Flood prevention early warning and monitoring integrated station and intelligent management platform system

Abstract

The invention relates to a flood prevention early warning and monitoring integrated station and an intelligent management platform system, and the system comprises a multi-source data collection module, an intelligent analysis and prediction module, a three-dimensional early warning module and an emergency command module. And comprehensive monitoring, accurate prediction and multi-channel early warning of water regimen data are realized. The system adopts a section segmentation algorithm to carry out flow calculation, combines a deep learning prediction model correction technology, improves the flood prediction precision to be within + / -10%, shortens the early warning response time by 30%, and solves the technical problems of single data, early warning lagging, insufficient decision support and the like of an existing flood prevention system.

Description

Technical Field

[0001] This invention belongs to the field of water conservancy monitoring technology, especially the integrated station for flood prevention early warning and monitoring and the intelligent management platform system. Background Technology

[0002] A smart water management platform is a comprehensive management system that utilizes modern information technologies such as the Internet of Things, big data, cloud computing, and artificial intelligence to provide intelligent management and decision support for water conservancy facilities and water resources. The smart water management solutions provided by the platform can offer comprehensive support for reservoirs, hydropower stations, rivers, and irrigation districts, and possess the following functions:

[0003] 1. Data collection and integration:

[0004] Collect various types of hydrological data, meteorological data, water quality data, and water conservancy project operation data.

[0005] Integrate data from different sources and formats to establish unified data standards and specifications.

[0006] The platform primarily displays basic data, which is collected from devices or integrated with the platform.

[0007] 2. Real-time monitoring and early warning:

[0008] Real-time monitoring of important hydrological stations, water conservancy projects and water resources.

[0009] Establish an early warning mechanism to provide warnings for disasters such as extreme weather, floods, and droughts.

[0010] The platform identifies data alerts and displays them on the platform, primarily through alert displays and push notifications. However, there is no linkage between the platform and devices, or the linkage mechanism is fixed and simplistic.

[0011] 3. Data analysis and decision support:

[0012] Big data analytics is used to mine historical data and predict future hydrological conditions and water resource changes. However, since it is based solely on historical data and does not take into account topographic features and real-time weather conditions, the prediction results are mostly table lookup results or linear analysis.

[0013] Provide decision support tools to assist managers in formulating strategies for water resource allocation, flood control, and drought relief.

[0014] 4. Resource Management and Optimized Scheduling:

[0015] By combining platform data with analysis results, water resources can be managed in a refined manner, and rationally allocated and scheduled.

[0016] Optimize the operation plan of water conservancy projects and improve the efficiency of water resource utilization.

[0017] 5. Visual presentation:

[0018] Complex data is presented intuitively through charts, maps, and other formats, making it easier for users to understand and use.

[0019] Therefore, the traditional flood control system currently has the following technical defects:

[0020] 1. The data dimension is limited, monitoring only basic parameters such as water level and rainfall;

[0021] 2. The prediction model lacks accuracy and does not take into account landform features and weather changes;

[0022] 3. The early warning methods are outdated and lack a multi-channel coordination mechanism;

[0023] 4. Weak decision support, lacking historical data analysis and simulation capabilities;

[0024] 5. The system has poor robustness and data is easily interrupted under harsh environments. Summary of the Invention

[0025] The purpose of this invention is to overcome the shortcomings of existing technologies and propose an integrated flood control early warning and monitoring station and intelligent management platform system. It adopts a cross-section segmentation algorithm for flow calculation and combines deep learning prediction model correction technology to improve flood prediction accuracy to within ±10% and shorten early warning response time by 30%. It solves the technical problems of existing flood control systems such as single data, delayed early warning, and insufficient decision support.

[0026] The technical problem solved by this invention is achieved through the following technical solution:

[0027] The integrated flood control early warning and monitoring station and intelligent management platform system includes a multi-source data acquisition module, an intelligent analysis and prediction module, a three-dimensional early warning module, and an emergency command module. The multi-source data acquisition module, intelligent analysis and prediction module, and three-dimensional early warning module are connected sequentially. The emergency command module is connected to the multi-source data acquisition module, intelligent analysis and prediction module, and three-dimensional early warning module. The multi-source data acquisition module is used to collect multi-source data. The intelligent analysis and prediction module is used to perform data prediction and analysis based on the collected multi-source data. The three-dimensional early warning module is used to issue alarms based on the results of data prediction and analysis. The emergency command module is used to observe the on-site situation and real-time data in real time, support real-time command, handle alarms, and record command results.

[0028] Furthermore, the multi-source data acquisition module collects data including evaporation and rainfall. Evaporation data is collected by monitoring evaporation from river channels, vegetation, and soil using weather stations and sensors. An influence coefficient is configured based on the actual environment: the actual evaporation data is weighted and used as the evapotranspiration capacity (EP) in the model calculation.

[0029] The method for collecting rainfall data is as follows: For a region, rainfall data can be collected from multiple points and the relatively accurate areal rainfall can be calculated. The rainfall data from multiple points are grouped by hour, the average rainfall within the same time period is taken, and the rainfall within different time periods is summed.

[0030] Furthermore, the intelligent analysis and prediction module employs an improved Xin'anjiang model. This improved Xin'anjiang model is calculated using basic coefficients that have been applied in actual field conditions in a certain area for many years, and then manually calibrated based on the actual flow rate on site and the flow rate calculated by the model.

[0031] Surface runoff confluence:

[0032] QS = CS * lastQS + (1-CS) * RS * U;

[0033] Subsurface runoff confluence:

[0034] QI = CI * lastQI + (1-CI) * RI * U;

[0035] underground runoff confluence:

[0036] QG = CG * lastQG + (1 - CG) * RG * U;

[0037] Calculate the total inflow over the QT cell area:

[0038] QS+QI+QG;

[0039] The lag algorithm is used to calculate the river network confluence of unit areas.

[0040] I = CR * lastQ + (1 - CR) lastQt;

[0041] Calculate the current flow rate:

[0042] Q = C0*I + C1*lastI + C2*lastQ;

[0043] Reference current traffic:

[0044] Q=(1-Cc)*(C0*I+C1*lastI+C2*lastQ)+Cc*Qc;

[0045] Wherein, QS: surface runoff inflow, CS: surface runoff recession coefficient, LastQS: surface runoff inflow at the previous time, RS: surface runoff, QI: interflow inflow, CI: interflow recession coefficient, LastQI: interflow inflow at the previous time, RI: interflow, QG: groundwater runoff inflow, CG: groundwater runoff recession coefficient, LastQG: groundwater runoff inflow at the previous time, RG: groundwater runoff, U: unit conversion factor, Q, I: outflow and inflow values, CR: river network water storage recession coefficient, LastQ: outflow value at the previous time, LastQt: outflow value at the previous lag time, C0, C1, C2: calculation coefficients, C0+C1+C2=1, LastI: inflow value at the previous stage, Cc: current actual flow percentage, Qc: current actual flow.

[0046] Furthermore, the warning methods of the three-dimensional warning module include issuing warnings based on future data derived from the improved Xin'anjiang model, issuing warnings based on trends, and issuing warnings based on multi-level alarm settings.

[0047] Furthermore, the early warning based on future data extrapolated from the improved Xin'anjiang model includes the following steps:

[0048] Step 1.1: Calculate future flow based on the improved Xin'anjiang model and weather forecast data;

[0049] Step 1.2: The system has historical hydrological data reserves, and calculates the water level and flow velocity data at that time based on historical data:

[0050] Water level data: Based on the water level-flow curve table (generated from historical data), the water level value corresponding to the flow rate is obtained.

[0051] Flow velocity data: The cross-sectional area at that time can be calculated based on the simulated water level. Flow velocity = flow rate / cross-sectional area.

[0052] Step 1.3: Based on the water level, flow velocity, and flow rate thresholds configured in the system, the future water situation is judged. If there is an anomaly, an alarm is triggered. At the same time, for rainfall data, it can be compared with the rainfall threshold while connecting with the weather forecast to determine whether to trigger an alarm.

[0053] Moreover, the specific implementation method of the trend-based early warning is as follows: by configuring real-time data and comparing it with the previous hour, day, year, and the same period of the year, the growth rate or decline rate of the data can be obtained. Based on the comparison of time periods, it is possible to monitor whether there are potential flood risks on site and issue early warnings.

[0054] Furthermore, the pre-warning based on multi-level alarm settings includes the following steps:

[0055] Step 2.1: Set three warning values: blue, yellow, and red.

[0056] Step 2.2: Set up the corresponding alert triggers, such as triggering a platform notification for a blue alert; triggering SMS and voice notifications for a yellow alert; and triggering on-site equipment announcements for a red alert.

[0057] Step 2.3: An alarm is detected, and the corresponding action is triggered according to the level.

[0058] The advantages and positive effects of this invention are:

[0059] This invention comprises a multi-source data acquisition module, an intelligent analysis and prediction module, a three-dimensional early warning module, and an emergency command module. By integrating IoT sensing technology, an improved Xin'anjiang hydrological model, and AR real-scene command technology, it achieves comprehensive monitoring, accurate prediction, and multi-channel early warning of hydrological data. The system employs a cross-section segmentation algorithm for flow calculation, combined with deep learning prediction model correction technology, improving flood prediction accuracy to within ±10% and reducing early warning response time by 30%. This solves the technical problems of existing flood control systems, such as single data sources, delayed early warnings, and insufficient decision support. Attached Figure Description

[0060] Figure 1 This is a system structure diagram used in this invention;

[0061] Figure 2 This is a software architecture diagram of the present invention;

[0062] Figure 3 This is a diagram illustrating an alarm situation according to an embodiment of the present invention;

[0063] Figure 4 This is a flowchart illustrating the system interaction of the present invention.

[0064] Figure 5 This is a flowchart of the three-dimensional early warning mechanism of the present invention. Detailed Implementation

[0065] The present invention will be further described in detail below with reference to the accompanying drawings.

[0066] The integrated flood control early warning and monitoring station and intelligent management platform system are applied to, for example Figure 1 The illustrated traffic calculation system architecture includes users, a communication network, water conservancy equipment, an upper-level domain platform, and lower-level domain platforms. The platform is deployed in a secure network environment and can be used both on internal and external networks. If deployed on an external network, bastion hosts and firewalls are typically used to ensure platform security. The platform also supports hierarchical deployment; for example, at the district / county or provincial / municipal level, the upper-level platform can retrieve configurations from the lower-level platforms and simultaneously synchronize real-time data from the lower-level platforms.

[0067] like Figure 2 The software architecture used in this invention is shown below.

[0068] 1. Perception Layer: Multi-source sensor network

[0069] Combination Figure 1 It can be seen that the platform's perception of data mainly comes from water conservancy equipment, water conservancy sensors, third-party equipment and the platform.

[0070] 2. Transport Layer: Internal and external network data communication, hardware and software protocol interoperability.

[0071] To address the data input from multiple device networks, the platform has a dedicated interface layer for handling access. This interface layer supports parsing device protocols, water conservancy standard protocols (such as 206 / 651), mainstream interface protocols like HTTP and MQTT, and FTP file / image protocols. Simultaneously, it uses NIFI for data splitting, verification, and cleaning, parses multiple data sources into a unified data stream format.

[0072] 3. Platform Layer: Business Platform in Microservice Architecture

[0073] The core components mainly consist of water conservancy data collection services and basic information management services;

[0074] The basic information management service mainly provides basic configurations, and for this invention, it mainly provides model configuration and early warning rule configuration.

[0075] The water resources data acquisition service processes and stores all incoming data. For data analysis and processing, the acquisition service performs predictive calculations based on the configured model. Regarding alarm and early warning systems, the acquisition module calculates whether an alarm should be triggered based on the data and determines whether to trigger an alarm based on the configured early warning rules.

[0076] The alarm module supports configuring alarm linkage and setting linkage actions to achieve diverse alarm capabilities.

[0077] 4. Application Layer: Web / Mobile / Large Screen Multi-Platform Applications

[0078] Figure 2 The platform primarily features a UI presentation (a single map display of water resources and a comprehensive data display on a large screen), as well as a real-time command and control system that combines real-time video and data. In addition to the visual presentations shown in the images, the platform can also be accessed via an app.

[0079] The integrated flood control early warning and monitoring station and intelligent management platform system includes a multi-source data acquisition module, an intelligent analysis and prediction module, a three-dimensional early warning module, and an emergency command module. The multi-source data acquisition module, intelligent analysis and prediction module, and three-dimensional early warning module are connected sequentially. The emergency command module is connected to the multi-source data acquisition module, intelligent analysis and prediction module, and three-dimensional early warning module. The multi-source data acquisition module is used for multi-source data acquisition. The intelligent analysis and prediction module is used for data prediction and analysis based on the acquired multi-source data. The three-dimensional early warning module is used for issuing alarms based on the results of data prediction and analysis. The emergency command module is used for real-time observation of the on-site situation and real-time data, supports real-time command, handles alarms, and records command results, such as... Figure 3 As shown.

[0080] Real-time video monitoring: Provides on-site video and audio capabilities, enabling the module to acquire on-site information and conduct real-time command. Data acquisition and data analysis / prediction modules: Provide real-time and predicted data, supporting command and control. Comprehensive early warning module: Pushes real-time alerts and allows for processing of alarms after command has resolved them, creating a closed-loop system for handling incidents.

[0081] The multi-source data acquisition module collects data including evaporation and rainfall. Evaporation, as a crucial component of watershed water balance, directly impacts soil moisture content, surface runoff, and groundwater recharge. Using measured evaporation data improves the model's simulation accuracy. Evaporation data is collected by monitoring evaporation in river channels, vegetation, and soil using weather stations and sensors. Influence coefficients are configured based on the actual environment: for example, in farmland, topsoil evaporation can be configured to account for 30%, and vegetation evaporation for 70%. The weighted average of actual evaporation data is then used as the evapotranspiration capacity (EP) in the model calculation.

[0082] The method for collecting rainfall data is as follows: For a region, rainfall data can be collected from multiple points and the relatively accurate areal rainfall can be calculated. The rainfall data from multiple points are grouped by hour, the average rainfall within the same time period is taken, and the cumulative sum is calculated within different time periods. More scientific model data can be obtained through accurate areal rainfall data.

[0083] The intelligent analysis and prediction module uses an improved Xin'anjiang model. This improved model is calculated using basic coefficients from years of actual field application in a certain area (the model is mainly used in southern cities; if it is to be used in the north, a default model training point needs to be found first). Then, it is manually calibrated based on the actual flow rate on site and the flow rate calculated by the model.

[0084] Surface runoff confluence:

[0085] QS = CS * lastQS + (1-CS) * RS * U;

[0086] Subsurface runoff confluence:

[0087] QI = CI * lastQI + (1-CI) * RI * U;

[0088] underground runoff confluence:

[0089] QG = CG * lastQG + (1 - CG) * RG * U;

[0090] Calculate the total inflow over the QT cell area:

[0091] QS+QI+QG;

[0092] The lag algorithm is used to calculate the river network confluence of unit areas.

[0093] I = CR * lastQ + (1 - CR) lastQt;

[0094] Calculate the current flow rate:

[0095] Q = C0*I + C1*lastI + C2*lastQ;

[0096] Current actual traffic percentage Cc:

[0097] Q=(1-Cc)*(C0*I+C1*lastI+C2*lastQ)+Cc*;

[0098] Reference current traffic:

[0099] Q=(1-Cc)*(C0*I+C1*lastI+C2*lastQ)+Cc*Qc;

[0100] Wherein, QS: surface runoff inflow, CS: surface runoff recession coefficient, LastQS: surface runoff inflow at the previous time, RS: surface runoff, QI: interflow inflow, CI: interflow recession coefficient, LastQI: interflow inflow at the previous time, RI: interflow, QG: groundwater runoff inflow, CG: groundwater runoff recession coefficient, LastQG: groundwater runoff inflow at the previous time, RG: groundwater runoff, U: unit conversion factor, Q, I: outflow and inflow values, CR: river network water storage recession coefficient, LastQ: outflow value at the previous time, LastQt: outflow value at the previous lag time, C0, C1, C2: calculation coefficients, C0+C1+C2=1, LastI: inflow value at the previous stage, Cc: current actual flow percentage, Qc: current actual flow.

[0101] The three-dimensional early warning module's early warning methods include early warning based on future data extrapolated from the improved Xin'anjiang model, early warning based on trends, and early warning based on multi-level alert settings.

[0102] Early warning based on future data projection using the improved Xin'anjiang model includes the following steps:

[0103] Step 1.1: Calculate future flow based on the improved Xin'anjiang model and weather forecast data;

[0104] Step 1.2: The system has historical hydrological data reserves, and calculates the water level and flow velocity data at that time based on historical data:

[0105] Water level data: Based on the water level-flow curve table (generated from historical data), the water level value corresponding to the flow rate is obtained.

[0106] Flow velocity data: The cross-sectional area at that time can be calculated based on the simulated water level. Flow velocity = flow rate / cross-sectional area.

[0107] Step 1.3: Based on the water level, flow velocity, and flow rate thresholds configured in the system, the future water situation is judged. If there is an anomaly, an alarm is triggered. At the same time, for rainfall data, it can be compared with the rainfall threshold while connecting with the weather forecast to determine whether to trigger an alarm.

[0108] The specific implementation method for trend-based early warning is as follows: by configuring real-time data and comparing it with the previous hour, day, year, and the same period of the year, the growth rate or decline rate of the data can be obtained. Based on the comparison of time periods, it is possible to monitor whether there are potential flood risks on site and issue early warnings.

[0109] The steps to set up an early warning system based on multi-level alert settings are as follows:

[0110] Step 2.1: Set three warning values: blue, yellow, and red.

[0111] Step 2.2: Set up the corresponding alert triggers, such as triggering a platform notification for a blue alert; triggering SMS and voice notifications for a yellow alert; and triggering on-site equipment announcements for a red alert.

[0112] Step 2.3: An alarm is detected, and the corresponding action is triggered according to the level.

[0113] Based on the aforementioned integrated flood control early warning and monitoring station and intelligent management platform system, tests were conducted to verify the effectiveness of the invention.

[0114] The multi-source data fusion module used in this invention is compatible with multi-sensor data such as water level, flow velocity, flow rate, rainfall, and water quality; the improved Xin'anjiang prediction module includes evapotranspiration calculation and three-source separation algorithms; the three-dimensional early warning module supports multi-channel linkage; and the AR real-scene command module integrates SLAM scene alignment and data overlay technology.

[0115] The improved Xin'anjiang prediction module used in this invention includes: a real-time data assimilation interface that integrates measured evaporation and areal rainfall data; a dynamic parameter calibration engine that uses an automatic optimization algorithm based on historical flood data; and a multi-timescale prediction model that supports 24-72 hour flood evolution simulation.

[0116] The three-dimensional early warning module used in this invention achieves: multi-source triggering mechanism: equipment alarm, threshold alarm, predictive alarm, and manual alarm; hierarchical response strategy: alarm classification, supporting different alarm intensity strategies through alarm linkage configuration; and closed-loop management of alarm situations: full-process tracking of task assignment, handling feedback, and effect evaluation.

[0117] The AR real-scene command module used in this invention includes: multi-source video access: supporting the fusion of fixed monitoring and drone panoramic images; data overlay display: dynamically marking key indicators such as water level and flow rate on the real-scene image; and remote control interface: supporting real-time control of devices such as PTZ cameras.

[0118] The working process of this invention includes:

[0119] (1) Collect real-time hydrological data through a multi-source sensor network;

[0120] (2) Flood prediction based on the improved Xin'anjiang model;

[0121] (3) Activate tiered early warning based on the forecast results;

[0122] Evaporation correction: Evapotranspiration capacity is calculated using weighted average of measured data; Rainfall spatial interpolation: Areal rainfall is calculated using the Thiessen polygon method; Automatic parameter calibration: Optimized using machine learning based on historical flood data.

[0123] (4) Conduct emergency command through AR real-scene system;

[0124] (5) Optimize the prediction model based on disposal feedback;

[0125] Spatial registration of on-site video and GIS map; dynamic overlay of key data on video footage; and visualized scheduling and tracking of emergency resources.

[0126] This invention can initially achieve the above-mentioned effects by combining field investigation data, with the main benefits being:

[0127] 1) Based on the terrain configuration and weather forecast, future data can be extrapolated, and the model can be corrected by combining real-time actual data. Currently, the prediction results are highly similar to the actual data, and the prediction effect can be achieved.

[0128] 2) Emergency real-scene command was applied on site. Users can see real-time data and alarms on the real-scene command page. On-site personnel can dispatch the site according to the real-scene command and conduct safety drills on site according to the complete set of zero configuration, including data collection and linkage.

[0129] 3) Currently, there is no real disaster scenario data at the site, but by combining model configuration and historical data input, disaster simulations and drills can be conducted, which has been well received by users.

[0130] It should be emphasized that the embodiments described in this invention are illustrative rather than limiting. Therefore, this invention includes, but is not limited to, the embodiments described in the specific implementation. Any other implementations derived by those skilled in the art based on the technical solutions of this invention are also within the scope of protection of this invention.

Claims

1. A flood control early warning and monitoring integrated station and intelligent management platform system, characterized in that: It includes a multi-source data acquisition module, an intelligent analysis and prediction module, a three-dimensional early warning module, and an emergency command module. The multi-source data acquisition module, intelligent analysis and prediction module, and three-dimensional early warning module are connected in sequence. The emergency command module is connected to the multi-source data acquisition module, intelligent analysis and prediction module, and three-dimensional early warning module. The multi-source data acquisition module is used to collect multi-source data. The intelligent analysis and prediction module is used to perform data prediction and analysis based on the collected multi-source data. The three-dimensional early warning module is used to issue alarms based on the results of data prediction and analysis. The emergency command module is used to observe the on-site situation and real-time data in real time, support real-time command, handle alarms, and record command results.

2. The integrated flood control early warning and monitoring station and intelligent management platform system according to claim 1, characterized in that: The multi-source data acquisition module collects data including evaporation and rainfall. Evaporation data is collected by monitoring evaporation from river channels, vegetation, and soil using weather stations and sensors. An influence coefficient is configured based on the actual environment: the actual evaporation data is weighted and used as the evapotranspiration capacity (EP) in the model calculation. The method for collecting rainfall data is as follows: For a region, rainfall data can be collected from multiple points and the relatively accurate areal rainfall can be calculated. The rainfall data from multiple points are grouped by hour, the average rainfall within the same time period is taken, and the rainfall within different time periods is summed.

3. The integrated flood control early warning and monitoring station and intelligent management platform system according to claim 1, characterized in that: The intelligent analysis and prediction module uses an improved Xin'anjiang model, which is calculated based on fundamental coefficients that have been applied in actual field conditions in a certain area for many years. Then, it is manually calibrated based on the actual flow rate on site and the flow rate calculated by the model. Surface runoff confluence: QS = CS * lastQS + (1-CS) * RS * U; Subsurface runoff confluence: QI = CI * lastQI + (1-CI) * RI * U; underground runoff confluence: QG = CG * lastQG + (1 - CG) * RG * U; Calculate the total inflow over the QT cell area: QS+QI+QG; The lag algorithm is used to calculate the river network confluence of unit areas. I = CR * lastQ + (1 - CR) lastQt; Calculate the current flow rate: Q = C0*I + C1*lastI + C2*lastQ; Reference current traffic: Q=(1-Cc)*(C0*I+C1*lastI+C2*lastQ)+Cc*Qc; Wherein, QS: surface runoff inflow, CS: surface runoff recession coefficient, LastQS: surface runoff inflow at the previous time, RS: surface runoff, QI: interflow inflow, CI: interflow recession coefficient, LastQI: interflow inflow at the previous time, RI: interflow, QG: groundwater runoff inflow, CG: groundwater runoff recession coefficient, LastQG: groundwater runoff inflow at the previous time, RG: groundwater runoff, U: unit conversion factor, Q, I: outflow and inflow values, CR: river network water storage recession coefficient, LastQ: outflow value at the previous time, LastQt: outflow value at the previous lag time, C0, C1, C2: calculation coefficients, C0+C1+C2=1, LastI: inflow value at the previous stage, Cc: current actual flow percentage, Qc: current actual flow.

4. The integrated flood control early warning and monitoring station and intelligent management platform system according to claim 1, characterized in that: The warning methods of the three-dimensional early warning module include issuing warnings based on future data derived from the improved Xin'anjiang model, issuing warnings based on trends, and issuing warnings based on multi-level alarm settings.

5. The integrated flood control early warning and monitoring station and intelligent management platform system according to claim 4, characterized in that: The method of providing early warnings based on future data derived from the improved Xin'anjiang model includes the following steps: Step 1.1: Calculate future flow based on the improved Xin'anjiang model and weather forecast data; Step 1.2: The system has historical hydrological data reserves, and calculates the water level and flow velocity data at that time based on historical data: Water level data: Based on the water level-flow curve table, obtain the water level value corresponding to the flow rate; Flow velocity data: The cross-sectional area at that time can be calculated based on the simulated water level. Flow velocity = flow rate / cross-sectional area. Step 1.3: Based on the water level, flow velocity, and flow rate thresholds configured in the system, the future water situation is judged. If there is an anomaly, an alarm is triggered. At the same time, for rainfall data, it can be compared with the rainfall threshold while connecting with the weather forecast to determine whether to trigger an alarm.

6. The integrated flood control early warning and monitoring station and intelligent management platform system according to claim 4, characterized in that: The specific implementation method of early warning based on trends is as follows: by configuring real-time data and comparing it with the previous hour, day, year, and the same period of the year, the growth rate or decline rate of the data can be obtained. Based on the comparison of time periods, it is possible to monitor whether there are potential flood risks on site and issue early warnings.

7. The integrated flood control early warning and monitoring station and intelligent management platform system according to claim 4, characterized in that: The method of setting up early warnings based on multi-level alarm settings includes the following steps: Step 2.1: Set three warning values: blue, yellow, and red. Step 2.2: Set up the corresponding alert triggers, such as triggering a platform notification for a blue alert; triggering SMS and voice notifications for a yellow alert; and triggering on-site equipment announcements for a red alert. Step 2.3: An alarm is detected, and the corresponding action is triggered according to the level.

Images