid analysis of the drop echelon, test the automated control system, establish a data analysis model for fluid flow rate, establish a deep data learning model, establish a multi-echelon drop fluid mathematical model, and establish a big data analysis and management model through deep learning data.

[0019] A hydropower station automation control device, characterized in that it is used to implement a hydropower station automation control method, and the device comprises:

[0020] A data acquisition module is used to collect state parameters of the hydropower station; wherein the state parameters include: space parameters, water level parameters, ground parameters, bottom parameters, air parameters, wind speed parameters, and environmental parameters;

[0021] A data analysis model is used for analyzing the collected state parameters using a preset data analysis method to obtain a control method corresponding to the analysis result;

[0022] A data prediction module, used to predict the collected state parameters and obtain prediction data;

[0023] Model building module, used to build ecological control models;

[0024] A prediction analysis module, used to analyze the prediction data using the ecological control model to obtain a corresponding control method;

[0025] The automatic control module performs automatic control of the hydropower station according to the control method corresponding to the analysis result and the control method corresponding to the prediction data.

[0026] Optionally, the model building module establishes a data management AI intelligent model learning computing power structure, establishes an effective SERVER data model computing power operator, establishes a data APP and mini-program terminal, provides a C / S and B / S data management and control platform, and realizes the logical control interface, control interface, control switch logic unit and algorithm unit of multiple judgments such as OR, AND, NOR.

[0027] Optionally, the automation control module adopts an embedded interface design, provides a variety of compatible expansion units and accessible sensor design interfaces, and supports data encoding upload and data download design.

[0028] Optionally, the automation control module is also used to complete long-distance IO control, long-distance voltage control, long-distance current control, long-distance Modbus control, and long-distance custom protocol control.

[0029] The beneficial effects of the present invention are:

[0030] The present invention first obtains the state parameters of the hydropower station; then analyzes and predicts the state parameters; proposes an effective data analysis method to comprehensively and systematically accumulate hydropower station operation-related data and lay a solid foundation for establishing a big data analysis library and analysis model; then constructs an ecological control model, inputs the predicted state parameters into the ecological control model, obtains the corresponding control method, and performs automatic control of the hydropower station; the present invention realizes the architecture and closed-loop control method of intelligent monitoring and deep intelligent control, provides intelligent AI control computing power, realizes intelligent distributed management and control decision-making methods and decision-making management applications, and the device realizes full-process working status monitoring of the hydropower station, realizes comprehensive and multi-dimensional automated management and control, and multi-extreme joint prevention and control, realizing an intelligent platform for remote management. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0032] Figure 1 This is a general flow chart of a hydropower station automation control method according to an embodiment of the present invention;

[0033] Figure 2 This is a node data flow chart of an embodiment of the present invention;

[0034] Figure 3 This is a multi-echelon control flow chart of an embodiment of the present invention;

[0035] Figure 4 It is a multi-dimensional flow chart of an embodiment of the present invention. DETAILED DESCRIPTION

[0036] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0037] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0038] like Figure 1-Figure 4 As shown, this embodiment proposes a method for automatic control of a hydropower station, including: according to changes in state parameters of the hydropower station, autonomous control of the switch quantity and the automatic adjustment control unit of the frequency conversion control system is realized through a cloud-based autonomous control system and a local gateway control system, thereby realizing a control system optimization method under an AI large model.

[0039] Obtain the status parameters of the hydropower station; wherein the status parameters include: space parameters (illuminance, temperature and humidity, wind speed), water level parameters (page height, water temperature), ground parameters (ground obstacles, ground temperature, ground slope), bottom parameters (water flow, water temperature), air parameters (air pressure,), wind speed parameters (wind speed), environmental parameters (oxygen, carbon dioxide, hydrogen sulfide);

[0040] Analyzing and predicting the state parameters;

[0041] Constructing an ecological control model, wherein the ecological control model is established based on a CNN algorithm and is obtained by training using a data set, wherein the data set includes: the state parameters and corresponding control methods;

[0042] The predicted state parameters are input into the ecological control model to obtain the corresponding control method and perform automatic control on the hydropower station.

[0043] Further, predicting the state parameter includes:

[0044] Monitor and analyze water flow status, flow width, control algorithm optimization, water pump control water volume regulation, control water flow control valve, realize water flow and flow rate control, conduct estimated flow analysis and prediction for different control flows and river widths, form data analysis and data statistics, and use AI computing power to effectively predict water flow and monitor fluid temperature, status, and floating data.

[0045] Furthermore, constructing the ecological control model includes:

[0046] Establish a water ecological standard control model, implement a training model library, automatically identify multiple states, and obtain the state parameters and corresponding control methods;

[0047] Based on the state parameters and the corresponding control methods, construct the data set;

[0048] The CNN model is trained using the data set to obtain the ecological control model, and the training algorithm is used to perform autonomous model optimization.

[0049] Further, analyzing the state parameters includes:

[0050] Effectively analyze and manage the status parameters of the hydropower station, establish a multi-dimensional data analysis model, establish ground data and aerial data, propose effective data analysis methods, establish data model standard parameter analysis management, implement prefabricated models, count data for more than 10 days, conduct effective superposition budgeting and analysis, repeat superposition, and effectively enter the next model superposition budget, realizing the stage of continuous work and continuous model training.

[0051] Furthermore, a vertical echelon data model is established, data and data fluid analysis of the drop echelon is carried out, the automated control system is tested, a data analysis model of fluid flow rate is established, a deep data learning model is established, a multi-echelon drop fluid mathematical model is established, and a big data analysis and management model is established through deep learning data.

[0052] Specifically, in this embodiment, the first step is to effectively collect space, water level, ground, bottom of water, air, and wind speed; the second step is to effectively analyze various state parameters such as the environment; the third step is to manage the automatic control system of the hydropower station; the fourth step is to realize the local deployment of the control interface and the control method, the B / S control architecture and the control method, and the configuration of the SERVER control platform method; the fifth step is to realize the architecture and closed-loop control method of intelligent monitoring and deep intelligent control, provide intelligent AI control computing power, and realize intelligent distributed management and control decision-making methods and decision-making management applications; the device realizes the full-process working status monitoring of the hydropower station, realizes comprehensive and multi-dimensional automated management and control, and realizes multi-extreme joint prevention and control, and realizes an intelligent platform for remote management.

[0053] This embodiment implements the design of the water temperature, water level, water pressure, and pipeline flow control platform of the hydropower station and aggregates data with the data cloud or local server, and combines data analysis computing power to perform effective vector management and flow planning design.

[0054] This embodiment implements the design of the water temperature, water level, water pressure, and pipeline flow control platform of the hydropower station and aggregates data with the data cloud or local server, and combines data analysis computing power to perform effective vector management and flow planning design.

[0055] This embodiment monitors and analyzes water flow status, performs expected flow analysis and prediction for different control flows and river widths, forms data analysis and data statistics, and uses AI computing power to effectively predict the flow of water flow and monitor fluid temperature, status, and floating data. The AI ​​computing power implementation method includes an artificial intelligence control system model, establishing a water ecological standard control model, realizing a training model library, automatically identifying multiple states, and establishing a control algorithm model package, which is not limited to data model algorithms such as CNN, and establishing an ecological control model. At the same time, it combines machine vision status to effectively analyze various data.

[0056] This embodiment uses a visual monitoring device to monitor moving objects, effectively prevent floating objects from entering the vicinity of the hydropower station, and conduct real-time and efficient monitoring and safety management of the environment around the hydropower station.

[0057] This embodiment optimizes the control structure of the hydropower station, establishes an AI computing power implementation method including an artificial intelligence control system model, establishes a water ecological standard control model, implements a training model library, automatically identifies multiple states, and establishes a control algorithm model package, which is not limited to data model algorithms such as CNN. An ecological control model is established, and a training algorithm is used to achieve autonomous model optimization. Compared with traditional comparative control methods, a fuzzy control algorithm is implemented, a neural algorithm is implemented, and optimized control is performed. The optimized control structure analyzes the improvement of the power quality of the hydropower station. The control structure includes sensor detection for controlling fluid mechanics, summary analysis of the power of the hydropower station, analysis of different states, and establishment of a data control method and control principle.

[0058] like Figure 4 As shown, this embodiment adopts a multi-dimensional management concept, effectively analyzes and manages various state parameters of the hydropower station, such as space, water level, ground, bottom of water, air, wind speed, environment, etc., establishes a multi-dimensional data analysis model, establishes ground data and air data, and proposes an effective data analysis method, which lays a solid foundation for comprehensively and systematically accumulating hydropower station operation-related data and establishing a big data analysis library and analysis model.

[0059] This embodiment establishes a vertical echelon data model, realizes data and data fluid analysis of the drop echelon, tests the automated control system, establishes a data analysis model for fluid flow rate, establishes a deep data learning model, establishes a multi-echelon drop fluid mathematical model, and establishes a big data analysis and management model through deep learning data to effectively judge the estimated energy efficiency analysis data of the data drop. It establishes an AI computing power implementation method including an artificial intelligence control system model, establishes a water ecological standard control model, implements a training model library, automatically identifies multiple states, and establishes a control algorithm model package, which is not limited to CNN and other data model algorithms. It establishes an ecological control model and uses a training algorithm to realize autonomous model optimization. Compared with the traditional comparative control method, it implements the fuzzy control algorithm and the neural algorithm to perform optimized control. Multi-echelon control such as Figure 3 shown.

[0060] This embodiment effectively analyzes and manages various state parameters such as space, water level, ground, bottom of water, air, wind speed, environment, etc., establishes data management AI intelligent model learning computing power construction, establishes effective SERVER data model computing power operator, establishes data APP and small program terminals, provides C / S and B / S data management and control platforms, and realizes logical control interfaces for multiple judgments such as OR, AND, NOR, control interfaces, control switch logic units and algorithm unit designs.

[0061] This embodiment also proposes a hydropower station automation control device, including:

[0062] A data acquisition module is used to collect state parameters of the hydropower station; wherein the state parameters include: space parameters, water level parameters, ground parameters, bottom parameters, air parameters, wind speed parameters, and environmental parameters;

[0063] A data analysis model is used for analyzing the collected state data using a preset data analysis method to obtain a control method corresponding to the analysis result;

[0064] A data prediction module, used to predict the collected state data and obtain predicted data;

[0065] Model building module, used to build ecological control models;

[0066] A prediction analysis module, used to analyze the prediction data using the ecological control model to obtain a corresponding control method;

[0067] The automatic control module performs automatic control of the hydropower station according to the control method corresponding to the analysis result and the control method corresponding to the prediction data.

[0068] Furthermore, the model building module establishes a data management AI intelligent model learning computing power structure, establishes an effective SERVER data model computing power operator, establishes a data APP and mini-program terminal, provides a C / S and B / S data management and control platform, and realizes OR, AND, NOR and other multiple judgment logic control interfaces, control interfaces, control switch logic units and algorithm units.

[0069] Furthermore, the automation control module adopts an embedded interface design, provides a variety of compatible expansion units and accessible sensor design interfaces, and supports data encoding upload and data download design.

[0070] Furthermore, the automation control module is also used to complete long-distance IO control, long-distance voltage control, long-distance current control, long-distance Modbus control, and long-distance custom protocol control; Figure 2 shown.

[0071] Specifically, in this embodiment, the core control structure adopts an embedded interface design, provides a variety of compatible expansion units and accessible sensor design interfaces, and supports data encoding upload and data download design.

[0072] This embodiment supports radio frequency transmission, and realizes a wireless networking design structure that supports multiple data transparent transmission modes such as Lora and Wifi, making data aggregation more convenient, more optimized control methods, and a more complete networking mode.

[0073] This embodiment has an effective configuration supervision platform, which makes the platform more perfect and more intuitive, and establishes an effective data test structure.

[0074] This embodiment has an effective networking design to ensure the implementation of the original specific data communication method.

[0075] This embodiment has the function of effectively completing remote IO control, completing the open / closed state control of the multi-way controller control switch, realizing the state monitoring of remote energy-consuming equipment, and at the same time has the function of transmitting information of the closed-loop detection device data of the sensor as well as the signal.

[0076] This embodiment has the function of effectively completing long-distance voltage control, completing the open / closed state control of the multi-way controller control switch, realizing the state monitoring of remote energy-consuming equipment, and at the same time has the function of transmitting information equivalent to the closed-loop detection device data of the sensor.

[0077] This embodiment has the function of effectively completing long-distance current control, completing the open / closed state control of the multi-channel controller control switch, realizing the state monitoring of remote energy-consuming equipment, and at the same time has the function of transmitting information of the closed-loop detection device data of the sensor as well as the signal.

[0078] This embodiment has the function of effectively completing remote control Modbus control, completing the open / closed state control of the multi-way controller control switch, realizing the state monitoring of remote energy-consuming equipment, and at the same time has the function of transmitting information equivalent to the closed-loop detection device data of the sensor.

[0079] This embodiment has the function of effectively completing remote control custom protocol control, completing the open / closed state control of the multi-way controller control switch, realizing the state monitoring of remote energy-consuming equipment, and at the same time has the function of transmitting information equivalent to the closed-loop detection device data of the sensor.

[0080] This embodiment has the function of effectively completing the monitoring of various equipment in the hydropower station, and at the same time completing the remote frequency conversion control of the control equipment and electrical equipment, and the remote frequency conversion control of lights, fans, air conditioners, household appliances, high-power electrical equipment, three-phase energy consumption equipment, etc.

[0081] This embodiment has the function of effectively completing the B / S architecture cloud control and status display of the hydropower station, remote frequency conversion control of electrical equipment, remote frequency conversion control of lights, fans, air conditioners, home appliances, high-power electrical equipment, three-phase energy consumption equipment, etc.

[0082] This embodiment has the function of effectively completing the APP architecture cloud control and status display of the hydropower station, remote frequency conversion control of electrical equipment, remote frequency conversion control of lights, fans, air conditioners, home appliances, high-power electrical equipment, three-phase energy consumption equipment, etc.

[0083] This embodiment has the function of effectively completing the local equipment control and status display of the hydropower station, remote frequency conversion control of electrical equipment, remote frequency conversion control of lights, fans, air conditioners, home appliances, high-power electrical equipment, three-phase energy consumption equipment, etc.

[0084] The control system uses a remote control collector to further control the IO controller, or further control the Modbus control to achieve flexible switching of multiple control methods, while monitoring the status of the generator, further controlling the motor to achieve the power conversion of the hydropower station, and realizing the control method of circulating water resources.

[0085] The controller directly supports 0-30KM distance networking communication, realizes step networking, realizes long-distance networking, drives the monitoring of motor control generator, and transmits data over long distances. It can sense wind speed, water flow rate, and the output status of control signals, and realize data monitoring of various power plants, hydropower plants, thermal power plants, and energy-related units.

[0086] The embodiments described above are only descriptions of the preferred embodiments of the present invention and are not intended to limit the scope of the present invention. Without departing from the design spirit of the present invention, various modifications and improvements made to the technical solutions of the present invention by ordinary technicians in this field should all fall within the protection scope determined by the claims of the present invention.

Claims

1. A hydropower station automation control method, characterized in that: include: Obtaining state parameters of the hydropower station; wherein the state parameters include: space parameters, water level parameters, ground parameters, bottom parameters, air parameters, wind speed parameters, and environmental parameters; Analyzing and predicting the state parameters; Constructing an ecological control model, wherein the ecological control model is established based on a CNN algorithm and is obtained by training using a data set, wherein the data set includes: the state parameters and corresponding control methods; The predicted state parameters are input into the ecological control model to obtain the corresponding control method and perform automatic control on the hydropower station.

2. The hydropower station automation control method according to claim 1, characterized in that: Predicting the state parameter includes: Monitor and analyze water flow status, flow width, control algorithm optimization, water pump control water volume regulation, control water flow control valve, realize water flow and flow rate control, conduct estimated flow analysis and prediction for different control flows and river widths, form data analysis and data statistics, and use AI computing power to effectively predict water flow and monitor fluid temperature, status, and floating data.

3. The hydropower station automation control method according to claim 1, characterized in that: Constructing the ecological control model includes: Establish a water ecological standard control model, implement a training model library, automatically identify multiple states, and obtain the state parameters and corresponding control methods; Based on the state parameters and the corresponding control methods, construct the data set; The CNN model is trained using the data set to obtain the ecological control model, and the training algorithm is used to perform autonomous model optimization.

4. The hydropower station automation control method according to claim 1, characterized in that: Analyzing the state parameters includes: Effectively analyze and manage the status parameters of the hydropower station, establish a multi-dimensional data analysis model, establish ground data and aerial data, propose effective data analysis methods, establish data model standard parameter analysis management, realize prefabricated models, count data of preset time, conduct effective superposition budget and analysis, repeat superposition, effectively enter the next model superposition budget, and realize continuous work and continuous model training.

5. The hydropower station automation control method according to claim 1, characterized in that: Establish a vertical echelon data model, conduct data and data fluid analysis of the drop echelon, test the automated control system, establish a data analysis model for fluid flow rate, establish a deep data learning model, establish a multi-echelon drop fluid mathematical model, and establish a big data analysis and management model through deep learning data.

6. A hydropower station automation control device, characterized in that: Used to implement the hydropower station automation control method according to any one of claims 1 to 5, the device comprises: A data acquisition module is used to collect state parameters of the hydropower station; wherein the state parameters include: space parameters, water level parameters, ground parameters, bottom parameters, air parameters, wind speed parameters, and environmental parameters; A data analysis model is used for analyzing the collected state parameters using a preset data analysis method to obtain a control method corresponding to the analysis result; A data prediction module, used to predict the collected state parameters and obtain prediction data; Model building module, used to build ecological control models; A prediction analysis module, used to analyze the prediction data using the ecological control model to obtain a corresponding control method; The automatic control module performs automatic control of the hydropower station according to the control method corresponding to the analysis result and the control method corresponding to the prediction data.

7. The hydropower station automation control device according to claim 6, characterized in that: The model building module establishes data management AI intelligent model learning computing power construction, establishes effective SERVER data model computing power operator, establishes data APP and mini-program terminals, provides C / S and B / S data management and control platforms, and realizes logical control interfaces, control interfaces, control switch logic units and algorithm units for multiple judgments such as OR, AND, and NOR.

8. The hydropower station automation control device according to claim 6, characterized in that: The automation control module adopts an embedded interface design, provides a variety of compatible expansion units and accessible sensor design interfaces, and supports data encoding upload and data download design.

9. The hydropower station automation control device according to claim 6, characterized in that: The automation control module is also used to complete long-distance IO control, long-distance voltage control, long-distance current control, long-distance Modbus control, and long-distance custom protocol control.

Images