Basin disaster prevention and control system based on big data
By building a watershed disaster prevention and control system based on big data, using hydrology-hydropower model and simulation system for intelligent scheduling and optimization allocation, the shortcomings of existing systems in data acquisition and prediction accuracy are solved, and more efficient and more Scientific disaster prevention and control.
Patent Information
- Application Number
- CN202411074245.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-07
- Publication Date
- 2024-12-06
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The existing basin disaster prevention and control system has shortcomings in the comprehensiveness of data acquisition, processing efficiency, prediction accuracy and prevention and control strategy flexibility, and it is difficult to effectively deal with complex and changeable natural disasters.
Build a watershed disaster prevention and control system based on big data, including data monitoring and acquisition subsystem, data analysis and management subsystem, intelligent scheduling and optimization scheduling subsystem, remote monitoring and simulation subsystem, and use hydrology-hydrodynamic model and simulation system Carry out intelligent scheduling and optimized provisioning to realize real-time data acquisition, in-depth analysis and accurate prediction.
It improves the timeliness and timeliness of the disaster prevention and control system, enhances the accuracy of disaster prediction and the scientificity of prevention and control strategies, and ensures safety and development in the river basin.
Smart Images

Figure CN119091604A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of intelligent watershed prevention and control, and in particular to a watershed disaster prevention and control system based on big data. Background Art
[0002] Natural disasters such as floods, droughts, and saltwater tides are becoming increasingly severe. These disasters not only seriously threaten human life and property safety, but also increase the difficulty of disaster prevention and control due to the complexity and uncertainty of hydrological and meteorological conditions in the river basin. With the increase of climate change and extreme weather events, the frequency and destructiveness of river basin disasters have become increasingly prominent, and higher requirements have been put forward for the regulation and control of disaster prevention and mitigation.
[0003] In the field of natural disaster prevention and control, existing technologies can collect, store, process and analyze massive amounts of data, providing strong support for basin disaster prediction, early warning and emergency response. However, the traditional basin disaster prevention and control system has obvious shortcomings in terms of comprehensive data acquisition, processing efficiency, prediction accuracy and flexibility of prevention and control strategies, which limits the ability of existing methods to deal with complex and changeable disasters.
[0004] Therefore, it is necessary to build an intelligent system for watershed disaster prevention and control driven by big data. This system needs to integrate data acquisition technology to achieve comprehensive, real-time and efficient collection of monitoring watershed information; big data processing and analysis algorithms can be used to improve the speed and depth of data processing, and enhance the accuracy and timeliness of disaster prediction; at the same time, it is necessary to combine intelligent analysis technology to achieve intelligent scheduling, scenario simulation and remote monitoring of watershed disaster prevention and control, and provide information support for decision makers to formulate scientific and accurate disaster prevention and control plans. Summary of the invention
[0005] In view of the shortcomings of existing methods and the needs of practical applications, in order to realize the intelligent regulation and implementation monitoring of river basin disaster prevention and control plans, the existing river basin disaster prevention and control system is comprehensively optimized to build a more efficient, accurate and flexible prevention and control system to cope with the complex and changeable challenges of natural disasters and ensure the safety and development of people’s lives and property in the basin. On the one hand, the present invention provides a watershed disaster prevention and control system based on big data, and the system includes: a data monitoring and collection subsystem, a data analysis and management subsystem, an intelligent scheduling and optimization deployment subsystem, and a remote monitoring and simulation subsystem; the data monitoring and collection subsystem is used to collect data from the monitored watershed and obtain a watershed monitoring data set; the data analysis and management subsystem receives the watershed monitoring data set, analyzes the watershed monitoring data set, and obtains a digital analysis result of the hydrological information of the monitored watershed; a hydrological-hydrodynamic model and simulation system is established in the data analysis and management subsystem based on the digital analysis result of the hydrological information; the intelligent scheduling and optimization deployment subsystem performs intelligent scheduling and optimization deployment on the monitored watershed based on the digital analysis result of the hydrological information and the hydrological-hydrodynamic model and simulation system; the remote monitoring and simulation subsystem receives the output information of each subsystem of the watershed disaster prevention and control system, and realizes scene simulation and remote monitoring of the monitored watershed based on the output information. The system of the present invention can obtain various data in the monitored basin in real time and accurately, providing a solid foundation for subsequent analysis and management, ensuring that the system can respond quickly before or when a disaster occurs, and improving the timeliness and timeliness of the disaster prevention and control system.
[0006] Optionally, the data analysis and management subsystem receives the watershed monitoring data set, and analyzing the watershed monitoring data set includes: the data analysis and management subsystem is communicatively connected with the data monitoring and acquisition subsystem; a water level monitoring module, a flow rate monitoring module and a flow monitoring module are set in the data analysis and management subsystem; a watershed flow prediction model is set in the flow monitoring module, and the watershed flow prediction model satisfies the following relationship:
[0007]
[0008] Among them, Q represents the flow prediction result of the monitoring basin, N represents the number of control sections in the monitoring basin, represents the average flow velocity at different vertical depths of the control section, S i Indicates the cross-sectional area of different flood control sections; the data analysis and management subsystem uses the water level monitoring module, the flow rate monitoring module and the flow rate monitoring module to analyze the basin monitoring data set. The present invention sets up water level, flow rate and flow rate monitoring modules to conduct all-round and refined monitoring and analysis of key parameters in the basin, which helps to more accurately grasp the actual situation of the monitored basin.
[0009] Optionally, the analysis of the watershed monitoring data set and obtaining the digital analysis results of the hydrological information of the monitored watershed include: the data analysis and management subsystem analyzes the watershed monitoring data set through the water level monitoring module and obtains the water level of the monitored watershed; the data analysis and management subsystem analyzes the watershed monitoring data set through the flow rate monitoring module and obtains the flow rate of the monitored watershed; the data analysis and management subsystem analyzes the watershed monitoring data set through the flow rate monitoring module and obtains the flow rate of the monitored watershed. The present invention uses the monitoring of water level, flow rate and flow rate as key parameters, which can more comprehensively and accurately grasp the actual situation in the watershed, help to more deeply understand the characteristics of the watershed, and provide a basis for subsequent disaster prevention and control and water resources management.
[0010] Optionally, the establishment of a hydrological-hydrodynamic model and simulation system in the data analysis and management subsystem based on the digital analysis results of the hydrological information includes: constructing a physical watershed mechanism model in the data analysis and management subsystem: constructing an interpretable empirical model in the data analysis and management subsystem: constructing a simulation system model in the data analysis and management subsystem; and obtaining a hydrological-hydrodynamic model and simulation system based on the physical watershed mechanism model, the interpretable empirical model and the simulation system model. Based on the hydrological-hydrodynamic model and simulation system, the present invention can formulate a more reasonable and effective prevention and control plan, thereby improving the efficiency and effectiveness of prevention and control work.
[0011] Optionally, the intelligent dispatching and optimization deployment subsystem performs intelligent dispatching and optimization deployment on the monitored basin based on the digital analysis results of the hydrological information and the hydrological-hydrodynamic model and simulation system, including: establishing a multi-objective dispatching optimization model in the intelligent dispatching and optimization deployment subsystem. The present invention combines the digital analysis results of the hydrological information and the hydrological-hydrodynamic model and simulation system, and the multi-objective dispatching optimization model accurately predicts the hydrological situation and evaluates different disaster dispatching plans, so that the system of the present invention can respond to the complex and changeable basin environment more scientifically and accurately.
[0012] Optionally, the establishment of a multi-objective scheduling optimization model in the intelligent scheduling and optimization allocation subsystem includes: establishing a peak flow analysis model, a water balance constraint model, a downstream flow constraint model and a water level constraint model in the intelligent scheduling and optimization allocation subsystem. The establishment and application of the multi-objective scheduling optimization model of the present invention promotes the improvement of the level of watershed prevention and control, and realizes the refined management and effective analysis of the watershed.
[0013] Optionally, the peak flow analysis model satisfies the following relationship:
[0014]
[0015] Among them, M max represents the minimum peak flow and of the monitored basin, f represents the peak flow and analysis function of the basin, N represents the number of control sections in the monitored basin, Q(y,t) represents the peak flow of the control section of the monitored basin in the t period, Q maxy represents the flood peak extreme value of the control section of the monitoring basin, and ω represents the flood peak impact weight of the monitoring basin;
[0016] The water balance constraint model satisfies the following relationship:
[0017] q (v,t) =q (v,t-1) +[Q(iny,t)-Q(outy,t) ′ -Q(s,t)]·Δt
[0018] Among them, q (v , t) represents the reservoir capacity at the end of period t in the monitoring basin, q (v , t-1) represents the reservoir capacity at the end of the monitoring basin t-1 period, Q(iny,t) represents the inflow of the monitoring basin during the monitoring basin period t, and Q(outy,t) ′ represents the average outflow of the monitored basin in period t, Q(s,t) represents the natural loss of the monitored basin in period t, and Δt represents the expected scheduling time interval of the monitored basin;
[0019] The downstream flow constraint model satisfies the following relationship:
[0020] O(qmin,t)≤O(q,t)≤O(qmax,t)
[0021] Among them, O(qmin,t) represents the minimum discharge flow in the monitoring basin during the t period, O(q,t) represents the actual discharge flow in the monitoring basin during the t period, and O(qmax,t) represents the maximum discharge flow in the monitoring basin during the t period;
[0022] The water level constraint model satisfies the following relationship:
[0023] L(l,min)≤L(l,t)≤L(l,max)
[0024] Among them, L(l,min) represents the lowest water level of the monitored basin, L(l,t) expresses the water level at the end of the monitored basin period t, and L(l,max) represents the highest water level of the monitored basin. The establishment and application of the model of the present invention promotes the scientific management and intelligent prevention and control of the basin, provides data support and decision-making basis for basin prevention and control, so that more scientific and reasonable management measures and disaster dispatch plans can be formulated.
[0025] Optionally, the basin disaster prevention and control system based on big data also includes: using the peak flow analysis model to analyze and monitor the minimum peak flow of the basin; using the water balance constraint model to analyze and monitor the reservoir capacity of the basin at any time period; using the downstream flow constraint model to analyze and monitor the downstream flow at any time period in the basin; using the water level constraint model to analyze and monitor the water level in the basin. The basin disaster prevention and control system based on big data of the present invention integrates and utilizes multiple key models, which not only improves the accuracy and timeliness of disaster warnings, but also optimizes the scheduling and allocation of water resources, and realizes the intelligent and efficient management of basins.
[0026] Optionally, the intelligent dispatching and optimization deployment subsystem performs intelligent dispatching and optimization deployment on the monitored basin based on the digital analysis results of the hydrological information and the hydrological-hydrodynamic model and simulation system, including: the intelligent dispatching and optimization deployment subsystem adjusts and optimizes the basin dispatching plan according to the minimum peak flow and reservoir capacity, downstream flow and water level of the monitored basin. The system of the present invention can cope with various complex hydrological conditions and changes in the basin, ensuring the adaptability, flexibility and effectiveness of the disaster dispatching plan.
[0027] Optionally, the remote monitoring and simulation subsystem receives output information from each subsystem of the watershed disaster prevention and control system, and implements scene simulation and remote monitoring of the monitored watershed based on the output information, including: the remote monitoring and simulation subsystem performs scene simulation on the monitored watershed based on the output information to obtain panoramic simulation results and key area display results of the monitored watershed; the remote monitoring and simulation subsystem performs remote real-time monitoring of the monitored watershed based on the panoramic simulation results, the key area display results and the output information. The remote monitoring and simulation subsystem of the present invention plays a vital role in the watershed disaster prevention and control system, realizes scene simulation and remote monitoring of the monitored watershed, thereby enhancing decision-making support capabilities, improving emergency response speed, optimizing resource allocation and improving disaster prevention and control efficiency. BRIEF DESCRIPTION OF THE DRAWINGS
[0028] Figure 1 This is a flow chart of the watershed disaster prevention and control system based on big data of the present invention;
[0029] Figure 2 This is a structural diagram of the watershed disaster prevention and control system based on big data of the present invention. DETAILED DESCRIPTION
[0030] The specific embodiments of the present invention will be described in detail below. It should be noted that the embodiments described herein are only for illustration and are not intended to limit the present invention. In the following description, a large number of specific details are set forth in order to provide a thorough understanding of the present invention. However, it is obvious to those of ordinary skill in the art that these specific details do not need to be adopted to implement the present invention. In other examples, in order to avoid confusing the present invention, known circuits, software or methods are not specifically described.
[0031] Throughout the specification, references to "one embodiment," "an embodiment," "an example," or "an example" mean that a particular feature, structure, or characteristic described in conjunction with the embodiment or example is included in at least one embodiment of the present invention. Therefore, the phrases "in one embodiment," "in an embodiment," "an example," or "an example" appearing in various places throughout the specification do not necessarily all refer to the same embodiment or example. In addition, particular features, structures, or characteristics may be combined in one or more embodiments or examples in any suitable combination and / or subcombination. In addition, it should be understood by those of ordinary skill in the art that the figures provided herein are for illustrative purposes and that the figures are not necessarily drawn to scale.
[0032] See also Figure 1 The present invention constructs a comprehensive, efficient and intelligent watershed disaster prevention and control system, which not only improves the timeliness, accuracy and scientificity of disaster prevention and control, realizes the timely adjustment and optimization of watershed disaster prevention and control plans, but also provides a strong guarantee for the sustainable development of different watersheds. The present invention provides a watershed disaster prevention and control system based on big data, and the watershed disaster prevention and control system based on big data includes the following steps:
[0033] The watershed disaster prevention and control system based on big data in the embodiment mainly includes: data monitoring and collection subsystem, data analysis and management subsystem, intelligent scheduling and optimization deployment subsystem, and remote monitoring and simulation subsystem.
[0034] S1. Use the above data monitoring and collection subsystem to collect data from the monitoring basin and obtain the basin monitoring data set. The specific steps and implementation contents are as follows:
[0035] In the process of using the data monitoring and acquisition subsystem to collect data from the monitored basin to obtain the basin monitoring data set, modern technologies such as 3D GIS, VR, AR, etc. can be combined to obtain 3D scene basin monitoring data information. In addition, it is also necessary to collect historical disaster data for the monitored basin, which will help to divide the key areas of the basin and create virtual scenes.
[0036] The three-dimensional GIS technology is used in the embodiment to construct a digital three-dimensional full scene of the monitoring basin. The above scene not only covers all the information of the monitored basin, but also can provide more comprehensive basin monitoring data information for relevant management personnel through virtual reality (VR) and augmented reality (AR) technology.
[0037] In an optional embodiment, the data monitoring and acquisition subsystem uses 3D animation and 3D graphics to intuitively and stereoscopically display the overall hydrological conditions of the monitored basin and the hydrodynamic information of the estuary, so that relevant personnel can understand the dynamic change information of the basin from multiple angles. In addition, the data monitoring and acquisition subsystem also uses physical basin mapping technology to map the complex terrain, water system distribution, water conservancy engineering facilities, etc. of the actual basin into a digital 3D scene, ensuring the accuracy of the basin monitoring data and the authenticity of the scene.
[0038] In another optional embodiment, key disaster areas are divided based on historical disaster data of the monitored river basin.
[0039] Based on the historical disaster data of the monitored basin, key areas of natural disasters such as floods, droughts and saltwater tides are scientifically divided. The above historical data provides a reliable reference basis and can accurately identify high-risk areas in the basin. Furthermore, for the key disaster areas in the monitored basin, the above subsystem uses high-precision modeling technology to create virtual scenes of key disaster areas, which not only restores the real geomorphic features and hydrological conditions, but also simulates the hydrological and hydrodynamic conditions of the river section or the estuary in combination with the monitoring data, as well as the operating status information of water conservancy engineering facilities, providing data support for the subsequent evaluation of disaster prevention and control plans. In the virtual scene, the function of switching perspectives at the mesoscopic and microscopic levels is provided, and the perspective can be switched freely as needed to grasp the overall situation of the basin from a global perspective, and to understand the specific hydrological characteristics and disaster risk information locally.
[0040] The data monitoring and collection subsystem provides strong technical support for watershed management and disaster prevention and control. It can not only be used for daily hydrological monitoring and data analysis, but also provide an intuitive reference for emergency response and decision-making when disasters occur.
[0041] Furthermore, the data acquisition method of the data monitoring and collection subsystem in this embodiment is only an optional condition of the present invention. In one or some other embodiments, the data acquisition method of the system can be adjusted according to the specific conditions of the monitored river basin and the data detection requirements, thereby enhancing the flexibility and adaptability of the system. The data acquisition method can be flexibly adjusted according to the different geographical, climatic, hydrological and other conditions of different river basins to ensure the accuracy and feasibility of the system data.
[0042] S2. The data analysis and management subsystem receives the watershed monitoring data set, analyzes the watershed monitoring data set, and obtains the digital analysis results of the hydrological information of the monitored watershed. The specific implementation contents are as follows:
[0043] In this embodiment, the data analysis and management subsystem is communicatively connected with the data monitoring and acquisition subsystem.
[0044] The communication connection between the data analysis and management subsystem and the data monitoring and collection subsystem is an important link to achieve data-driven decision-making, real-time monitoring and efficient management. The data monitoring and collection subsystem is mainly responsible for collecting data from various data sources, such as sensors, databases, API interfaces, etc., in real time or regularly. The above data includes but is not limited to the temperature, humidity, soil properties, vegetation, flow, location information, river roughness and river shape of the monitoring basin. The specific components of the data need to be adjusted and improved based on the actual application scenario. The data monitoring and collection subsystem can also perform preliminary cleaning and formatting of the data set to ensure the quality and consistency of the data set.
[0045] In an optional embodiment, the data monitoring and collection subsystem can be a hardware interface, which is connected to hardware devices such as sensors through physical interfaces such as USB, serial port, GPIO, etc., and the data reading can be a software interface that obtains data from other software systems or cloud services through API calls, Web services, etc., and then stores the data, and stores the collected data in a local database or cloud storage for subsequent analysis.
[0046] The data analysis and management subsystem is responsible for receiving, processing and analyzing the data obtained from the data acquisition subsystem. It can use statistical methods, machine learning algorithms and other technical means to extract valuable information from massive watershed monitoring data sets to provide support for watershed disaster prevention and control.
[0047] The communication connection between the data analysis subsystem and the data acquisition subsystem is the key to realizing data flow, analysis and application. Without an effective communication connection, the data analysis subsystem cannot obtain the latest data in time, which in turn affects the accuracy and timeliness of subsequent basin prevention and control decisions. In an optional embodiment, the connection method can use API interface technology, the data monitoring and acquisition subsystem provides interfaces such as RESTful API and GraphQL, and the data analysis and management subsystem calls the above interface through HTTP requests and obtains the basin monitoring data set. Further, message queue technology can be used, that is, using message queue systems such as Kafka and RabbitMQ, the collected data is sent to the queue, and the data analysis and management subsystem obtains data from the queue to achieve asynchronous data processing and load balancing; database sharing technology can also be used, the two subsystems share the same database or data warehouse, the data monitoring and acquisition subsystem writes data to the database, and the data analysis and management subsystem reads data from the database for analysis. This method also needs to ensure the security and concurrent access performance of the database.
[0048] The water level monitoring module, flow rate monitoring module and flow rate monitoring module are set up in the data analysis and management subsystem. The specific contents are as follows:
[0049] In an optional embodiment, a water level monitoring module is firstly provided in the data analysis and management subsystem, and the data analysis and management subsystem analyzes the watershed monitoring data set through the water level monitoring module and obtains the water level condition of the monitored watershed.
[0050] The water level monitoring module obtains the water level-related information and video files of each station in the monitoring basin based on the basin monitoring data set, and uses video processing tools or programming scripts to convert the video files frame by frame into image sequences for subsequent processing; then the images are imported and preprocessed, and the extracted image sequences are imported into the image processing subsystem of the water level monitoring module for necessary preprocessing operations, including but not limited to size adjustment, which can be unified into the 416x416 pixels required by YOLOv2, normalization processing, etc., to improve the processing efficiency and accuracy of related algorithms.
[0051] The water level monitoring module also includes a water gauge position recognition model, which is trained based on the processed data. The pre-trained YOLOv2 model is introduced into the water level monitoring module, and the model parameters such as learning rate, number of iterations, and anchor box size are adjusted according to the characteristics of the water gauge detection task.
[0052] Then, the water level information is gridded and candidate boxes are predicted. In the embodiment, the input image in the water level information is divided into S×S (specifically 13×13) grids, and each grid is responsible for predicting n (5) candidate boxes with different aspect ratios. Each candidate box contains the center point coordinates (x, y), width and height (w, h) and a confidence score, which is used to predict the possible position of the water gauge.
[0053] Next, feature extraction and model fine-tuning are performed. The Darknet-19 network is used as a feature extractor. The above network consists of 19 convolutional layers and 5 maximum pooling layers. First, pre-training is performed on the ImageNet classification dataset to learn common visual features. Then, the model is fine-tuned on a specific water gauge image dataset to optimize the network parameters to adapt to the water level detection task.
[0054] Finally, the model is tested and saved. After the water gauge position recognition model training is completed, the recognition effect of the model is evaluated using the test set, including but not limited to indicators such as accuracy and recall rate. The model with good performance is saved for subsequent use in water level detection in the monitoring basin.
[0055] In an optional embodiment, the data analysis and management subsystem analyzes the watershed monitoring data set through the water level monitoring module and obtains the water level conditions of the monitored watershed.
[0056] The YOLOv2 model in the water level monitoring module performs further image processing on the detected water gauge area in the monitoring basin, including but not limited to orthogonal correction to eliminate perspective deformation, edge detection to highlight the water level line, image binarization to simplify the complexity of the image, and inversion processing to enhance contrast.
[0057] Through morphological operations such as image clustering, hole filling, and closing operations, the water level line position of the monitoring basin is accurately located. According to the ordinate position of the water level line in the ruler image, combined with the scale information of the ruler, such as by fitting a mathematical function, the water level value represented by the bottom of the ruler is calculated, and the calculated water level value is output in the form of numbers or charts, thereby obtaining the water level situation of the monitoring basin.
[0058] In another optional embodiment, a flow rate monitoring module is provided in the data analysis and management subsystem, and the data analysis and management subsystem analyzes the watershed monitoring data set through the flow rate monitoring module and obtains the flow rate conditions of the monitored watershed.
[0059] In the embodiment, a flow velocity detection algorithm of large-scale particle image velocimetry (LSPIV) is introduced into the flow velocity monitoring module. First, images are extracted frame by frame from the watershed section video stream of the watershed monitoring data set to form a series of continuous image sequences, and the extracted image sequences are imported into the image processing software, which is conducive to subsequent information analysis and processing.
[0060] The velocity monitoring module will perform 3D to 2D mapping and image correction. The velocity monitoring module uses the central perspective projection model to establish the correspondence between 3D space coordinates and 2D image pixels, and performs orthorectification on the channel image sequence in the video through the collinear equation group (Direct Linear Transformation, DLT) to eliminate the perspective distortion of the image. The above process includes selecting 6 speed measurement points on the channel image, using the above points to solve the DLT equation group to obtain the corrected image parameters, and then adjusting the parameters of the corrected image to ensure that each pixel has a clear measurement size to facilitate subsequent velocity calculations.
[0061] The flow rate monitoring module spreads highly reflective tracer particles in the flow field and uses 16×16 pixel ripples as tracers. The movement trajectory of the tracer particles is recorded through continuously exposed images, and the image is divided into a calculation window of M×N pixels using the least square difference method. The particle image in each window is statistically analyzed, and the average displacement of the particle image in each window is analyzed using image processing algorithms such as autocorrelation and cross-correlation methods, thereby calculating the vector flow field on the surface of the channel image sequence, and then obtaining the water level of the monitored basin based on the vector flow field analysis results.
[0062] In addition, the velocity monitoring module also includes velocity field calculation and conversion. In the embodiment, binocular stereo vision technology is combined to calculate the velocity field in three-dimensional space based on image sequences from two different perspectives, and then the time-averaged velocity of the section is calculated based on the vector flow field. The above process involves averaging the velocity of multiple velocity measurement points. At the same time, the velocity of adjacent velocity measurement points is interpolated to obtain the velocity distribution on a specific section. The water surface velocity is further converted into the vertical depth average velocity through the velocity coefficient to more accurately reflect the velocity characteristics of the entire section. In the embodiment, the velocity monitoring module is based on the velocity detection algorithm, image processing and three-dimensional space mapping technology of LSPIV, which realizes the accurate measurement of the flow velocity of the monitored basin section, which not only overcomes the limitations of traditional single-point velocity measurement technology, but also provides rich flow field spatial structure and flow characteristics information, which provides strong support for fluid mechanics research and disaster prevention and control strategies.
[0063] In another optional embodiment, a flow monitoring module is provided in the data analysis and management subsystem, and the data analysis and management subsystem analyzes the watershed monitoring data set through the flow monitoring module and obtains the flow conditions of the monitored watershed.
[0064] Based on the watershed monitoring data set, the layout of monitoring points is understood and relevant data is obtained. Based on the watershed monitoring data set, multiple representative tributary sections are selected as monitoring standard data sets to ensure the representativeness and accuracy of the flow estimation results. The flow monitoring module uses YOLOv2 water level detection technology, which can automatically and in real time capture and identify the water level of each sub-section, and then combine three-dimensional terrain data and geometric calculation methods to determine the actual water flow area of each section. The above process integrates machine vision and geographic information system (GIS) technology, which significantly improves the efficiency and accuracy of obtaining relevant data.
[0065] Then, the flow monitoring module performs flow velocity measurement and integration. With the help of the velocity detection submodule of the large-scale particle image velocimetry (LSPIV), the water flow on the selected section is finely analyzed. By continuously capturing and processing the tracer particle images in the water flow, the velocity distribution of each section at different depth layers is calculated, and the vertical depth average velocity is obtained based on this. The application of LSPIV technology makes the velocity measurement no longer limited to a single point or surface layer, but realizes the overall grasp of the velocity field of the entire section.
[0066] The vertical depth average flow velocity of each section and the corresponding cross-sectional area are substituted into the calculation formula of the velocity-area method. The above formula is based on the principles of physical fluid mechanics. By accumulating the flow contribution of each section, the total flow of the entire monitored basin is obtained, which reflects the flow estimation idea from the local to the overall, ensuring the accuracy and scientificity of the flow calculation.
[0067] The basin flow prediction model in the flow monitoring module satisfies the following relationship:
[0068]
[0069] Among them, Q represents the flow prediction result of the monitoring basin, N represents the number of flood control sections in the monitoring basin, It represents the average flow velocity at different vertical depths of flood control sections, S i Indicates the cross-sectional area of different flood control sections;
[0070] In order to verify the reliability of the flow prediction results of the monitored basin, the estimated flow prediction results are compared and analyzed with the measured values. In the embodiment, the root mean square error (RMSE), determination coefficient (R 2 ) and other statistical indicators to quantify the estimation error and thus evaluate the performance of the data analysis and management subsystem.
[0071] The flow monitoring module is based on the velocity-area method (VAM) flow monitoring method, and combines machine vision, GIS technology and physical fluid mechanics principles to achieve high-precision, real-time monitoring of basin flow. The above module not only improves the accuracy and efficiency of flow estimation results, but also provides strong support for basin disaster prevention and control.
[0072] Furthermore, the specific steps and methods for analyzing data through the data management and analysis subsystem in this embodiment are merely an optional condition of the present invention. In one or some other embodiments, the system analysis module can be adjusted according to the monitoring environment conditions and basin requirements, and the data management and analysis subsystem can be adjusted according to the specific situation, so that the basin disaster prevention and control system can better adapt to various complex and changeable monitoring scenarios.
[0073] S3. Based on the digital analysis results of hydrological information, a hydrological-hydrodynamic model and simulation system is established in the data analysis and management subsystem. The specific implementation contents are as follows:
[0074] In the data analysis and management subsystem, a physical watershed mechanism model, an interpretable empirical model and a simulation system model are constructed; based on the above physical watershed mechanism model, interpretable empirical model and simulation system model, a hydrological-hydrodynamic model and a simulation system are obtained. The specific contents are as follows:
[0075] In an optional embodiment, the construction content of the physical watershed mechanism model in the data analysis and management subsystem is as follows:
[0076] The data analysis and management subsystem needs to integrate the basin monitoring data and map the physical processes, so as to obtain a data set that can fully reflect the natural and social characteristics of the basin. This data set integrates the core mechanisms such as hillside runoff, river confluence and estuary dynamics. Through the careful screening and integration of underlying surface features, such as topography, geomorphology, geological structure, water conservancy facility operation data such as sluice scheduling records, social and economic activity data, and meteorological and hydrological observation data such as precipitation and flow time series, it ensures the true mapping of the input data of the physical basin mechanism model and the physical process. In addition, it is necessary to consider the dual impact of climate change and human activities on the basin environment and enhance the prediction ability of the physical basin mechanism model for the monitoring basin scenario.
[0077] Furthermore, the embodiment adopts a method combining multi-source data fusion with intelligent optimization algorithm to optimize the model parameters intelligently. The reasonable range of model parameters is preliminarily defined by using field observation information, laboratory simulation experiment data and literature research results. Subsequently, by integrating the efficient global search capability of genetic algorithms and the robustness of Bayes parameter estimation, the model parameters are finely adjusted to ensure a high degree of consistency between the model output and the measured data. The above process not only improves the accuracy of the physical basin mechanism model, but also enhances the adaptability of the model under different basin conditions.
[0078] In order to further improve the prediction accuracy and timeliness of the model, a data assimilation and fusion framework was established based on multi-dimensional remote sensing data, real-time hydrological monitoring information and model simulation results. Advanced data assimilation technologies such as Kalman filtering and particle filtering were used to effectively integrate multi-source heterogeneous data, achieve real-time update of model status and error correction, and use a closed-loop model iteration optimization process to continuously compare model output with measured data, regularly adjust model structure and parameter settings, and continuously promote the optimization and improvement of model performance.
[0079] The physical watershed mechanism model provides strong technical support for the fields of water resources management, flood control, drought relief and disaster reduction, ecological environment protection, etc. in the watershed, and continuously improves the model system and data processing capabilities to ensure the scientificity, practicality and reliability of the model.
[0080] In an optional embodiment, the construction content of the interpretable empirical model in the data analysis and management subsystem is as follows:
[0081] First, based on the above-mentioned basin monitoring data set, extract multi-dimensional key data information closely related to the dynamic changes of the basin system, including but not limited to the basin natural attribute data, and record the characteristics of the basin underlying surface in detail, such as vegetation cover type and density, soil type and distribution, topography and geomorphology, and basin geometric characteristics, so as to reflect the natural background of the monitored basin to the greatest extent; hydrological process parameters, collect physical parameters about the flow generation-confluence process, such as river channel roughness, river channel geometry and soil permeability, etc., which are crucial for understanding water flow movement; human activity impact, record and quantify the impact of human activities on the basin, such as dam scheduling strategies, frequency and scale of water intake and drainage activities, and land use changes, so as to evaluate the interference of human activities on the basin hydrological cycle. Subsequently, the above-mentioned multi-dimensional key data are cleaned, integrated and preprocessed to ensure data quality and lay a solid foundation for subsequent modeling.
[0082] The data analysis and management subsystem uses machine learning, statistical learning and system dynamics methods to build interpretable empirical models. Among them, artificial neural networks (ANN) can capture nonlinear relationships in data and thus can handle complex hydrological processes; random forests (RF) integrate multiple decision trees to improve prediction accuracy and robustness; long short-term memory networks (LSTM) are suitable for processing time series data and can capture long-term dependencies; support vector machines (SVM) find the optimal classification or regression hyperplane in high-dimensional space and are suitable for processing small sample data; structural equation models (SEM) can clearly express the causal relationship between variables, which helps to understand the internal mechanism of the basin. The above models are modularly packaged to form interpretable empirical models that are easy to manage, expand and call.
[0083] In order to enhance the generalization ability and reliability of the model and optimize the interpretable empirical model, K-fold cross validation can be performed, and the data set can be divided multiple times for training and verification to evaluate the stability and generalization ability of the model. Parameter adaptive adjustment can also be performed, and the model parameters can be automatically adjusted using an optimization algorithm to minimize the risk of overfitting. The local cumulative effect analysis technology can be used to identify and quantify the local impact of specific input variables on the model output, thereby obtaining the interpretable empirical model in this embodiment.
[0084] In an optional embodiment, the construction content of the simulation system model in the data analysis and management subsystem is as follows:
[0085] First, the disaster levels are divided and scenarios are customized based on the historical data in the basin monitoring data set. Based on the historical data of precipitation, flow and drought index in the monitored basin, the disaster level classification is implemented to clearly define the severity of various disasters such as floods, droughts and saltwater tides. Subsequently, according to the specific needs of basin management, such as simulation accuracy, prediction time and response speed, a variety of scenario combinations are designed. For example, in response to the sudden severe rainstorm scenario in the upstream, a rapid response flood simulation plan for the downstream basin is customized to ensure that accurate disaster prediction information can be quickly provided in an emergency.
[0086] In the framework of multiple scenarios, the hydrological mechanism model and the empirical statistical model are used in combination in the implementation example, and the two complement each other. The laws and patterns in the historical data are deeply explored to build a hybrid model system that is both in line with the physical process and has data-driven characteristics. In order to select the optimal model combination, the data analysis and management subsystem adopts strict evaluation indicators such as NSE (Nash-Sutcliffe efficiency coefficient), RMSE (root mean square error), MAE (mean absolute error) and R 2 (Determination coefficient), the above indicators can comprehensively measure the predictive performance and applicability of the simulation system model.
[0087] In order to achieve high-precision simulation under multi-objective requirements, the flexible combination and seamless connection of the implementation model modules are realized. The physical watershed mechanism model can explain the free combination of empirical models and statistical models according to the specific needs of the prediction elements to form a variety of simulation paths. Based on this, the hydrological-hydrodynamic model and simulation system are further constructed, which can comprehensively consider all aspects of the hydrological cycle, including but not limited to precipitation, evaporation, infiltration, runoff and hydrodynamic processes, so as to carry out multi-dimensional analysis, prediction and prevention and control support for disasters such as floods, droughts and saltwater tides in a complex and changing environment.
[0088] Due to the continuous changes in basin environmental conditions, the hydrological-hydrodynamic model and simulation system also has a high degree of adaptability and dynamic adjustment capabilities. Through real-time monitoring and data analysis, the hydrological-hydrodynamic model and simulation system can promptly discover and respond to the impact of basin environmental changes on the model prediction results, thereby automatically or manually intervening to adjust the model parameters and structure to ensure the continued high accuracy and reliability of the simulation results.
[0089] The hydrological-hydrodynamic model and simulation system constructed in the embodiment performs high-precision analysis and simulation of disasters such as floods, droughts and saltwater tides. It not only realizes the fine division of disaster levels and scenario customization, but also meets the high-precision prediction and defense requirements under multi-objective needs through strategies such as model optimization, modular combination and coupled simulation, providing strong technical support for watershed management.
[0090] Furthermore, the method for constructing the hydrological-hydrodynamic model and simulation system in the present embodiment is only an optional condition of the present invention. In one or some other embodiments, the model construction method can be flexibly adjusted according to the basin environmental conditions and disaster prediction needs, thereby ensuring that the simulation system is more in line with the actual conditions of a specific basin and improving the accuracy and reliability of the simulation results.
[0091] S4, intelligent dispatching and optimization allocation subsystem performs intelligent dispatching and optimization allocation of the monitored basin based on the digital analysis results of hydrological information and the hydrological-hydrodynamic model and simulation system. The specific implementation contents are as follows:
[0092] In order to enhance system adaptability and flexibility, improve resource utilization efficiency and intelligent decision-making, a multi-objective scheduling optimization model is established in the intelligent scheduling and optimization allocation subsystem. In the embodiment, the peak flow analysis model, water balance constraint model, downstream flow constraint model and water level constraint model are established in the intelligent scheduling and optimization allocation subsystem, which mainly include the peak flow analysis model, water balance constraint model, downstream flow constraint model and water level constraint model.
[0093] In order to realize the dynamic dispatch and optimization of the monitoring basin by the intelligent dispatch and optimization deployment subsystem, this system needs to closely combine multi-dimensional information such as basin characteristics, water situation forecast, project operation status and potential disaster risks, conduct forward-looking prediction and situation analysis of the current basin status, and lay a solid foundation for formulating scientific and reasonable dispatch strategies.
[0094] The peak flow analysis model is used to analyze the minimum peak flow and of the monitored basin.
[0095] A peak flow analysis model is established based on basin characteristics, data availability, and basin analysis needs. Relevant parameters are set according to the model prediction requirements, such as the number of basin controls, confluence time, and peak flow volume, and the preprocessed data is input into the peak flow analysis model for simulation calculations. The model will calculate the peak flow under different scenarios based on the input data and set parameters. Furthermore, in order to determine the minimum peak flow, multiple scenarios can be set for analysis, such as rainfall processes under extreme drought conditions, natural conditions without the influence of large-scale water conservancy engineering facilities in the basin, etc. By comparing the calculation results under different scenarios, the minimum peak flow of the monitored basin can be found.
[0096] The peak flow analysis model in the intelligent scheduling and optimization allocation subsystem satisfies the following relationship:
[0097]
[0098] Among them, M max represents the minimum flood peak flow and the sum of the monitored basin, f represents the flood peak flow and the analysis function of the basin, N represents the number of flood control sections in the monitored basin, Q(y,t) represents the flood peak flow of the flood control section in the monitored basin in the t period, Q maxy represents the flood peak extreme value of the flood control section in the monitoring basin, and ω represents the flood peak impact weight of the monitoring basin;
[0099] The water balance constraint model is used to analyze and monitor the reservoir capacity in any period of time in the basin.
[0100] The intelligent scheduling and optimal allocation subsystem uses the water balance constraint model to analyze the reservoir capacity in the monitored basin at any time period, mainly conducting a comprehensive analysis of the inflow, outflow and storage of water resources in the monitored basin.
[0101] In the embodiment, the input water flow, outflow water volume and natural loss of the monitoring basin at different times are selected as model parameters. The accuracy of the model is highly dependent on the accuracy and reliability of the input data. When making long-term predictions, the impact of external factors in the area where the monitoring basin is located also needs to be considered.
[0102] The water balance constraint model in the intelligent scheduling and optimal allocation subsystem satisfies the following relationship:
[0103] q (v,t) =q (v,t-1) +[Q(iny,t)-Q(outy,t) ′ -Q(s,t)]·Δt
[0104] Among them, q (v , t) represents the reservoir capacity at the end of period t in the monitoring basin, q (v , t-1) represents the reservoir capacity at the end of the monitoring basin t-1 period, Q(iny,t) represents the inflow of the monitoring basin during the monitoring basin period t, and Q(outy,t) ′ represents the average outflow of the monitored basin in period t, Q(s,t) represents the natural loss of the monitored basin in period t, and Δt represents the expected scheduling time interval of the monitored basin;
[0105] The discharge flow constraint model is used to analyze and monitor the discharge flow in any period of time in the basin.
[0106] The downstream flow constraint model in the intelligent dispatching and optimal allocation subsystem satisfies the following relationship:
[0107] O(qmin,t)≤O(q,t)≤O(qmax,t)
[0108] Among them, O(qmin,t) represents the minimum discharge flow in the monitoring basin during the t period, O(q,t) represents the actual discharge flow in the monitoring basin during the t period, and O(qmax,t) represents the maximum discharge flow in the monitoring basin during the t period;
[0109] The downstream flow constraint model is used to analyze the downstream flow in any period of the monitored basin. In order to ensure that in different time periods, the actual downstream flow of the monitored basin in the embodiment can be maintained between the set minimum and maximum downstream flows to meet the various needs of the basin such as flood control, ecology, irrigation or power generation.
[0110] Compare the predicted discharge flow with the minimum and maximum discharge flows. If the actual discharge flow of the monitored flow during a specific period is within the preset discharge flow range, it means that the current discharge flow meets all constraints and does not need to be adjusted; if the actual discharge flow is less than the minimum discharge flow, the discharge flow needs to be increased to meet the minimum flow requirement, which may involve adjusting the water release strategy or considering other water replenishment measures; if the actual discharge flow is greater than the maximum discharge flow, the discharge flow needs to be reduced to avoid adverse effects on the downstream, which may involve adjusting the water storage plan or considering other discharge control measures.
[0111] The intelligent scheduling and optimal allocation subsystem that meets the downstream flow constraint model can further consider optimizing the water storage and release process in the monitored basin to maximize the utilization and benefits of water resources in the basin.
[0112] The water level constraint model is used to analyze and monitor the water level conditions in the basin.
[0113] The water level constraint model in the intelligent scheduling and optimal allocation subsystem satisfies the following relationship:
[0114] L(l,min)≤L(l,t)≤L(l,max)
[0115] Among them, L(min,t) represents the lowest water level in the monitoring basin, L(l,t) expresses the water level at the end of period t in the monitoring basin, and L(l,max) represents the highest water level in the monitoring basin.
[0116] The minimum water level of the monitored basin refers to the minimum water level that the monitored basin should maintain within the t period (or at the end of the t period). In the embodiment, the minimum water level is determined based on factors such as ecological protection, shipping demand, water extraction convenience, or preventing the riverbed from drying up.
[0117] The water level at the end of period t in the monitoring basin refers to the actual water level in the monitoring basin at the end of period t, which is the key data obtained through monitoring or prediction.
[0118] The maximum water level in the monitored basin refers to the maximum water level allowed in the monitored basin within time period t (or at the end of time period t). The maximum water level is limited by factors such as reservoir capacity, embankment flood control capacity, and downstream river safety.
[0119] The actual water level is compared with the minimum and maximum water level constraints. If the actual water level is within the preset water level range, the current water level meets the water level constraints and no special intervention or adjustment is required; if the actual water level is lower than the minimum water level, measures need to be taken to increase the amount of water in the basin, such as reducing the release of water from upstream reservoirs, implementing artificial water replenishment, etc.; if the actual water level is higher than the maximum water level, immediate measures need to be taken to lower the water level, such as increasing the release of water from reservoirs, opening spillways, etc., to prevent flood disasters.
[0120] Evaluating the effectiveness of water level management is beneficial to the flood control effect, ecological impact and socio-economic benefits of the basin. Adjusting water level constraints or optimizing scheduling strategies based on the evaluation results can improve the efficiency and effectiveness of water level management of the monitored stream.
[0121] Furthermore, the intelligent scheduling and optimization deployment subsystem can perform iterative optimization and multi-objective coordination on the above-mentioned multi-objective scheduling optimization model. In order to maximize the basin scheduling effect, the embodiment adopts an iterative calculation method to continuously fine-tune and optimize the multi-objective scheduling optimization model to ensure its robustness and feasibility in a complex and changing environment, and provide efficient, accurate and sustainable disaster prevention and control solutions for basin management through the multi-objective scheduling optimization model.
[0122] The intelligent scheduling and optimal allocation subsystem adjusts and optimizes the basin scheduling plan based on the minimum flood peak flow, reservoir capacity, downstream flow and water level conditions of the monitored basin.
[0123] In the management of river basin disaster prevention and control, the intelligent scheduling and optimization allocation subsystem dynamically adjusts and optimizes the river basin prevention and control scheduling plan through real-time monitoring and analysis of key parameters of the river basin, including but not limited to minimum flood peak flow, reservoir capacity, downstream flow and water level conditions, to ensure the effective use of water resources in the river basin, while ensuring the smooth progress of flood control safety, ecological protection and social and economic activities.
[0124] Analyze the current minimum peak flow in the basin and assess flood risks.
[0125] Check reservoir capacity and determine the reservoir's water storage and release capabilities.
[0126] Monitor the downstream flow to ensure that it meets the downstream ecological, irrigation, shipping and other needs, and does not exceed the safe discharge capacity of the river.
[0127] Assess the current water level and ensure that it is between the set minimum and maximum water levels.
[0128] Based on the results of the status assessment, a preliminary scheduling strategy is formulated, which takes into account the balance between multiple objectives such as flood control, water supply, power generation, and ecology, and determines the optimal scheduling plan to improve flood control effects, increase water resource utilization efficiency, or reduce ecological impacts.
[0129] The multi-objective scheduling optimization model can analyze the actual effects of different scheduling objectives, achieve balance and coordination among multiple objectives, and integrate historical scheduling scenario data for review and data feature extraction. The above process not only reviews the effectiveness of historical key events and their response strategies, but also promotes the evolution and optimization of basin prevention and control scheduling plans, making them more adaptable to the dynamic changes of the basin.
[0130] On this basis, the intelligent scheduling and optimization allocation subsystem combines the actual situation of the current monitored basin, such as climate change, water resources, social and economic needs, etc., to evaluate and screen the relevant control parameters of the basin control plan to ensure that the selected plan is in line with long-term planning and can effectively respond to short-term challenges. This reflects the core advantage of the basin disaster prevention and control system, and can dynamically adjust the scheduling strategy according to changes in the external environment to achieve optimal allocation of resources and effective management of risks.
[0131] Ultimately, the watershed disaster prevention and control system based on scheduling rules and risk feedback mechanisms was able to make timely adjustments and optimizations to watershed disaster prevention and control plans, which not only improved the decision-making efficiency and accuracy of watershed scheduling management, but also provided strong technical support for responding to extreme events that may occur in the future, so as to better serve the sustainable development and ecological security of the watershed.
[0132] Furthermore, in the present embodiment, the method for establishing the multi-objective scheduling optimization model is only an optional condition of the present invention. In one or some other embodiments, the multi-objective scheduling optimization model can be modified and optimized according to the actual situation of the river basin disaster and the conditions of the river basin prevention and control system. Through the optimization model, the feasibility of different river basin prevention and control scheduling schemes can be evaluated more scientifically, providing decision makers with a more reasonable and feasible basis for scheme regulation.
[0133] S5. The remote monitoring and simulation subsystem receives the output information of each subsystem of the watershed disaster prevention and control system, and implements the scene simulation and remote monitoring of the monitoring watershed based on the output information of each subsystem. The specific implementation steps and contents are as follows:
[0134] The remote monitoring and simulation subsystem simulates the monitoring basin based on the output information to obtain the panoramic simulation results of the monitoring basin and the display results of key areas. The specific implementation contents are as follows:
[0135] In an optional embodiment, scenes of key areas of the monitored watershed are constructed and results displayed.
[0136] First, the remote monitoring and simulation subsystem clearly identifies and divides key areas such as frequent disasters such as historical floods, droughts and saltwater tides, potential risk points, sensitive areas invaded by saltwater tides, and estuaries and coasts. The above key areas are highlighted through the three-dimensional map platform to ensure that managers and decision makers can intuitively and quickly grasp the overall situation and provide a spatial positioning basis for precise policy implementation.
[0137] For the designated key areas, digital technology is used in the implementation example to construct a detailed three-dimensional panoramic scene. In the above process, it is necessary not only to simulate the natural elements in the monitoring basin, such as tributaries, lakes and other water system structures, but also to integrate the information of cultural facilities, including but not limited to important water conservancy engineering facilities, hydrological monitoring stations, town layout and buildings. Through high-precision modeling, the real-life restoration of the river channel and surrounding environment in the monitoring basin is achieved, from water surface fluctuations to bridge structures, from river embankment protection to residential area layout, all of which are fully displayed in a three-dimensional perspective. At the same time, a virtual mirror image of the monitoring basin is established to provide an intuitive perspective for subsequent operation and maintenance management.
[0138] Based on real-time updated data resources, the remote monitoring and simulation subsystem embeds panoramic monitoring functions in the digital panoramic scenes of key areas, allowing real-time monitoring of key information such as river flow, water level changes, water quality, and peak flow from a panoramic perspective, and realizing multi-scale observation and analysis from macro overview to meso details and micro close-ups. Based on this, it not only improves the efficiency and accuracy of monitoring, but also provides rich data support and visualization assistance for the judgment of the situation in the basin. Based on the above information, the disaster risk of the basin can be quickly assessed, and scientific and reasonable scheduling and response measures can be formulated to ensure the safety and social stability of the monitored basin.
[0139] In another optional embodiment, a panoramic scene of the monitored watershed is constructed and the results are displayed.
[0140] The watershed disaster prevention and control system has made detailed divisions and annotations of areas affected by historical floods and droughts, potential disaster risk points, high-risk areas for saltwater intrusion, and sensitive areas such as estuaries and coasts, providing managers with an intuitive and global perspective, enabling them to quickly identify and focus on key areas of watershed disasters, thereby more effectively formulating prevention and response measures.
[0141] In order to better understand and manage key areas of river basin disasters, the remote monitoring and simulation subsystem constructed a three-dimensional panoramic scene of the monitoring basin. The above process integrates rich geographical and environmental information, including but not limited to tributaries, lakes, key water conservancy projects such as dams, pumping stations, important hydrological monitoring stations, and surrounding towns and building layouts in the basin. Through high-precision three-dimensional modeling technology, not only the natural form and water flow dynamics of the river channel are restored, but also the details of water surface fluctuations, bridge structures, surrounding flood control embankments and residential buildings on the monitored river section are simulated, realizing comprehensive visualization from natural landscapes to artificial facilities. At the same time, a virtual model of water conservancy project facilities is constructed in the digital panoramic scene, providing intuitive and convenient digital tools for the operation, maintenance and management of the facilities.
[0142] The basin disaster prevention and control system realizes panoramic monitoring and situation assessment of the monitored basin based on real-time data. Based on the continuously updated basin monitoring data set, the system integrates panoramic monitoring functions into the digital panoramic scenes of key areas, which can observe the river hydrological changes, water quality conditions and potential risk points in the monitored basin in real time from a panoramic perspective. On the other hand, by combining the overall situation analysis of the river in the monitored basin at the meso-level with detailed observations at the micro-level, it provides managers with a more comprehensive and in-depth support basis for disaster prevention and control plans, which helps managers to promptly discover and respond to potential disaster risks, thereby ensuring the safety and stability of the basin.
[0143] The remote monitoring and simulation subsystem performs remote real-time monitoring of the monitoring basin based on the panoramic simulation results, the key area display results and the output information. The specific implementation contents are as follows:
[0144] The watershed disaster prevention and control system based on big data of the present invention can also provide early warning based on digital panoramic scenes.
[0145] The remote monitoring and simulation subsystem receives and monitors composite early warning information on disasters such as floods, droughts, and saltwater tides in river basins, and generates a variety of targeted disaster prevention and control decision-making plans accordingly.
[0146] Furthermore, the remote monitoring and simulation subsystem conducts real-time data monitoring, and through the remote monitoring interface, displays various data in the monitoring basin, such as water level, flow, water quality parameters, meteorological data, etc. in real time. The relevant data can also be presented in various forms such as charts, curves, maps, etc., so that managers can intuitively understand the basin status. On the other hand, big data analysis technology is used to deeply mine and analyze real-time data to identify potential risks and anomalies.
[0147] The remote monitoring and simulation subsystem provides intelligent early warning for the monitored basin. Based on the digital panoramic scene, basin monitoring data set, model analysis and prediction results, it provides visual early warning for possible disasters. Through the remote monitoring interface, the warning area, warning level and expected impact time are marked in the panoramic scene of the monitored basin, providing intuitive disaster warning information. It can also generate a variety of targeted disaster prevention and control decision-making plans based on the warning information and panoramic simulation results, including but not limited to evacuation routes, emergency material allocation, engineering scheduling and other specific measures to minimize disaster losses.
[0148] When a disaster occurs, the remote monitoring and simulation subsystem can quickly start the emergency response mechanism, track the development of the disaster in real time, provide decision support for emergency command, and ensure the effective implementation of emergency measures. The remote monitoring and simulation subsystem integrates multi-source data, uses panoramic simulation technology and intelligent data analysis methods, realizes remote real-time monitoring and digital panoramic early warning of the monitoring basin, provides strong technical support and decision-making basis for basin disaster prevention and control, and helps to improve the scientific management and effective early warning of basin disaster prevention and control.
[0149] Furthermore, the remote monitoring and simulation subsystem constituent condition in the present embodiment is merely an optional condition of the present invention. In one or some other embodiments, the specific functions of the remote monitoring and simulation subsystem may be adjusted and replaced according to specific practical conditions and disaster prevention and control requirements. Different river basins have unique geographical environments, climatic conditions and disaster types, and therefore require customized monitoring and simulation strategies to ensure that the system better adapts to the actual conditions of different river basins and improves the pertinence and effectiveness of disaster prevention and control.
[0150] See also Figure 2 In an optional embodiment, in order to efficiently execute the basin disaster prevention and control system based on big data provided by the present invention, the system includes a data monitoring and acquisition subsystem, a data analysis and management subsystem, an intelligent scheduling and optimization allocation subsystem, and a remote monitoring and simulation subsystem. The data monitoring and acquisition subsystem, the data analysis and management subsystem, the intelligent scheduling and optimization allocation subsystem, and the remote monitoring and simulation subsystem are interconnected. The basin disaster prevention and control system based on big data implements the specific steps of the basin disaster prevention and control related embodiments provided by the present invention. The basin disaster prevention and control system based on big data of the present invention has a complete structure, is objective and stable, and can efficiently execute the relevant embodiments of the present invention, thereby improving the overall applicability and practical application capabilities of the present invention.
[0151] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents. These modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be included in the scope of the claims and specification of the present invention.
Claims
1. A river basin disaster prevention and control system based on big data, characterized in that: The watershed disaster prevention and control system based on big data includes: data monitoring and collection subsystem, data analysis and management subsystem, intelligent scheduling and optimization deployment subsystem, remote monitoring and simulation subsystem; Using the data monitoring and collection subsystem to collect data from the monitored watershed and obtain a watershed monitoring data set; The data analysis and management subsystem receives the watershed monitoring data set, analyzes the watershed monitoring data set, and obtains digital analysis results of hydrological information of the monitored watershed; Establishing a hydrological-hydrodynamic model and simulation system in the data analysis and management subsystem based on the digital analysis results of the hydrological information; The intelligent dispatching and optimization deployment subsystem performs intelligent dispatching and optimization deployment on the monitored basin based on the digital analysis results of the hydrological information and the hydrological-hydrodynamic model and simulation system; The remote monitoring and simulation subsystem receives output information from each subsystem of the watershed disaster prevention and control system, and implements scene simulation and remote monitoring of the monitored watershed based on the output information.
2. The watershed disaster prevention and control system based on big data according to claim 1 is characterized in that: The data analysis and management subsystem receives the watershed monitoring data set, and analyzing the watershed monitoring data set includes: The data analysis and management subsystem is communicatively connected with the data monitoring and collection subsystem; A water level monitoring module, a flow rate monitoring module and a flow rate monitoring module are set in the data analysis and management subsystem; A watershed flow prediction model is set in the flow monitoring module, and the watershed flow prediction model satisfies the following relationship: Among them, Q represents the flow prediction result of the monitoring basin, N represents the number of control sections in the monitoring basin, represents the average flow velocity at different vertical depths of the control section, S i Indicates the cross-sectional area of different flood control sections; The data analysis and management subsystem uses the water level monitoring module, the flow rate monitoring module and the flow rate monitoring module to analyze the watershed monitoring data set.
3. The watershed disaster prevention and control system based on big data according to claim 2 is characterized in that: The analysis of the watershed monitoring data set and obtaining the digital analysis results of the hydrological information of the monitored watershed include: The data analysis and management subsystem analyzes the watershed monitoring data set through the water level monitoring module and obtains the water level conditions of the monitored watershed; The data analysis and management subsystem analyzes the watershed monitoring data set through the flow rate monitoring module and obtains the flow rate of the monitored watershed; The data analysis and management subsystem analyzes the watershed monitoring data set through the flow monitoring module and obtains the flow conditions of the monitored watershed.
4. The watershed disaster prevention and control system based on big data according to claim 1 is characterized in that: The establishment of a hydrological-hydrodynamic model and simulation system in the data analysis and management subsystem based on the digital analysis results of the hydrological information includes: Constructing a physical watershed mechanism model in the data analysis and management subsystem: Constructing interpretable empirical models in the data analysis and management subsystem: Constructing a simulation system model in the data analysis and management subsystem; A hydrological-hydrodynamic model and a simulation system are obtained based on the physical watershed mechanism model, the interpretable empirical model and the simulation system model.
5. The watershed disaster prevention and control system based on big data according to claim 1 is characterized in that: The intelligent dispatching and optimization deployment subsystem performs intelligent dispatching and optimization deployment of the monitored basin based on the digital analysis results of the hydrological information and the hydrological-hydrodynamic model and simulation system, including: A multi-objective scheduling optimization model is established in the intelligent scheduling and optimization allocation subsystem.
6. The watershed disaster prevention and control system based on big data according to claim 5 is characterized in that: The establishment of a multi-objective scheduling optimization model in the intelligent scheduling and optimization allocation subsystem includes: A flood peak flow analysis model, a water balance constraint model, a downstream flow constraint model and a water level constraint model are established in the intelligent scheduling and optimization allocation subsystem.
7. The watershed disaster prevention and control system based on big data according to claim 6 is characterized in that: The peak flow analysis model satisfies the following relationship: Among them, M max represents the minimum peak flow and of the monitored basin, f represents the peak flow and analysis function of the basin, N represents the number of control sections in the monitored basin, Q(y,t) represents the peak flow of the control section of the monitored basin in the t period, Q maxy represents the flood peak extreme value of the control section of the monitoring basin, and ω represents the flood peak impact weight of the monitoring basin; The water balance constraint model satisfies the following relationship: q (v,t) =q (v,t-1) +[Q(iny,t)-Q(outy,t) ′ -Q(s,t)]·Δt Among them, q (v , t) represents the reservoir capacity at the end of period t in the monitoring basin, q (v , t-1) represents the reservoir capacity at the end of the monitoring basin t-1 period, Q(iny,t) represents the inflow of the monitoring basin during the monitoring basin period t, and Q(outy,t) ′ represents the average outflow of the monitored basin in period t, Q(s,t) represents the natural loss of the monitored basin in period t, and Δt represents the expected scheduling time interval of the monitored basin; The downstream flow constraint model satisfies the following relationship: O(qmin,t)≤O(q,t)≤O(qmax,t) Among them, O(qmin,t) represents the minimum discharge flow in the monitoring basin during the t period, O(q,t) represents the actual discharge flow in the monitoring basin during the t period, and O(qmax,t) represents the maximum discharge flow in the monitoring basin during the t period; The water level constraint model satisfies the following relationship: L(l,min)≤L(l,t)≤L(l,max) Among them, L(l,min) represents the lowest water level in the monitoring basin, L(l,t) expresses the water level at the end of period t in the monitoring basin, and L(l,max) represents the highest water level in the monitoring basin.
8. The watershed disaster prevention and control system based on big data according to claim 7 is characterized in that: The watershed disaster prevention and control system based on big data also includes: Analyze the minimum peak flow and of the monitored basin by using the peak flow analysis model; The water balance constraint model is used to analyze and monitor the reservoir capacity in any period of time in the basin; The downstream flow constraint model is used to analyze and monitor the downstream flow situation in any period of time in the basin; The water level constraint model is used to analyze and monitor the water level conditions in the basin.
9. The watershed disaster prevention and control system based on big data according to claim 8 is characterized in that: The intelligent dispatching and optimization deployment subsystem performs intelligent dispatching and optimization deployment of the monitored basin based on the digital analysis results of the hydrological information and the hydrological-hydrodynamic model and simulation system, including: The intelligent scheduling and optimization allocation subsystem adjusts and optimizes the basin scheduling plan based on the minimum flood peak flow and reservoir capacity, downstream flow and water level conditions of the monitored basin.
10. The watershed disaster prevention and control system based on big data according to claim 1 is characterized in that: The remote monitoring and simulation subsystem receives output information from each subsystem of the watershed disaster prevention and control system, and implements scene simulation and remote monitoring of the monitored watershed based on the output information, including: The remote monitoring and simulation subsystem performs scene simulation on the monitored watershed according to the output information to obtain panoramic simulation results of the monitored watershed and display results of key areas; The remote monitoring and simulation subsystem performs remote real-time monitoring of the monitoring basin based on the panoramic simulation results, the key area display results and the output information.
Citation Information
Patent Citations
River peak discharge range calculation method
CN113269376A
Reservoir group multi-objective optimization scheduling simulation method and system based on digital twinning
CN117010575A
Multi-region flood control dispatching calculation method coupled with reservoir downstream river flood routing
CN117764300A
Mountain torrent disaster early warning method and system based on distributed hydrological model
CN117953648A
Hydrological information prediction method and system based on regional drainage basin
CN118211481A
Cited By
Natural disaster landslide early warning risk assessment method and system based on model workflow
CN120509743A
