Hydropower station primary equipment monitoring and control method based on three-dimensional simulation monitoring system
Through a three-dimensional simulation monitoring system and machine learning algorithms, a prediction model for overheating faults of primary equipment in hydropower stations was established, which solved the problem of insufficient fault prediction in traditional monitoring technology and achieved accurate analysis of equipment status and safe and efficient operation.
Patent Information
- Application Number
- CN202510793088.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-06-13
- Publication Date
- 2025-09-16
AI Technical Summary
Traditional hydropower station primary equipment monitoring technology has difficulty capturing subtle changes in equipment operation, lacks accuracy and timeliness in fault prediction, and the control strategy cannot adapt to the complex and changing operating environment, increasing the risk of equipment overheating failure.
A three-dimensional simulation monitoring system and machine learning algorithm are used to establish a prediction model for overheating failures of primary equipment in hydropower stations. Through real-time monitoring data analysis and mathematical model optimization control strategies, accurate analysis of equipment status and fault prediction are achieved.
It significantly improves the accuracy and timeliness of fault prediction, reduces the incidence of equipment overheating failures, and improves the operational safety and efficiency of hydropower stations.
Smart Images
Figure CN120652799A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of primary equipment control of a hydropower station, and in particular to a primary equipment monitoring and control method of a hydropower station based on a three-dimensional simulation monitoring system. Background Art
[0002] Primary equipment in hydropower stations (such as generators and transformers) is a core component of hydropower station operations, and its operating status directly affects the safety and efficiency of the station. As the scale of hydropower stations expands and the operating environment becomes more complex, equipment overheating failures have become one of the main issues affecting their stable operation. Traditional monitoring technology for primary equipment in hydropower stations has many shortcomings. On the one hand, it relies on manual inspections and simple threshold alarms, which makes it difficult to capture subtle changes in equipment operation, resulting in insufficient accuracy and timeliness in fault prediction. On the other hand, traditional methods lack comprehensive analysis of equipment operating status and cannot fully utilize multi-dimensional monitoring data, resulting in fault diagnosis and preventive measures often lagging behind actual needs. In addition, traditional control strategies are usually based on fixed rules and are difficult to adapt to complex and changing operating environments. This not only reduces the operating efficiency of the equipment, but also may increase the risk of overheating failures. Summary of the Invention
[0003] The purpose of the present invention is to provide a method for monitoring and controlling primary equipment of a hydropower station based on a three-dimensional simulation monitoring system. Through real-time monitoring and machine learning algorithms, it improves the accuracy of fault prediction, optimizes the control strategy, ensures the safe and efficient operation of equipment, reduces the risk of failure, and improves the overall efficiency of the hydropower station.
[0004] The present invention is achieved through the following technical solutions:
[0005] A method for monitoring and controlling primary equipment of a hydropower station based on a three-dimensional simulation monitoring system, the method comprising the following steps:
[0006] The operating status of the primary equipment of the hydropower station is analyzed based on the monitoring data of the primary equipment of the hydropower station. An overheating fault prediction model for the primary equipment of the hydropower station is established through a machine learning algorithm. The operating status analysis results of the primary equipment of the hydropower station are input into the overheating fault prediction model of the primary equipment of the hydropower station for calculation to obtain the overheating fault prediction results of the primary equipment of the hydropower station;
[0007] A mathematical model of the primary equipment of a hydropower station is established, and the optimal control strategy of the primary equipment of the hydropower station is solved based on the overheating failure prediction results of the primary equipment of the hydropower station.
[0008] Optionally, it also includes obtaining monitoring data of the primary equipment of the hydropower station and performing preprocessing, which is specifically as follows:
[0009] Obtain monitoring data of primary equipment of hydropower stations, including historical monitoring data and real-time monitoring data of primary equipment of hydropower stations;
[0010] Conduct integrity checks on the historical monitoring data and real-time monitoring data of the hydropower station's primary equipment, and perform data cleaning and data normalization on the historical monitoring data and real-time monitoring data of the hydropower station's primary equipment in turn;
[0011] Output the pre-processed historical monitoring data and real-time monitoring data of the primary equipment of the hydropower station.
[0012] Optionally, the pre-processed real-time monitoring data of the primary equipment of the hydropower station is used to construct a three-dimensional model of the hydropower station, which is specifically:
[0013] Collect topographic data of hydropower stations;
[0014] Based on the topographic data of the hydropower station, a 3D model of the hydropower station is constructed in the 3D simulation monitoring system;
[0015] The real-time monitoring data of the primary equipment of the hydropower station is matched with the three-dimensional model of the hydropower station to obtain a real-time three-dimensional model of the hydropower station combined with the real-time monitoring data of the primary equipment of the hydropower station.
[0016] Optionally, the operating status of the primary equipment of the hydropower station is analyzed based on the monitoring data of the primary equipment of the hydropower station, which is specifically:
[0017] Extract features from real-time monitoring data of primary equipment in hydropower stations to obtain temperature and flow indicators of primary equipment in hydropower stations;
[0018] Analyze the temperature and flow indicators of the primary equipment of the hydropower station, including:
[0019] Calculate the mean and standard deviation of the hydropower station's primary equipment temperature indicators to determine whether the current temperature of the hydropower station's primary equipment deviates from its mean by more than 2 standard deviations, or whether the current temperature of the hydropower station's primary equipment exceeds the set safety temperature threshold;
[0020] Calculate the mean and standard deviation of the primary equipment of the hydropower station to determine whether the current flow of the primary equipment of the hydropower station deviates from its mean by more than 2 times the standard deviation, or whether the current flow of the primary equipment of the hydropower station is lower than the set minimum flow threshold;
[0021] The evaluation results of the temperature and flow indicators of the primary equipment of the hydropower station are integrated into the operating status analysis results of the primary equipment of the hydropower station, and defined as input data to the overheating fault prediction model of the primary equipment of the hydropower station.
[0022] Optionally, the overheating fault prediction model for primary equipment of a hydropower station is established by a machine learning algorithm, which specifically adopts a support vector machine algorithm.
[0023] Optionally, the training process of the hydropower station primary equipment overheating fault prediction model is:
[0024] The fault status of the primary equipment of the hydropower station is defined as the target variable, and the temperature index and flow index are defined as the characteristic variables. Based on the support vector machine algorithm, a prediction model for the overheating fault of the primary equipment of the hydropower station is constructed.
[0025] Based on the pre-processed historical monitoring data of the primary equipment of the hydropower station, the historical operating status analysis results of the primary equipment of the hydropower station are obtained, and the data set is used as an input to the overheating fault prediction model of the primary equipment of the hydropower station;
[0026] The dataset is divided into a training set and a test set. The overheating fault prediction model of the primary equipment of the hydropower station is calculated using the training set, and the loss value of the overheating fault prediction model of the primary equipment of the hydropower station on the test set is calculated. The parameters of the overheating fault prediction model of the primary equipment of the hydropower station are iteratively updated according to the loss value.
[0027] Completed the training of the overheating failure prediction model for primary equipment in hydropower stations.
[0028] Optionally, the mathematical model of the primary equipment of the hydropower station is established by using an MPC algorithm.
[0029] Optionally, the specific process of establishing the mathematical model of the primary equipment of the hydropower station is as follows:
[0030] Define the dynamic equations of the primary equipment of the hydropower station and characterize the relationship between the temperature and flow of the primary equipment of the hydropower station;
[0031] The dynamic equation is combined with the overheating fault prediction results of the primary equipment of the hydropower station, and an optimization objective function is set. By minimizing the temperature deviation and optimizing the flow control, the objective function is solved, and the optimal input flow and output flow are output to represent the optimal control strategy of the primary equipment of the hydropower station.
[0032] Optionally, the dynamic equation defining the primary equipment of the hydropower station is calculated as follows:
[0033]
[0034] Where T(t) is the temperature of the primary equipment of the hydropower station at time t, is the rate of change of the temperature of the primary equipment of the hydropower station over time, Q in (t) is the input flow at time t, Q out (t) is the output flow at time t, H is the heat loss function, and C is the heat capacity of the primary equipment of the hydropower station.
[0035] Optionally, the objective function is calculated as follows:
[0036]
[0037] Among them, J is the objective function, T set To set the safety temperature, T f is the end point of the control time range, and λ is the weight coefficient.
[0038] The technical solution of the present invention has at least the following advantages and beneficial effects:
[0039] By integrating real-time monitoring data and machine learning algorithms, the present invention significantly improves the accuracy and timeliness of overheating fault predictions for primary equipment in hydropower stations. On the one hand, operating status analysis based on multi-dimensional data can comprehensively assess the health of the equipment and provide a more reliable basis for fault prediction. On the other hand, by establishing a dynamic mathematical model and optimizing the objective function, the optimal control strategy can be solved to ensure that the equipment operates efficiently within a safe temperature range. This not only reduces the workload of manual inspections, but also reduces the incidence of equipment overheating failures, thereby extending the service life of the equipment and improving the overall operating efficiency of the hydropower station, providing a scientific basis and practical tools for the safety management and performance optimization of primary equipment in hydropower stations. BRIEF DESCRIPTION OF THE DRAWINGS
[0040] Figure 1 A schematic flow chart of a method for monitoring and controlling primary equipment of a hydropower station based on a three-dimensional simulation monitoring system provided by the present invention;
[0041] Figure 2 A logical diagram of the operating status analysis provided by the present invention;
[0042] Figure 3 This is a schematic diagram of the training logic of the hydropower station primary equipment overheating fault prediction model provided by the present invention. DETAILED DESCRIPTION
[0043] To make the objectives, technical solutions, and advantages of the present invention more apparent, the following will provide a clear and complete description of the technical solutions of the present invention in conjunction with the accompanying drawings. It should be understood that the description is only a portion of the present invention, not all of it. The components of the present invention generally described and illustrated in the drawings herein may be arranged and designed in a variety of different configurations.
[0044] like Figure 1 As shown, the present invention provides one embodiment: a method for monitoring and controlling primary equipment of a hydropower station based on a three-dimensional simulation monitoring system, the method comprising the following steps:
[0045] The operating status of the primary equipment of the hydropower station is analyzed based on the monitoring data of the primary equipment of the hydropower station. An overheating fault prediction model for the primary equipment of the hydropower station is established through a machine learning algorithm. The operating status analysis results of the primary equipment of the hydropower station are input into the overheating fault prediction model of the primary equipment of the hydropower station for calculation to obtain the overheating fault prediction results of the primary equipment of the hydropower station;
[0046] A mathematical model of the primary equipment of a hydropower station is established, and the optimal control strategy of the primary equipment of the hydropower station is solved based on the overheating failure prediction results of the primary equipment of the hydropower station.
[0047] In a specific application of this embodiment, a sensor network is used to monitor various operating parameters of a hydropower station's primary equipment in real time, including key data such as temperature, flow rate, and pressure. This data is transmitted to a central processing unit via a data acquisition system to form a complete monitoring data set. Data processing software then preprocesses the historical monitoring data to extract relevant features, such as mean, standard deviation, and outliers, to assess the current operating status of the hydropower station's primary equipment. After data analysis is complete, a machine learning algorithm is used to establish a prediction model for overheating failures in the hydropower station's primary equipment. This model is trained to improve its accuracy in fault prediction by combining known historical failure data with current monitoring data. Real-time analysis results of the hydropower station's primary equipment operating status are then input into this prediction model for calculations to obtain overheating failure predictions for the hydropower station's primary equipment, providing data support for subsequent optimization of control strategies. Furthermore, this embodiment establishes a mathematical model to describe the dynamic characteristics of the hydropower station's primary equipment. This model comprehensively considers factors such as the equipment's thermal capacity, flow dynamics, and heat loss to establish a relationship between temperature and flow rate. Based on the overheating fault prediction results, an optimization objective function is set, and the optimal control strategy is solved by adjusting the input flow and output flow to ensure that the equipment operates efficiently within a safe temperature range. This not only achieves accurate analysis of the operating status and fault prediction of the primary equipment of the hydropower station, but also provides effective mathematical support for the control optimization of the primary equipment of the hydropower station, significantly improving the operational safety and economy of the hydropower station.
[0048] Specifically, it also includes obtaining monitoring data of the primary equipment of the hydropower station and performing preprocessing, which is specifically as follows:
[0049] Obtain monitoring data of primary equipment of hydropower stations, including historical monitoring data and real-time monitoring data of primary equipment of hydropower stations;
[0050] Conduct integrity checks on the historical monitoring data and real-time monitoring data of the hydropower station's primary equipment, and perform data cleaning and data normalization on the historical monitoring data and real-time monitoring data of the hydropower station's primary equipment in turn;
[0051] Output the pre-processed historical monitoring data and real-time monitoring data of the primary equipment of the hydropower station.
[0052] In the specific implementation of this embodiment, the pre-processed real-time monitoring data of the primary equipment of the hydropower station is used to construct a three-dimensional model of the hydropower station, which is specifically:
[0053] Collect topographic data of hydropower stations;
[0054] Based on the topographic data of the hydropower station, a 3D model of the hydropower station is constructed in the 3D simulation monitoring system;
[0055] The real-time monitoring data of the primary equipment of the hydropower station is matched with the three-dimensional model of the hydropower station to obtain a real-time three-dimensional model of the hydropower station combined with the real-time monitoring data of the primary equipment of the hydropower station.
[0056] During implementation, this embodiment uses a geographic information system (GIS) to collect topographic data for the hydropower station's area, including information such as the station's terrain elevation, river flow, regional vegetation, and water source distribution. After obtaining this topographic data, an initial 3D model of the hydropower station is constructed within a 3D simulation monitoring system. Real-time monitoring data from the hydropower station's primary equipment is then matched to the constructed 3D model. By linking real-time data (such as monitoring parameters like temperature, flow, and pressure) with the location and status of primary equipment in the 3D model, the 3D model is dynamically updated, creating a real-time monitoring 3D visualization system. This not only provides a visual display of monitoring data in space but also supports analysis of equipment performance under specific circumstances. Notably, the constructed 3D model provides a spatial foundation for the overheating fault model and digital model developed subsequently in this embodiment, enabling more precise consideration of primary equipment layout, heat conduction paths, and environmental factors during thermal analysis. Furthermore, the 3D model provides spatial information about the equipment layout and operating environment for the overheating fault prediction model, helping to more accurately locate fault risk areas. Furthermore, by integrating the 3D model with the digital model, and linking real-time monitoring data from the equipment with the dynamic equations and objective functions in the digital model, the optimal control strategy for the equipment can be more efficiently determined. For example, the digital model can optimize flow regulation and temperature control strategies based on the equipment location and environmental conditions in the 3D model, thereby reducing the probability of overheating failures.
[0057] like Figure 2 As shown, in a further implementation, the operating status of the primary equipment of the hydropower station is analyzed based on the monitoring data of the primary equipment of the hydropower station, which is specifically:
[0058] Extract features from real-time monitoring data of primary equipment in hydropower stations to obtain temperature and flow indicators of primary equipment in hydropower stations;
[0059] Analyze the temperature and flow indicators of the primary equipment of the hydropower station, including:
[0060] Calculate the mean and standard deviation of the hydropower station's primary equipment temperature indicators to determine whether the current temperature of the hydropower station's primary equipment deviates from its mean by more than 2 standard deviations, or whether the current temperature of the hydropower station's primary equipment exceeds the set safety temperature threshold;
[0061] Calculate the mean and standard deviation of the primary equipment of the hydropower station to determine whether the current flow of the primary equipment of the hydropower station deviates from its mean by more than 2 times the standard deviation, or whether the current flow of the primary equipment of the hydropower station is lower than the set minimum flow threshold;
[0062] The evaluation results of the temperature and flow indicators of the primary equipment of the hydropower station are integrated into the operating status analysis results of the primary equipment of the hydropower station, and defined as input data to the overheating fault prediction model of the primary equipment of the hydropower station.
[0063] In specific implementation, this embodiment performs feature extraction on the real-time monitoring data of the primary equipment of the hydropower station to obtain the temperature index and flow index of the equipment respectively. In the temperature index analysis, the historical mean and standard deviation of the equipment temperature are calculated to determine whether the current temperature deviates from the mean by more than 2 times the standard deviation, or whether it exceeds the set safety temperature threshold. If it deviates or exceeds the limit, it is marked as an abnormal state. In the flow index analysis, the historical mean and standard deviation of the flow are also calculated to determine whether the current flow deviates from the mean by more than 2 times the standard deviation, or whether it is lower than the set minimum flow threshold. If it deviates or is lower than the threshold, it is marked as an abnormal state. The evaluation results of the temperature index and the flow index are integrated into the operating status analysis results of the primary equipment of the hydropower station, and input as input data into the overheating fault prediction model of the primary equipment of the hydropower station.
[0064] like Figure 3 As shown, in the specific application of this embodiment, the overheating fault prediction model of the primary equipment of the hydropower station is established by using a machine learning algorithm, which specifically adopts a support vector machine algorithm.
[0065] The training process of the hydropower station primary equipment overheating fault prediction model is as follows:
[0066] The fault status of the primary equipment of the hydropower station is defined as the target variable, and the temperature index and flow index are defined as the characteristic variables. Based on the support vector machine algorithm, a prediction model for the overheating fault of the primary equipment of the hydropower station is constructed.
[0067] Based on the pre-processed historical monitoring data of the primary equipment of the hydropower station, the historical operating status analysis results of the primary equipment of the hydropower station are obtained, and the data set is used as an input to the overheating fault prediction model of the primary equipment of the hydropower station;
[0068] The dataset is divided into a training set and a test set. The overheating fault prediction model of the primary equipment of the hydropower station is calculated using the training set, and the loss value of the overheating fault prediction model of the primary equipment of the hydropower station on the test set is calculated. The parameters of the overheating fault prediction model of the primary equipment of the hydropower station are iteratively updated according to the loss value.
[0069] Completed the training of the overheating failure prediction model for primary equipment in hydropower stations.
[0070] Specifically, this embodiment defines the fault status of a hydropower station's primary equipment as the target variable, and temperature and flow indicators as feature variables. The fault status is a binary variable indicating whether the equipment has experienced an overheating fault. The temperature and flow indicators serve as model input features, used to predict the probability of a fault. Based on preprocessed historical monitoring data of the hydropower station's primary equipment, historical equipment operating status analysis results are obtained, including the mean and standard deviation of the temperature and flow indicators, as well as records of whether the equipment has experienced an overheating fault. This data is integrated into a dataset, which serves as the basis for model training. This embodiment divides the dataset into a training set and a test set, typically in a ratio of 7:3 or 8:2. The training set is used for model learning, while the test set is used to evaluate model performance. A support vector machine model is calculated using the training set. The model classifies the data using a radial basis kernel function and learns the relationship between the temperature and flow indicators and the fault status. During training, the model's loss on the test set is calculated using the cross-entropy loss function to evaluate the model's prediction accuracy and generalization ability. Based on the loss value, the model parameters are iteratively updated using the gradient descent method to gradually reduce the loss and improve the model's prediction accuracy. After model training was completed, the resulting hydropower station primary equipment overheating failure prediction model was able to predict the likelihood of equipment overheating failure based on temperature and flow indicators in real-time monitoring data. This provided a reliable tool for subsequent equipment status monitoring and fault prevention, improving the stability and safety of hydropower station operations.
[0071] In a further implementation, the mathematical model of the primary equipment of the hydropower station is established by using an MPC algorithm.
[0072] The specific process of establishing the mathematical model of the primary equipment of the hydropower station is as follows:
[0073] Define the dynamic equation of the primary equipment of the hydropower station to characterize the relationship between the temperature and flow of the primary equipment of the hydropower station. The calculation formula is:
[0074]
[0075] Where T(t) is the temperature of the primary equipment of the hydropower station at time t, is the rate of change of the temperature of the primary equipment of the hydropower station over time, Q in(t) is the input flow at time t, Q out (t) is the output flow at time t, H is the heat loss function, and C is the heat capacity of the primary equipment of the hydropower station.
[0076] The dynamic equation is combined with the overheating fault prediction results of the primary equipment of the hydropower station, and an optimization objective function is set. By minimizing the temperature deviation and optimizing the flow control, the objective function is solved, and the optimal input flow and output flow are output to represent the optimal control strategy of the primary equipment of the hydropower station.
[0077] The objective function is calculated as follows:
[0078]
[0079] Among them, J is the objective function, T set To set the safety temperature, T f is the end point of the control time range, and λ is the weight coefficient.
[0080] This embodiment collects real-time monitoring data of the primary equipment of the hydropower station, including temperature, input flow and output flow, and pre-processes the data to ensure its integrity and accuracy. Based on the collected data, a dynamic equation is constructed to describe the rate of change of the temperature of the primary equipment over time. The heat loss function and the heat capacity of the equipment are introduced into the equation to reflect the impact of flow changes on temperature. Subsequently, this embodiment sets an objective function to quantify the deviation between the equipment temperature and the set safety temperature, as well as the difference between the input flow and the output flow. The objective function adjusts the contribution of each item through the weight coefficient λ. After the digital model is constructed, the real-time monitoring data is input into the dynamic equation and the objective function. The operating parameters of the primary equipment of the hydropower station are adjusted in real time according to the final output solution, which can achieve safe and efficient operation of the primary equipment of the hydropower station.
[0081] The above is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Those skilled in the art will readily appreciate that the present invention is susceptible to various modifications and variations. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention shall be included within the scope of protection of the present invention.
Claims
1. A method for monitoring and controlling primary equipment of a hydropower station based on a three-dimensional simulation monitoring system, characterized in that: The steps of the method include: The operating status of the primary equipment of the hydropower station is analyzed based on the monitoring data of the primary equipment of the hydropower station. An overheating fault prediction model for the primary equipment of the hydropower station is established through a machine learning algorithm. The operating status analysis results of the primary equipment of the hydropower station are input into the overheating fault prediction model of the primary equipment of the hydropower station for calculation to obtain the overheating fault prediction results of the primary equipment of the hydropower station; A mathematical model of the primary equipment of a hydropower station is established, and the optimal control strategy of the primary equipment of the hydropower station is solved based on the overheating failure prediction results of the primary equipment of the hydropower station.
2. The method for monitoring and controlling primary equipment of a hydropower station based on a three-dimensional simulation monitoring system according to claim 1 is characterized in that: It also includes obtaining monitoring data of primary equipment of hydropower station and preprocessing it, specifically: Obtain monitoring data of primary equipment of hydropower stations, including historical monitoring data and real-time monitoring data of primary equipment of hydropower stations; Conduct integrity checks on the historical monitoring data and real-time monitoring data of the hydropower station's primary equipment, and perform data cleaning and data normalization on the historical monitoring data and real-time monitoring data of the hydropower station's primary equipment in turn; Output the pre-processed historical monitoring data and real-time monitoring data of the primary equipment of the hydropower station.
3. The method for monitoring and controlling primary equipment of a hydropower station based on a three-dimensional simulation monitoring system according to claim 2 is characterized in that: The pre-processed real-time monitoring data of the primary equipment of the hydropower station is used to construct a three-dimensional model of the hydropower station, which is specifically: Collect topographic data of hydropower stations; Based on the topographic data of the hydropower station, a 3D model of the hydropower station is constructed in the 3D simulation monitoring system; The real-time monitoring data of the primary equipment of the hydropower station is matched with the three-dimensional model of the hydropower station to obtain a real-time three-dimensional model of the hydropower station combined with the real-time monitoring data of the primary equipment of the hydropower station.
4. The method for monitoring and controlling primary equipment of a hydropower station based on a three-dimensional simulation monitoring system according to claim 3 is characterized in that: The analysis of the operating status of the primary equipment of the hydropower station based on the monitoring data of the primary equipment of the hydropower station is specifically as follows: Extract features from real-time monitoring data of primary equipment in hydropower stations to obtain temperature and flow indicators of primary equipment in hydropower stations; Analyze the temperature and flow indicators of the primary equipment of the hydropower station, including: Calculate the mean and standard deviation of the hydropower station's primary equipment temperature indicators to determine whether the current temperature of the hydropower station's primary equipment deviates from its mean by more than 2 standard deviations, or whether the current temperature of the hydropower station's primary equipment exceeds the set safety temperature threshold; Calculate the mean and standard deviation of the primary equipment of the hydropower station to determine whether the current flow of the primary equipment of the hydropower station deviates from its mean by more than 2 times the standard deviation, or whether the current flow of the primary equipment of the hydropower station is lower than the set minimum flow threshold; The evaluation results of the temperature and flow indicators of the primary equipment of the hydropower station are integrated into the operating status analysis results of the primary equipment of the hydropower station, and defined as input data to the overheating fault prediction model of the primary equipment of the hydropower station.
5. The method for monitoring and controlling primary equipment of a hydropower station based on a three-dimensional simulation monitoring system according to claim 4 is characterized in that: The overheating fault prediction model of the primary equipment of the hydropower station is established by using a machine learning algorithm, which specifically adopts a support vector machine algorithm.
6. The method for monitoring and controlling primary equipment of a hydropower station based on a three-dimensional simulation monitoring system according to claim 5 is characterized in that: The training process of the hydropower station primary equipment overheating fault prediction model is as follows: The fault status of the primary equipment of the hydropower station is defined as the target variable, and the temperature index and flow index are defined as the characteristic variables. Based on the support vector machine algorithm, a prediction model for the overheating fault of the primary equipment of the hydropower station is constructed. Based on the pre-processed historical monitoring data of the primary equipment of the hydropower station, the historical operating status analysis results of the primary equipment of the hydropower station are obtained, and the data set is used as an input to the overheating fault prediction model of the primary equipment of the hydropower station; The dataset is divided into a training set and a test set. The overheating fault prediction model of the primary equipment of the hydropower station is calculated using the training set, and the loss value of the overheating fault prediction model of the primary equipment of the hydropower station on the test set is calculated. The parameters of the overheating fault prediction model of the primary equipment of the hydropower station are iteratively updated according to the loss value. Completed the training of the overheating failure prediction model for primary equipment in hydropower stations.
7. The method for monitoring and controlling primary equipment of a hydropower station based on a three-dimensional simulation monitoring system according to claim 6 is characterized in that: The mathematical model of the primary equipment of the hydropower station is established by using the MPC algorithm.
8. The method for monitoring and controlling primary equipment of a hydropower station based on a three-dimensional simulation monitoring system according to claim 7 is characterized in that: The specific process of establishing the mathematical model of the primary equipment of the hydropower station is as follows: Define the dynamic equations of the primary equipment of the hydropower station and characterize the relationship between the temperature and flow of the primary equipment of the hydropower station; The dynamic equation is combined with the overheating fault prediction results of the primary equipment of the hydropower station, and an optimization objective function is set. By minimizing the temperature deviation and optimizing the flow control, the objective function is solved, and the optimal input flow and output flow are output to represent the optimal control strategy of the primary equipment of the hydropower station.
9. The method for monitoring and controlling primary equipment of a hydropower station based on a three-dimensional simulation monitoring system according to claim 8, characterized in that: The dynamic equations defining the primary equipment of a hydropower station are calculated as follows: Where T(t) is the temperature of the primary equipment of the hydropower station at time t, is the rate of change of the temperature of the primary equipment of the hydropower station over time, Q in (t) is the input flow at time t, Q out (t) is the output flow at time t, H is the heat loss function, and C is the heat capacity of the primary equipment of the hydropower station.
10. The method for monitoring and controlling primary equipment of a hydropower station based on a three-dimensional simulation monitoring system according to claim 9, characterized in that: The objective function is calculated as follows: Among them, J is the objective function, Tse t To set the safety temperature, T f is the end point of the control time range, and λ is the weight coefficient.