Movatterモバイル変換


[0]ホーム

URL:


CN120562674A - Dam break flood emergency evacuation path planning method and system based on improved NSGA-III - Google Patents

Dam break flood emergency evacuation path planning method and system based on improved NSGA-III

Info

Publication number
CN120562674A
CN120562674ACN202511053758.6ACN202511053758ACN120562674ACN 120562674 ACN120562674 ACN 120562674ACN 202511053758 ACN202511053758 ACN 202511053758ACN 120562674 ACN120562674 ACN 120562674A
Authority
CN
China
Prior art keywords
evacuation
points
priority
point
refuge
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202511053758.6A
Other languages
Chinese (zh)
Other versions
CN120562674B (en
Inventor
王林
杨康杰
胡浩然
杨永胜
吴吉东
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Zhuhai Campus Of Beijing Normal University
Original Assignee
Zhuhai Campus Of Beijing Normal University
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Zhuhai Campus Of Beijing Normal UniversityfiledCriticalZhuhai Campus Of Beijing Normal University
Priority to CN202511053758.6ApriorityCriticalpatent/CN120562674B/en
Publication of CN120562674ApublicationCriticalpatent/CN120562674A/en
Application grantedgrantedCritical
Publication of CN120562674BpublicationCriticalpatent/CN120562674B/en
Activelegal-statusCriticalCurrent
Anticipated expirationlegal-statusCritical

Links

Classifications

Landscapes

Abstract

According to the dam-break flood emergency evacuation path planning method and system based on the improved NSGA-III, dam-break flood simulation, evacuation point and refuge point selection, multi-objective optimization and heuristic strategies are fused, efficient evacuation path optimization for people with different priorities can be achieved under the extreme dam-break scene, the overall evacuation efficiency and the priority are improved, and an evacuation optimization model adapting to the spatial distribution characteristics of flood risks is constructed by carrying out two-dimensional unsteady flow dam-break simulation in HEC-RAS and combining with scientific selection and priority division of the evacuation point and the refuge point by an ArcGIS Pro platform.

Description

Dam break flood emergency evacuation path planning method and system based on improved NSGA-III
Technical Field
The invention relates to the field of dam break flood disaster emergency management and path optimization, in particular to a dam break flood emergency evacuation path planning method and system based on improved NSGA-III, which are suitable for multi-objective optimization and auxiliary decision-making of rapid and orderly evacuation paths of personnel in flood disaster situations.
Background
With the aggravation of climate change and the frequent occurrence of extreme rainfall events, the risk of flood disasters caused by reservoir dam break increases, and serious threat is formed to the downstream people's mouth dense area. Dam break flood has the characteristics of strong burst, hong Fenggao, high propagation speed and the like, and is extremely easy to cause large-scale casualties and property loss. Therefore, after the flood early warning is issued, how to rapidly plan the efficient and reasonable personnel evacuation path according to the influence degree of the flood becomes a key problem in disaster emergency management.
The traditional evacuation path planning method is mostly based on a single-target shortest path algorithm (such as Dijkstra algorithm), and although the shortest path can be quickly solved, a plurality of actual demands such as personnel risk priority, refuge point capacity constraint, region distribution balance and the like are difficult to comprehensively consider, and adaptability and practicability under extreme flood situations are lacking. As a novel multi-objective evolutionary algorithm, NSGA-III has good global searching capability and multi-objective weighing capability, and is suitable for complex optimization. However, in large-scale evacuation path planning, the direct application of NSGA-III still faces the problems of slow convergence speed, poor solution feasibility, high computing resource consumption and the like.
Therefore, an improved NSGA-III evacuation path optimization method that integrates dam-break flood simulation results, priority classification, path caching mechanism and heuristic strategies is needed to improve timeliness, scientificity and life protection capability of evacuation scheduling, and adapt to rapid emergency response requirements in extreme situations of sudden dam-break flood.
Disclosure of Invention
Aiming at the defects, the invention provides the dam-break flood emergency evacuation path priority planning method based on the improved NSGA-III, solves the problem that the existing evacuation path planning method is difficult to consider multi-objective optimization, evacuation priority grading and refuge point capacity constraint under the dam-break flood situation with strong burst property and wide influence range, realizes the differential evacuation path optimization of high, medium and low priority groups, improves the overall evacuation efficiency and emergency response capability, and maximally ensures the life safety of personnel.
In order to solve the technical problems, the invention adopts the following technical scheme:
the dam break flood emergency evacuation path priority planning method based on the improved NSGA-III comprises the following steps:
step S1, collecting relevant data and parameter information of a research area, and determining a digital elevation model diagram, a satellite image diagram, a river distribution diagram, a road network diagram and dam structure parameter information of the research area;
s2, setting parameters of the HEC-RAS model to perform dam break simulation;
Setting extreme flood scene and breach parameters in an HEC-RAS model based on the acquired digital elevation model diagram, satellite image diagram, river distribution diagram, road network diagram and dam structure parameters, carrying out two-dimensional unsteady flow dam break simulation in the HEC-RAS module, outputting a result file of a maximum flood submerged depth diagram, and importing a simulation result to an ArcGIS Pro platform;
Step S3, selecting evacuation points and difficulty avoidance points by combining flood inundation and grading;
In the ArcGIS Pro platform, combining a satellite image map, a road network map, a flood submerged depth map, a high-resolution population density map and a building block vector map, and comprehensively analyzing to select evacuation points and refuge points;
s4, constructing topology, calculating all shortest paths and caching;
Constructing a road network topological structure by utilizing a Python NetworkX tool, calculating the shortest path distance from each evacuation point to all avoidance points based on Dijkstra algorithm, and caching calculation results;
step S5, based on the space position of the evacuation points and the priority weights thereof, performing weighted K-means cluster initialization to construct an initial population solution of an NSGA-III algorithm;
step S6, the initial population solution of the NSGA-III algorithm is updated through multi-objective optimization iteration of the NSGA-III algorithm;
Under the NSGA-III multi-objective optimization algorithm framework, taking a minimized multi-objective function as an objective, and combining with refuge point capacity limitation, iteratively updating an initial population solution to obtain an initial Pareto solution set;
step S7, fine-tuning a Pareto solution set by a heuristic strategy;
Introducing a heuristic fine tuning strategy to the initially obtained Pareto solution set, namely carrying out local exchange optimization on the distribution relation between evacuation points and refuge points based on path length comparison results among the evacuation points with different priorities, and executing load exchange optimization aiming at the evacuation points with path lengths exceeding a preset improvement threshold;
s8, obtaining and visualizing an optimal evacuation path structure;
The heuristic fine tuning strategy is optimized to obtain an optimal Pareto solution set, an optimal refuge point corresponding to each evacuation point and a path allocation scheme thereof are output, and the final evacuation path result is imported into an ArcGIS Pro platform for visual display to generate results such as a distribution map, an evacuation pressure thermodynamic diagram and the like of each priority evacuation path for emergency dispatch reference.
Further, the step S2 of performing the two-dimensional unsteady flow dam break simulation in the HEC-RAS module comprises the following steps:
Drawing a range of a reservoir water Storage Area by using a Storage Area tool, defining a flood simulation Area boundary by using a 2D Flow Area tool, setting dam axis and breach parameters by using an SA/2D Connection tool, setting simulation working conditions including an initial water level, a dam break water level, simulation time length and time step, and starting unsteady Flow simulation after constructing a two-dimensional calculation grid.
Further, in the step S3, a process of selecting evacuation points and avoiding difficulties in the ArcGIS Pro platform includes the following steps:
based on the satellite image map, the building block vector map and the high-resolution population density map, intersections and open places of a high population gathering area of a flood inundation area are selected as evacuation points, and difficulty avoidance points are arranged in resident areas and large public facility areas outside the flood influence range.
Further, when the NetworkX tool of Python is used to construct the road network topology in the step S4, the method includes the following steps:
Firstly, the preprocessed road data are converted into graph structures, wherein each road section corresponds to a side with weight in the graph structure, the weight of the side is the actual road distance, and the nodes represent road intersections or key geographic positions. Then, the evacuation area and the position of the shelter are projected to the nearest node in the network map through a space mapping method, so that the corresponding relation between the evacuation points and the shelter points in the road network is established;
The method comprises the steps of ensuring that the topological structure of a network accords with the actual road passing logic, avoiding unreasonable cross connection, checking the connectivity of the network, carrying out connectivity correction if a non-connected segment exists, confirming that all evacuation points and evacuation points are located on nodes, and adjusting if the evacuation points and the evacuation points are not in accord.
Further, in the step S4, the Dijkstra algorithm calculates a shortest path distance process from each evacuation point to all avoidance points, including the following steps:
Sequentially calculating the path lengths from all evacuation points to each refuge point by using a Dijkstra algorithm, and storing a binary group consisting of the evacuation points and the refuge points and the path lengths thereof into a cache structure such as a hash table and the like so as to support subsequent quick inquiry and repeated use and avoid repeated calculation paths of each model iteration;
The two groups of evacuation points and refuge points are ordered pairing of one evacuation point and one refuge point, and are used for uniquely identifying the corresponding relation between the two positions, and in the path cache, each of the two groups represents a specific evacuation path, and the shortest path length corresponding to the specific evacuation path is stored in the hash table as a numerical value.
Further, the method for initializing the weighted K-means cluster in the step S5 comprises the following steps:
setting weight according to the priority of the evacuation points, executing weighted clustering to generate initial grouping, matching the evacuation points closest to each clustering center as default evacuation targets, completing initial evacuation point distribution, and constructing an initial population solution of NSGA-III algorithm.
Further, the objective functions adopted by the NSGA-III multi-objective optimization in step S6 include:
the total length of all evacuation paths;
Consider the total path length of the priority weighting;
the total length of the high priority evacuation path.
Further, the objective function calculation process adopted by the NSGA-III multi-objective optimization is as follows:
;
wherein, theDecision variables, N is the total number of evacuation points 192, reviewed inAn evacuation point index which represents the allocation of the ith evacuation point, S is the total number of the evacuation points 32; Evacuation pointTo the refuge pointIs the shortest path length of (a); representing flood priority weightCorresponding to the weight [10, 5, 1 ]); a high priority evacuation point set; penalty terms are constrained for capacity.
Further, the heuristic fine-tuning strategy is divided into three stages:
step one, after the NSGA-III calculates the preliminary Pareto solution set in step S7, if the path length of a certain high-priority evacuation point is found to exceed a certain low or medium-priority point, performing the evacuation point allocation exchange operation, and when the path length of the medium-priority evacuation point is significantly greater than that of the low-priority evacuation point, performing the allocation exchange to improve the high-priority evacuation efficiency;
Step two, after the operation of the step one is finished, if the path length of a certain high-priority evacuation point is found to exceed a certain low-priority point, continuing to execute the exchange operation of the evacuation point until no more exchange pairs can be obviously improved or the preset iteration times are reached, and obtaining an optimized Pareto solution set;
And thirdly, screening out extreme evacuation points with path length exceeding a preset threshold value on the optimized Pareto solution set obtained in the second stage, traversing all the avoidance points, screening out candidate avoidance points which do not exceed capacity limit and can shorten the path to the maximum extent, replacing the original allocation avoidance points with the candidate avoidance points, and updating allocation information of the corresponding paths and the avoidance points.
Dam break flood emergency evacuation path priority planning system based on improved NSGA-III, comprising:
The parameter determining unit is used for acquiring digital elevation model diagrams, satellite image diagrams, river distribution diagrams, road network diagrams and dam structure parameter information of the research area;
the flood simulation unit is used for performing two-dimensional unsteady flow dam break simulation in the HEC-RAS and deriving a simulation result;
The space point selection unit is used for comprehensively analyzing the flood influence range, the building distribution and the population density in the ArcGIS Pro platform, scientifically selecting evacuation points and refuge points and dividing the priority class of the evacuation points;
The path pre-calculation unit is used for constructing a road network topological structure and caching the shortest paths between all evacuation points and refuge points through a Dijkstra algorithm;
the cluster initialization unit is used for generating an initial group based on a weighted K-means method and constructing an NSGA-III initial population solution;
The multi-objective optimization unit is used for executing path optimization under an NSGA-III multi-objective optimization framework to obtain an initial Pareto solution set;
The heuristic fine tuning unit is used for carrying out high-priority path tuning and extreme path load exchange optimization on the initial solution set;
the result visualization unit is used for exporting the optimal Pareto solution set distribution result between the evacuation points and the refuge points to form a file, and displaying the distribution map of each priority evacuation path and the evacuation pressure thermodynamic diagram in the ArcGIS Pro platform.
Compared with the prior art, the invention has the following technical effects:
According to the dam-break flood emergency evacuation path planning method and system based on the improved NSGA-III, dam-break flood simulation, evacuation point and refuge point selection, multi-objective optimization and heuristic strategies are fused, efficient evacuation path optimization for people with different priorities can be achieved under the extreme dam-break scene, the overall evacuation efficiency and the priority are improved, and an evacuation optimization model adapting to the spatial distribution characteristics of flood risks is constructed by carrying out two-dimensional unsteady flow dam-break simulation in HEC-RAS and combining with scientific selection and priority division of the evacuation point and the refuge point by an ArcGIS Pro platform.
The method introduces a path caching mechanism and weighted K-means initialization under an NSGA-III multi-objective optimization framework, remarkably improves the known convergence speed and feasibility, and simultaneously, carries out local fine adjustment on the preliminary solution set through heuristic priority exchange and load adjustment strategies to further optimize the evacuation efficiency of high-priority groups. Compared with the traditional evacuation method based on shortest path or single objective optimization, the method can more reasonably consider the shortest path, the priority and the capacity limit of the refuge points, and provide high-timeliness and operability decision support for dam-break flood disaster emergency response.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below. Like elements or portions are generally identified by like reference numerals throughout the several figures. In the drawings, elements or portions thereof are not necessarily drawn to scale.
Fig. 1 is a flowchart of a dam break flood emergency evacuation path planning method and system based on an improved NSGA-III according to an embodiment of the present invention;
FIG. 2 is a diagram of the locations of three high, medium, and low priority evacuation points and avoidance points in a specific example;
FIG. 3 is a three-dimensional graph of evacuation path distribution for improving each priority of NSGA-III model;
FIG. 4 is an evacuation path profile for a high priority evacuation point in a particular example;
fig. 5 is a schematic structural diagram of a dam break flood emergency evacuation path planning system based on an improved NSGA-III according to an embodiment of the present invention.
Detailed Description
The present invention is further described below with reference to examples, but it should not be construed that the scope of the above subject matter of the present invention is limited to the following examples. Various substitutions and alterations are made according to the ordinary skill and familiar means of the art without departing from the technical spirit of the invention, and all such substitutions and alterations are intended to be included in the scope of the invention.
An embodiment, as shown in fig. 1, of a dam break flood emergency evacuation path priority planning method based on an improved NSGA-III, includes the following steps:
Step S1, collecting relevant data and parameter information of a research area;
digital Elevation Model (DEM) map, satellite image map, river profile map, road network map and dam structure parameter information of the study area are determined.
The dam structure parameter information comprises dam elevation, dam length, dam width, reservoir capacity-water level curve, design flood level and water storage capacity.
S2, setting parameters of the HEC-RAS model to perform dam break simulation;
Based on the acquired digital elevation model diagram, satellite image diagram, river distribution diagram, road network diagram and dam structure parameters, setting extreme flood scene and breach parameters in an HEC-RAS model, carrying out two-dimensional unsteady flow dam break simulation on the HEC-RAS module, outputting a result file of a maximum flood submerged depth diagram, and importing a simulation result to an ArcGIS Pro platform.
The crumple parameters comprise crumple mode, crumple position, crumple shape, crumple weir flow coefficient and crumple forming time.
The method comprises the steps of drawing a reservoir water Storage Area range by using a Storage Area tool, defining a flood simulation Area boundary by using a 2D Flow Area tool, setting dam axis and breach parameters by using an SA/2D Connection tool, setting simulation working conditions including initial water level, dam break water level, simulation duration, time step and the like, constructing a two-dimensional calculation grid, and then starting up the non-constant Flow simulation.
Step S3, selecting evacuation points and difficulty avoidance points by combining flood inundation and grading;
In the ArcGIS Pro platform, a satellite image map, a road network map, a flood submerging depth map, a high-resolution population density map and a building block vector map are combined, evacuation points and refuge points are selected after comprehensive analysis, and meanwhile, the evacuation points are divided into three priority levels of high, medium and low according to the flood submerging depth and influence degree.
Specifically, 80 high-priority evacuation points, 56 medium-priority evacuation points with the water depth of 5-10 meters, 56 low-priority evacuation points with the water depth of 5 meters and less than 192 evacuation points and 32 difficult avoidance points are screened according to the influence of more than 10 meters of water depth.
After the HEC-RAS finishes dam break flood evolution simulation, grid results such as maximum water Depth (Max Depth) and the like can be exported through RAS MAPPER, and then the grid results are imported into an ArcGIS Pro platform to manufacture and display the flood Depth map. The high resolution population density map is from a publicly published chinese seven-population grid dataset (resolution 100 m) that has been publicly shared at the Figshare platform. The building block vector diagram is generated by processing a building boundary extraction algorithm based on Google Earth remote sensing images (with the spatial resolution of 0.5 m) acquired in 2020-2022, and can effectively represent the spatial distribution and morphological characteristics of buildings in a research area. The data set is publicly available and can be downloaded and acquired from Zenodo databases and is used for supporting the space references selected by evacuation points and refuge points.
The process for selecting evacuation points and avoiding difficulties in the ArcGIS Pro platform comprises the following steps:
based on the satellite image map, the building block vector map and the high-resolution population density map, intersections and open places of a high population gathering area of a flood inundation area are selected as evacuation points, and difficulty avoidance points are arranged in resident areas and large public facility areas outside the flood influence range.
In order to scientifically and reasonably select evacuation points and refuge points, researching and combining a road network diagram and a satellite image diagram, in a high-density building area within the influence range of flood, visually interpreting satellite images to preferentially lay the evacuation points at road intersections and key nodes, and meanwhile, setting up the refuge points in a resident concentrated area outside the influence range of flood. In order to further verify the rationality of evacuation points and refuge points, 100 m resolution population density map and building block vector data are introduced for research, and although the data have certain limitations in spatial resolution and precision, the data can be used as auxiliary references. Based on the superposition analysis of the data, the preliminarily set evacuation points and the refuge points are properly adjusted so as to enhance the scientificity and rationality of the spatial distribution of the evacuation points and the refuge points.
S4, constructing topology, calculating all shortest paths and caching;
and constructing a road network topological structure by utilizing a Python NetworkX tool, calculating the shortest path distance from each evacuation point to all the avoidance points based on a Dijkstra algorithm, and caching the calculation result.
The construction of the road network topology by using the NetworkX tool of Python comprises the following steps:
Firstly, the preprocessed road data (including the information of the start point, the end point, the distance and the like of the road) are converted into graph structures, wherein each road section corresponds to a weighted side in the graph structure, the weight of the side is the actual road distance, and the node represents the road intersection or the key geographic position. And then, projecting the positions of the evacuation area and the shelter to the nearest node in the network map by a space mapping method, so that the corresponding relation between the evacuation points and the shelter points in the road network is established.
The method comprises the steps of ensuring that the topological structure of a network accords with the actual road passing logic, avoiding unreasonable cross connection, checking network connectivity, carrying out connectivity correction if a non-connected segment exists, confirming that all evacuation points and evacuation points are located on network nodes, and adjusting if the evacuation points and the evacuation points are not in accord.
The Dijkstra algorithm calculates the shortest path distance process from each evacuation point to all avoidance points, including:
and sequentially calculating the path lengths from all evacuation points to each evacuation point by using a Dijkstra algorithm, and storing the (evacuation points, difficulty avoidance points) binary groups and the path lengths thereof into a cache structure such as a hash table and the like so as to support subsequent quick inquiry and repeated use and avoid repeated calculation paths of each model iteration.
The (evacuation points, escape points) doublets refer to ordered pairing consisting of one evacuation point and one escape point, and are used for uniquely identifying the corresponding relation between the two positions, and in the path cache, each such doublet represents a specific evacuation path, and the corresponding shortest path length is stored as a numerical value in the hash table. By the method, the path length from any evacuation point to the evacuation point can be rapidly inquired in the subsequent model iteration, and repeated calculation is avoided.
And S5, based on the spatial position of the evacuation points and the priority weights thereof, performing weighted K-means cluster initialization to construct an initial population solution of the NSGA-III algorithm.
The weighted K-means clustering initialization method comprises the steps of setting weights according to priorities of evacuation points, executing weighted clustering to generate initial groups, matching the evacuation points closest to each clustering center as default evacuation targets, completing initial evacuation point distribution, and constructing an initial population solution of an NSGA-III algorithm.
Step S6, the initial population solution of the NSGA-III algorithm is updated through multi-objective optimization iteration of the NSGA-III algorithm;
Under the NSGA-III multi-objective optimization algorithm framework, taking a minimized multi-objective function as an objective, and combining with refuge point capacity limitation, iteratively updating an initial population solution to obtain an initial Pareto solution set;
the objective functions adopted by the NSGA-III multi-objective optimization comprise:
;
wherein, theDecision variables, N is the total number of evacuation points 192, reviewed inAn evacuation point index which represents the allocation of the ith evacuation point, S is the total number of the evacuation points 32; Evacuation pointTo the refuge pointIs the shortest path length of (a); representing flood priority weightCorresponding to the weight [10, 5, 1 ]); a high priority evacuation point set; penalty terms are constrained for capacity.
Step S7, fine-tuning a Pareto solution set by a heuristic strategy;
And introducing a heuristic fine tuning strategy to the initially obtained Pareto solution set, namely carrying out local exchange optimization on the distribution relation between the evacuation points and the refuge points based on the path length comparison results among the evacuation points with different priorities, and executing load exchange optimization aiming at the evacuation points with the path length exceeding a preset improvement threshold.
The heuristic fine-tuning strategy is divided into three phases:
after the NSGA-III calculates the preliminary Pareto solution set, if the path length of a certain high-priority evacuation point is found to be greater than a certain low-priority or medium-priority point, performing the evacuation point allocation exchange operation, and when the path length of the medium-priority evacuation point is significantly greater than the low-priority evacuation point, performing the allocation exchange to improve the high-priority evacuation efficiency.
And step two, after the operation of the step one is finished, if the path length of a certain high-priority evacuation point is found to exceed a certain low-priority point, continuing to execute the exchange operation of the evacuation point until no more exchange pairs can be obviously improved or the preset iteration times are reached, and obtaining the optimized Pareto solution set.
And thirdly, screening out extreme evacuation points with path length exceeding a preset threshold value on the optimized Pareto solution set obtained in the second stage, traversing all the avoidance points, screening out candidate avoidance points which do not exceed capacity limit and can shorten the path to the maximum extent, replacing the original allocation avoidance points with the candidate avoidance points, and updating allocation information of the corresponding paths and the avoidance points.
The Pareto solution set is based on an original NSGA-III algorithm, and the optimal solution set obtained after three-stage local path adjustment and refuge point redistribution optimization has higher evacuation efficiency and more reasonable priority path distribution.
S8, obtaining and visualizing an optimal evacuation path structure;
The heuristic fine tuning strategy is optimized to obtain an optimal Pareto solution set, an optimal refuge point corresponding to each evacuation point and a path allocation scheme thereof are output, and the final evacuation path result is imported into an ArcGIS Pro platform for visual display to generate results such as a distribution map, an evacuation pressure thermodynamic diagram and the like of each priority evacuation path for emergency dispatch reference.
In order to further understand the technical solution of the present invention, the method of the present invention is described below by way of specific examples. In this example, a dam and a water outlet area of a reservoir are selected as research areas for implementation, and positions of escape points and evacuation points with three priority levels of high, medium and low are selected, as shown in fig. 2, and the specific implementation process is as follows:
1) Acquiring information such as a Digital Elevation Model (DEM) diagram, a satellite image diagram, a river distribution diagram, a road network diagram, dam structure parameters and the like of a research area;
2) Setting extreme flood situations and breach parameters in the HEC-RAS two-dimensional hydrodynamic model, carrying out two-dimensional unsteady flow dam break simulation, and outputting result files such as a maximum flood submerged depth map;
3) The simulation result is imported into an ArcGIS Pro platform, and the evacuation points and the refuge points are scientifically selected after comprehensive analysis by combining a satellite image map, a road network map, a flood submerging depth map, a population density map and a building block vector map, and meanwhile, the evacuation points are divided into three priority levels of high, medium and low according to the flood submerging depth and influence degree.
Figure 3 shows the evacuation path distribution of the priority avoidance points of the improved NSGA-III model. The points of different shapes in the figure represent evacuation points of different flood priorities, black squares are high priority (. Gtoreq.10m), grey dots are medium priority (5-10 m), and grey triangles are low priority (< 5 m). The modified NSGA-III model after heuristic fine tuning enables the path length of the evacuation points of three flood priorities to show obvious grading effect. It can be seen from the figure that the path lengths of the high priority evacuation points are mostly concentrated in relatively short intervals, medium priority ones, low priority ones are distributed relatively wider. Meanwhile, the extreme maximum value of the evacuation path is reduced to about 10000 meters, so that the occurrence of overlong paths is effectively avoided, and the rationality of the evacuation path planning is improved.
Fig. 4 shows an evacuation path plan based on evacuation points under the influence of a flood depth ∈10m, i.e. the evacuation path distribution of high priority evacuation points. The evacuation route is connected with the high-priority evacuation points and the refuge points at different positions, so that the evacuation planning layout of the high-priority evacuation points is intuitively presented, the evacuation route arrangement formulated for the high-priority area when the dam-break flood risk is dealt with is reflected, and the understanding of the evacuation direction of the high-priority evacuation points and the distribution situation of the accessible refuge points is facilitated.
Based on the same inventive concept, the dam-break flood emergency evacuation path planning method, system and device based on the improved NSGA-III according to the above embodiment of the present application, correspondingly, another embodiment of the present application further provides dam-break flood emergency evacuation path priority planning based on the improved NSGA-III, as shown in fig. 5, which is a schematic diagram of the system structure, the system includes:
A parameter determining unit 501, configured to obtain information such as a digital elevation model map, a satellite image map, a river distribution map, a road network map, and a dam structure parameter of a research area;
a flood simulation unit 502, configured to perform two-dimensional unsteady flow dam break simulation in the HEC-RAS, and derive a simulation result;
The space point selection unit 503 is configured to comprehensively analyze a flood influence range, building distribution and population density in the ArcGIS Pro platform, scientifically select evacuation points and refuge points, and divide priority classes of the evacuation points;
The path pre-calculation unit 504 is configured to construct a road network topology structure, and buffer the shortest paths between all evacuation points and evacuation points through Dijkstra algorithm;
the cluster initialization unit 505 is configured to generate an initial group based on a weighted K-means method, and construct an NSGA-III initial population solution;
A multi-objective optimization unit 506, configured to perform path optimization under an NSGA-III multi-objective optimization framework, and obtain an initial Pareto solution set;
the heuristic fine tuning unit 507 is configured to perform high-priority path tuning and extreme path load switching optimization on the initial solution set;
the result visualization unit 508 is configured to export a file of an optimal Pareto solution set allocation result between the evacuation points and the refuge points, and display an evacuation path distribution map and an evacuation pressure thermodynamic diagram of each priority in the arcgipro platform.
The description of the present invention has been presented for purposes of illustration and description, and is not intended to be exhaustive or limited to the invention in the form disclosed. Many modifications and variations will be apparent to those of ordinary skill in the art. The embodiments were chosen and described in order to best explain the principles of the invention and the practical application, and to enable others of ordinary skill in the art to understand the invention for various embodiments with various modifications as are suited to the particular use contemplated.

Claims (10)

Translated fromChinese
1.基于改进NSGA-III的溃坝洪水应急疏散路径优先级规划方法,其特征在于:包括以下步骤:1. A priority planning method for emergency evacuation paths for dam-break floods based on an improved NSGA-III is characterized by comprising the following steps:步骤S1,收集研究区域相关数据和参数信息;确定研究区域的数字高程模型图、卫星影像图,河流分布图、道路网络图和大坝结构参数信息;Step S1, collecting relevant data and parameter information of the study area; determining the digital elevation model map, satellite image map, river distribution map, road network map and dam structure parameter information of the study area;步骤S2,HEC-RAS模型设定参数开展溃坝模拟,将模拟结果导入至ArcGIS Pro平台;Step S2, setting parameters of the HEC-RAS model to carry out dam break simulation, and importing the simulation results into the ArcGIS Pro platform;步骤S3,结合洪水淹没选取疏散点与避难点并分级;Step S3, selecting evacuation points and refuge points based on flood inundation and grading them;在ArcGIS Pro平台中,选取疏散点与避难点;根据洪水淹没深度和影响程度,将疏散点划分为高、中、低三个优先级等级;In ArcGIS Pro, select evacuation points and refuge points; classify evacuation points into three priority levels: high, medium, and low, based on the depth of flooding and the degree of impact;步骤S4,构建拓扑,计算所有最短路径并缓存;Step S4: Build the topology, calculate all shortest paths and cache them;利用Python NetworkX工具构建道路网络拓扑结构,基于Dijkstra算法计算每个疏散点至所有避难点的最短路径距离,并将计算结果缓存;Use Python NetworkX tools to build the road network topology, calculate the shortest path distance from each evacuation point to all refuge points based on the Dijkstra algorithm, and cache the calculation results;步骤S5,基于疏散点的空间位置及其优先级权重,执行加权K-means聚类初始化,构建NSGA-III算法的初始种群解;Step S5, based on the spatial location of the evacuation points and their priority weights, perform weighted K-means clustering initialization to construct the initial population solution of the NSGA-III algorithm;步骤S6,NSGA-III多目标优化迭代更新NSGA-III算法的初始种群解,获取初始的Pareto解集;Step S6, NSGA-III multi-objective optimization iteratively updates the initial population solution of the NSGA-III algorithm to obtain the initial Pareto solution set;步骤S7,对初始的Pareto解集引入启发式微调策略,获得最优的Pareto解集;Step S7, introducing a heuristic fine-tuning strategy for the initial Pareto solution set to obtain the optimal Pareto solution set;基于不同优先级疏散点间的路径长度比较结果,对疏散点与避难点的分配关系进行局部交换优化,路径长度超出预设改进阈值的疏散点,执行负载交换优化;Based on the comparison results of the path lengths between evacuation points of different priorities, the allocation relationship between evacuation points and refuge points is optimized locally. For evacuation points whose path length exceeds the preset improvement threshold, load exchange optimization is performed;步骤S8,获得最优的疏散路径结构并可视化;Step S8, obtaining the optimal evacuation path structure and visualizing it;基于最优的Pareto解集输出每个疏散点对应的最优避难点及其路径分配方案,并将结果导入ArcGIS Pro平台进行可视化展示,生成各优先级疏散路径分布图、疏散压力热力图。Based on the optimal Pareto solution set, the optimal refuge point and its path allocation plan corresponding to each evacuation point are output, and the results are imported into the ArcGIS Pro platform for visualization, generating the evacuation path distribution map of each priority level and the evacuation pressure heat map.2.如权利要求1所述的基于改进NSGA-III的溃坝洪水应急疏散路径优先级规划方法,其特征在于:所述步骤S2中,HEC-RAS模型设定参数开展溃坝模拟具体步骤如下:2. The method for priority planning of emergency evacuation routes for dam-break floods based on the improved NSGA-III according to claim 1, wherein: in step S2, the HEC-RAS model sets parameters to carry out dam-break simulation in the following specific steps:基于所获取的数字高程模型图、卫星影像图、河流分布图、道路网络图和大坝结构参数,在HEC-RAS模型中设定极端洪水情景及溃口参数,在HEC-RAS模块开展二维非恒定流溃坝模拟,输出洪水最大淹没深度图的结果文件,并将模拟结果导入至ArcGIS Pro平台;Based on the acquired digital elevation model, satellite imagery, river distribution map, road network map, and dam structural parameters, extreme flood scenarios and breach parameters were set in the HEC-RAS model. A two-dimensional unsteady flow dam breach simulation was conducted in the HEC-RAS module. The maximum flood inundation depth map was output as a result file, and the simulation results were imported into the ArcGIS Pro platform.在HEC-RAS模块开展二维非恒定流溃坝模拟包括以下步骤:Carrying out a 2D unsteady flow dam-break simulation in the HEC-RAS module involves the following steps:使用Storage Area工具绘制水库储水区范围,利用2D Flow Area工具划定洪水模拟区域边界,并通过SA/2D Connection工具设置大坝轴线和溃口参数;随后设定模拟工况,包括初始水位、溃坝水位、模拟时长和时间步长,构建二维计算网格后启动非恒定流模拟。Use the Storage Area tool to map the reservoir storage area, the 2D Flow Area tool to define the flood simulation area boundary, and the SA/2D Connection tool to set the dam axis and breach parameters. Then, set the simulation conditions, including the initial water level, dam breach level, simulation duration, and time step. After constructing the 2D computational grid, initiate the unsteady flow simulation.3. 如权利要求1所述的基于改进NSGA-III的溃坝洪水应急疏散路径优先级规划方法,其特征在于:所述步骤S3中,在ArcGIS Pro平台中选取疏散点与避难点的过程,包括以下步骤:3. The method for priority planning of emergency evacuation routes for dam-break floods based on the improved NSGA-III according to claim 1, wherein the process of selecting evacuation points and refuge points in the ArcGIS Pro platform in step S3 comprises the following steps:基于卫星影像图、建筑体块矢量图与高分辨率人口密度图,选取洪水淹没区的高人口聚集区的路口与开阔场所作为疏散点;在洪水影响范围外的居民居住区、大型公共设施区域设置避难点。Based on satellite images, building block vector maps and high-resolution population density maps, intersections and open places in high-population areas in the flood-inundated area are selected as evacuation points; shelters are set up in residential areas and large public facilities areas outside the flood-affected area.4.如权利要求1所述的基于改进NSGA-III的溃坝洪水应急疏散路径优先级规划方法,其特征在于:所述步骤S4中,使用Python的NetworkX工具构建道路网络拓扑结构时,包括以下步骤:4. The method for priority planning of emergency evacuation paths for dam-break floods based on the improved NSGA-III according to claim 1, wherein in step S4, when constructing the road network topology using the Python NetworkX tool, the method comprises the following steps:首先将经过预处理的道路数据转化为图结构,其中每个路段对应图结构中带权重的边,边的权重为实际道路距离;节点则代表道路交叉口或关键地理位置,随后,通过空间映射方法将疏散区域与避难所的位置投影到网络图中的最近节点,从而建立起疏散点与避难点在道路网络中的对应关系;First, the preprocessed road data is converted into a graph structure, where each road segment corresponds to a weighted edge in the graph, with the weight of the edge representing the actual road distance. Nodes represent road intersections or key geographical locations. Then, using a spatial mapping method, the locations of evacuation areas and shelters are projected to the nearest nodes in the network graph, thereby establishing a correspondence between evacuation points and shelters in the road network.确保网络的拓扑结构符合实际道路通行逻辑,避免不合理的交叉连接;检查网络连通性,若存在非连通片段,则进行连通性修正;确认所有疏散点与避难点均位于节点上,如不符合则进行调整。Ensure that the network topology conforms to the actual road traffic logic and avoid unreasonable cross-connections; check the network connectivity and make connectivity corrections if there are non-connected segments; confirm that all evacuation points and refuge points are located on the nodes, and make adjustments if they are not.5.如权利要求1所述的基于改进NSGA-III的溃坝洪水应急疏散路径优先级规划方法,其特征在于:所述步骤S4中,Dijkstra算法计算每个疏散点至所有避难点的最短路径距离过程,包括以下步骤:5. The method for priority planning of emergency evacuation paths for dam-break floods based on the improved NSGA-III according to claim 1, wherein in step S4, the process of calculating the shortest path distance from each evacuation point to all refuge points using the Dijkstra algorithm comprises the following steps:利用Dijkstra算法依次计算所有疏散点至各避难点之间的路径长度,并将疏散点和避难点组成的二元组与其路径长度存入哈希表等缓存结构,以支持后续快速查询与重复使用,避免每次模型迭代重复计算路径;The Dijkstra algorithm is used to sequentially calculate the path lengths between all evacuation points and each refuge point. The tuples consisting of the evacuation point and the refuge point and their path lengths are stored in a cache structure such as a hash table to support subsequent fast query and reuse, avoiding repeated path calculations in each model iteration.所述疏散点和避难点组成的二元组,指由一个疏散点与一个避难点组成的有序配对,用于唯一标识这两个位置之间的对应关系,在路径缓存中,每一个这样的二元组代表一条特定的疏散路径,其对应的最短路径长度被作为数值存入哈希表中。The tuple consisting of an evacuation point and a refuge point refers to an ordered pair consisting of an evacuation point and a refuge point, which is used to uniquely identify the correspondence between the two locations. In the path cache, each such tuple represents a specific evacuation path, and the corresponding shortest path length is stored as a value in the hash table.6.如权利要求1所述的基于改进NSGA-III的溃坝洪水应急疏散路径优先级规划方法,其特征在于:所述步骤S5中,加权K-means聚类初始化方法,包括以下步骤:6. The method for priority planning of emergency evacuation routes for dam-break floods based on improved NSGA-III according to claim 1, wherein in step S5, the weighted K-means clustering initialization method comprises the following steps:根据疏散点的优先级设定权重,执行加权聚类生成初始分组;为每个聚类中心匹配距离最近的避难点作为其默认避难目标,并完成初始疏散点分配,构建 NSGA-III 算法的初始种群解。Weights are set according to the priorities of the evacuation points, and weighted clustering is performed to generate initial groups. The nearest refuge point is matched to each cluster center as its default refuge target, and the initial evacuation point allocation is completed to construct the initial population solution of the NSGA-III algorithm.7. 如权利要求1所述的基于改进NSGA-III的溃坝洪水应急疏散路径优先级规划方法,其特征在于:所述步骤S6中 ,NSGA-III 多目标优化所采用的目标函数包括:7. The method for priority planning of emergency evacuation routes for dam-break floods based on the improved NSGA-III according to claim 1, wherein in step S6, the objective function used in the NSGA-III multi-objective optimization includes:所有疏散路径的总长度;The total length of all evacuation routes;考虑优先级加权的总路径长度;Total path length weighted by priority;高优先级疏散路径的总长度。The total length of high-priority evacuation routes.8. 如权利要求7所述的基于改进NSGA-III的溃坝洪水应急疏散路径优先级规划方法,其特征在于:所述 NSGA-III 多目标优化所采用的目标函数计算过程如下:8. The method for priority planning of emergency evacuation routes for dam-break floods based on the improved NSGA-III algorithm according to claim 7, wherein the objective function calculation process used in the NSGA-III multi-objective optimization is as follows: ;其中,, 决策变量,N为疏散点总数192;综述表示第i个疏散点分配的避难点索引,S为避难点总数32;,疏散点到避难点的最短路径长度;表示洪水优先级权重 (, 对应权重[10, 5, 1]);: 高优先级疏散点集合;为容量约束惩罚项。in, , decision variables, N is the total number of evacuation points 192; Overview represents the index of the refuge point assigned to the i-th evacuation point, and S is the total number of refuge points, 32; , evacuation point Go to the evacuation point The shortest path length; represents the flood priority weight ( , corresponding weights [10, 5, 1]); : High priority evacuation point collection; is the capacity constraint penalty term.9.如权利要求1所述的基于改进NSGA-III的溃坝洪水应急疏散路径优先级规划方法,其特征在于:所述启发式微调策略分为三个阶段:9. The dam-break flood emergency evacuation path priority planning method based on the improved NSGA-III according to claim 1, wherein the heuristic fine-tuning strategy is divided into three stages:阶段一,步骤S7中NSGA-III计算出初步的Pareto解集后,若发现某个高优先级疏散点的路径长度超过某个低或中优先级点,则执行避难点分配交换操作,当中优先级疏散点的路径长度显著大于低优先级疏散点时,亦执行分配交换,以提升高优先级疏散效率;In the first stage, after NSGA-III calculates the preliminary Pareto solution set in step S7, if it is found that the path length of a high-priority evacuation point exceeds that of a low- or medium-priority point, the evacuation point allocation and exchange operation is performed. When the path length of the medium-priority evacuation point is significantly longer than that of the low-priority evacuation point, the allocation and exchange operation is also performed to improve the high-priority evacuation efficiency;阶段二,在阶段一运行完毕后,若发现某个高优先级疏散点的路径长度超过某个低优先级点,则继续执行避难点交换操作,直至无更多可显著改善交换对或达到预设迭代次数,获得优化后Pareto解集;Phase 2: After Phase 1 is completed, if it is found that the path length of a high-priority evacuation point exceeds that of a low-priority point, the refuge point exchange operation will continue until there are no more exchange pairs that can be significantly improved or the preset number of iterations is reached, and the optimized Pareto solution set is obtained;阶段三,在阶段二取得的优化后Pareto解集上,筛选出路径长度超出预设阈值的极端疏散点,遍历所有避难点,筛选出既未超出容量限制且能最大幅度缩短路径的候选避难点,将原分配避难点替换为候选避难点,更新相应路径与避难点分配信息。In the third stage, based on the optimized Pareto solution set obtained in the second stage, extreme evacuation points whose path length exceeds the preset threshold are screened out. All refuge points are traversed to screen out candidate refuge points that do not exceed the capacity limit and can shorten the path to the greatest extent. The original assigned refuge points are replaced with the candidate refuge points, and the corresponding path and refuge point allocation information are updated.10.基于改进NSGA-III的溃坝洪水应急疏散路径优先级规划系统,其特征在于:所述规划系统应用于如权利要求1-9任意一权利要求所述的规划方法中,包括:10. A dam-break flood emergency evacuation route priority planning system based on an improved NSGA-III, characterized in that: the planning system is applied to the planning method according to any one of claims 1 to 9, comprising:参数确定单元,用于获取研究区域的数字高程模型图、卫星影像图、河流分布图、道路网络图和大坝结构参数信息;Parameter determination unit, used to obtain digital elevation model map, satellite image map, river distribution map, road network map and dam structure parameter information of the study area;洪水模拟单元,用于在HEC-RAS中进行二维非恒定流溃坝模拟,并导出模拟结果;Flood simulation unit, used to perform two-dimensional unsteady flow dam break simulation in HEC-RAS and export simulation results;空间选点单元,用于在ArcGIS Pro平台中综合分析洪水影响范围、建筑分布与人口密度,科学选取疏散点与避难点,并划分疏散点优先级类别;The spatial point selection unit is used to comprehensively analyze the flood impact range, building distribution, and population density in the ArcGIS Pro platform, scientifically select evacuation points and refuge points, and classify evacuation point priority categories;路径预计算单元,用于构建道路网络拓扑结构,并通过 Dijkstra 算法缓存所有疏散点与避难点之间的最短路径;Path pre-calculation unit, used to build the road network topology and cache the shortest paths between all evacuation points and refuge points using the Dijkstra algorithm;聚类初始化单元,用于基于加权K-means方法生成初始分组,构建NSGA-III初始种群解;Cluster initialization unit, used to generate initial groups based on the weighted K-means method and construct the initial population solution of NSGA-III;多目标优化单元,用于在NSGA-III多目标优化框架下执行路径优化,获取初始的Pareto解集;The multi-objective optimization unit is used to perform path optimization under the NSGA-III multi-objective optimization framework and obtain the initial Pareto solution set;启发式微调单元,用于对初始解集进行高优先级路径调优与极端路径负载交换优化;A heuristic fine-tuning unit is used to optimize the high-priority paths and the extreme path load exchange of the initial solution set;结果可视化单元,用于将疏散点与避难点之间的最优Pareto解集分配结果导出文件,在ArcGIS Pro平台中展示各优先级疏散路径分布图及疏散压力热力图。The result visualization unit is used to export the optimal Pareto solution set allocation results between evacuation points and refuge points to a file, and display the distribution map of evacuation paths of various priorities and the evacuation pressure heat map on the ArcGIS Pro platform.
CN202511053758.6A2025-07-302025-07-30Dam break flood emergency evacuation path planning method and system based on improved NSGA-IIIActiveCN120562674B (en)

Priority Applications (1)

Application NumberPriority DateFiling DateTitle
CN202511053758.6ACN120562674B (en)2025-07-302025-07-30Dam break flood emergency evacuation path planning method and system based on improved NSGA-III

Applications Claiming Priority (1)

Application NumberPriority DateFiling DateTitle
CN202511053758.6ACN120562674B (en)2025-07-302025-07-30Dam break flood emergency evacuation path planning method and system based on improved NSGA-III

Publications (2)

Publication NumberPublication Date
CN120562674Atrue CN120562674A (en)2025-08-29
CN120562674B CN120562674B (en)2025-10-03

Family

ID=96826513

Family Applications (1)

Application NumberTitlePriority DateFiling Date
CN202511053758.6AActiveCN120562674B (en)2025-07-302025-07-30Dam break flood emergency evacuation path planning method and system based on improved NSGA-III

Country Status (1)

CountryLink
CN (1)CN120562674B (en)

Citations (1)

* Cited by examiner, † Cited by third party
Publication numberPriority datePublication dateAssigneeTitle
US20240386015A1 (en)*2015-10-282024-11-21Qomplx LlcComposite symbolic and non-symbolic artificial intelligence system for advanced reasoning and semantic search

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication numberPriority datePublication dateAssigneeTitle
US20240386015A1 (en)*2015-10-282024-11-21Qomplx LlcComposite symbolic and non-symbolic artificial intelligence system for advanced reasoning and semantic search

Also Published As

Publication numberPublication date
CN120562674B (en)2025-10-03

Similar Documents

PublicationPublication DateTitle
Sun et al.Modeling urban land use change and urban sprawl: Calgary, Alberta, Canada
WO2020233152A1 (en)Urban building space data-based built-up area boundary identification method and device
CN107180450A (en)A kind of algorithm of the river valley transverse shape based on DEM
CN110992458A (en)Large-scale oblique photography model organization and scheduling method
CN105160889B (en)More source points collaboration leading method of road network traffic flow under a kind of urban waterlogging scene
CN109992923B (en)Phased power transmission line path planning method based on variable resolution cost surface
CN110046213B (en)Power line selection method considering path distortion correction and cross crossing correction
KR101394976B1 (en)Generating methodology of multi-scale model for the attached cadastral map
KR20100136604A (en) 3D Terrain Image Real-Time Visualization System and Its Method
CN113724279B (en)System, method, equipment and storage medium for automatically dividing traffic cells into road networks
CN104200044A (en)GIS (geographic information system)-based three-dimensional power transmission line path selection method
CN111080080A (en)Method and system for estimating risk of geological disaster of villages and small towns
CN114840896B (en)Waterlogging and ponding simulation analysis method based on urban road BIM
CN120374665A (en)Automatic segmentation method and system based on deep foundation pit point cloud model
CN116434509A (en) A remote monitoring and early warning system for dams
CN120562674B (en)Dam break flood emergency evacuation path planning method and system based on improved NSGA-III
CN114969944A (en)High-precision road DEM construction method
CN114386536A (en)Region determination method, device, computing equipment and storage medium
CN113987969A (en)Land-water dynamic simulation model of multi-elevation scale water flow network
CN116579518A (en) A method for identifying target areas for water ecological space protection and restoration
CN114842163A (en)Multi-scale dynamic gridding model construction method for disaster assessment
CN112487131A (en)PostGIS calculation land utilization homogeneity degree method based on open source space database
CN119963762B (en) Dynamic optimization method of urban multi-level low-altitude airspace functional areas enhanced by spatiotemporal knowledge
CN118013637B (en) A decision-making method for resilient urban design solutions for water disasters
Sulaiman et al.Integration of geographic information system (GIS) and hydraulic modelling to simulate floodplain inundation level for Bandar Segamat

Legal Events

DateCodeTitleDescription
PB01Publication
PB01Publication
SE01Entry into force of request for substantive examination
SE01Entry into force of request for substantive examination
GR01Patent grant

[8]ページ先頭

©2009-2025 Movatter.jp