Hydroelectric generator parameter control method and system based on water potential dynamic analysis

Abstract

The present application provides a method and system for controlling parameters of a hydroelectric generator based on dynamic analysis of water potential, which relates to the technical field of hydroelectric power generation. The method and system perform power generation impact analysis by acquiring historical hydroelectric power generation records, and obtain power generation impact analysis results; extract multiple key influencing factors based on the power generation impact analysis results; obtain multiple key control parameters of the hydroelectric generator, associate and map them with multiple key influencing factors, and establish a water potential-parameter control mapping; collect real-time water potential data, perform dynamic analysis of water potential in combination with a water potential prediction model, and obtain water potential prediction results; read the real-time operating parameters of the generator, combine the water potential prediction results and the water potential-parameter control mapping, perform dynamic optimization of the control strategy, obtain the optimized control strategy, and perform generator parameter control. The present application solves the technical problem that it is difficult to effectively cope with water potential fluctuations in traditional hydroelectric power generation, which leads to a decrease in power generation efficiency, and achieves the technical effect of improving the power generation efficiency and stability of the hydroelectric generator.

Description

Technical Field

[0001] The present application relates to the technical field of hydroelectric power generation, and in particular to a method and system for controlling parameters of a hydroelectric generator based on dynamic analysis of water potential. Background Art

[0002] Hydropower is a renewable energy technology that converts the energy of water flow into electricity. Its efficiency is affected by many natural factors, especially the change of water potential. Due to the unpredictability of natural conditions, such as rainfall and water level changes, hydroelectric power plants often face the challenge of rapid changes in water potential.

[0003] In traditional hydropower generation operations, there is often a lack of effective prediction and response mechanisms for dynamic changes in water potential, resulting in unstable power generation efficiency and sometimes even inability to fully utilize water resources. Especially during extreme weather events such as floods or droughts, drastic fluctuations in water potential can bring additional operational challenges to hydropower stations, which may lead to a significant drop in power generation. In addition, since the control parameters of hydropower generators are usually fixed and cannot adapt to changes in water potential in a timely manner, this limits the further improvement of power generation efficiency. With the development of information technology, especially the advancement of data analysis and predictive models, new opportunities have been provided to improve the flexibility and efficiency of hydropower generation. However, how to effectively integrate these technologies to achieve dynamic control of hydropower generator parameters remains a challenge. Summary of the invention

[0004] The present application provides a method and system for controlling parameters of a hydroelectric generator based on dynamic analysis of water potential, which solves the technical problem that it is difficult to effectively cope with water potential fluctuations in traditional hydroelectric power generation, resulting in a decrease in power generation efficiency. By accurately predicting and responding to changes in water potential in real time, the operating parameters of the generator are dynamically adjusted, thereby achieving the technical effect of improving the power generation efficiency and stability of the hydroelectric generator.

[0005] In view of the above problems, on the one hand, the present application provides a method for controlling parameters of a hydroelectric generator based on dynamic analysis of water potential, the method comprising: obtaining historical hydroelectric power generation records, the historical hydroelectric power generation records comprising historical water potential data and historical power generation data; based on the historical hydroelectric power generation records, performing power generation impact analysis, and obtaining power generation impact analysis results; extracting multiple key influencing factors according to the power generation impact analysis results, the multiple key influencing factors being the water potential parameters that affect power generation; obtaining multiple key control parameters of the hydroelectric generator, performing correlation mapping with the multiple key influencing factors, and establishing a water potential-parameter control mapping; collecting real-time water potential data, performing dynamic analysis of water potential in combination with a water potential prediction model, and obtaining water potential prediction results; reading the real-time operating parameters of the generator, performing dynamic optimization of the control strategy in combination with the water potential prediction results and the water potential-parameter control mapping, obtaining an optimized control strategy, and performing generator parameter control based on the optimized control strategy.

[0006] On the other hand, the present application also provides a hydroelectric generator parameter control system based on water potential dynamic analysis, the system comprising: a historical record acquisition module, the historical record acquisition module is used to acquire historical hydroelectric power generation records, the historical hydroelectric power generation records include historical water potential data and historical power generation data; a power generation impact analysis module, the power generation impact analysis module is used to perform power generation impact analysis based on the historical hydroelectric power generation records, and obtain power generation impact analysis results; an influence factor extraction module, the influence factor extraction module is used to extract multiple key influence factors according to the power generation impact analysis results, and the multiple key influence factors are water potential parameters that affect power generation; an association mapping module, the association mapping module is used to acquire multiple key control parameters of the hydroelectric generator, associate and map with the multiple key influence factors, and establish a water potential-parameter control mapping; a water potential prediction module, the water potential prediction module is used to collect real-time water potential data, perform water potential dynamic analysis in combination with a water potential prediction model, and obtain water potential prediction results; a control optimization module, the control optimization module is used to read the real-time operating parameters of the generator, combine the water potential prediction results and the water potential-parameter control mapping, perform dynamic optimization of the control strategy, obtain an optimized control strategy, and perform generator parameter control based on the optimized control strategy.

[0007] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0008] By obtaining historical hydropower generation records, a data basis is provided for subsequent power generation impact analysis, helping to understand the relationship between water potential changes and power generation efficiency; based on the historical hydropower generation records, power generation impact analysis is performed, power generation impact analysis results are obtained, and key factors affecting power generation are further identified and analyzed, providing a basis for subsequent key influencing factor extraction to ensure the pertinence of the control strategy. According to the power generation impact analysis results, multiple key influencing factors are extracted, and the most critical water potential parameters are identified from complex data, making the control strategy more efficient and accurate. Multiple key control parameters of the hydropower generator are obtained, and associated mapping is performed with the multiple key influencing factors to establish a water potential-parameter control mapping, and a direct connection between the water potential parameters and the generator control parameters is established, providing a basis for rapid decision-making for real-time control and improving the response speed. Real-time water potential data is collected, and water potential dynamic analysis is performed in combination with the water potential prediction model to obtain water potential prediction results, ensuring the real-time and forward-looking nature of the control strategy and improving the ability to respond to sudden water potential changes. The real-time operating parameters of the generator are read, and the control strategy is dynamically optimized in combination with the water potential prediction result and the water potential-parameter control mapping to obtain an optimized control strategy. Based on the optimized control strategy, the generator parameters are controlled and the generator operating parameters are dynamically adjusted to maximize the power generation efficiency and maintain the stable operation of the hydroelectric generator.

[0009] In summary, the present application can monitor, predict and respond to changes in water potential in real time, and continuously adjust operating parameters based on real-time water potential data and prediction results, thereby optimizing the operation of hydroelectric generators, improving power generation efficiency and stability, and enabling generators to adapt to environmental changes more flexibly and reduce energy waste.

[0010] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1 A flow chart of a method for controlling parameters of a hydroelectric generator based on dynamic analysis of water potential provided in an embodiment of the present application;

[0012] Figure 2 A schematic diagram of a flow chart of obtaining power generation impact analysis results in a method for controlling parameters of a hydroelectric generator based on water potential dynamic analysis provided in an embodiment of the present application;

[0013] Figure 3 A schematic diagram of a flow chart of obtaining an optimized control strategy in a method for controlling parameters of a hydroelectric generator based on dynamic analysis of water potential provided in an embodiment of the present application;

[0014] Figure 4 A schematic diagram of the structure of a hydraulic generator parameter control system based on water potential dynamic analysis provided in an embodiment of the present application.

[0015] Explanation of reference numerals: historical record acquisition module 10 , power generation impact analysis module 20 , impact factor extraction module 30 , association mapping module 40 , water potential prediction module 50 , control optimization module 60 . DETAILED DESCRIPTION

[0016] The embodiments of the present application provide a method and system for controlling parameters of a hydroelectric generator based on dynamic analysis of water potential, optimize the operation of the hydroelectric generator by accurately predicting and responding to changes in water potential in real time, and dynamically adjusting the operating parameters of the generator. This solves the technical problem that it is difficult to effectively cope with water potential fluctuations in traditional hydroelectric power generation, resulting in a decrease in power generation efficiency, and achieves the technical effect of improving the power generation efficiency and stability of the hydroelectric generator.

[0017] Embodiment 1, as Figure 1 As shown, the embodiment of the present application provides a method for controlling parameters of a hydraulic generator based on dynamic analysis of water potential, the method comprising:

[0018] Step S1: Acquire historical hydropower generation records, wherein the historical hydropower generation records include historical water potential data and historical power generation data.

[0019] Specifically, through information interaction, the database, log files or other record forms of the hydropower station are accessed to obtain historical hydropower generation records, including historical water potential data and historical power generation data. Historical water potential data include data such as the water level, flow, flow rate, and water quality of the river or reservoir. Historical power generation data refers to the power generation records of the hydropower station over a period of time in the past, including daily, monthly or annual power generation, and the operating status of the generator, such as load rate, efficiency, etc. Both historical water potential data and historical power generation data are timestamped, and there is a corresponding relationship between historical water potential data and historical power generation data with the same timestamp, that is, each historical water potential data has its corresponding historical power generation data at the same time. By obtaining historical hydropower generation records, a detailed and accurate historical data set is established to provide a reliable data basis for power generation impact analysis.

[0020] Step S2: Based on the historical hydropower generation records, perform power generation impact analysis to obtain power generation impact analysis results.

[0021] Specifically, the historical hydroelectric power generation records collected and sorted in step S1 are used to study the relationship between different water potential parameters, such as water level, water flow velocity, etc., and power generation efficiency through data analysis methods, such as statistical analysis, correlation analysis, etc. The potential pattern or trend between water potential changes and power generation efficiency is identified through data analysis, and a power generation impact analysis report is formed to provide a scientific basis for subsequent parameter control. Among them, the power generation impact analysis results refer to the conclusions or data on the relationship between water potential parameters and power generation efficiency obtained through data analysis, including a list of key influencing factors and their specific impact on power generation efficiency.

[0022] Furthermore, if Figure 2 As shown, step S2 of the embodiment of the present application also includes:

[0023] Step S21: After data cleaning of the historical hydropower generation records, a plurality of historical power generation data samples corresponding to a plurality of historical water potential data samples are obtained.

[0024] Step S22: Calculate the correlation between multiple water potential parameters and power generation through the Pearson correlation coefficient to obtain a correlation analysis result.

[0025] Step S23: Based on the correlation analysis result, a power generation impact analysis result is obtained.

[0026] Specifically, first, the historical hydropower generation records are cleaned to ensure the accuracy and completeness of the data. Data cleaning includes checking whether the data has missing values, outliers or duplicates, and correcting or deleting them to ensure the accuracy of the analysis. The cleaned data will be divided into multiple historical water potential data samples and corresponding historical power generation data samples. Each sample contains water potential information and corresponding power generation in a specific time period.

[0027] Then the Pearson correlation coefficient between each water potential parameter and power generation is calculated to evaluate the linear correlation between the water potential parameter and power generation. The Pearson correlation coefficient is a statistical method that measures the strength of the linear relationship between two variables based on the covariance and standard deviation of the two variables. Its value is between -1 and 1, where 1 represents a perfect positive correlation, -1 represents a perfect negative correlation, and 0 represents no linear correlation. The correlation analysis results are calculated by the Pearson correlation coefficient. Among them, the correlation analysis results refer to the quantitative results of the correlation between the water potential parameters and the power generation. The correlation analysis results are analyzed and interpreted to obtain the power generation impact analysis results. This process is to find out the key factors that affect the power generation efficiency, which will help to establish the mapping relationship between water potential and control parameters in the subsequent steps.

[0028] Step S3: extracting a plurality of key influencing factors according to the power generation impact analysis result, wherein the plurality of key influencing factors are water potential parameters that affect power generation.

[0029] Specifically, based on the strength and statistical significance of the correlation, determine which water potential parameters have a significant impact on power generation. Generally, parameters with high correlation and statistical significance are considered key influencing factors. For example, if the correlation coefficient between water level and power generation is high and this correlation is statistically significant, then water level will be identified as a key influencing factor. These key influencing factors are extracted from the numerous water potential parameters. These factors will be the basis for the subsequent establishment of water potential-parameter control mapping and optimization of control strategies.

[0030] Furthermore, step S3 of the embodiment of the present application also includes:

[0031] Based on the power generation impact analysis results, the water potential parameter-power generation relationship is fitted through decision tree regression to obtain an impact assessment model; according to the coefficients of the impact assessment model and combined with the correlation analysis results, key water potential parameters are identified to obtain multiple key influencing factors.

[0032] Specifically, first, a decision tree regression model is established using data analysis tools and techniques, such as R, Python, etc. Then, the power generation impact analysis results obtained in step S2, especially the correlation data between water potential parameters and power generation, are used as input data, and a decision tree regression model is applied to fit these data, and the model is trained to learn the association between them, and a relationship model between water potential parameters and power generation is established, that is, an impact assessment model. The impact assessment model obtained by decision tree regression can simulate complex nonlinear relationships through a series of segmentation rules, and evaluate the degree of influence of different water potential parameters on power generation.

[0033] Based on the established impact assessment model, combined with the correlation analysis results in step S2, key water potential parameters are identified. Key water potential parameters refer to water potential parameters that have a significant impact on power generation. The identification of these key water potential parameters is usually based on the coefficient size and statistical significance of each parameter in the model. Among them, the coefficient reflects the importance of each parameter to the power generation forecast. Parameters with larger coefficients mean that they have a greater impact on power generation. By viewing and comparing the coefficient sizes of each water potential parameter in the model, combined with the correlation analysis results in step S2, the importance of these parameters is further confirmed and they are identified as key influencing factors.

[0034] The above process identifies and extracts key influencing factors, selects a few parameters that are critical to power generation efficiency from a large amount of water potential data, and provides clear goals and basis for subsequent parameter control. This is conducive to more accurately adjusting the operating parameters of the generator to adapt to changes in water potential.

[0035] Step S4: Acquire multiple key control parameters of the hydroelectric generator, perform correlation mapping with the multiple key influencing factors, and establish a water potential-parameter control mapping.

[0036] Specifically, key control parameters refer to the operating parameters of the hydroelectric generator that can be directly adjusted and controlled, such as power generation capacity, speed, operating efficiency, water volume, net drop, etc. These parameters can be directly adjusted by the control system in response to changes in external water potential, thereby affecting the power generation efficiency. The water potential-control parameter mapping is a mapping relationship that links the water potential conditions determined by key influencing factors with the control parameters, and is used to preset or adjust the control parameters according to the current water potential conditions to achieve the optimal power generation effect. First, data related to the key control parameters are collected, which usually come from the operation log of the hydroelectric generator. This uses statistical or machine learning methods, such as linear regression, decision trees, or other algorithms, to build a model, apply historical data to train the model, and enable the model to predict the best control parameter settings based on the key influencing factors. The established model is integrated into the control system so that it can receive water potential data in real time and adjust the control parameters based on this data. By establishing a water potential-control parameter mapping, the control parameters of the generator can be automatically adjusted according to the current water potential conditions in real-time operation to optimize the power generation efficiency.

[0037] Furthermore, step S4 of the embodiment of the present application also includes:

[0038] Based on the model characteristics of the target hydroelectric generator, multiple key control parameters of the hydroelectric generator are obtained, and the multiple key control parameters include but are not limited to power generation capacity, rotation speed, operating efficiency, water volume, and net drop; according to the historical hydroelectric power generation records, mathematical statistical analysis is performed, and a mapping relationship between the multiple key influencing factors and the multiple key control parameters is established to obtain a water potential-parameter control mapping, and the water potential-parameter control mapping includes a variety of mapping combinations.

[0039] Specifically, the target hydroelectric generator refers to any hydroelectric generator that needs to be controlled. Obtain the model characteristics of the target hydroelectric generator, that is, the specific model and design and performance parameters of the target hydroelectric generator, which are usually provided by the manufacturer. Based on the model characteristics of the target hydroelectric generator, obtain its key control parameters. These parameters include power generation capacity, speed, operating efficiency, water volume, net drop, etc., which directly affect the operating status and output of the generator. Among them, power generation capacity refers to the maximum power that the hydroelectric generator can generate. Speed ​​refers to the rotation speed of the turbine, which affects the output power of the generator. Operating efficiency refers to the energy conversion efficiency of the generator under specific conditions. Water volume refers to the total amount of water flowing through the turbine. Net drop refers to the energy loss when water flows through the turbine.

[0040] Statistical methods, such as regression analysis and correlation analysis, are used to analyze the relationship between key influencing factors and key control parameters. For example, multiple regression may be used to analyze the relationship between factors such as water level and water flow velocity and power generation. Based on the results of statistical analysis, a mapping relationship between key influencing factors and key control parameters is established, namely, water potential-parameter control mapping. This mapping relationship can be a mathematical model, such as a linear equation, a polynomial equation, etc., which describes how the generator control parameters should be adjusted when the water potential parameters change. Since the relationship between the water potential parameters and the control parameters may not be a simple linear relationship, it is necessary to establish multiple mapping combinations to more accurately describe this relationship. For example, it may be found that the relationship between water level and speed is different in different water level intervals, so different mapping relationships need to be established for each interval. After the mapping relationship is established, historical data is used for verification to ensure the accuracy and reliability of the mapping relationship. If it is found that the mapping relationship cannot predict the actual power generation well, it is necessary to adjust the model parameters or use a more complex model. Finally, a water potential-parameter control mapping containing multiple mapping combinations is obtained.

[0041] The above process finds the best mapping relationship between water potential parameters and generator control parameters through historical data analysis, so as to automatically adjust the generator control parameters according to the current water potential conditions in real-time operation, thereby optimizing the power generation efficiency.

[0042] Step S5: Collect real-time water potential data, perform water potential dynamic analysis in combination with a water potential prediction model, and obtain water potential prediction results.

[0043] Specifically, real-time water potential data refers to the water potential situation at the current moment, such as water level, water flow rate, etc. The water potential prediction model is a mathematical model used to predict water potential changes in the future. The water potential prediction results refer to the future water potential changes based on the water potential prediction model. First, real-time water potential data is obtained through sensors such as water level meters and flow meters installed in the hydropower station. For example, the water level meter can provide the current water level height of the reservoir, while the flow meter can measure the water flow rate through the turbine. A water potential prediction model is trained based on historical data, such as a time series analysis model, a neural network model, etc. This model can predict the water potential change trend in the future based on historical water potential data and current real-time data, and obtain water potential prediction results. These results will be used for subsequent hydropower generator parameter control to optimize power generation efficiency and stability.

[0044] Furthermore, step S5 of the embodiment of the present application also includes:

[0045] Based on the multiple key influencing factors, multiple sensor types are determined; multiple key collection points are configured, and sensors are deployed in combination with the multiple sensor types to build a sensor network; real-time water potential data is acquired based on the sensor network; a water potential prediction model is constructed, and a water potential dynamic analysis is performed on the real-time water potential data to obtain a water potential prediction result.

[0046] Preferably, constructing a water potential prediction model comprises:

[0047] Based on the historical watershed information of the target area, a sample water potential data sequence is extracted; based on the sample water potential data sequence, supervised training is performed in combination with a long short-term memory network until the output data converges to obtain the water potential prediction model.

[0048] Specifically, according to the key influencing factors extracted in step S3, suitable sensor types are selected to monitor these factors. For example, if the water level is a key influencing factor, a water level meter will be selected; if it is flow, a flow meter may be selected. These sensors must be able to accurately measure these parameters and adapt to the field environment. Through terrain analysis and fluid dynamics simulation, the optimal sensor layout is determined, multiple key collection points are configured, and sensors are deployed in combination with the determined sensor types to build a sensor network. For example, water level meters and flow meters are deployed at key locations upstream and downstream of a hydroelectric power station to ensure that water potential changes can be fully monitored. Real-time water potential data is obtained through the constructed sensor network. These data will be used for subsequent water potential prediction and generator parameter control.

[0049] Collect historical water potential data for the target area, which includes water potential changes over a period of time, such as rainfall, temperature, humidity, etc. The target area refers to the working area of ​​the target hydroelectric generator, such as the area where the hydroelectric power station and hydroelectric power plant are located. Convert the historical data into a time series format to obtain a sample water potential data sequence for the long short-term memory network to learn. Use the long short-term memory network to conduct supervised training on these time series data, taking part of the data sequence as input and the other part as the expected output, so that the model can learn how to predict future water potential changes based on historical data. During the training process, the model will continuously adjust its internal parameters to minimize the prediction error. The training process will continue until the output data of the model converges, that is, the prediction error no longer decreases significantly. This indicates that the model has learned the key patterns in the data and can be used for actual water potential prediction. Use an independent validation data set to test the performance of the model. If the model's prediction effect is not good, it may be necessary to adjust the model structure or training process and then retrain the model. Output the trained model to obtain a water potential prediction model, which will analyze the real-time water potential data and give prediction results. These results will be used to guide the adjustment of the control strategy.

[0050] The above process deploys a sensor network based on key influencing factors to obtain accurate and effective real-time water potential data, and constructs a water potential prediction model to perform precise water potential prediction, providing reliable reference data for subsequent control strategy optimization.

[0051] Step S6: Read the real-time operating parameters of the generator, dynamically optimize the control strategy in combination with the water potential prediction result and the water potential-parameter control mapping, obtain the optimized control strategy, and perform generator parameter control based on the optimized control strategy.

[0052] Specifically, the real-time operating parameters of the generator refer to the operating status data of the generator at the current moment, including speed, flow, voltage, etc. The water potential prediction result obtained in step S5 is input into the water potential-parameter control mapping to obtain the expected generator control parameters, and then the real-time operating parameters of the generator are obtained through the control system of the generator. According to the real-time operating parameters and the expected generator control parameters, the control strategy is dynamically optimized to obtain the optimized control strategy. A communication connection is established with the control system of the target hydroelectric generator, and the optimized control strategy is sent to the control system. The optimized control strategy refers to the specific behavior or instructions for adjusting the control parameters of the target hydroelectric generator so that the target hydroelectric generator executes the best control parameter combination. The control system executes the optimized control strategy and adjusts the control parameters of the generator to achieve efficient and stable power generation.

[0053] Furthermore, if Figure 3 As shown, step S6 of the embodiment of the present application also includes:

[0054] Step S61: Read the real-time operating parameters of the generator through the generator control center.

[0055] Step S62: According to the water potential prediction result, the target control parameter mapping is performed using the water potential-control parameter mapping to obtain the target control parameter range.

[0056] Step S63: performing difference comparison calculation based on the real-time operating parameters of the generator and the target control parameter range to obtain a target parameter adjustment value.

[0057] Step S64: dynamically optimizing the control strategy according to the target parameter adjustment value to obtain an optimized control strategy.

[0058] Specifically, the generator control center monitors various parameters of the generator in real time, including speed, power generation capacity, etc. These parameters reflect the current working status of the generator. According to the water potential prediction results, the water potential-parameter control mapping is used to determine the ideal control parameter range that should be achieved under the predicted water potential conditions, that is, the range of the target control parameters. These parameters are set to maximize power generation efficiency or minimize potential risks. The real-time operating parameters of the current generator are compared with the target control parameter range, and the difference between each real-time operating parameter and the target control parameter range is calculated. According to these differences, the control parameter value that needs to be adjusted is calculated, that is, the target parameter adjustment value. For example, if the speed difference is 50 rpm, then the target parameter adjustment value is to increase the speed by 50 rpm. Finally, according to the calculated target parameter adjustment value, the control strategy of the generator is adjusted to obtain the optimized control strategy to ensure that the generator can maintain the optimal operating state under the predicted water potential changes.

[0059] In summary, the method for controlling parameters of a hydraulic generator based on dynamic analysis of water potential provided in the embodiment of the present application has the following technical effects:

[0060] By obtaining historical hydropower generation records, a data basis is provided for subsequent power generation impact analysis, helping to understand the relationship between water potential changes and power generation efficiency; based on the historical hydropower generation records, power generation impact analysis is performed, power generation impact analysis results are obtained, and key factors affecting power generation are further identified and analyzed, providing a basis for subsequent key influencing factor extraction to ensure the pertinence of the control strategy. According to the power generation impact analysis results, an impact assessment model is obtained through decision tree regression, multiple key influencing factors are extracted, and the most critical water potential parameters are identified from complex data, making the control strategy more efficient and accurate. Multiple key control parameters of the hydropower generator are obtained, and associated mapping is performed with the multiple key influencing factors to establish a water potential-parameter control mapping, establish a direct connection between water potential parameters and generator control parameters, provide a basis for rapid decision-making for real-time control, and improve response speed. Deploy a sensor network, collect real-time water potential data, combine the water potential prediction model to perform water potential dynamic analysis, obtain water potential prediction results, ensure the real-time and forward-looking nature of the control strategy, and improve the ability to respond to sudden water potential changes. The real-time operating parameters of the generator are read, and the control strategy is dynamically optimized in combination with the water potential prediction result and the water potential-parameter control mapping to obtain an optimized control strategy. Based on the optimized control strategy, the generator parameters are controlled and the generator operating parameters are dynamically adjusted to maximize the power generation efficiency and maintain the stable operation of the hydroelectric generator.

[0061] Overall, the embodiments of the present application can monitor, predict and respond to changes in water potential in real time, and continuously adjust operating parameters based on real-time water potential data and prediction results, thereby optimizing the operation of the hydroelectric generator, improving power generation efficiency and stability, and enabling the generator to adapt to environmental changes more flexibly and reduce energy waste.

[0062] Embodiment 2, as Figure 4 As shown, the embodiment of the present application provides a hydraulic generator parameter control system based on water potential dynamic analysis, the system comprising:

[0063] The historical record acquisition module 10 is used to acquire historical hydropower generation records, and the historical hydropower generation records include historical water potential data and historical power generation data.

[0064] The power generation impact analysis module 20 is used to perform power generation impact analysis based on the historical hydropower generation records and obtain power generation impact analysis results.

[0065] The influencing factor extraction module 30 is used to extract a plurality of key influencing factors according to the power generation impact analysis result, and the plurality of key influencing factors are water potential parameters that affect the power generation.

[0066] The association mapping module 40 is used to obtain a plurality of key control parameters of the hydroelectric generator, perform association mapping with the plurality of key influencing factors, and establish a water potential-parameter control mapping.

[0067] The water potential prediction module 50 is used to collect real-time water potential data, perform water potential dynamic analysis in combination with a water potential prediction model, and obtain water potential prediction results.

[0068] The control optimization module 60 is used to read the real-time operating parameters of the generator, dynamically optimize the control strategy in combination with the water potential prediction result and the water potential-parameter control mapping, obtain the optimized control strategy, and perform generator parameter control based on the optimized control strategy.

[0069] Furthermore, the power generation impact analysis module 20 of the embodiment of the present application is also used to perform the following steps:

[0070] After data cleaning of the historical hydropower generation records, multiple historical power generation data samples corresponding to multiple historical water potential data samples are obtained; the correlation between multiple water potential parameters and power generation is calculated through the Pearson correlation coefficient to obtain correlation analysis results; based on the correlation analysis results, power generation impact analysis results are obtained.

[0071] Furthermore, the impact factor extraction module 30 of the embodiment of the present application is also used to perform the following steps:

[0072] Based on the power generation impact analysis results, the water potential parameter-power generation relationship is fitted through decision tree regression to obtain an impact assessment model; according to the coefficients of the impact assessment model and combined with the correlation analysis results, key water potential parameters are identified to obtain multiple key influencing factors.

[0073] Furthermore, the association mapping module 40 in the embodiment of the present application is also used to perform the following steps:

[0074] Based on the model characteristics of the target hydroelectric generator, multiple key control parameters of the hydroelectric generator are obtained, and the multiple key control parameters include but are not limited to power generation capacity, rotation speed, operating efficiency, water volume, and net drop; according to the historical hydroelectric power generation records, mathematical statistical analysis is performed, and a mapping relationship between the multiple key influencing factors and the multiple key control parameters is established to obtain a water potential-parameter control mapping, and the water potential-parameter control mapping includes a variety of mapping combinations.

[0075] Furthermore, the water potential prediction module 50 of the embodiment of the present application is also used to perform the following steps:

[0076] Based on the multiple key influencing factors, multiple sensor types are determined; multiple key collection points are configured, and sensors are deployed in combination with the multiple sensor types to build a sensor network; real-time water potential data is acquired based on the sensor network; a water potential prediction model is constructed, and a water potential dynamic analysis is performed on the real-time water potential data to obtain a water potential prediction result.

[0077] Preferably, the water potential prediction module 50 of the embodiment of the present application is also used to perform the following steps:

[0078] Based on the historical watershed information of the target area, a sample water potential data sequence is extracted; based on the sample water potential data sequence, supervised training is performed in combination with a long short-term memory network until the output data converges to obtain the water potential prediction model.

[0079] Furthermore, the control optimization module 60 of the embodiment of the present application is also used to perform the following steps:

[0080] The real-time operating parameters of the generator are read through the generator control center; according to the water potential prediction result, the water potential-parameter control mapping is used to perform target control parameter mapping to obtain the target control parameter range; based on the real-time operating parameters of the generator and the target control parameter range, a difference comparison calculation is performed to obtain the target parameter adjustment value; according to the target parameter adjustment value, the control strategy is dynamically optimized to obtain the optimized control strategy.

[0081] Through the above-mentioned detailed description of the method for controlling parameters of a hydraulic generator based on dynamic analysis of water potential, those skilled in the art can clearly understand that the hydraulic generator parameter control system based on dynamic analysis of water potential in this embodiment, for the system disclosed in the second embodiment, since it corresponds to the method disclosed in the first embodiment, it has corresponding functional modules and beneficial effects, and the relevant parts can be referred to the description of the method part.

[0082] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for controlling parameters of a hydroelectric generator based on dynamic analysis of water potential, characterized in that: The method comprises: Acquiring historical hydropower generation records, wherein the historical hydropower generation records include historical water potential data and historical power generation data; Based on the historical hydropower generation records, perform power generation impact analysis and obtain power generation impact analysis results; Extracting a plurality of key influencing factors according to the power generation impact analysis result, wherein the plurality of key influencing factors are water potential parameters that affect power generation; Acquire multiple key control parameters of the hydroelectric generator, perform correlation mapping with the multiple key influencing factors, and establish a water potential-parameter control mapping; Collect real-time water potential data, conduct dynamic water potential analysis in combination with water potential prediction models, and obtain water potential prediction results; The real-time operating parameters of the generator are read, and the control strategy is dynamically optimized in combination with the water potential prediction result and the water potential-parameter control mapping to obtain the optimized control strategy, and the generator parameters are controlled based on the optimized control strategy.

2. The method for controlling parameters of a hydroelectric generator based on water potential dynamic analysis according to claim 1, characterized in that: Based on the historical hydropower generation records, a power generation impact analysis is performed to obtain power generation impact analysis results, including: After data cleaning of the historical hydropower generation records, a plurality of historical power generation data samples corresponding to the plurality of historical water potential data samples are obtained; The correlation between multiple water potential parameters and power generation is calculated through the Pearson correlation coefficient to obtain the correlation analysis results; Based on the correlation analysis result, a power generation impact analysis result is obtained.

3. The method for controlling parameters of a hydroelectric generator based on water potential dynamic analysis according to claim 2, characterized in that: According to the power generation impact analysis results, multiple key impact factors are extracted, including: Based on the power generation impact analysis results, the water potential parameter-power generation relationship is fitted through decision tree regression to obtain an impact assessment model; According to the coefficients of the impact assessment model and in combination with the correlation analysis results, key water potential parameters are identified to obtain a plurality of key impact factors.

4. The method for controlling parameters of a hydroelectric generator based on water potential dynamic analysis according to claim 1, characterized in that: Acquire multiple key control parameters of the hydroelectric generator, associate and map them with the multiple key influencing factors, and establish a water potential-parameter control mapping, including: Based on the model characteristics of the target hydroelectric generator, a plurality of key control parameters of the hydroelectric generator are obtained, wherein the plurality of key control parameters include but are not limited to power generation capacity, rotation speed, operation efficiency, water volume, and net drop; According to the historical hydropower generation records, mathematical statistical analysis is performed to establish a mapping relationship between the multiple key influencing factors and the multiple key control parameters to obtain a water potential-parameter control mapping, which includes a variety of mapping combinations.

5. The method for controlling parameters of a hydroelectric generator based on water potential dynamic analysis according to claim 1, characterized in that: Collect real-time water potential data, combine it with the water potential prediction model to perform water potential dynamic analysis, and obtain water potential prediction results, including: Based on the multiple key influencing factors, determining multiple sensor types; Configure multiple key collection points, combine the multiple sensor types, deploy sensors, and build a sensor network; acquiring real-time water potential data according to the sensor network; A water potential prediction model is constructed, and a water potential dynamic analysis is performed on the real-time water potential data to obtain a water potential prediction result.

6. The method for controlling parameters of a hydroelectric generator based on water potential dynamic analysis according to claim 5, characterized in that: Construct a water potential prediction model, including: Based on the historical watershed information of the target area, sample water potential data series are extracted; According to the sample water potential data sequence, supervised training is performed in combination with a long short-term memory network until the output data converges to obtain the water potential prediction model.

7. The method for controlling parameters of a hydroelectric generator based on water potential dynamic analysis according to claim 1, characterized in that: Read the real-time operating parameters of the generator, combine the water potential prediction results and the water potential-parameter control mapping, perform dynamic optimization of the control strategy, and obtain the optimized control strategy, including: Read the real-time operating parameters of the generator through the generator control center; According to the water potential prediction result, the target control parameter mapping is performed using the water potential-parameter control mapping to obtain the target control parameter range; Perform difference comparison calculation based on the real-time operating parameters of the generator and the target control parameter range to obtain a target parameter adjustment value; According to the target parameter adjustment value, the control strategy is dynamically optimized to obtain an optimized control strategy.

8. A hydraulic generator parameter control system based on water potential dynamic analysis, characterized in that: The system comprises: A historical record acquisition module, the historical record acquisition module is used to acquire historical hydropower generation records, the historical hydropower generation records include historical water potential data and historical power generation data; A power generation impact analysis module, the power generation impact analysis module is used to perform power generation impact analysis based on the historical hydropower generation records and obtain power generation impact analysis results; An influencing factor extraction module, wherein the influencing factor extraction module is used to extract a plurality of key influencing factors according to the power generation impact analysis result, wherein the plurality of key influencing factors are water potential parameters that affect power generation; An association mapping module, the association mapping module is used to obtain a plurality of key control parameters of the hydroelectric generator, perform association mapping with the plurality of key influencing factors, and establish a water potential-parameter control mapping; A water potential prediction module, which is used to collect real-time water potential data, perform water potential dynamic analysis in combination with a water potential prediction model, and obtain water potential prediction results; A control optimization module is used to read the real-time operating parameters of the generator, dynamically optimize the control strategy in combination with the water potential prediction result and the water potential-parameter control mapping, obtain the optimized control strategy, and perform generator parameter control based on the optimized control strategy.

Images