Power station anti-flooding monitoring system and method based on Internet

Abstract

The invention discloses an internet-based power station anti-flooding monitoring system and method, and relates to the technical field of power station management. Comprising an intelligent water regimen prediction module, an intelligent drainage optimization control module, an underwater sensing network module, an environment collaborative sensing module, an automatic facility protection module, an abnormal event instant alarm module and a community linkage emergency response module. According to the monitoring system and method for preventing the power station from being flooded based on the Internet, by integrating technologies of intelligent water regimen prediction, real-time drainage optimization, underwater sensing network and the like, the defects in the prior art are overcome, and multi-dimension of data sensing, dynamic prediction analysis and intelligence of protective measures are achieved; the monitoring precision and response efficiency of complex hydrological events are remarkably improved, the transparency and fairness of resource scheduling can be enhanced through a block chain-based cooperative network, and a comprehensive and efficient protection solution is provided for a power station and surrounding communities.

Description

Technical Field

[0001] The present invention relates to the technical field of power station management, and in particular to an Internet-based monitoring system and method for preventing power station flooding. Background Art

[0002] In recent years, global climate change has triggered frequent extreme weather events. As critical energy infrastructure, power plants face an increasingly severe threat from flooding. Traditional flood prevention and monitoring technologies typically rely on a single data source and simple water regime prediction models. Their shortcomings are primarily reflected in the following aspects: The data is single and updated with lag: Existing systems typically rely solely on data from ground sensors or weather stations and lack comprehensive perception of multi-dimensional environmental factors (such as soil moisture, surface roughness, and underwater dynamics), resulting in limited data coverage and real-time performance.

[0003] Insufficient accuracy of the prediction model: Traditional flood forecasting models are mostly based on static empirical formulas and fail to fully utilize machine learning or physical simulation techniques to dynamically optimize forecasts. This results in limited ability to simulate flood responses in complex river basins. In particular, the lack of high-resolution three-dimensional flood modeling makes it difficult to refine risk assessments.

[0004] In order to solve the above problems, we propose an Internet-based monitoring system and method for power station flooding prevention. Summary of the Invention

[0005] In view of the deficiencies in the prior art, the present invention provides an Internet-based monitoring system and method for power station flooding prevention, so as to solve the problems raised in the above background technology.

[0006] To achieve the above objectives, the present invention provides the following technical solutions: an Internet-based monitoring system for power station flooding prevention, comprising an intelligent water regime prediction module, an intelligent drainage optimization control module, an underwater sensing network module, an environmental collaborative sensing module, an automated facility protection module, an abnormal event instant alarm module, and a community linkage emergency response module; An intelligent water regime prediction module uses meteorological data and machine learning algorithms to predict water regime changes around power stations; The intelligent drainage optimization control module is used to monitor the status of the power station drainage system in real time and make intelligent decisions to open, close or adjust the operating parameters of the drainage equipment based on the prediction data output by the intelligent water condition prediction module; The underwater sensing network module, based on acoustic communication technology, monitors the water flow dynamics within the power station area in real time, providing real-time water flow speed, depth, and flow direction data to the intelligent drainage optimization control module, thereby refining the execution of drainage optimization strategies. The collaborative environmental perception module is used to collaboratively perceive multi-dimensional environmental factors, including hydrology, geology, meteorology, and soil moisture. It combines data monitored by the underwater perception network module to generate a comprehensive risk map of the power station and its surrounding environment. The automated facility protection module, based on the comprehensive risk map provided by the collaborative environmental perception module and the forecast data provided by the intelligent water situation prediction module, is responsible for quickly initiating facility protection measures when the power station is predicted to be facing flooding threats. It adjusts the protection devices, including the position and height of protective panels, automatic sealing doors, and underwater isolation walls, according to the real-time water conditions. Abnormal event instant alarm module, used to quickly capture potential flood abnormal events and issue alarms to relevant personnel, and to monitor the execution of the intelligent water situation prediction module, intelligent drainage optimization control module, and automated facility protection module in real time; The community-linked emergency response module builds an Internet-based multi-party collaboration platform. Based on the alarm mechanism triggered by the abnormal event instant alarm module, it quickly coordinates various emergency resources, supports intelligent resource scheduling, and generates the optimal scheduling plan by analyzing the materials, equipment and personnel inside and outside the power station.

[0007] To further optimize this technical solution, the intelligent water regime prediction module collects meteorological data, including historical data on rainfall, wind speed, temperature, and river water level, and uses the time series prediction model LSTM to perform real-time calculation and trend prediction; The intelligent water situation prediction module has a built-in flood basin simulation model, and constructs a three-dimensional flood model based on the geographic information system GIS and basin analysis algorithm.

[0008] To further optimize this technical solution, the flood basin simulation model achieves dynamic prediction of the basin's hydrological behavior and the hydrological response of the basin surrounding the power station to heavy rainfall events by modeling rainfall, topography, and basin characteristics. The flood basin simulation model is shown below: ; in, :The basin around the power station in time The total amount of flow at that time; : In subunit Time rainfall intensity at that time; : Subunit The rainfall runoff coefficient represents the efficiency of converting rainfall into surface runoff under different terrain and soil conditions, and its value range is ; : Subunit area; : The damping factor of the path in the basin, reflecting the The loss of water flowing to the power station depends on the characteristics of the basin slope and surface roughness; : Subunit Length of water flow path to the power station; : Damping attenuation coefficient, which depends on the characteristics of the watershed surrounding the power station; :time evapotranspiration.

[0009] To further optimize this technical solution, the intelligent drainage optimization control module uses Internet of Things control technology to monitor the drainage equipment in the power station, including pumps and drainage gates, adjust the operating parameters of the drainage equipment, and automatically adapt to different drainage demand scenarios, thereby optimizing the drainage strategy; Before a flood strikes, the module will link data with the intelligent water situation prediction module to start drainage equipment in advance to reduce the risk of waterlogging. At the same time, after rainfall, it will intelligently assess whether additional drainage facilities need to be opened to minimize waste of power station resources.

[0010] To further optimize this technical solution, the intelligent drainage optimization control module constructs an intelligent evaluation model when intelligently evaluating whether additional drainage facilities need to be opened after rainfall. The intelligent evaluation model is as follows: ; in, : In time The total amount of flow at that time; :Intelligent evaluation results; when When , it means that the current drainage and protection capabilities are insufficient and additional drainage needs to be started; when When , it means that the current resources are sufficient and there is no need to increase the equipment operation; :For all power stations The sum of the operating capacities of the drainage equipment; :Drainage equipment In time Actual drainage capacity; : Equipment operating efficiency factor, used to consider aging and environmental impact, the value range is ; : The current operating status of the device, on = 1, off = 0.

[0011] Further optimizing this technical solution, the underwater sensing network module uses sound waves to transmit data by arranging underwater sensor nodes; The sensor nodes are responsible for measuring water flow speed, depth, and direction, and uploading the data to the buoy receiver via hydroacoustic signals, and then uploading it to the cloud of the monitoring system via wireless networks.

[0012] To further optimize this technical solution, the collaborative environmental perception module generates a comprehensive risk map of the power plant and its surrounding environment by integrating high-altitude drone imagery, remote sensing satellite data, and ground sensor networks. Using hyperspectral remote sensing technology to detect the turbidity and pollutant content of surface water to determine whether floodwaters may carry large amounts of sediment that could damage power plant facilities; By analyzing geological information, the risk of soil landslide or subsidence around the power station is monitored, providing comprehensive flood-related information.

[0013] To further optimize this technical solution, the abnormal event instant alarm module identifies abnormal signals that may indicate flooding risks through real-time monitoring of hydrological data; If the water level sensor reports a sudden increase in a short period of time, consider combining it with the water situation forecast to assess whether the abnormal signal represents a real risk. The abnormal event instant alarm module integrates natural language processing (NLP) technology to mine flood warning information related to the power station area from unstructured data sources such as social media platforms and news, enabling early perception of unknown risks.

[0014] To further optimize this technical solution, the community-linked emergency response module, based on a multi-party collaborative platform, pushes early warning information to community residents in real time through a mobile app, providing key data such as evacuation route planning, real-time traffic conditions, and water level change maps; The multi-party collaboration platform is built based on blockchain technology, and all operation records can be traced, thus ensuring the transparency and fairness of the emergency resource allocation process.

[0015] An Internet-based power station flooding prevention monitoring method is operated based on the above-mentioned Internet-based power station flooding prevention monitoring system and includes the following specific steps: S1, environmental data collection and preprocessing; S2, real-time water situation forecast; S3, intelligent drainage optimization; S4, Facility protection started; S5. Warning of abnormal events; S6. Community-linked emergency response.

[0016] Compared with the existing technology, the present invention provides an Internet-based monitoring system and method for power station flooding prevention, which has the following beneficial effects: This internet-based monitoring system and method for power station flooding prevention overcomes the shortcomings of existing technologies by integrating technologies such as intelligent water situation prediction, real-time drainage optimization, and underwater sensing networks. It achieves multidimensional data perception, dynamic predictive analysis, and intelligent protection measures. It not only significantly improves the monitoring accuracy and response efficiency of complex hydrological events, but also enhances the transparency and fairness of resource scheduling through a blockchain-based collaborative network, providing a comprehensive and efficient protection solution for power stations and surrounding communities. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 This is a schematic structural diagram of an Internet-based power station flooding prevention monitoring system proposed by the present invention; Figure 2 This is a flow chart of a flood basin simulation model in an Internet-based power station flood prevention monitoring system proposed by the present invention; Figure 3 The present invention provides a flow chart of an Internet-based method for monitoring power station flooding prevention. DETAILED DESCRIPTION

[0018] The following will be combined with the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0019] Example 1: See also Figure 1 and Figure 2 , an Internet-based monitoring system for power station flooding prevention, includes an intelligent water situation prediction module, an intelligent drainage optimization control module, an underwater sensing network module, an environmental collaborative sensing module, an automated facility protection module, an abnormal event instant alarm module, and a community linkage emergency response module.

[0020] The intelligent water regime prediction module uses meteorological data and machine learning algorithms to predict water regime changes around power stations.

[0021] In this embodiment, meteorological data, including historical data of rainfall, wind speed, temperature, and river water level, is collected and a time series prediction model (such as LSTM or Prophet) is used to perform real-time calculation and trend prediction.

[0022] This enables higher spatial resolution in forecasts, not only indicating the likelihood of power plant flooding but also quantifying its severity and potential impact range. For example, when heavy rainfall is predicted within a certain range, the system can calculate the time and flow rate of rainwater flowing into rivers, and visualize the potential flooded area and timeline.

[0023] The intelligent water situation prediction module has a built-in flood basin simulation model, and constructs a three-dimensional flood model based on the geographic information system GIS and basin analysis algorithm.

[0024] Furthermore, the flood basin simulation model achieves dynamic prediction of the basin's hydrological behavior and the hydrological response of the basin around the power station to heavy rainfall events by modeling rainfall, topography, and basin characteristics. The flood basin simulation model is shown below: ; in, :The basin around the power station in time The total amount of flow at that time; : In subunit Time rainfall intensity at that time; : Subunit The rainfall runoff coefficient represents the efficiency of converting rainfall into surface runoff under different terrain and soil conditions, and its value range is ; : Subunit area; : The damping factor of the path in the basin, reflecting the The loss of water flowing to the power station depends on the characteristics of the basin slope and surface roughness; : Subunit Length of water flow path to the power station; : Damping attenuation coefficient, which depends on the characteristics of the watershed surrounding the power station; :time evapotranspiration.

[0025] Wherein, the subunit The rainfall runoff coefficient , combined with real-time rainfall intensity , soil moisture, and land use type, and dynamically calculate runoff efficiency through machine learning algorithms such as random forest or decision tree regression: ; in, : Subunit Real-time soil moisture; : Subunit land use types, including grassland, farmland, and urban hardened surfaces; The path damping factor within the basin , which is different from the traditional model, incorporates terrain slope and land roughness into the formula for calculating path loss: ; in, : weight factors, representing the relative impact of slope and roughness on path loss; : Subunit slope; : Subunit surface roughness.

[0026] When using this model, the following processes are involved: Step 1: Spatial gridding of watershed The hydropower station basin is divided into several grid cells through GIS, each cell contains an area , terrain slope , roughness , soil moisture These data are collected through remote sensing and field sensors.

[0027] Step 2: Rainfall data input Obtain rainfall intensity for each subunit from meteorological models or radar monitoring , which is input into the model with a time step of 10 minutes.

[0028] Step 3: Dynamic flow calculation Based on real-time soil moisture and rainfall intensity, the runoff coefficient of each subunit is dynamically calculated through a machine learning model. , and combined with the area Converted into runoff.

[0029] Step 4: Path Damping Calculation Length of water flow path from each subunit to the power station and path damping coefficient Calculate water loss and correct runoff.

[0030] Step 5: Calculate and output the total flow Summarize the water flow of all subunits , minus evapotranspiration losses , and finally outputs the water flow at the power station to generate a flooding risk assessment.

[0031] Step 6: 3D flood modeling and visualization The simulation results are used to generate a three-dimensional flood model, which visually displays the depth, scope and temporal evolution of the flooded area through the GIS platform to help managers formulate response measures.

[0032] In practical application, it is assumed that the basin area of ​​a power station is 100km 2 During a heavy rainfall event, the system runs the above model every 10 minutes. By monitoring soil moisture and rainfall intensity in real time, the model dynamically adjusts and , combined with path loss and evapotranspiration calculations, it was finally predicted that the flood would reach the power station in 3 hours, and that the flooding range would cover a range of 1 km downstream with a water depth of about 1.2 meters.

[0033] The intelligent drainage optimization control module is used to monitor the status of the power station drainage system in real time, and make intelligent decisions to open, close or adjust the operating parameters of the drainage equipment through the prediction data output by the intelligent water condition prediction module.

[0034] In this embodiment, the drainage equipment in the power station, including pumps and drainage gates, is monitored through IoT control technology, and the operating parameters of the drainage equipment are adjusted to automatically adapt to different drainage demand scenarios, thereby optimizing the drainage strategy. Before a flood strikes, the module will link data with the intelligent water situation prediction module to start drainage equipment in advance to reduce the risk of waterlogging. At the same time, after rainfall, it will intelligently assess whether additional drainage facilities need to be opened to minimize waste of power station resources.

[0035] The intelligent drainage optimization control module constructs an intelligent evaluation model when intelligently evaluating whether additional drainage facilities need to be opened after rainfall. The intelligent evaluation model is as follows: ; in, : In time The total amount of flow at that time; :Intelligent evaluation results; when When , it means that the current drainage and protection capabilities are insufficient and additional drainage needs to be started; when When , it means that the current resources are sufficient and there is no need to increase the equipment operation; :For all power stations The sum of the operating capacities of the drainage equipment; :Drainage equipment In time Actual drainage capacity; : Equipment operating efficiency factor, used to consider aging and environmental impact, the value range is ; : The current operating status of the device, on = 1, off = 0.

[0036] When used, the model includes: The real-time flow prediction value of each sub-unit is obtained from the flood basin simulation model, and the real-time operation data, efficiency coefficient, and operation status of all drainage equipment in the power station are obtained.

[0037] Dynamically calculate total catchment flows for future time periods using a flood basin simulation model .

[0038] Obtain the total drainage capacity of the current drainage facilities (i.e. the denominator in the model) and sum up the operating capacities of all equipment.

[0039] calculate value, judge whether the current drainage facilities are sufficient to deal with the risk: If , start the backup drainage equipment or adjust the protection strategy, if , maintain the current state and avoid waste of resources.

[0040] according to The size of the dynamic adjustment: If the gap is large , priority will be given to dispatching more drainage facilities and starting backup pumping stations.

[0041] If it approaches the critical value , maintain current operations and strengthen water situation monitoring to prevent emergencies.

[0042] The underwater sensing network module, based on acoustic wave communication technology, monitors the water flow dynamics in the power station area in real time, provides real-time water flow speed, depth, and flow direction data to the intelligent drainage optimization control module, and refines the execution of drainage optimization strategies.

[0043] In summary, this model can be applied to the following scenarios: Before heavy rainfall arrives, the need to activate backup drainage equipment in advance can be predicted by combining flood basin simulation models; Real-time monitoring can be performed during floods Dynamically adjust equipment operating status according to changes in the power plant environment and optimize power plant resource utilization; Historical flood events can be Review the data and optimize the layout and operation strategy of the power station drainage facilities.

[0044] In an environment with turbulent water flow, traditional electromagnetic waves will be interfered with by the water, but sound waves can be transmitted stably, so the system can provide longer-term, real-time and reliable monitoring.

[0045] When some sensors are damaged, the network can rebuild the communication path to ensure uninterrupted data collection.

[0046] In this embodiment, traditional wireless communication is difficult to implement underwater, and this module uses sound waves to transmit data by arranging underwater sensor nodes; The sensor nodes measure water velocity, depth, and direction, transmitting this data via hydroacoustic signals to a buoy receiver. This data is then uploaded to the monitoring system's cloud via a wireless network. The introduction of acoustic networks significantly improves the coverage of hydrological monitoring at power plants, making them particularly suitable for locations near dams or complex hydrological environments.

[0047] The collaborative environmental perception module is used for collaborative perception of multi-dimensional environmental factors, including hydrology, geology, meteorology, and soil moisture, and combines the data monitored by the underwater perception network module to generate a comprehensive risk map of the power station and its surrounding environment.

[0048] In this embodiment, a comprehensive environmental risk map is generated by integrating high-altitude drone imagery, remote sensing satellite data, and ground sensor networks; Using hyperspectral remote sensing technology to detect the turbidity and pollutant content of surface water to determine whether floodwaters may carry large amounts of sediment that could damage power plant facilities; By analyzing geological information, the risk of soil landslide or subsidence around the power station is monitored, providing comprehensive flood-related information.

[0049] The automated facility protection module, based on the comprehensive risk map provided by the environmental collaborative perception module and the predictive data provided by the intelligent water situation prediction module, is responsible for quickly initiating facility protection measures when it predicts that the power station is facing the threat of flooding. It adjusts the protection devices according to the real-time water situation, including the position and height of protective panels, automatic sealing doors, and underwater isolation walls.

[0050] This embodiment utilizes autonomous sensing and control technology, enabling the position and height of protective devices to be adjusted based on real-time water conditions. For example, if the module detects a rapid rise in water levels, it automatically calculates the hydraulic load and dynamically adjusts the support strength of the protective device, effectively preventing failure. Furthermore, the module incorporates a self-cleaning function, ensuring the protective device remains highly effective even after extended operation.

[0051] The abnormal event instant alarm module is used to quickly capture potential flood abnormal events and issue alarms to relevant personnel, and monitor the execution of the intelligent water situation prediction module, intelligent drainage optimization control module and automated facility protection module in real time.

[0052] In this embodiment, through real-time monitoring of hydrological data, abnormal signals that may indicate flooding risks are identified; If the water level sensor reports a sudden increase in a short period of time, consider combining it with the water situation forecast to assess whether the abnormal signal represents a real risk. The abnormal event instant alarm module integrates natural language processing (NLP) technology to mine flood warning information related to the power station area from unstructured data sources such as social media platforms and news, enabling early perception of unknown risks.

[0053] The community-linked emergency response module builds an Internet-based multi-party collaboration platform. Based on the alarm mechanism triggered by the abnormal event instant alarm module, it quickly coordinates various emergency resources, supports intelligent resource scheduling, and generates the optimal scheduling plan by analyzing the materials, equipment and personnel inside and outside the power station.

[0054] In this embodiment, based on a multi-party collaborative platform, early warning information is pushed to community residents in real time via a mobile app, providing key data such as evacuation route planning, real-time traffic conditions, and water level change maps; The multi-party collaboration platform is built based on blockchain technology, and all operation records can be traced, thus ensuring the transparency and fairness of the emergency resource allocation process.

[0055] Example 2: See also Figure 3 A method for monitoring power station flooding prevention based on the Internet is operated based on the power station flooding prevention monitoring system based on the Internet described in Example 1, and includes the following specific steps: S1. Environmental data collection and preprocessing Remote sensing satellites, high-altitude drones, ground sensor networks and underwater acoustic communication nodes are used to collect multi-dimensional environmental data, including rainfall, soil moisture, water flow velocity, watershed topography, etc.

[0056] Decode the real-time data collected by underwater sensors to ensure that no information on river depth, flow rate and turbidity is missed.

[0057] Use data cleaning algorithms to remove outliers, such as erroneous sensor readings.

[0058] The collected spatial data are gridded in conjunction with the GIS platform, ready to be input into subsequent models.

[0059] S2. Real-time water situation forecast Use time series prediction models (such as LSTM or Prophet) to predict real-time rainfall and water level change trends and generate basin precipitation distribution maps for the next few hours.

[0060] Environmental data is input into the flood basin simulation model, and a dynamic three-dimensional flood model is constructed based on GIS to assess the future water flow and possible inundation range.

[0061] Output visualization results of flooding risk, including depth distribution of flooded areas and arrival timeline.

[0062] S3, Intelligent Drainage Optimization Based on the predicted water conditions data, the reinforcement learning algorithm is used to optimize the operation strategy of the power station's drainage equipment and adjust the operating parameters of the pumps or drainage gates in advance.

[0063] Use the Internet of Things to control drainage equipment to respond to water situation changes in real time, such as reducing the risk of waterlogging in advance or responding quickly to sudden floods.

[0064] S4. Facility protection starts Based on flood simulation data, when it is determined that the water level may exceed the critical value, the facility protection system, such as lifting protective panels, sealing doors or underwater isolation walls, will be automatically activated.

[0065] Monitor water flow changes in real time and adjust the location and strength of protective facilities to respond to actual water pressure loads.

[0066] S5. Abnormal event warning The system performs real-time anomaly detection on the collected hydrological data, such as a sharp rise in water level in a short period of time or abnormal operation of drainage system equipment.

[0067] Emergency alerts are sent to power station managers via SMS, App notifications, etc.

[0068] Integrate NLP technology to mine real-time flood information from social media or news to form auxiliary early warnings.

[0069] S6. Community-linked emergency response A collaborative platform built through blockchain technology shares flood forecasts and real-time water level change data with community residents and relevant agencies.

[0070] Intelligently dispatch power station and community emergency resources, including rescue equipment, shelter supplies, and emergency transportation.

[0071] Provide detailed evacuation route planning to surrounding residents and display real-time updated traffic conditions and safe area locations.

[0072] The beneficial effects of the present invention are: This internet-based monitoring system and method for power station flooding prevention overcomes the shortcomings of existing technologies by integrating technologies such as intelligent water situation prediction, real-time drainage optimization, and underwater sensing networks. It achieves multidimensional data perception, dynamic predictive analysis, and intelligent protection measures. It not only significantly improves the monitoring accuracy and response efficiency of complex hydrological events, but also enhances the transparency and fairness of resource scheduling through a blockchain-based collaborative network, providing a comprehensive and efficient protection solution for power stations and surrounding communities.

[0073] In the description of this specification, the reference terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" mean that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art can combine and combine different embodiments or examples described in this specification and features of different embodiments or examples without contradiction.

[0074] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. An Internet-based monitoring system for power station flooding prevention, characterized in that: It includes intelligent water situation prediction module, intelligent drainage optimization control module, underwater sensing network module, environmental collaborative sensing module, automated facility protection module, abnormal event instant alarm module and community linkage emergency response module; An intelligent water regime prediction module uses meteorological data and machine learning algorithms to predict water regime changes around power stations; The intelligent drainage optimization control module is used to monitor the status of the power station drainage system in real time and make intelligent decisions to open, close or adjust the operating parameters of the drainage equipment based on the prediction data output by the intelligent water condition prediction module; The underwater sensing network module, based on acoustic communication technology, monitors the water flow dynamics within the power station area in real time, providing real-time water flow speed, depth, and flow direction data to the intelligent drainage optimization control module, thereby refining the execution of drainage optimization strategies. The collaborative environmental perception module is used to collaboratively perceive multi-dimensional environmental factors, including hydrology, geology, meteorology, and soil moisture. It combines data monitored by the underwater perception network module to generate a comprehensive risk map of the power station and its surrounding environment. The automated facility protection module, based on the comprehensive risk map provided by the collaborative environmental perception module and the forecast data provided by the intelligent water situation prediction module, is responsible for quickly initiating facility protection measures when the power station is predicted to be facing flooding threats. It adjusts the protection devices, including the position and height of protective panels, automatic sealing doors, and underwater isolation walls, according to the real-time water conditions. Abnormal event instant alarm module, used to quickly capture potential flood abnormal events and issue alarms to relevant personnel, and to monitor the execution of the intelligent water situation prediction module, intelligent drainage optimization control module, and automated facility protection module in real time; The community-linked emergency response module builds an Internet-based multi-party collaboration platform. Based on the alarm mechanism triggered by the abnormal event instant alarm module, it quickly coordinates various emergency resources, supports intelligent resource scheduling, and generates the optimal scheduling plan by analyzing the materials, equipment and personnel inside and outside the power station.

2. The Internet-based power station flooding prevention monitoring system according to claim 1, characterized in that: In the intelligent water regime prediction module, by collecting meteorological data, including historical data of rainfall, wind speed, temperature and river water level, the time series prediction model LSTM is used for real-time calculation and trend prediction; The intelligent water situation prediction module has a built-in flood basin simulation model, and constructs a three-dimensional flood model based on the geographic information system GIS and basin analysis algorithm.

3. The Internet-based power station flooding prevention monitoring system according to claim 2, characterized in that: The flood basin simulation model achieves dynamic prediction of the basin's hydrological behavior and the hydrological response of the basin surrounding the power station to heavy rainfall events by modeling rainfall, topography, and basin characteristics. The flood basin simulation model is shown below: ； in, :The basin around the power station in time The total amount of flow at that time; : In subunit Time rainfall intensity at that time; : Subunit The rainfall runoff coefficient represents the efficiency of converting rainfall into surface runoff under different terrain and soil conditions, and its value range is ; : Subunit area; : The damping factor of the path in the basin, reflecting the The loss of water flowing to the power station depends on the characteristics of the basin slope and surface roughness; : Subunit Length of water flow path to the power station; : Damping attenuation coefficient, which depends on the characteristics of the watershed surrounding the power station; :time evapotranspiration.

4. The Internet-based power station flooding prevention monitoring system according to claim 1, characterized in that: The intelligent drainage optimization control module uses IoT control technology to monitor drainage equipment within the power station, including pumps and drainage gates, adjust the operating parameters of the drainage equipment, and automatically adapt to different drainage demand scenarios, thereby optimizing drainage strategies. Before a flood strikes, the module will link data with the intelligent water situation prediction module to start drainage equipment in advance to reduce the risk of waterlogging. At the same time, after rainfall, it will intelligently assess whether additional drainage facilities need to be opened to minimize waste of power station resources.

5. The Internet-based power station flooding prevention monitoring system according to claim 4, characterized in that: The intelligent drainage optimization control module constructs an intelligent evaluation model when intelligently evaluating whether additional drainage facilities need to be opened after rainfall. The intelligent evaluation model is as follows: ； in, : In time The total amount of flow at that time; :Intelligent evaluation results; when When , it means that the current drainage and protection capabilities are insufficient and additional drainage needs to be started; when When , it means that the current resources are sufficient and there is no need to increase the equipment operation; :For all power stations The sum of the operating capacities of the drainage equipment; :Drainage equipment In time Actual drainage capacity; : Equipment operating efficiency factor, used to consider aging and environmental impact, the value range is ; : The current operating status of the device, on = 1, off = 0.

6. The Internet-based power station flooding prevention monitoring system according to claim 1, characterized in that: The underwater sensing network module uses sound waves to transmit data by arranging underwater sensor nodes; The sensor nodes are responsible for measuring water flow speed, depth, and direction, and uploading the data to the buoy receiver via hydroacoustic signals, and then uploading it to the cloud of the monitoring system via wireless networks.

7. The Internet-based power station flooding prevention monitoring system according to claim 1, characterized in that: The collaborative environmental perception module generates a comprehensive risk map of the power plant and its surrounding environment by integrating high-altitude drone images, remote sensing satellite data, and ground sensor networks. Using hyperspectral remote sensing technology to detect the turbidity and pollutant content of surface water to determine whether floodwaters may carry large amounts of sediment that could damage power plant facilities; By analyzing geological information, the risk of soil landslide or subsidence around the power station is monitored, providing comprehensive flood-related information.

8. The Internet-based power station flooding prevention monitoring system according to claim 1, characterized in that: The abnormal event instant alarm module identifies abnormal signals that may indicate flooding risks through real-time monitoring of hydrological data; If the water level sensor reports a sudden increase in a short period of time, consider combining it with the water situation forecast to assess whether the abnormal signal represents a real risk. The abnormal event instant alarm module integrates natural language processing (NLP) technology to mine flood warning information related to the power station area from unstructured data sources such as social media platforms and news, enabling early perception of unknown risks.

9. The Internet-based power station flooding prevention monitoring system according to claim 1, characterized in that: The community-linked emergency response module, based on a multi-party collaborative platform, pushes early warning information to community residents in real time through a mobile app, providing key data such as evacuation route planning, real-time traffic conditions, and water level change maps; The multi-party collaboration platform is built based on blockchain technology, and all operation records can be traced, thus ensuring the transparency and fairness of the emergency resource allocation process.

10. An Internet-based monitoring method for power station flooding prevention, operated based on the Internet-based monitoring system for power station flooding prevention according to any one of claims 1 to 9, characterized in that: The specific steps include: S1, environmental data collection and preprocessing; S2, real-time water situation forecast; S3, intelligent drainage optimization; S4, Facility protection started; S5. Warning of abnormal events; S6. Community-linked emergency response.

Images