A Real-time Scheduling Visualization Dynamic Modeling Method and System for a Complex Water Project System in a Basin

Abstract

The present invention belongs to the cross - field of hydrological water resources scheduling and water conservancy informatization, and discloses a real - time scheduling visual dynamic modeling method and system for a complex water project system in a basin. The method includes: constructing a real - time scheduling topological visualization graph of the water project system in the basin; based on the real - time scheduling topological visualization graph, performing fusion configuration on the characteristic parameters of water project nodes and the characteristic parameters of river cross - section nodes; constructing a composite flood routing model based on the fusion - configured node characteristic parameters; and constructing an intelligent scheduling model based on the composite flood routing model. The present invention combines computer graphical interaction technology and multi - model coupling algorithms to realize the full - process digital management of water project scheduling.

Description

Technical Field

[0001] The present invention belongs to the cross - field of hydrological water resources scheduling and water conservancy informatization, and particularly relates to a real - time scheduling visualization dynamic modeling method and system for a complex water project system in a basin. Background Technique

[0002] The real - time scheduling of a complex water project system in a basin is the core technical means to ensure flood control safety and optimize water resources allocation. With the intensification of global climate change and the frequent occurrence of extreme hydrological events, traditional scheduling systems are difficult to meet the dynamic requirements of multi - project coordination and multi - objective optimization. Especially in the scenario of extreme floods, how to quickly construct a scheduling topology that includes the linkage of reservoir groups, sluice - dam networks, and flood detention areas, and realize the scenario deduction with a minute - level response ability is directly related to the safety and efficiency of the basin flood control system. At present, the largest water project cluster in the world has been built in key basins in China, but the timeliness and accuracy of scheduling decisions still face major technical challenges.

[0003] Existing water project scheduling systems mostly adopt a predefined static topology architecture, and their modeling process depends on manual coding and offline configuration. When encountering the reconstruction, expansion or sudden danger of engineering facilities that requires temporary adjustment of the topology, the system must rewrite the underlying connection logic. Practical application data shows that the modeling cycle in such scenarios is generally calculated in weeks or months, seriously restricting the emergency response ability. More prominently, the traditional visualization interface can only achieve the planar display of topological relationships and lacks a dynamic coupling mechanism with the hydraulic calculation model, resulting in "data islands" in the formulation of scheduling plans and simulation verification.

[0004] In terms of model integration, the existing technology has not overcome the problem of collaborative calculation of heterogeneous models. The reservoir scheduling model (based on the principle of water balance) and the river channel evolution model (requiring the solution of hydrodynamic equations) often cause conflicts in calculation results due to differences in algorithm principles and spatio - temporal scales. Especially when facing a mixed - connection project group, the system cannot autonomously identify the topological structure characteristics to adapt to the joint scheduling model, resulting in more than 30% of the scheduling plans requiring manual intervention and correction. This phenomenon is particularly prominent in cross - provincial boundary basin scheduling, seriously threatening the reliability and execution efficiency of scheduling instructions.

[0005] The current system architecture generally has scalability bottlenecks. When adding new scheduling models or adjusting calculation processes, the core code needs to be reconstructed, and each iterative upgrade takes up to 2-3 months. The verification mechanism also remains at the level of single model parameter verification, lacking full-link verification of topological integrity, model coupling, and scheme feasibility. A 2022 actual combat exercise in a certain basin showed that the deduction error caused by the mismatch between the time step of the dam model and the river model was as high as 25%, exposing major defects in the traditional verification system. In addition, when the topological structure changes dynamically (such as the emergency activation of flood diversion facilities), the existing system takes more than 2 hours to re-define the calculation boundaries, which makes it difficult to meet the minute-level response requirements of the "four predictions" (forecast, warning, rehearsal, and plan) for flood control.

[0006] In view of the above problems, the present invention proposes a new visual dynamic modeling method and system for real-time scheduling of complex water engineering systems in a river basin. Summary of the invention

[0007] In order to solve the problems existing in the prior art, the present invention provides a visual dynamic modeling method and system for real-time scheduling of complex water engineering systems in a river basin, which combines computer graphical interaction technology with a multi-model coupling algorithm to realize full-process digital management of water engineering scheduling.

[0008] To achieve the above object, the present invention provides the following solutions:

[0009] A visual dynamic modeling method for real-time scheduling of a complex water engineering system in a river basin, the method comprising:

[0010] Construct a real-time scheduling topology visualization diagram of the basin water engineering system;

[0011] Based on the real-time scheduling topology visualization diagram, the characteristic parameters of the water project nodes and the characteristic parameters of the river section nodes are integrated and configured;

[0012] Based on the node characteristic parameters of the fusion configuration, a composite flood evolution model is constructed;

[0013] Based on the composite flood evolution model, an intelligent scheduling model is constructed.

[0014] Preferably, the method for constructing a real-time scheduling topology visualization diagram of a watershed water engineering system includes:

[0015] Construct flood forecasting topological base layer based on river basin GIS data;

[0016] Based on the flood forecasting topological base layer, a multi-dimensional extensible graphic element library for basin water project scheduling is constructed;

[0017] Based on the multi-dimensional extensible graphic element library, dynamic topological linking is implemented to complete the construction of a real-time scheduling topological visualization diagram of the watershed water engineering system.

[0018] Preferably, the method for constructing a multi-dimensional extensible primitive library based on the flood forecasting topological basic layer includes:

[0019] Design a composite parameter system including geometric parameters, hydraulic parameters, and control logic parameters for each type of primitive based on the physical characteristics and regulation behaviors of engineering entities;

[0020] At the same time, realize the dynamic injection of new engineering features through the multi-layer open extension interface, customize the parameter dimension according to the characteristics of the basin, and establish a structured database that supports the topological reconstruction and intelligent calculation of complex water networks;

[0021] Among them, the method for realizing the dynamic injection of new engineering features through the multi-layer open extension interface, customizing the parameter dimension according to the characteristics of the basin, and establishing a structured database that supports the topological reconstruction and intelligent calculation of complex water networks includes: hierarchical interface protocol design, parameter dynamic binding and conflict detection mechanism, and construction of an intelligent parameter recommendation system;

[0022] The hierarchical interface protocol design includes: a core interface layer, an extended interface layer, and a basin adaptation layer; the core interface layer is used to forcibly inherit the hydraulic conduction attributes and spatial topological constraints of the basic primitive; the extended interface layer is used to declare the physical dimension, value range, and data verification rules of the newly added parameters based on the domain-specific language DSL, and support non-programmers to define parameters through configuration files; the basin adaptation layer internally sets the terrain slope , soil permeability coefficient , river network density basin characteristic parameterization templates for dynamically generating parameter legality functions;

[0023] The parameter dynamic binding and conflict detection mechanism includes: hydraulic model symbolic binding: using a symbolic calculation engine to automatically analyze the partial derivative relationship between the newly added parameters and the hydraulic control equation to generate a row column Jacobian matrix, ensuring that the parameters are automatically integrated into the calculation kernel after injection without reconstructing the model code; constructing a parameter dependence network based on a directed acyclic graph, detecting contradictory combinations through topological sorting, triggering real-time alarms and locking the calculation process, and realizing conflict self-checking through mathematical symbol binding and graph theory algorithms;

[0024] For hydraulic structures, construct an intelligent parameter recommendation system based on engineering feature fingerprints and cross-engineering topological association learning, specifically including: extracting core parameters for each type of hydraulic structure, and generating a unique feature fingerprint code by weighting through the random forest algorithm , where is the parameter importance weight, It is the core physical parameter value extracted from the project, used to quantify the structural or functional characteristics of different projects; based on the graph convolutional network GCN, an associated topological graph of hydraulic structures is constructed, where the nodes are the engineering feature fingerprints and the edges are the river connections between projects. The matching degree score between the new parameters and the target project is calculated through neighborhood feature aggregation, and the optimal parameter combination is recommended dynamically.

[0025] Preferably, the method for implementing topological dynamic linking based on the multi-dimensional extensible graph element library includes:

[0026] Decompose the river and lake node conductive graph elements into connector units with direction vectors, and construct a mathematical representation of the unstructured water network topological relationship through a set of directed line segments , where and are the starting and ending coordinates of the connector, where , is the abscissa and ordinate of the starting point of the connector, , is the abscissa and ordinate of the ending point of the connector, is the cross-sectional area function varying with the water level, where , are the functions of the cross-sectional area varying with the water level of the starting section and the ending section respectively, is the dynamic conductivity matrix, driven by the water level gradient , where and are the conductivity coefficients from the starting point to the ending point and from the ending point to the starting point respectively;

[0027] Each connector unit realizes the asymmetric conduction characteristic through the direction vector weight function, and the dynamic correction formula of the conductivity coefficient is:

[0028]

[0029]

[0030] Among them, is the reference conductivity, is the connector direction vector, is the asymmetric adjustment factor, is the gradient response intensity coefficient, , are the starting water level and the ending water level of the connector.

[0031] Preferably, the method for constructing the composite flood routing model includes: combining multiple methods such as the improved Muskingum sectional calculation, the hydrodynamic model solved by the unstructured grid Godunov format, and the coupled model of the river-connected lakes, comprehensively considering different flow characteristics, and constructing the composite flood routing model;

[0032] Among them, the improved Muskingum segmentation calculation model is used to divide the basin into several sub-river sections based on the terrain slope, roughness distribution, cross-section morphology, and hydrological station location attributes. The local Muskingum coefficient is introduced into each sub-river section. That is, the storage parameters and That is, the flow weight factor. The improved Muskingum method adopts a physically related initial parameter mapping mechanism. The initial value sets a nonlinear mapping function according to the sub-reach attributes. , ,in , , is a hyperparameter, The length of the river section, is the slope, For Manning's roughness, For the width of the river, For water depth; Sub-river sections, outflow ,in , , Depend on , Decide and satisfy , For time, is the time step; the inlet flow of the sub-river section and export flow The monitoring data is taken as input and the objective function is constructed , using recursive least squares RLS, real-time update and , and introduced the particle filter algorithm PF, which integrates historical flood event data with a Bayesian framework and periodically modifies hyperparameters , , During the calculation process, the basin is divided into multiple sub-sections, and the improved Muskingum model is applied to flood calculations according to the characteristics of the sub-sections. Then the results of each sub-section are integrated to obtain the flood evolution of the entire basin.

[0033] Preferably, the method for constructing an intelligent scheduling model includes:

[0034] Engineering connection relationship matrix analysis and hybrid structure eigenvalue decomposition based on graph theory;

[0035] Based on the results of analysis and decomposition, multi-mode scheduling of single projects and collaborative scheduling of project groups are carried out to complete the construction of an intelligent scheduling model.

[0036] Preferably, the method for multi-mode scheduling of single projects and collaborative scheduling of project groups includes: using an improved starfish optimization algorithm, and the steps are as follows:

[0037] Initialize the population size , when the improved starfish optimization algorithm initializes the population generation, it adopts a constraint satisfaction initialization method based on chaotic mapping, that is, under the dynamic feasible region that satisfies the reservoir discharge flow, the population is initialized by adopting the chaotic mapping Cubic mapping strategy, and the formula for initializing the population by Cubic mapping is:

[0038] ;

[0039] Among them, is the population position matrix, , is the length of the scheduling period, is the upper boundary of the population position, which represents the upper boundary of the water level process in this problem, is the lower boundary of the population position, representing the lower boundary of the water level process, , and the finally generated initial population matrix is:

[0040] ;

[0041] Calculate the initial fitness value of each individual, that is, the objective function value. The minimum objective function value means the maximum peak shaving rate, and the position of the corresponding individual, that is, the reservoir discharge process, is recorded as , represents the th individual, and the position of the th dimension, represents the current iteration number;

[0042] Update the positions of the population individuals according to the position update formula of the improved starfish optimization algorithm, that is, update the reservoir discharge process. The position update of the improved starfish optimization algorithm includes an exploration stage and a development stage:

[0043] Exploration stage:

[0044] ;

[0045] ;

[0046] ;

[0047] Among them, is the updated position, is the position before update, is the current best position, is is 5 dimensions randomly selected from, is a random number between 0 and 1, is the current iteration number, is the maximum iteration number, is a randomly generated angle parameter, is a dynamically adjusted angle parameter, ;

[0048] Development stage: Two position update strategies are designed according to the predation and regeneration behaviors of starfish:

[0049] ;

[0050] ;

[0051] ;

[0052] Among them, is the updated position, is the position before update, and are random numbers between 0 and 1, is the population size, is the distance between the best position and the positions of 5 randomly selected dimensions, and are randomly selected from , is the current optimal position, are the positions of 5 randomly selected starfish;

[0053] After the development stage, a tail mutation strategy is introduced, that is, a forced perturbation is added to the positions of the population to avoid falling into local optimal solutions, and the intensity of the perturbation gradually decreases as the number of iterations increases, accelerating the convergence in the later stage of the algorithm. The Lévy flight strategy is selected in the improved starfish optimization algorithm to perturb the positions of the population, where is the Lévy distribution;

[0054] ;

[0055] For each updated position, that is, the reservoir release process, the objective function is calculated. If the objective function value is better than the objective function value before the position update, the position is updated; otherwise, the original position is retained. The loop is continuously iterated until the loop termination condition is met or the iteration is completed. The position of the optimal individual is the optimal release flow process.

[0056] The present invention also discloses a real-time scheduling visualization dynamic modeling system for a complex water project system in a basin. The system is used to implement any one of the above methods. The system includes: a first construction module, a fusion configuration module, a second construction module, and a third construction module;

[0057] The first construction module is used to construct a real-time scheduling topology visualization diagram of the basin water project system;

[0058] The fusion configuration module is used to perform fusion configuration on the characteristic parameters of the water project nodes and the characteristic parameters of the river cross-section nodes based on the real-time scheduling topology visualization diagram;

[0059] The second construction module is used to construct a composite flood routing model based on the characteristic parameters of the nodes with fusion configuration;

[0060] The third construction module is used to construct an intelligent scheduling model based on the composite flood routing model.

[0061] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0062] 1. Visual dynamic modeling: By constructing a draggable basic primitive tool, a real-time scheduling topology relationship diagram is constructed in a visual manner, enabling users to intuitively understand and operate the scheduling relationships of complex water project systems, greatly improving the efficiency and accuracy of modeling, which is rare in the prior art.

[0063] 2. Flexible configuration of multiple models: It covers a variety of flood routing models and water project scheduling models, and supports a variety of solution algorithms. It can flexibly select appropriate models and algorithms according to the characteristics of different basins and water projects to meet complex and changeable actual needs, reflecting stronger versatility and adaptability.

[0064] 3. Automatic verification and inspection mechanism: Set the functions of automatically verifying the integrity of the model and application configuration data and calculating and inspecting the scheduling scheme to ensure the accuracy of the modeling data and the reliability of the model, effectively avoiding model deviation caused by data missing or errors, and improving the practicality and application value of the model.

[0065] 4. Digital coding of hydraulic connections: By constructing a hydraulic relationship matrix (including the construction of an adjacency matrix based on a directed graph and the fuzzy membership assignment of a weight matrix), the hydraulic relationships between nodes in the water project system can be more accurately described, considering various factors such as flow transmission coefficients and hydraulic losses, providing necessary conditions for accurate calculation task scheduling. The three-layer nested grid division of space-time discretization, the topological sorting algorithm for calculation priorities, and the event-driven dynamic step control in the calculation task scheduling can reasonably arrange calculation tasks in terms of space and time. It can accurately grasp the basin situation both macroscopically and microscopically, and can reasonably determine the calculation order and step size according to the topological structure and key events, improving the calculation efficiency and avoiding waste of computing resources. Description of the Drawings

[0066] To more clearly illustrate the technical solution of the present invention, the accompanying drawings required in the embodiments will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other accompanying drawings can be obtained based on these drawings.

[0067] Figure 1 It is a schematic flow diagram of a real-time scheduling visualization dynamic modeling method for a complex water project system in an embodiment of the present invention;

[0068] Figure 2 It is a schematic flow diagram of an improved starfish optimization algorithm in an embodiment of the present invention. Detailed implementation manners

[0069] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the protection scope of the present invention.

[0070] To make the above objects, features, and advantages of the present invention more obvious and understandable, the present invention will be further described in detail below in conjunction with the accompanying drawings and specific implementation manners.

[0071] The "real-time scheduling visualization dynamic modeling method and system for a complex water project system in a basin" of the present invention mainly solves the following technical problems:

[0072] I. Improve the flexibility and real-time performance of scheduling topology construction

[0073] Aiming at the problems in the prior art that rely on fixed templates in scheduling topology construction, lack of utilization of real-time flood forecasting topologies, and visualization construction tools, the present invention aims to create a method that can obtain real-time flood forecasting topologies, use drag-and-drop basic primitive tools, classify primitives according to different water project types, and visually construct a real-time scheduling topology relationship diagram of a complex water project system, thereby improving the flexibility and real-time performance of scheduling topology construction and making the constructed topology relationship diagram more accurately reflect the actual water project system structure.

[0074] II. Enhance the adaptability and comprehensiveness of scheduling model configuration

[0075] Since the scheduling models in the existing technologies are not flexible enough in dealing with different types of engineering structures and the model solving algorithms are single, the present invention is committed to developing a scheduling model that can enable a single project to flexibly adapt to various rain and water conditions and scheduling scenarios, support the conventional scheduling and joint optimization scheduling of different structural engineering groups (parallel, series, hybrid, etc.), and enable the model solving algorithm to comprehensively utilize the advantages of various algorithms (piecewise trial algorithm, mathematical programming algorithm, heuristic intelligent algorithm, etc.), enhance the adaptability and comprehensiveness of the scheduling model configuration, so as to improve the effectiveness of the model in actual complex situations.

[0076] III. Ensure the accuracy and efficiency of data verification and inspection

[0077] Considering the problems existing in the existing technologies in terms of data verification and calculation inspection of scheduling schemes, such as the inability to comprehensively and accurately verify the data integrity, the lack of the ability of rapid assembly, release and deployment, and the insufficient depth and accuracy of inspection, the object of the present invention is to establish a perfect automatic verification mechanism for the integrity of model and application configuration data, which can timely and accurately inspect the integrity of the configuration information of all water projects and section nodes, improve the ability of calculation inspection of scheduling schemes at the same time, realize rapid assembly, one-key release and deployment application, and use historical or real-time flood data to deeply and accurately inspect the constructed model to ensure the reliability and accuracy of the model in actual applications.

[0078] IV. Overall improve the effect of real-time scheduling of the complex water project system in the basin

[0079] Generally speaking, the present invention aims to solve the defects existing in the real-time scheduling of the complex water project system in the basin in many aspects in the existing technologies. By solving the above technical problems, the efficiency and accuracy of the real-time scheduling of the entire basin water project system are improved, and the goals of reasonable allocation of water resources, flood control and disaster reduction, and ecological protection are better realized, meeting the needs of modern society for the efficient operation of the basin water project system.

[0080] Embodiment 1

[0081] As Figure 1 shown, the present invention provides a method and system for visual dynamic modeling of real-time scheduling of a complex water project system in a basin, including the following steps: S1. Visual construction of real-time scheduling topology; S2. Multi-source heterogeneous data fusion configuration; S3. Construction of a composite flood evolution model; S4. Intelligent scheduling model architecture; S5. Topological digital coding system; S6. Intelligent verification and validation system.

[0082] In this embodiment, S1. Visual construction of real-time scheduling topology:

[0083] S11. Construct a flood forecasting topology basic layer based on basin GIS data:

[0084] The data of the basin Geographic Information System (GIS) contains rich spatial information such as terrain and water systems. First, high-precision GIS data within the basin is collected, including terrain elevation, river network distribution, basin boundary, etc. Through geospatial analysis techniques, terrain features related to flood formation and propagation are extracted, such as easily waterlogged areas like valleys and depressions, as well as information such as the slope and width of river channels. Based on this information, a network of possible flood flow paths is constructed, which serves as the basic framework for flood forecasting topology. For example, using Digital Elevation Model (DEM) data, the natural flow direction of water from high-altitude areas to low-altitude areas is determined through a water flow direction algorithm to form a preliminary topological network, providing a basic geospatial reference for subsequent flood forecasting and scheduling topology construction.

[0085] Specifically, the data collection methods for terrain elevation, river network distribution, and basin boundary are as follows:

[0086] Terrain elevation data can be obtained through various methods. Aerial photogrammetry is one of the common means. An aircraft is equipped with an aerial camera to photograph the basin. After obtaining the aerial images, photogrammetry software is used for processing, such as stereoscopic image pair matching technology, etc., to obtain terrain elevation information. Satellite mapping is also feasible. For example, sensors on satellites such as TanDEM X are used to obtain surface reflection signals, and digital elevation models (DEMs) are generated through radar interferometry (InSAR) or optical image stereoscopic mapping technology. Ground survey is to set control points within the basin and use instruments such as total stations and levels for on-site measurement. The total station measures the three-dimensional coordinates of the control points, and the level measures the elevation difference. These on-site measurement data are fused with data obtained by other methods to improve accuracy.

[0087] There are various ways to obtain river network distribution data. During on-site investigation, professional personnel are dispatched to conduct inspections along the rivers, using GPS positioning equipment to record information such as river directions, confluence points, and river channel widths, and at the same time observing characteristics such as water flow conditions and riverbank types. In terms of remote sensing image interpretation, high-resolution satellite remote sensing images (such as Landsat, high-resolution series satellite images) or aerial remote sensing images are used. By analyzing their spectral characteristics to identify the locations of rivers, for example, according to the reflectance characteristics of water bodies in different bands, a suitable water body index (such as the Normalized Difference Water Index NDWI) is used for extraction, and the river width can also be calculated through the spatial resolution of the image. In addition, existing river network distribution data can also be queried from the databases of water conservancy departments. These data are often accumulated through various methods before and have relatively high accuracy and integrity.

[0088] For watershed boundary data, terrain watershed division is an important method. Using terrain elevation data, through hydrological analysis tools in GIS software, the flow direction and flow accumulation are calculated based on DEM data to determine the watershed location and thus obtain the watershed boundary. Determining administrative divisions is also a way. Referring to the local administrative division map, using the administrative boundary as part of the watershed boundary is more convenient when the watershed spans multiple administrative regions. In addition, on-site investigation and visits are indispensable. For areas with unclear or disputed boundaries, organize professional personnel for on-site investigation and at the same time visit local residents to understand the geographical and water flow ownership situation, assist in determining the final watershed boundary and convert it into GIS vector data.

[0089] Specifically, the steps of extracting terrain features related to flood formation and propagation through geospatial analysis technology include:

[0090] Calculation of flow direction: For a raster cell, it compares the elevation values of this cell with its 8 adjacent cells (up, down, left, right, upper left, upper right, lower left, lower right) around it. Starting from the central raster cell, the water flow will flow towards the adjacent cell with the largest elevation drop. Assume the elevation of the central raster cell is , and the elevations of its adjacent cells are respectively , calculate , select The direction of the adjacent cell corresponding to the maximum value in as the flow direction. For example, if is the largest, then the flow direction is from the central raster cell to its left adjacent cell.

[0091] Calculation of flow accumulation: After determining the flow direction, calculate the flow accumulation of each raster cell. The flow accumulation represents how many raster cells upstream of this raster cell the water flow converges here. Starting from the uppermost reaches of the watershed, initialize the flow accumulation of each raster cell to 1. Then, according to the flow direction, add the flow accumulation of the downstream raster cell to the flow accumulation of the upstream raster cell. For example, if the water flow of raster cell (A) flows towards raster cell (B), then the flow accumulation of raster cell (B) is equal to the original flow accumulation of raster cell (B) plus the flow accumulation of raster cell (A).

[0092] Specifically, the steps of constructing a network of possible flood flow paths are as follows:

[0093] Constructing flood flow paths based on terrain features: First, determine the easily waterlogged areas such as valleys and depressions based on terrain elevation data. These areas are where floods converge. At the same time, combine river network distribution data to determine the river channels. Then, starting from the valleys and depressions, according to the natural flow direction of the water (from high altitude to low altitude), connect the valleys, depressions and river channels to construct a network of flood flow paths.

[0094] Optimizing flow paths using the accumulation of flow concentration: Areas with a larger accumulation of flow concentration indicate more water flow convergence and are more likely to be the main flow paths of floods. For areas where the accumulation of flow concentration exceeds a certain threshold (T) (determined according to the actual situation of the basin, for example, T = 1000 grid cells), when constructing the flood flow path network, these areas are preferentially connected.

[0095] Mathematical formula construction: Assume that (P) is a path in the flood flow path network, (H) is the elevation value of each point on the path, (L) is the length of the path, and (F) is the flood flow probability function. It can be defined as ( ), where (n) is the number of points on the path (P). The larger the value of (F), the greater the probability that the flood flows along this path. When constructing the flood flow path network, paths with larger (F) values are preferentially selected for connection.

[0096] S12. Construction of a multi-dimensional extensible graphic element library:

[0097] In this step, a multi-dimensional extensible graphic element library for basin water project scheduling is constructed. Based on the engineering function attributes, the graphic elements are divided into three categories: regulation type, protection type, and conduction type. Through parametric modeling and dynamic association rule definition, a structured database that supports complex water network topology reconstruction and intelligent calculation is established. Specifically, based on the physical characteristics and regulation behaviors of engineering entities, a composite parameter system including geometric parameters, hydraulic parameters, and control logic parameters is designed for each type of graphic element. Among them, the geometric parameters realize the instantiation positioning of graphic elements through spatial coordinate transformation, the hydraulic parameters construct calculation models based on hydraulic principles such as Manning's formula and Saint-Venant equations, and the control logic parameters define the equipment operation rules and timing constraints. At the same time, different from the traditional method that only supports single static rule verification, the dynamic injection of new engineering features is realized through the method of multi-layer open extension interfaces, and the parameter dimensions can be customized according to the basin characteristics. The specific technical features include the following:

[0098] S121. Regulation type graphic elements (reservoirs, sluices and dams):

[0099] For the reservoir model in the regulation type graphic elements, the relationship between reservoir capacity and water level is characterized by a seasonal function. Specifically, the reservoir capacity curve during the flood season (May - October) and during the dry season (November - April) , where the coefficient is determined by fitting historical hydrological data using the least squares method, and the fitting error is controlled within 3%; the flood discharge calculation model is defined as , where is the discharge coefficient ( ), is the width of the spillway, is the gate opening, is the sill elevation.

[0100] In the lock and dam graphic element, the dynamic model of the upstream and downstream water level difference adopts , where is the correction coefficient of the river bed roughness ([[]] ), is the duration of the discharge (minutes), and this model quantifies the attenuation effect of the long-term discharge on the water level.

[0101] S122. Protective graphic elements (dikes, flood storage and detention areas):

[0102] The calculation of the flood storage and detention capacity of the protective graphic element introduces a piecewise function: when the water level , the volume ; when , it expands to , where the terrain correction factor ranges from 0.2 to 0.5 and is calibrated through terrain data.

[0103] S123. Conductive graphic elements (river cross-section, lake node connected to the river):

[0104] The calculation of the river cross-section roughness of the conductive graphic element is based on the Manning formula , and dynamically assigns values in combination with the type of river bed material: concrete lining ( ), gravel river bed ( ), vegetated river bed ( ), where R is the hydraulic radius, S is the energy slope, and v is the average cross-sectional velocity.

[0105] S124. Dynamic interface and basin adaptive parameter system:

[0106] Through the hierarchical extended interface architecture and the parameter intelligent adaptation technology driven by basin characteristics, the dynamic injection of new engineering features and the flexible expansion of parameter dimensions are realized.

[0107] Hierarchical interface protocol design:

[0108] Core interface layer: Forcibly inherit the hydraulic conductivity attributes and spatial topological constraints of the basic graphic element to ensure the mathematical compatibility of the newly added parameter dimension with the existing model. For example, when adding an ecological flow parameter, it is automatically associated with the mass conservation term in the Saint-Venant equation to avoid manually modifying the control equation. Extended interface layer: Based on the domain-specific language (DSL), declare the physical dimension, value range and data verification rules of the newly added parameter, and support non-programmers to define parameters through configuration files. Basin adaptation layer: Built-in terrain slope , soil permeability coefficient , river network density Parametric templates for basin characteristics are used to dynamically generate parameter legality functions.

[0109] Parameter dynamic binding and conflict detection mechanism:

[0110] Symbolic binding of hydraulic models: Use a symbolic computing engine (such as SymPy) to automatically parse new parameters and the partial derivative relationship with the hydraulic control equation to generate row column Jacobian matrix, ensuring that the parameters are automatically integrated into the calculation kernel after injection without reconstructing the model code. Build a parameter dependency network based on a directed acyclic graph, detect contradictory combinations (such as logical conflicts between gate openings and ecological flows) through topological sorting, trigger real-time alarms and lock the calculation process. Implement conflict self-checking through mathematical symbol binding and graph theory algorithms to avoid manual debugging.

[0111] Intelligent parameter recommendation system:

[0112] For hydraulic structures such as reservoirs, sluice dams, levees, flood storage and detention areas, river cross-sections, and lakes connected to rivers, build an intelligent parameter recommendation system based on engineering feature fingerprints and cross-engineering topological association learning, specifically including:

[0113] Engineering feature fingerprint library: Extract core parameters for each type of hydraulic structure (such as the storage capacity curve coefficient of a reservoir, the discharge capacity curve of a sluice dam, and the roughness coefficient n of a river cross-section), and generate a unique feature fingerprint code through weighted random forest algorithm where, is the parameter importance weight, is the core physical parameter value extracted from the project, used to quantify the structural or functional characteristics of different projects; build an associated topological graph of hydraulic structures based on a graph convolutional network (GCN), with nodes being engineering feature fingerprints and edges being river connections between projects, and calculate the matching degree score between new parameters and the target project through neighborhood feature aggregation, and dynamically recommend the optimal parameter combination (such as automatically matching historical parameters of similar storage capacity and sluice dam elevation in the topological graph when recommending a flood discharge coefficient for a newly built reservoir).

[0114] S13. Implement topological dynamic linking:

[0115] In this step, through spatial topological modeling and hydraulic conduction relationship calculation, dynamic topological construction and self-consistency verification of the basin water project system are realized, and a topological network with physical rationality and computational robustness is established based on the parametric attributes and constraint rule library of graph elements. The specific implementation methods include:

[0116] S131. Topological node generation and verification:

[0117] Pre - build a primitive library that contains various primitives corresponding to the basin water project system, such as reservoir primitives, river cross - section primitives, etc. Each primitive is designed to have a clear mapping relationship with the actual basin water project, and this relationship is determined based on characteristics such as the type and function of the water project. For example, the reservoir primitive corresponds to the actual reservoir project entity and is intended to accurately represent the position and role of the reservoir in the basin water project system during topological construction. For each primitive, a set of basic attribute information is defined, and this information will be retained when the primitive is converted into a topological node. When the user drags the primitive to the geographic coordinate system through the interactive interface, the system automatically generates topological nodes based on the parametric attributes of the primitive (such as the storage - water level function of the reservoir , the flow - discharge control logic of the sluice dam). The node data includes spatial coordinates (longitude , latitude and elevation ), hydraulic parameters (design flow , roughness coefficient ) and dynamic control variables (such as gate opening ). After the nodes are generated, double - verification is performed:

[0118] Spatial logic verification: Using the pre - obtained topographic and geomorphic data, such as contour distribution data, analyze in detail the topographic characteristics of the catchment area, including the shape, the distribution of high and low terrain, etc. Make a judgment based on the principle of natural water flow convergence. In the natural state, water flow tends to converge towards low - lying areas. By comparing the terrain corresponding to the reservoir location coordinates with the overall terrain of the catchment area, if the reservoir location is relatively low - lying compared to the surrounding terrain and conforms to the overall water flow convergence direction of the catchment area, it is determined that the reservoir is located within a reasonable catchment area; otherwise, it is determined to be unreasonable and a coordinate correction suggestion is triggered.

[0119] Parameter compatibility verification: Build a parameter constraint library based on engineering specifications. For example, the embankment height needs to meet m, and the relationship between the gate opening and the discharge needs to conform to , where is the discharge coefficient, which comprehensively considers various resistance factors of the water flow and the influence of the shape of the cross - sectional area of flow, roughness coefficient, etc. on the flow, dimensionless, represents the cross - sectional area of flow, that is, the cross - sectional area through which the water flow passes, with the unit of m 2 . If it is detected that the parameters exceed the limit, analyze the normal value range and change trend of the parameters in the historical data, and combine with the experience in engineering practice to determine the reasonable correction direction and amplitude.

[0120] S132. Hydraulic conductivity relationship modeling:

[0121] Modeling of hydraulic conductivity relationship: Different from the existing methods that use homogenized grid cells or fixed connection rules, this method decomposes conductive primitive elements such as river channels and lake nodes into connector units with direction vectors, and constructs a mathematical representation of the unstructured water network topology through a set of directed line segments. , where , are the coordinates of the starting point and the ending point of the connector, where , are the abscissa and ordinate of the starting point of the connector, , are the abscissa and ordinate of the ending point of the connector, is the cross-sectional area function that varies with the water level, where , are the functions of the cross-sectional area varying with the water level of the starting cross-section and the ending cross-section respectively, is the dynamic conductivity coefficient matrix, driven by the water level gradient , where and are the conductivity coefficients from the starting point to the ending point and from the ending point to the starting point respectively.

[0122] Each connector unit not only integrates geometric attributes such as spatial coordinates and cross-sectional morphology, but also has a built-in dynamic conductivity parameter matrix, which can correct the flow direction and conductivity coefficient in real time according to the water level gradient, and accurately depict the asymmetric conductivity characteristics of complex braided river channels and the two-way flow state switching caused by water level fluctuations in natural river channels. It breaks the symmetry of the conductivity coefficient matrix , and realizes the asymmetric conductivity characteristics through the direction vector weight function. The dynamic correction formula of the conductivity coefficient is as follows:

[0123] ;

[0124] ;

[0125] Among them, is the reference conductivity, is the direction vector of the connector, is the asymmetric adjustment factor, is the gradient response intensity coefficient, , are the water levels at the starting point and the ending point of the connector.

[0126] This technology abandons the static simplification assumptions of the traditional model for the conduction path. While maintaining the calculation efficiency, it significantly improves the hydraulic coupling simulation accuracy in mountainous river channels and plain river networks, providing a new structured solution for the high-fidelity simulation of the basin hydrodynamic system. By defining the hydraulic conductivity relationship between nodes through vectorized connectors, conductive primitive elements such as river channels and nodes of lakes connected to the river are abstracted as directed line segments , and its attributes include:

[0127] Hydraulic conductivity: Based on the Manning formula Dynamically calculated, where the hydraulic radius R is determined by the cross-section geometric parameters (bottom width B, side slope coefficient m) and the real-time water depth , and the energy slope is calculated through the elevation difference between adjacent nodes and the connection length as ;

[0128] Dynamic flow direction control: Forces the connection direction to be consistent with the water level gradient. When it is detected that and there is no pump station driving, automatically reverse the connection direction and trigger a recalculation of the head loss to ensure that the water flow direction conforms to the physical laws;

[0129] Head loss fusion model: The total head loss is jointly calculated by the frictional head loss (the Darcy friction factor is iteratively solved through the Colebrook-White equation) and the local head loss (the local head loss coefficient , assigned based on the connector type lookup table) to achieve high-precision quantification of the conduction resistance.

[0130] S133. Real-time detection and correction of topological conflicts:

[0131] Hydraulic conflict detection: Real-time calculation of node water levels and flows. If it is detected that the downstream water level is higher than the upstream and there is no reverse flow device, it is marked as a water level reverse difference conflict;

[0132] Spatial conflict detection: Determine the method for comparing spatial positions. For each graphic element, obtain its position coordinate range. For example, for a reservoir graphic element, obtain the coordinates of its four corner points or the center and the coordinate values of the coverage range to determine its position range in the geographical space.

[0133] Hierarchical correction strategy: Adopt threshold-limited automatic correction for hydraulic conflicts. For example, in the water level reverse difference conflict, adjust the connection direction and limit the water level correction amplitude by m; for spatial conflicts, solve the minimum displacement vector through the optimization model , recommend that the user adjust the position of the graphic element according to while keeping the topological connection relationship unchanged.

[0134] In this embodiment, S2. Multi-source heterogeneous data fusion configuration:

[0135] S21. Configuration of characteristic parameters of water project nodes:

[0136] S211. Construct a three-dimensional parameter matrix (geometric characteristics, hydraulic characteristics, scheduling rules):

[0137] For each project node (such as reservoirs, sluices, etc.), construct a three-dimensional parameter matrix to comprehensively describe its characteristics. In the dimension of geometric characteristics, record spatial information such as the shape and size of the project, for example, the dam length, dam height, and storage capacity shape (such as valley type, plain type, etc.) of the reservoir; in the dimension of hydraulic characteristics, include parameters such as the water level - discharge relationship curve, seepage characteristics (for the dam body), and flow resistance; in the dimension of scheduling rules, define the scheduling strategies under different working conditions (such as flood season, dry season), for example, the flood discharge rules of the reservoir (determine the flood discharge volume according to factors such as water level and inflow), and the opening and closing conditions of the sluice. Through this three-dimensional parameter matrix method, integrate the multi-faceted characteristics of the project node to provide comprehensive data support for subsequent scheduling calculations.

[0138] S212. Dynamic interpolation expression of non-linear storage capacity curve:

[0139] Considering that the storage capacity curve of an actual reservoir is often non-linear, traditional linear approximation methods may lead to large errors. Adopt the method of dynamic interpolation to accurately represent the storage capacity curve. Collect the measured storage capacity data at different water levels, and then use an interpolation algorithm (such as cubic spline interpolation) to construct a continuous functional relationship between the storage capacity and the water level.

[0140] Establish a cubic spline interpolation function, and the cubic spline interpolation function is a piecewise cubic function. On each sub-interval , where is the water level, are the coefficients to be determined. Determine the boundary conditions. Assume that the second derivative is zero at the interval endpoints, that is, and . Construct a system of linear equations. At the internal node , the function value and its first derivative and second derivative are continuous. According to the continuity of the function value, we have: According to the continuity of the first derivative, we have: , and according to the continuity of the second derivative, we have:

[0141] Combined with the boundary conditions, a system of linear equations containing intervals with a total of unknowns can be constructed.

[0142] Arrange the above conditions in matrix form where is the coefficient matrix, is the vector containing the unknowns , is the constant term vector. Solve this system of linear equations using methods of linear algebra (such as Gaussian elimination, LU decomposition, etc.) to obtain the value of.

[0143] During the reservoir operation calculation process, when a water level is given, first determine the sub - interval where it is located, and then substitute it into the corresponding cubic spline function to calculate the corresponding reservoir capacity value .

[0144] In this way, during the operation calculation process, regardless of the value of the water level, the corresponding reservoir capacity value can be accurately obtained through the interpolation function, improving the accuracy of reservoir capacity calculation, and thus providing a more reliable data basis for the reservoir operation decision - making.

[0145] S22. Channel cross - section node feature configuration:

[0146] S221. B - spline parametric modeling of cross - section shape:

[0147] To accurately describe the shape of the channel cross - section, B - spline curves are used for parametric modeling. First, obtain the three - dimensional coordinates of several key control points on the cross - section shape through measurement or from GIS data. These control points should include the turning points of the channel shoreline, the deepest point, the shoal position, etc., which can reflect the cross - section shape characteristics. Fit these control points using B - spline functions to obtain the mathematical expression of the cross - section shape.

[0148] For a given number of control points , the expression of the order B - spline curve

[0149] is:

[0150] where , is the order B - spline basis function.

[0151] When then

[0152] ;

[0153] When When

[0154] ;

[0155] where is an element in the knot vector, and the knot vector , and the way of determining the knot vector affects the shape of the B-spline curve. Generally speaking, or is more common in practical applications, which can not only ensure the smoothness of the curve but also have good flexibility. Substitute the control point coordinates and the determined knot vector into the B-spline function expression, and the B-spline curve is obtained through calculation, that is, the mathematical expression of the river channel cross-section shape.

[0156] This method can accurately represent various complex cross-section shapes, such as irregular natural river channel cross-sections. In the scheduling calculation, according to the B-spline parameterization model, the hydraulic parameters such as the cross-sectional area and wetted perimeter of the cross-section can be accurately calculated, providing an accurate geometric basis for the flow calculation.

[0157] For a given water level , first determine the intersection point of the B-spline curve and the water level . Solve the equation to obtain the parameter values and corresponding to the intersection point.

[0158] Cross-sectional area ;

[0159] Wetted perimeter ;

[0160] where and are respectively 's and coordinate components, is 's derivative with respect to . S222. Piecewise polynomial characterization of the water level-discharge relationship:

[0161] Since the water level - flow relationship of the river channel cross - section may exhibit different characteristics in different water level segments, a piece - wise polynomial is used to characterize this relationship. By analyzing historical water level and flow data, water level segments with different characteristics are determined (such as the slow - flow segment at low water levels, the transition segment at medium water levels, and the rapid - flow segment at high water levels). The slow - flow segment at low water levels usually shows that when the water level is relatively low, the change in flow rate with respect to the water level is relatively slow. The transition segment at medium water levels is the area connecting the slow - flow segment at low water levels and the rapid - flow segment at high water levels. Its characteristic is that the water level - flow relationship begins to change significantly, and the growth rate of the flow rate with respect to the water level gradually increases. At high water levels, the change in flow rate with respect to the water level is very rapid, presenting a rapid - flow state. For each water level segment, a polynomial function is fitted to describe the water level - flow relationship. A quadratic polynomial may be used in the slow - flow segment at low water levels.

[0162] ;

[0163] where is the flow rate, is the water level, 、 、 are the coefficients to be determined.

[0164] For the sets of water level - flow data points in the slow - flow segment at low water levels , according to the least - squares principle, an error function is constructed.

[0165] ;

[0166] To minimize the error function, partial derivatives are taken with respect to 、 、 respectively and set them equal to zero.

[0167] ;

[0168] ;

[0169] ;

[0170] Solving this system of linear equations gives the coefficients 、 、 of the quadratic polynomial in the slow - flow segment at low water levels.

[0171] In the transition segment at medium water levels and the rapid - flow segment at high water levels, higher - degree polynomials such as may be required. The method for determining the coefficients of this polynomial is the same as the method for determining the coefficients of the quadratic polynomial described above.

[0172] This piecewise polynomial representation method can more accurately reflect the actual changes in the water level - discharge relationship and improve the accuracy of flood routing calculations.

[0173] In this embodiment, S3. Composite flood routing model construction:

[0174] S31. Multi - method model container architecture:

[0175] S311. Hydrological model (improved Muskingum piecewise calculus):

[0176] The Muskingum piecewise calculus model is a classic flood routing model, but it has certain limitations in practical applications. Existing piecewise methods are mostly based on fixed characteristic river lengths or empirical divisions. In this invention, an improved Muskingum piecewise calculus model is adopted. The basin is divided into several sub - reaches based on attributes such as terrain slope, roughness distribution, cross - section shape, and hydrological station location. Each sub - reach introduces local Muskingum coefficients (storage parameter) and (discharge weight factor). When setting the initial values of the parameters, it is different from the traditional Muskingum model parameters that lack hydraulic interpretability , Rather than relying on empirical trial - and - error or global optimization methods, the improved Muskingum method adopts a physically - related initial parameter mapping mechanism. The initial values set a non - linear mapping function according to the sub - reach attributes , , where , , are hyperparameters, is the reach length, is the slope, is the Manning roughness, is the river width, is the water depth. For the th sub - reach, the outflow , where , , is determined by , , and satisfies , is time, is the time step. The parameters of the model are optimized according to the specific characteristics of the basin. Considering the influence of the channel characteristics (such as slope, roughness, etc.) of different reaches on flood propagation, the Muskingum coefficients are dynamically adjusted. Using the monitoring data of the inflow and outflow at the sub - reach entrance as input, construct the objective function , and adopt the recursive least - squares method (RLS) to update and and introduce the Particle Filter (PF) algorithm to fuse historical flood event data in a Bayesian framework and periodically correct hyperparameters , , , solve the local overfitting problem of RLS, and improve the simulation accuracy of the model for the flood evolution process. During the calculation, the basin is divided into multiple sub-reaches, and the improved Muskingum model is applied to perform flood routing according to the characteristics of each sub-reach, and then the results of each sub-reach are integrated to obtain the flood evolution of the entire basin.

[0177] S312. Hydrodynamic model (solved by unstructured grid Godunov scheme):

[0178] For complex basin topography and flow conditions, a hydrodynamic model solved by the unstructured grid Godunov scheme is adopted. The unstructured grid can better adapt to irregular basin boundaries and complex topographies and landforms, improving the adaptability of the model. The Godunov scheme has the characteristics of high accuracy and stability and can accurately solve the equations of motion of water flow. During the model construction process, the Delaunay triangulation algorithm is first used to discretize the basin into unstructured grids, and each grid cell is assigned corresponding physical parameters (such as roughness, water depth, etc.) according to the terrain and flow characteristics. The numerical algorithm based on the Godunov scheme is used to solve the basic equations such as the mass conservation equation and momentum conservation equation of water flow.

[0179] Mass conservation equation: ;

[0180] Momentum conservation equation: ;

[0181] Where is the water depth, is the velocity vector, is the time, is the gravitational acceleration, is the water level, is the Chezy coefficient, is other external forces.

[0182] At each time step within, for the boundary of each grid cell, based on the water depth values and velocities of the left and right adjacent grid cells, a Riemann problem at the grid cell boundary is constructed. The left state at a discontinuity surface is , and the right state is , that is, the special initial condition of the Riemann problem. The flux at the boundary is solved, and then the physical quantities inside the grid cell are updated according to the flux to simulate the movement process of water flow in the basin, including the propagation of floods and the change of water levels.

[0183] S313. River-connected Lake Coupling Model (Characteristic Line - Implicit Alternating Solution):

[0184] There is a complex water flow exchange relationship between river-connected lakes and river channels. Considering the lake and the river channel as an interrelated whole system, a river-connected lake coupling model is constructed by considering multiple key factors to simulate the movement and change process of water flow in this system. The method of characteristic line - implicit alternating solution is adopted, and the two-way water flow exchange between the lake and the river channel, the water flow movement driven by the water level difference, and the storage function of the lake itself are considered in the model.

[0185] Solving river channel water flow by the characteristic line method: Divide the characteristic line grid along the river channel and solve the characteristic equation to obtain the propagation characteristics of the discharge and water level . The discharge and water level at the end section of the river channel are output as the boundary conditions at the lake inlet.

[0186] Solving the lake water level - volume relationship by the implicit method: Based on the continuity equation of the lake, a nonlinear equation system

[0187] ;

[0188] where is the lake area, , is the inflow and outflow discharge, , are the precipitation and evaporation. The equation is discretized by the implicit difference format and the lake water level is updated by iterative solution.

[0189] The characteristic line method is used to deal with the propagation characteristics of water flow, which can accurately calculate the propagation time and discharge change of water flow between the lake and the river channel; the implicit method is used to solve the water level - volume relationship of the lake and the river channel to improve the calculation stability. Through this coupling model, the special flood evolution process in the river-connected lake area can be accurately simulated, providing more comprehensive support for the flood evolution calculation of the entire basin.

[0190] S32. Intelligent Adaptation of Model Parameters:

[0191] S321. Model Selection Decision Tree Based on River Channel Characteristics:

[0192] Construct a decision tree for model selection according to different characteristics of the river channel (such as river channel length, slope, roughness coefficient, cross-sectional shape, etc.). First, collect various characteristic data of the river channel, including river channel length, slope, roughness coefficient, and cross-sectional shape, etc., and determine the threshold or range of each characteristic. Then, select a characteristic as the root node, for example, the river channel length, and set a judgment condition, such as "whether the river channel length is greater than a certain threshold". According to the judgment result, it is divided into two sub-nodes, representing the two situations of "yes" and "no" respectively. In each sub-node, continue to select the next characteristic for judgment, forming the branches of the tree until the preset model selection criteria or leaf nodes are reached. The leaf nodes correspond to specific flood routing models (such as the Muskingum model or hydrodynamic model). In this way, the decision tree can automatically guide the system to select the most suitable model according to different combinations of river channel characteristics, improving the pertinence and calculation efficiency of the model.

[0193] S322. Multi-objective optimization calibration of parameter sensitivity:

[0194] After determining the flood routing model, optimize the parameters in the model. Consider multiple objective functions, such as the accuracy of flood routing simulation, calculation efficiency, etc. By analyzing the influence of parameter changes on these objective functions, determine the sensitivity of the parameters. Then, use optimization algorithms (such as genetic algorithms, particle swarm algorithms, etc.) to optimize the parameters.

[0195] Construct an objective function, using the root mean square error to measure the accuracy, and time to measure the calculation efficiency.

[0196] By initializing the position and direction of the particle swarm, that is, randomly generating the initial values of the parameters to be optimized within the empirical range. For each particle , randomly initialize its position in the decision variable space, where is the number of decision variables, that is, the number of parameters calibrated as parameters to be optimized in the model to be optimized. Randomly initialize the velocity of the particle.

[0197] Based on the individual fitness values in the initial population, that is, the objective function values, continuously update the positions of the individuals in the population through the position update formula of the particle swarm algorithm, that is, update the values of the parameters in the selected flood routing model, and obtain the population after updating the individual positions until the accuracy requirement is met or the maximum number of iterations is reached; specifically, the velocity and position update formulas of the particle swarm algorithm are as follows:

[0198] Velocity update formula: ;

[0199] Position update formula: ;

[0200] where is the inertia weight, which controls the degree of inheritance of the particle's previous velocity and generally takes values between 0.4 and 0.9; and are the learning factors, which respectively represent the learning abilities of the particle to its own experience and the group experience. Usually around; and are random numbers between 0 and 1.

[0201] Select the parameter combination that makes the objective function optimal during the iteration process, that is, the model parameters with the highest accuracy of flood routing simulation and the fastest calculation efficiency. For example, in the improved Muskingum model, optimize and calibrate the Muskingum coefficient so that it can accurately simulate the flood routing process under different flood conditions and improve the calculation efficiency at the same time.

[0202] In this embodiment, S4. Intelligent scheduling model architecture:

[0203] S41. Engineering structure topology analysis:

[0204] S411. Analysis of the engineering connection relationship matrix based on graph theory:

[0205] Regard the water projects in the basin as nodes in graph theory and the connection relationships between water projects as edges to construct an engineering connection relationship matrix. The elements in the matrix represent the connection relationships between nodes (1 for connection and 0 for no connection) and the attributes of the connections (such as flow transmission coefficient, hydraulic loss, etc.). By analyzing this matrix, topological information of the engineering structure can be obtained, such as the degree of nodes (the number of edges connected to the node), connectivity (whether there is a path from one node to another), etc. These topological information helps to deeply understand the characteristics of the engineering structure and provides a basis for the subsequent construction of the scheduling model.

[0206] S412. Hybrid structure eigenvalue decomposition:

[0207] For complex engineering structures such as parallel, series, and mixed connections, use the method of eigenvalue decomposition to analyze their structural characteristics. By calculating the eigenvalues and eigenvectors of the engineering connection relationship matrix, key characteristic information of the structure can be obtained. Construct the engineering connection relationship matrix to describe the connection strength and directionality between nodes, where the element represents the node to the node interaction weight. Through eigenvalue decomposition (where is the eigenvalue diagonal matrix, is the eigenvector matrix), the structural characteristics can be quantitatively revealed, and the largest eigenvalue characterizes the overall stability of the system. When There is a risk of instability in the system at this time; the eigenvector The amplitude of the elements in reflects the participation of the node at the th order mode, and thus the key nodes can be identified. Based on this characteristic information, the impact of complex engineering structures on scheduling decisions can be better understood, providing a basis for formulating reasonable scheduling strategies.

[0208] S42. Multi-mode scheduling for individual projects:

[0209] S421. Rule-based scheduling (dual-threshold control of water level / flow):

[0210] For individual projects (such as a single reservoir or sluice), task scheduling is carried out according to pre-set rules and priorities, setting dual thresholds for water level and flow. When the reservoir water level reaches the upper threshold, flood discharge operations are initiated to ensure that the reservoir water level is within a safe range; when the flow is lower than the lower threshold, the discharge of the sluice is reduced to maintain a certain ecological flow in the river channel. During the scheduling process, water level and flow data are monitored in real time, and corresponding operations are carried out according to the set thresholds to meet the safety and ecological requirements of project operation.

[0211] S422. Optimal scheduling:

[0212] To achieve the optimal scheduling of individual projects, the project scheduling problem is modeled and solved using the starfish optimization algorithm. In reservoir scheduling, taking objectives such as power generation benefit, flood control benefit, and ecological benefit as the optimization objectives, and solving through the starfish optimization algorithm to determine the optimal flood discharge and water storage strategies at different time periods, so as to maximize the comprehensive benefit of individual projects. For example, for flood control problems, the maximum peak shaving criterion is taken as the objective function.

[0213] Objective function:

[0214] ;

[0215] where is the number of time periods in the scheduling period, h; is the outflow of the reservoir at time 3 / s.

[0216] Constraint conditions:

[0217] Water balance constraint:

[0218] ;

[0219] where are respectively the initial reservoir storage, inflow, and outflow at the time period; They are respectively the reservoir storage at the end of the time period, the inflow, and the outflow; is the time period length.

[0220] Reservoir maximum water level constraint:

[0221] ;

[0222] where is the calculated reservoir water level value at time is the maximum reservoir water level allowed to reach at time

[0223] Discharge capacity constraint:

[0224] ;

[0225] where is the outflow at time is the discharge capacity value corresponding to the water level at time, including the water passing capacity of the bottom outlet, spillway, and turbine.

[0226] Initial boundary condition constraint:

[0227] ;

[0228] where is the scheduling period; is the initial value of the water level at the beginning of the scheduling; is the given water level at the end of the scheduling, which reflects the reserved storage capacity for subsequent rainfall in the rising flood section and the beneficial storage water level reached considering the utilization of rainstorm flood resources at the end of the flood.

[0229] Outflow variation range constraint:

[0230] ;

[0231] where is the outflow variation range between adjacent time periods; is the allowable value of the outflow variation range between adjacent time periods.

[0232] When using the improved starfish optimization algorithm to solve, the penalty function method is adopted. It is necessary to select an appropriate penalty coefficient and add a penalty term to the objective function to handle the above complex constraints; the forced repair method uses appropriate rules to transform the infeasible solution into a feasible solution to ensure the effectiveness of the search. Taking the maximum water level constraint as an example, it is constructed as a penalty function and added to the objective function. The treatment methods of other constraint conditions are similar to it.

[0233] ;

[0234] ;

[0235] ;

[0236] where is the objective function with penalty function added; and are the penalty functions for the lowest water level and the highest water level respectively;

[0237] When using the improved starfish optimization algorithm to solve the reservoir flood control optimization scheduling problem, each optimization individual represents the reservoir discharge flow during the scheduling period. The search space of the population is the search range of the reservoir discharge flow. The quality of the individual position is judged by the objective function. The higher the reservoir peak shaving rate, the better the individual position. The basic steps are as follows:

[0238] Initialize the population size , different from the way of randomly generating initial solutions by using the pseudo-random number generation strategy in general intelligent algorithms, the population generated in this way has insufficient uniformity in the solution space distribution and is prone to cause the algorithm to fall into local optimum. The improved starfish optimization algorithm adopts a constraint satisfaction initialization method based on chaotic mapping when initializing the population generation, that is, under the condition of satisfying the dynamic feasible region of the reservoir discharge flow, the population is initialized by adopting the chaotic mapping Cubic mapping strategy, providing a higher quality initial solution set for the subsequent algorithm optimization iteration. The formula for initializing the population by adopting Cubic mapping is as follows:

[0239] ;

[0240] where is the population position matrix, , is the length of the scheduling period, is the upper boundary of the population position, which represents the upper boundary of the water level process in this problem, is the lower boundary of the population position, representing the lower boundary of the water level process, , and the finally generated initialized population matrix is:

[0241] ;

[0242] Calculate the initial fitness value of each individual, that is, the objective function value. The minimum objective function value means the maximum peak shaving rate, and the position of the corresponding individual, that is, the reservoir discharge process, is denoted as , represents the th individual, the position of the th dimension, represents the current iteration number.

[0243] Update the positions of the individuals in the population according to the position update formula of the improved starfish optimization algorithm, that is, update the reservoir release process. The position update of the improved starfish optimization algorithm includes an exploration phase and a development phase.

[0244] Exploration phase:

[0245] ;

[0246] ;

[0247] ;

[0248] where is the updated position, is the position before update, is the current best position, is five dimensions randomly selected from is a random number between 0 and 1, is the current iteration number, is the maximum iteration number, is a randomly generated angle parameter, is a dynamically adjusted angle parameter, .

[0249] Development phase: Two position update strategies are designed according to the predation and regeneration behaviors of starfish.

[0250] ;

[0251] ;

[0252] ;

[0253] where, is the updated position, is the position before update, and are random numbers between 0 and 1, is the population size, is the distance between the best position and the positions of five randomly selected dimensions, and are randomly selected from , is the current optimal position, are the positions of five randomly selected starfish.

[0254] After the development stage, a tail mutation strategy is introduced, that is, a forced perturbation is added to the positions of the population to avoid falling into local optimal solutions, and the intensity of the perturbation gradually decreases as the number of iterations increases to accelerate the convergence in the later stage of the algorithm. In the improved starfish optimization algorithm, the Lévy flight strategy is selected to perturb the positions of the population. Among them is the Lévy distribution.

[0255] ;

[0256] Calculate the objective function for the position after each update, that is, the reservoir outflow process. If the value of the objective function is better than that before the position update, the position is updated; otherwise, the original position is retained. Continuously loop and iterate until the loop termination condition is met or the iteration is completed. At this time, the position of the optimal individual is the optimal outflow process. As Figure 2 shown.

[0257] S43. Joint operation of water project groups:

[0258] S431. Feedforward-feedback coupling control of series systems:

[0259] For a series of water project systems (such as multiple reservoirs connected in sequence), a feedforward-feedback coupling control strategy is adopted. The feedforward control adjusts the operating parameters of the downstream project in advance according to the operating status of the upstream project (such as flood discharge, water level, etc.). For example, when the flood discharge of the upstream reservoir increases, the downstream reservoir adjusts the opening of the intake sluice in advance to cope with the upcoming flood. The feedback control adjusts the scheduling strategy of the upstream project according to the actual response of the downstream project (such as water level change, flood discharge capacity, etc.) to ensure the stable operation of the entire series system. Through the feedforward-feedback coupling control, the flood response ability of the series system and the water resource allocation efficiency are improved.

[0260] S432. Nash equilibrium scheduling strategy for parallel systems:

[0261] In a parallel water project system (such as multiple sluices and dams operating in parallel), a Nash equilibrium scheduling strategy is adopted. Each sluice and dam pursues its own interests (such as the minimum flood control pressure and the maximum power generation benefit of itself) while considering the operating strategies of other sluices and dams, and finally reaches an equilibrium state. By establishing a game model, analyzing the strategy space and benefit function of each sluice and dam, the Nash equilibrium point is found, that is, all sluices and dams are not willing to change their own strategies alone at this point. This scheduling strategy can ensure the optimal operation of the entire parallel system while guaranteeing the benefits of each sluice and dam itself.

[0262] In the game theory scheduling modeling of a parallel water project system, the realization of the Nash equilibrium requires the following five steps:

[0263] Formal definition of game participants:

[0264] Suppose the system includes parallel sluice dams that form the set of participants , and for each sluice dam , the strategic variable is the flood discharge , and its upper and lower bounds are determined by the physical constraints of the gate and safety regulations. The strategy space forms the Cartesian product .

[0265] Construct a multi-objective benefit function:

[0266] The benefit function of each sluice dam needs to integrate multiple objectives such as flood control, power generation, and ecology:

[0267] ;

[0268] where represents the strategy combinations of other sluice dams, is the water level in front of the gate (determined by the hydraulic equation ), is the risk sensitivity coefficient, is the power generation efficiency, is the weight coefficient.

[0269] Modeling of the constraint coupling mechanism:

[0270] The overall system needs to satisfy the constraint of the total flood discharge in the basin:

[0271] ;

[0272] and the hydraulic coupling relationship between the sluices:

[0273] ;

[0274] where is the water level difference coupling coefficient between the sluice dams, which is determined by the river channel topographic parameters.

[0275] Nash equilibrium solution algorithm:

[0276] Use the backward induction method to solve the non-cooperative game equilibrium:

[0277] Construct a reaction function mapping, and for each , solve the optimal reaction strategy:

[0278] ;

[0279] Subject to , where is the global constraint function.

[0280] Iterative convergence determination, update the strategy combination , calculate the change in the calculation strategy:

[0281] ;

[0282] When it is determined that the equilibrium point is reached .

[0283] In this embodiment, S5. Topological digital coding system:

[0284] S51. Generation of hydraulic relationship matrix:

[0285] S511. Construction of adjacency matrix based on directed graph:

[0286] Regard the basin water project system as a directed graph, where water projects and section nodes are nodes in the graph, and the water flow direction is the directed edge. Construct an adjacency matrix to represent the hydraulic relationship between nodes. If there is a direct hydraulic connection from node i to node j, the corresponding element in the adjacency matrix otherwise . And determine the positive and negative of the matrix elements according to the water flow direction. The connection from the upstream node to the downstream node corresponds to a positive element, and vice versa. In this way, the adjacency matrix intuitively presents the hydraulic conduction relationship of the water project system and provides a basic relationship description for subsequent calculations.

[0287] S512. Fuzzy membership degree assignment of weight matrix:

[0288] Construct a weight matrix based on the adjacency matrix. The weight matrix quantifies the strength of the hydraulic connection, where represents the influence weight of node on node , and .

[0289] ;

[0290] Use the fuzzy membership degree assignment method to determine the weight matrix element values. Among them, is the fuzzy membership degree function, which maps physical parameters to weight values. The strength of the weight matrix is determined by the flow transmission coefficient, hydraulic loss coefficient, and time delay factor. According to the actual hydraulic characteristics and engineering experience, define the membership degree function for different types of hydraulic connections. For example, for the flow transmission coefficient, if the transmission efficiency is high within a certain range, its fuzzy membership degree can be set to a value close to 1; if the transmission efficiency is low, it can be set to a value close to 0. In this way, the weight matrix can more accurately describe the hydraulic relationship and provide support for subsequent accurate calculations.

[0291] S52. Calculation task scheduling:

[0292] S521. Three - layer nested grid division for spatio - temporal discretization:

[0293] For the computational tasks of the basin, a three - layer nested grid division for spatio - temporal discretization is carried out. Spatially, the outermost layer is the large grid of the whole basin, the middle layer is the medium - sized grid divided according to different sub - basins or water project aggregation areas, and the innermost layer is the small grid around specific water projects or key cross - sections. This three - layer nested grid division method can not only grasp the overall situation of the basin macroscopically, but also accurately describe the flow details near water projects and key cross - sections microscopically. Temporally, according to the flood evolution speed and the response time requirements of project scheduling, the calculation time is discretized into different time steps. For example, shorter time steps are adopted in the rapid flood evolution stage to ensure calculation accuracy, and longer time steps are adopted in the relatively stable flood stage to improve calculation efficiency.

[0294] S522. Topological sorting algorithm for calculation priority:

[0295] Determine the priority of computational tasks based on the topological structure. Using the topological sorting algorithm, water projects and cross - section nodes are sorted according to their order in the topology. When mapping water projects and cross - section nodes to a graph structure, each node can be regarded as a vertex in the graph, and the associations between nodes based on the water flow direction or computational result dependency relationships are represented by directed edges.

[0296] When using the topological sorting algorithm, first calculate the in - degree and enqueue the nodes with in - degree zero. For each node in the graph , its in - degree needs to be calculated . The in - degree represents the number of directed edges pointing to the node, reflecting the number of dependencies of the node on the computational results of other nodes. Secondly, perform iterative processing on the nodes. Take a node from the queue . This node has the highest computational priority because it has no uncompleted pre - dependencies. For each adjacent node of the node (i.e., the node with a directed edge ), the following operations are performed: subtract 1 from the in - degree of , that is ; if the in - degree of becomes 0, then add to the queue , indicating that all pre - dependencies of the node have been processed and can enter the calculation process. Continue the iterative process until the queue is empty. Automatically sort and extract according to the topological relationship by the above method, providing necessary support for the calculation of the scheduling model.

[0297] S523. Event - driven dynamic step - size control:

[0298] Introduce an event-driven mechanism to achieve dynamic step size control and realize the adaptive allocation of computing resources in the spatio-temporal dimension. During the calculation process, define some key events, such as the flood peak reaching a certain node and the scheduling operations of water projects (such as reservoir flood discharge, sluice opening, etc.). When these events occur, adjust the calculation time step according to the nature of the event and the current calculation situation. For example, when the flood peak reaches a certain node, in order to more accurately capture the water flow changes near the peak, the time step is dynamically reduced through an exponential decay model where is the initial time step, is the decay intensity coefficient, which controls the speed of step size reduction and ranges from 0.1 to 0.3. The larger the value, the faster the step size decreases. is the value set for a certain node, is the design flow; when the water project scheduling operation is completed, trigger a progressive stability recovery strategy. According to the stability of the subsequent water flow, increase the time step according to where is the adjusted time step, is the current time step, is the step size recovery coefficient, is the decay rate coefficient, is the moment when the event triggering the step size adjustment occurs, is the maximum time step allowed by the system. This event-driven dynamic step size control can improve the calculation efficiency while ensuring the calculation accuracy.

[0299] In this embodiment, S6. Intelligent verification and validation system:

[0300] S61. Data integrity verification:

[0301] S611. Relevance verification based on knowledge graph:

[0302] Construct a knowledge graph about the basin water project system. Through multi-source heterogeneous data fusion technology, abstract water project entities (reservoirs, sluices, cross-sections), hydrological data (storage capacity curves, time-series flows) and scheduling rules into "physical-data-logic" three-layer entities; use semantic parsing and entity relationship modeling technology to establish a multi-dimensional association network including spatial topological relationships (upstream and downstream connections), data attribution relationships (storage capacity curves belong to reservoirs) and rule binding relationships (applicable conditions of scheduling rules), and store them using a spatio-temporal attribute graph model;

[0303] Design a verification framework based on a rule engine and a graph traversal algorithm. Combine the rule engine to verify the physical constraints of the storage capacity curve and flood discharge capacity (such as triggering an alarm when the scheduling trigger water level exceeds the limit), and use the temporal reasoning engine to detect spatio-temporal conflicts in upstream and downstream scheduling actions (such as overlapping time periods ), and use a graph neural network to identify abnormal patterns in historical data; locate the root cause of conflicts through knowledge tracing and generate a visual report to achieve interpretable verification of data logic.

[0304] S612. Bayesian network completion for missing data:

[0305] For possible missing data, use a Bayesian network for completion. First, construct a Bayesian network model, taking the known data as observed variables and the missing data as variables to be inferred. Determine the structure and parameters of the Bayesian network according to the causal and probability relationships in the water engineering system. For example, construct a Bayesian network based on the water level and flow data of a river section and their probability relationships. When the flow data of a certain section is missing, use the Bayesian network to infer the possible flow value based on the water level data and other relevant factors, so as to complete the missing data and improve the integrity of the data.

[0306] S62. Model verification system:

[0307] S621. Reconstruction verification of historical flood scenarios:

[0308] Use historical flood data for scenario reconstruction verification. According to the hydrological data of historical flood events (such as flood flow, water level changes, etc.), input them into the constructed model and run the model to obtain simulation results. Then compare the simulation results with the historical actual records, such as comparing key indicators such as flood propagation time, peak water level, and inundation area. If the simulation results are consistent with the actual records within a certain error range, it indicates that the model is reliable in dealing with similar flood scenarios; if there are large differences, the model needs to be adjusted and optimized.

[0309] S622. Rolling assimilation correction of real-time data:

[0310] Adopt real-time data for rolling assimilation correction. During the operation of the model, continuously obtain real-time hydrological data (such as water level, flow, etc.), and compare these real-time data with the prediction results of the model. If there is a deviation, adjust the parameters of the model according to the size and nature of the deviation. For example, if the real-time water level is higher than the model prediction water level, it may be necessary to adjust the flood propagation speed parameter in the model or the scheduling parameters of the water project. Through this rolling assimilation correction, the model can adapt to the changes in the actual situation in a timely manner and improve the accuracy of the model.

[0311] Example Two

[0312] The present invention also discloses a real-time scheduling visualization dynamic modeling system for a complex water project system in a basin. The system is used to implement the method described in any one of Embodiment 1. The system includes: a first construction module, a fusion configuration module, a second construction module, and a third construction module;

[0313] The first construction module is used to construct a real-time scheduling topology visualization graph of the water project system in the basin;

[0314] The fusion configuration module is used to perform fusion configuration on the characteristic parameters of the water project node and the characteristic parameters of the river cross-section node based on the real-time scheduling topology visualization graph;

[0315] The second construction module is used to construct a composite flood routing model based on the characteristic parameters of the nodes after fusion configuration;

[0316] The third construction module is used to construct an intelligent scheduling model based on the composite flood routing model.

[0317] The above embodiments are only descriptions of the preferred embodiments of the present invention, and do not limit the scope of the present invention. Without departing from the design spirit of the present invention, various deformations and improvements made by those of ordinary skill in the art to the technical solutions of the present invention shall fall within the protection scope determined by the claims of the present invention.

Claims

1. A real-time scheduling visualization dynamic modeling method for a complex water project system in a basin, characterized in that, The method includes: Constructing a real-time scheduling topology visualization graph of the basin water project system; Based on the real-time scheduling topology visualization graph, performing fusion configuration on the characteristic parameters of water project nodes and the characteristic parameters of river cross-section nodes; Based on the fused and configured node characteristic parameters, constructing a composite flood routing model; Based on the composite flood routing model, constructing an intelligent scheduling model; The method for constructing a real-time scheduling topology visualization graph of the basin water project system includes: Constructing a flood forecasting topology basic layer based on basin GIS data; Based on the flood forecasting topology basic layer, constructing a multi-dimensional extensible graphic element library for basin water project scheduling; Based on the multi-dimensional extensible graphic element library, implementing topological dynamic linking to complete the construction of the real-time scheduling topology visualization graph of the basin water project system; The method for constructing a multi-dimensional extensible graphic element library based on the flood forecasting topology basic layer includes: Based on the physical characteristics and regulation behaviors of engineering entities, designing a composite parameter system including geometric parameters, hydraulic parameters, and control logic parameters for each type of graphic element; At the same time, realizing the dynamic injection of new engineering characteristics through a multi-layer open extension interface, customizing parameter dimensions according to basin characteristics, and establishing a structured database supporting complex water network topology reconstruction and intelligent calculation; Among them, the method for realizing the dynamic injection of new engineering characteristics through a multi-layer open extension interface, customizing parameter dimensions according to basin characteristics, and establishing a structured database supporting complex water network topology reconstruction and intelligent calculation includes: hierarchical interface protocol design, parameter dynamic binding and conflict detection mechanism, and construction of an intelligent parameter recommendation system; The hierarchical interface protocol design includes: a core interface layer, an extended interface layer, and a basin adaptation layer; the core interface layer is used to forcibly inherit the hydraulic conductivity attributes and spatial topological constraints of basic graphic elements; the extended interface layer is used to declare the physical dimensions, value range, and data verification rules of newly added parameters based on the domain-specific language DSL, and support non-programmers to define parameters through configuration files; the basin adaptation layer internally has a terrain slope , soil permeability coefficient , river network density basin characteristic parameterization templates for dynamically generating parameter legality functions; The parameter dynamic binding and conflict detection mechanism includes: Hydraulic model symbolic binding: Using a symbolic calculation engine to automatically parse newly added parameters and the partial derivative relationship with the hydraulic control equation to generate a Jacobian matrix of rows and columns, ensuring that the parameters are automatically integrated into the calculation kernel after injection without reconstructing the model code; Constructing a parameter dependency network based on a directed acyclic graph, detecting contradictory combinations through topological sorting, triggering real-time alarms and locking the calculation process, and realizing conflict self-check through mathematical symbol binding and graph theory algorithms; For hydraulic structures, an intelligent parameter recommendation system based on engineering feature fingerprints and cross-project topological association learning is constructed, specifically including: extracting core parameters for each type of hydraulic structure, and generating a unique feature fingerprint code through weighted random forest algorithm , where is the parameter importance weight, is the core physical parameter value extracted from the project, which is used to quantify the structural or functional characteristics of different projects; constructing an associated topological graph of hydraulic structures based on the graph convolutional network GCN, where the nodes are engineering feature fingerprints and the edges are the river connections between projects, calculating the matching degree score between the new parameters and the target project through neighborhood feature aggregation, and dynamically recommending the optimal parameter combination; The method for implementing topological dynamic linking based on the multi-dimensional extensible graphic element library includes: Decompose the conduction-type graph elements of river channels and lakes into connector units with direction vectors, and construct a mathematical representation of the unstructured water network topology through a set of directed line segments , where , are the coordinates of the starting point and the ending point of the connector, where , is the abscissa and ordinate of the starting point of the connector, , is the abscissa and ordinate of the ending point of the connector, is the cross-sectional area function that varies with the water level, where , are the functions of the cross-sectional area varying with the water level of the starting cross-section and the ending cross-section respectively, is the dynamic conduction coefficient matrix, driven by the water level gradient , where and are the conduction coefficients from the starting point to the ending point and from the ending point to the starting point respectively; Each connector unit realizes an asymmetric conduction characteristic through a direction vector weight function, and the dynamic correction formula for the conduction coefficient is as follows: Among them, is the reference conductivity, is the connector direction vector, is the asymmetric adjustment factor, is the gradient response intensity coefficient, , are the starting water level and the ending water level of the connector.

2. The method according to claim 1, wherein The method for constructing a composite flood routing model includes: combining multiple methods such as the improved Muskingum sectional calculus, the non-structured grid Godunov format solution hydrodynamic model, and the coupled model of connected lakes, comprehensively considering different flow characteristics, and constructing a composite flood routing model; Among them, the improved Muskingum segmentation calculation model is used to divide the basin into several sub-river sections based on the terrain slope, roughness distribution, cross-section morphology, and hydrological station location attributes. The local Muskingum coefficient is introduced into each sub-river section. That is, the storage parameters and That is, the flow weight factor. The improved Muskingum method adopts a physically related initial parameter mapping mechanism. The initial value sets a nonlinear mapping function according to the sub-reach attributes. , ,in , , is a hyperparameter, The length of the river section, is the slope, For Manning's roughness, For the width of the river, For water depth; Sub-river sections, outflow ,in , , Depend on , Decide and satisfy , For time, is the time step; the inlet flow of the sub-river section and export flow The monitoring data is taken as input and the objective function is constructed , using recursive least squares RLS, real-time update and , and introduced the particle filter algorithm PF, which integrates historical flood event data with a Bayesian framework and periodically modifies hyperparameters , , During the calculation process, the basin is divided into multiple sub-sections, and the improved Muskingum model is applied to flood calculations according to the characteristics of the sub-sections. Then the results of each sub-section are integrated to obtain the flood evolution of the entire basin.

3. The method according to claim 1, wherein The method for constructing an intelligent scheduling model includes: Analysis of the engineering connection relationship matrix based on graph theory and decomposition of the mixed structure eigenvalue; Based on the results of the analysis and decomposition, performing multi-mode scheduling of single projects and collaborative scheduling of project groups to complete the construction of the intelligent scheduling model.

4. The method according to claim 3, wherein The method for performing multi-mode scheduling of single projects and collaborative scheduling of project groups includes: using an improved starfish optimization algorithm, and the steps are: Initial population size , when the improved starfish optimization algorithm generates the initial population, it adopts a constraint satisfaction initialization method based on chaotic mapping. That is, under the dynamic feasible region that satisfies the reservoir outflow discharge, the population is initialized by adopting the chaotic mapping Cubic mapping strategy. The formula for initializing the population by Cubic mapping is as follows: ； Among them, is the population position matrix, , is the length of the scheduling period, is the upper boundary of the population position, which represents the upper boundary of the water level process in this problem, is the lower boundary of the population position, representing the lower boundary of the water level process, , and the finally generated initial population matrix is: ； Calculate the initial fitness value of each individual, which is the objective function value. The minimum objective function value means the maximum peak shaving rate, and the position of the corresponding individual, i.e., the reservoir discharge process, is denoted as , denotes the th individual, the position of the th dimension, represents the current iteration number; Updating the positions of population individuals according to the position update formula of the improved starfish optimization algorithm, that is, updating the reservoir release process. The position update of the improved starfish optimization algorithm includes an exploration stage and a development stage: Exploration stage: ； ； ； Among them, is the updated position, is the position before update, is the current best position, is 5 dimensions randomly selected from, is a random number between 0 and 1, is the current iteration number, is the maximum iteration number, is a randomly generated angle parameter, is a dynamically adjusted angle parameter, ; Development stage: Two position update strategies are designed according to the predation and regeneration behaviors of starfish: ； ； ； Among them, is the updated position, is the position before update, and is a random number between 0 and 1, is the population size, is the distance between the best position and the positions of 5 randomly selected dimensions, and is selected randomly from ; is the current optimal position, are the positions of 5 randomly selected starfish; After the development stage, a tail mutation strategy is introduced, that is, a forced perturbation is added to the positions of the population to avoid falling into local optimal solutions, and the intensity of the perturbation gradually decreases as the number of iterations increases, accelerating the convergence in the later stage of the algorithm. The Levy flight strategy is selected in the improved starfish optimization algorithm to perturb the positions of the population, where is the Levy distribution; ； Calculating the objective function for the position after each update, that is, the reservoir release process. If the objective function value is better than the objective function value before the position update, then perform the position update; otherwise, retain the original position; continuously loop and iterate until the loop termination condition is met or the iteration is completed. The position of the optimal individual is the optimal release flow process.

5. A real-time scheduling visualization dynamic modeling system for a complex water project system in a basin, the system being used to implement the method according to any one of claims 1-4, characterized in that, The system includes: a first construction module, a fusion configuration module, a second construction module, and a third construction module; The first construction module is used to construct a real-time scheduling topology visualization graph of the basin water project system; The fusion configuration module is used to perform fusion configuration on the characteristic parameters of the water project nodes and the characteristic parameters of the river cross-section nodes based on the real-time scheduling topology visualization graph; The second construction module is used to construct a composite flood routing model based on the characteristic parameters of the nodes with fusion configuration; The third construction module is used to construct an intelligent scheduling model based on the composite flood routing model.

Images