Urban street block wind disaster comprehensive risk early warning method and device

Abstract

The application relates to the technical field of disaster early warning, in particular to a city block wind disaster comprehensive risk early warning method and device, wherein the method comprises the following steps: based on a pre-established physical inspiration-data driven learning framework, a target city block wind field is reconstructed in real time, and a real-time wind field of the target city block is obtained; based on a pre-constructed multi-disaster carrier wind disaster risk assessment model library, a corresponding sub-model of the real-time wind field is inquired; according to the real-time wind field and the sub-model, a wind disaster disaster carrier damage level and a comprehensive risk level spatial distribution result of the target city block are calculated, an early warning prompt is generated, and risk early warning is carried out. The application can calculate and output the city block disaster carrier damage level and the comprehensive risk level spatial distribution result, and based on the result, an early warning prompt is generated, different types of disaster bodies in the wind disaster are more comprehensively and accurately evaluated, and effective disaster prevention and mitigation measures are provided.

Description

Technical Field

[0001] This application relates to the field of disaster early warning technology, and in particular to a method and device for comprehensive risk early warning of wind-induced disasters in urban blocks. Background Technology

[0002] In recent years, frequent extreme wind events have led to various community safety incidents, including building collapses, window detachments from high-rise buildings, power and communication line outages, and fallen trees, seriously threatening the safety of urban blocks. Therefore, there is an urgent need to conduct comprehensive risk assessment research on wind damage to urban blocks to support real-time emergency decision-making, guide urban safety design, and ensure the safety of urban communities.

[0003] In related technologies, wind-induced disaster risk assessment techniques mostly focus on single disaster-bearing carriers in urban blocks (such as power transmission towers, power cables, buildings, building exteriors, and street trees). For example, the National Meteorological Center (China Meteorological Administration) has published a method for predicting the probability of wind damage to urban street trees based on the GALES model. This method uses wind speed forecast data from the China Meteorological Administration's smart grid with a spatial resolution of 5 kilometers, combined with bilinear interpolation, to obtain predicted urban wind speeds. Furthermore, it uses the GALES model to calculate the critical wind speeds for breakage and collapse of different tree species, thus obtaining the probability of damage to urban trees.

[0004] However, among the related technologies, the wind field calculation accuracy is low and the calculation speed is slow, making it impossible to quickly and effectively realize the fine real-time reconstruction of wind fields in urban blocks. Furthermore, it is impossible to achieve a comprehensive evaluation of the wind-induced risks of the complex and diverse disaster-bearing carriers in urban blocks in real-world scenarios. It also lacks a wind-induced disaster risk early warning system with a visual interface, quantitative results, and practical applications, which urgently needs to be addressed. Summary of the Invention

[0005] This application provides a method and device for comprehensive risk early warning of wind-induced disasters in urban blocks, in order to solve the problems in related technologies, such as low accuracy and slow calculation speed of wind field calculation, inability to quickly and effectively realize fine real-time reconstruction of wind field in urban blocks, inability to achieve comprehensive evaluation of wind-induced risks of complex and diverse disaster-bearing carriers in real-world scenarios, and lack of interface visualization, quantitative results, and practically applicable wind-induced disaster risk early warning.

[0006] The first aspect of this application provides a comprehensive risk early warning method for wind-induced disasters in urban blocks, comprising the following steps: based on a pre-established physical heuristic-data-driven learning framework, the wind field of a target urban block is reconstructed in real time to obtain the real-time wind field of the target urban block; based on a pre-built multi-disaster-bearing carrier wind-induced disaster risk assessment model library, the disaster-bearing carrier sub-model corresponding to the real-time wind field is queried; based on the real-time wind field and the disaster-bearing carrier sub-model, the spatial distribution results of the damage level of the wind-induced disaster-bearing carrier and the spatial distribution results of the comprehensive risk level of the target urban block are calculated to generate an early warning prompt and conduct risk warning.

[0007] Optionally, in one embodiment of this application, the real-time reconstruction of the wind field of a target urban block based on a pre-established physics-inspired data-driven learning framework to obtain the real-time wind field of the target urban block includes: reconstructing a deep learning model of flow field physical characteristics based on a target neural network; capturing the fluid physics mechanism and flow field structure characteristics of the urban block based on the simulated wind speed at feature points and a preset wind field CFD dataset to reconstruct the initial wind field on the simulated dataset; using sparse measured data at the feature points as input, calculating the real-time wind speed at each point in the urban block space based on the fluid physics mechanism and the flow field structure characteristics to obtain the initial wind field of the urban block based on the real-time wind speed; and correcting the initial wind field based on the modeling error driven by the sparse measured data to obtain the real-time wind field of the urban block.

[0008] Optionally, in one embodiment of this application, before constructing the multi-disaster-bearing carrier wind-induced disaster risk assessment model library for the urban block, the method further includes: identifying the potential damage types of the disaster-bearing carriers of the target urban block based on the wind-induced disaster-bearing carriers; and constructing the multi-disaster-bearing carrier wind-induced disaster risk assessment model library for the urban block based on the real-time wind field and the potential damage types of the disaster-bearing carriers, combined with a target probability distribution model, using critical wind speed and exceedance probability as measurement criteria.

[0009] Optionally, in one embodiment of this application, the step of calculating the spatial distribution results of the wind-induced disaster carrier damage level and comprehensive risk level of the target urban block based on the real-time wind field and the disaster carrier sub-model includes: obtaining at least one key area of ​​the urban block; and assigning weights to the disaster carrier sub-models in the multi-disaster carrier wind-induced disaster risk assessment model library based on the at least one key area to obtain the spatial distribution results of the wind-induced disaster carrier damage level and comprehensive risk level of the urban block.

[0010] Optionally, in one embodiment of this application, the step of calculating the spatial distribution results of the wind-induced disaster carrier damage level and the spatial distribution results of the comprehensive risk level of the target urban block based on the real-time wind field and the disaster carrier sub-model to generate an early warning prompt includes: obtaining actual sparse monitoring data of the urban block; calculating and outputting the spatial distribution results of the wind-induced disaster carrier damage level and the spatial distribution results of the comprehensive risk level of the target urban block based on the real-time wind field and the disaster carrier sub-model to generate the early warning prompt.

[0011] A second aspect of this application provides a comprehensive risk early warning device for wind-induced disasters in urban blocks, comprising: a first construction module, used to reconstruct the wind field of a target urban block in real time based on a pre-established physical heuristic-data-driven learning framework to obtain the real-time wind field of the target urban block; a query module, used to query the sub-model corresponding to the real-time wind field based on a pre-established multi-disaster-bearing carrier wind-induced disaster risk assessment model library; and an early warning module, used to calculate the spatial distribution results of damage levels of wind-induced disaster-bearing carriers and the spatial distribution results of comprehensive risk levels of the target urban block based on the real-time wind field and the sub-model, so as to generate an early warning prompt and conduct risk warning.

[0012] Optionally, in one embodiment of this application, the first construction module includes: a construction unit, configured to reconstruct a deep learning model of flow field physical characteristics based on a target neural network, and capture the fluid physics mechanism and flow field structure characteristics of the urban block according to the simulated wind speed at the feature points of the urban block and a preset wind field CFD dataset; a calculation unit, configured to take sparse measured data at the feature points as input, and calculate the real-time wind speed at each point in the urban block according to the fluid physics mechanism and the flow field structure characteristics, so as to obtain the initial wind field of the urban block according to the real-time wind speed; and a correction unit, configured to correct the initial wind field based on the modeling error driven by sparse measured data, so as to obtain the real-time wind field of the urban block.

[0013] Optionally, in one embodiment of this application, it further includes: an identification module, used to identify the potential damage types of the wind-borne carriers of the target urban block based on the wind-borne carriers of the target urban block before constructing the multi-disaster-bearing carrier wind-induced disaster risk assessment model library of the urban block; and a second construction module, used to construct the multi-disaster-bearing carrier wind-induced disaster risk assessment model library of the urban block based on the real-time wind field and the potential damage types of the disaster-bearing carriers combined with the target probability distribution model, using critical wind speed and exceedance probability as measurement criteria.

[0014] Optionally, in one embodiment of this application, the early warning module includes: a first acquisition unit, configured to acquire at least one key area of ​​the urban block; and a weighting unit, configured to assign weights to sub-models in the multi-disaster-bearing carrier wind-induced disaster risk assessment model library based on the at least one key area, so as to obtain the spatial distribution results of the damage level of the wind-induced disaster-bearing carrier and the spatial distribution results of the comprehensive risk level of the urban block.

[0015] Optionally, in one embodiment of this application, the early warning module includes: a second acquisition unit, used to acquire actual sparse monitoring data of the urban block; and a generation unit, used to calculate and output the spatial distribution results of wind-induced disaster carrier damage level and comprehensive risk level of the target urban block based on the real-time wind field and the disaster carrier sub-model, so as to generate the early warning prompt.

[0016] A third aspect of this application provides an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the comprehensive risk early warning method for wind-induced disasters in urban blocks as described in the above embodiments.

[0017] A fourth aspect of this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method for comprehensive risk warning of wind-induced disasters in urban blocks.

[0018] A fifth aspect of this application provides a computer program product, including a computer program that, when executed, is used to implement the above-described method for comprehensive risk early warning of wind-induced disasters in urban blocks.

[0019] This application's embodiments can construct a two-stage deep learning method inspired by physics and driven by data, and a multi-carrier wind-induced disaster risk assessment model library. It calculates and outputs the spatial distribution results of damage levels and comprehensive risk levels of urban street-level carriers, and provides early warnings based on these results. Thus, it achieves a real-time, refined inversion of urban street wind fields by fusing a deep learning model of flow field physical characteristics with error correction technology based on sparse measured data for wind field real-time reconstruction. It also constructs a multi-carrier wind-induced disaster risk assessment model library using a general construction method for urban street wind-induced disaster risk assessment models, enabling rapid calculation of the spatial distribution of damage probability and comprehensive risk levels of urban street-level carriers affected by wind-induced disasters. This provides real-time decision-making suggestions for decision-makers, contributing to scientific decision-making and precise prevention and control. Therefore, it solves the problems in related technologies, such as low wind field calculation accuracy, slow calculation speed, inability to quickly and effectively achieve refined real-time reconstruction of urban street wind fields, inability to comprehensively evaluate the complex and diverse wind-induced risks of urban street-level carriers in real-world scenarios, and lack of user-visualized interfaces, quantitative results, and practically applicable wind-induced disaster risk early warning systems.

[0020] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0021] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein:

[0022] Figure 1 This is a flowchart of a comprehensive risk early warning method for wind-induced disasters in urban blocks, provided according to an embodiment of this application.

[0023] Figure 2 This is a flowchart illustrating the construction of a multi-hazard-bearing carrier wind-induced disaster risk assessment model library according to one embodiment of this application;

[0024] Figure 3 This is a schematic diagram illustrating the comprehensive risk of wind-induced disasters in urban blocks according to one embodiment of this application;

[0025] Figure 4 This is a schematic diagram illustrating the framework of a data-model hybrid-driven comprehensive risk early warning system for wind-induced disasters in urban blocks, representing one embodiment of this application.

[0026] Figure 5 This is a schematic diagram of the structure of the urban street wind-induced disaster comprehensive risk early warning device according to an embodiment of this application;

[0027] Figure 6 This is a schematic diagram of the structure of an electronic device according to an embodiment of this application.

[0028] Figure label:

[0029] 10-Urban Street Wind-Induced Disaster Comprehensive Risk Early Warning Device: 100-First Construction Module, 200-Query Module and 300-Early Warning Module; 601-Memory, 602-Processor and 603-Communication Interface. Detailed Implementation

[0030] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0031] The following describes a method and apparatus for comprehensive risk early warning of wind-induced disasters in urban blocks, based on embodiments of this application, with reference to the accompanying drawings. Addressing the issues of low accuracy and slow calculation speed in the related technologies mentioned in the background section, which fail to quickly and effectively achieve refined real-time reconstruction of wind fields in urban blocks and cannot comprehensively evaluate the wind-induced risks of diverse and complex disaster-bearing carriers in real-world scenarios, and lack visually appealing, quantitatively quantifiable, and practically applicable wind-induced disaster risk early warning methods, this application provides a method for comprehensive risk early warning of wind-induced disasters in urban blocks. This method constructs a two-stage deep learning method inspired by physics and driven by data, and a multi-disaster-bearing carrier wind-induced disaster risk assessment model library. It calculates and outputs the spatial distribution results of damage levels and comprehensive risk levels of disaster-bearing carriers in urban blocks, and provides early warning prompts based on these results. This invention achieves a real-time, refined inversion of wind fields in urban blocks by integrating a deep learning model of flow field physical characteristics with error correction technology based on sparse measured data. A multi-carrier wind-induced disaster risk assessment model library is constructed using a general construction method for urban block wind-induced disaster risk assessment models. This enables rapid calculation of the spatial distribution of damage probability and comprehensive risk level of wind-induced disaster carriers in urban blocks, providing real-time decision-making suggestions and supporting scientific decision-making and precise prevention and control. This addresses the problems of low wind field calculation accuracy and slow calculation speed in related technologies, which hinder the rapid and effective real-time refined reconstruction of urban block wind fields, the inability to comprehensively evaluate the complex and diverse wind-induced risks of urban block carriers in real-world scenarios, and the lack of user-visualized interfaces, quantitative results, and practically applicable wind-induced disaster risk early warning systems.

[0032] Specifically, Figure 1 A flowchart illustrating a comprehensive risk early warning method for wind-induced disasters in urban blocks, provided as an embodiment of this application.

[0033] like Figure 1 As shown, the comprehensive risk early warning method for wind-induced disasters in this urban area includes the following steps:

[0034] In step S101, based on a pre-established physical-inspired data-driven learning framework, the wind field of the target city block is reconstructed in real time to obtain the real-time wind field of the target city block.

[0035] It is understandable that "target city blocks" here refers to city blocks that require comprehensive risk warnings for wind-induced disasters. Real-time wind field refers to the distribution of wind field parameters such as wind direction and speed at the current moment. Because wind fields are dynamically changing, real-time wind field data is of great significance for weather forecasting.

[0036] In some embodiments, real-time wind field data can be acquired through various means, such as official websites of meteorological departments, professional meteorological software or applications, satellite cloud images, or other remote sensing data. However, since wind fields are dynamic, in order to understand wind field changes in a timely manner and issue corresponding warnings, embodiments of this application can pre-establish a physical heuristic-data-driven learning framework (method). This physical heuristic-data-driven learning framework can be used to reconstruct the target city blocks in real time, thereby obtaining the real-time wind field of the target city blocks.

[0037] For example, a two-stage deep learning method inspired by physics and driven by data can be established to reconstruct wind fields in complex urban blocks with high-dimensional input uncertainty in real time. Furthermore, this two-stage deep learning method can also integrate a deep learning model of flow field physical characteristics with a modeling error correction method driven by sparse measured data, which helps ensure the accuracy of the obtained real-time wind field results.

[0038] The process will now be explained in more detail.

[0039] Optionally, in one embodiment of this application, the wind field of a target urban block is reconstructed in real time based on a pre-established physics-inspired data-driven learning framework to obtain the real-time wind field of the target urban block. This includes: reconstructing a deep learning model of the physical characteristics of the flow field based on the target neural network; capturing the fluid physics mechanism and flow field structure characteristics of the urban block based on the simulated wind speed at the feature points of the urban block and a preset wind field CFD dataset to reconstruct the initial wind field on the simulated dataset; using sparse measured data at the feature points as input, calculating the real-time wind speed at each point in the urban block space based on the fluid physics mechanism and flow field structure characteristics to obtain the initial wind field of the urban block based on the real-time wind speed; and correcting the initial wind field based on the modeling error driven by the sparse measured data to obtain the real-time wind field of the urban block.

[0040] It is understandable that the preset wind field CFD dataset here can be understood as a pre-generated wind field CFD dataset. A wind field CFD dataset can be understood as a collection of data specifically used for wind field simulation and analysis. It contains various parameters of wind field flow and simulation results, and can be used to analyze wind resource assessment, wind farm design, building wind environment, etc.

[0041] In some embodiments, the constructed two-stage deep learning method, based on physical inspiration and data-driven approaches, can integrate a deep learning model of flow field physical characteristics with a modeling error correction method driven by sparse measured data. Deep learning can directly establish end-to-end computational models, such as deep learning models of flow field physical characteristics, allowing for full consideration of fluid physics mechanisms in network architecture design, network input features, and output selection to capture significant features of CFD modeling. Meanwhile, data-driven error correction techniques can fill the remaining gaps between computational results and measured data, capturing uncertainties existing under real physical conditions.

[0042] Among them, the flow field reconstruction model based on neural networks, namely the deep learning model of flow field physical characteristics, can, but is not limited to, utilize a pre-generated wind field CFD dataset, take the simulated wind speed at N measurement points as input, and learn the physical mechanisms and flow field structure characteristics contained in the numerical calculation results through neural networks (such as fully connected neural network models, physical information neural network models, etc.), thereby inverting and calculating the real-time wind speed at each point in the entire field, thus realizing the rapid reconstruction of the wind field.

[0043] It should be noted that the pre-generated wind field CFD dataset in this embodiment can be generated, but is not limited to, by using numerical simulation tools, setting different inflow conditions, and running simulation examples in batches. Specifically, it can be generated by those skilled in the art according to the actual situation; this is only an illustrative example and does not impose any specific limitations.

[0044] Furthermore, embodiments of this application can also utilize a modeling error correction method driven by sparse measured data to capture errors caused by CFD modeling simplification and other uncertainties under real physical conditions. For example, a measured pseudo-dataset can be constructed using monitoring data from a target urban block at a limited number of points to assist the neural network model in point-to-point supervised learning, filling the remaining gaps between the calculation results and the measured data. This allows for the accurate reconstruction of the actual flow field of the target urban block, improving the accuracy of the reconstructed real-time wind field results.

[0045] In this embodiment of the application, when acquiring the real-time wind field of a target urban block, a deep learning model of flow field physical characteristics can be integrated with a modeling error correction method driven by sparse measured data. While fully considering the fluid physics mechanism to capture the significant features of CFD modeling, the remaining gap between the calculation results and the measured data is filled by the data-driven error correction technology, capturing the uncertainties existing under real physical conditions, realizing the real-time refined inversion of the wind field of the urban block, and effectively improving the accuracy of the obtained real-time wind field.

[0046] Step S102: Based on the pre-built multi-disaster-bearing carrier wind-induced disaster risk assessment model library, query the disaster-bearing carrier sub-model corresponding to the real-time wind field.

[0047] Those skilled in the art will understand that a multi-hazard-bearing carrier wind-induced disaster risk assessment model library can be understood as a comprehensive system designed to quantitatively assess the risk of different types of hazard-bearing carriers in wind-induced disasters through various models and methods. This type of model library typically contains multiple sub-models, each designed for different types of hazard-bearing carriers or disaster characteristics. Hazard-bearing carriers may include buildings, infrastructure, agriculture, forestry, densely populated areas, etc.

[0048] For example, a multi-carrier wind-induced disaster risk assessment model library may include, but is not limited to, building risk assessment models used to assess the structural response of buildings under wind loads, including displacement, stress, acceleration, etc. It can also assess the vulnerability of buildings under different wind levels based on the building's structural characteristics, material properties, and historical disaster data.

[0049] For example, infrastructure risk assessment models are used to evaluate the impact of wind-induced disasters on power grids, such as line outages and substation failures, as well as on transportation facilities such as roads, bridges, and airports. Risk assessment models for densely populated areas are used to assess the risk and possible causes of casualties in wind-induced disasters, as well as the evacuation capacity and efficiency of densely populated areas during such disasters.

[0050] Furthermore, based on this constructed multi-hazard-bearing carrier wind-induced disaster risk assessment model library, a comprehensive risk assessment method for wind-induced disasters in urban blocks can also be established. For example, historical data on wind-induced disasters, characteristic data of hazard-bearing carriers, and socio-economic data can be collected; appropriate models can be selected and constructed according to the data types and assessment needs; the input parameters of the models can be set according to the characteristics of the hazard-bearing carriers and the characteristics of the disasters; the models can be run to conduct risk assessments and obtain the risk level or loss prediction of the hazard-bearing carriers under different wind levels.

[0051] Therefore, when constructing a multi-hazard-bearing carrier wind-induced disaster risk assessment model library to conduct comprehensive risk assessments of wind-induced disasters in urban blocks, appropriate models can be built for different hazard-bearing carriers to improve the accuracy of model prediction results. Thus, when utilizing this model, one can first query the hazard-bearing carrier sub-model corresponding to the real-time wind field, and then perform further calculations.

[0052] This application's embodiments can construct a risk assessment model library for wind-induced disasters involving multiple disaster-bearing carriers, and conduct a comprehensive risk assessment of various disaster-bearing carriers in a city by querying the corresponding disaster-bearing carrier sub-models. By constructing and applying such a model library, the risks of different types of disaster-bearing bodies in wind-induced disasters can be assessed more comprehensively and accurately, providing strong support for the formulation of effective disaster prevention and mitigation measures.

[0053] Optionally, in one embodiment of this application, before constructing the multi-disaster-bearing carrier wind-induced disaster risk assessment model library for the target urban block, the method further includes: identifying the potential damage types of the disaster-bearing carriers of the target urban block based on the wind-induced disaster-bearing carriers of the target urban block; and constructing the multi-disaster-bearing carrier wind-induced disaster risk assessment model library for the urban block based on the real-time wind field and the potential damage types of the disaster-bearing carriers combined with the target probability distribution model, using the critical wind speed and the exceedance probability as measurement criteria.

[0054] Based on the descriptions of other embodiments, it is understood that when conducting risk assessments on target urban blocks, a multi-hazard-bearing carrier wind-induced disaster risk assessment model library can be constructed first for subsequent use. Furthermore, before constructing the model, the types of content and measurement criteria involved in the model can be set or selected.

[0055] In some embodiments, this application may first identify the possible damage types of the disaster-bearing carriers when wind-induced disasters occur in the target urban blocks, then use the critical wind speed and the probability of exceeding the threshold as the measurement criteria for the damage types, and then combine the target probability distribution model to construct a multi-disaster-bearing carrier wind-induced disaster risk assessment model library for urban blocks.

[0056] For example, Figure 2 This is a flowchart illustrating the construction process of a multi-hazard-bearing carrier wind-induced disaster risk assessment model library according to one embodiment of this application. Figure 2 As shown, its core may include, but is not limited to, technologies for identifying the carriers and damage types of wind-induced disasters in urban blocks and general methods for constructing risk assessment models for wind-induced disasters in urban blocks.

[0057] Among them, the technology for identifying the carriers and damage types of wind-induced disasters in urban blocks can, but is not limited to, sorting out the carriers that may exist in typical urban blocks through domestic and foreign literature surveys and case analysis of typical wind-induced disasters in urban blocks, and then determining the possible damage types based on the carriers.

[0058] Next, a general construction method for urban street wind-induced disaster risk assessment models can be determined. This means that for a specific type of damage to a particular disaster-bearing carrier, the criteria for determining the type of damage can be clearly defined, such as critical wind speed and exceedance probability. Furthermore, wind-induced disaster risk assessment models can be established by combining probability distribution models such as Weibull distribution and normal distribution, but not limited to these.

[0059] Among them, the carriers of wind-induced disasters in urban blocks include, but are not limited to: pedestrians, trees, buildings and their surrounding structures, infrastructure (such as: power transmission towers, power transmission cables, communication cables, gas pipelines, etc.). Table 1 shows the possible damage types of some of the carriers, which can be represented as follows:

[0060] Table 1

[0061]

[0062]

[0063] Taking the building's exterior window as an example, the possible types of damage to this structure include, but are not limited to, "breakage" and "detachment." The criterion for determining "breakage" is a critical wind speed ≥ a1 m / s, with a corresponding exceedance probability of "b1." The criterion for determining "detachment" is a critical wind speed ≥ a2 m / s, with a corresponding exceedance probability of "b2." Furthermore, by combining this with the Weibull distribution, a risk assessment model for the "breakage" and "detachment" of building exterior windows can be established.

[0064] This allows us to obtain risk assessment models for various damage types of wind-induced disasters on multiple disaster-bearing carriers in urban blocks, and further construct a risk assessment model library for wind-induced disasters on multiple disaster-bearing carriers.

[0065] Step S103: Calculate the spatial distribution results of wind-induced disaster damage level and comprehensive risk level of the target urban block based on the real-time wind field and disaster-bearing carrier sub-model, so as to generate early warning prompts and conduct risk warnings.

[0066] As one possible approach, after establishing a risk assessment model library for wind-induced disasters involving multiple disaster-bearing carriers and finding the corresponding disaster-bearing carrier sub-models for real-time wind fields, the obtained real-time wind fields can be used as input to determine the level of damage to the disaster-bearing carriers, i.e., the probability of damage to the disaster-bearing carriers and the spatial distribution of comprehensive risks.

[0067] For example, using the real-time wind field of the target city block as input, the spatial distribution results of the damage level of the disaster-bearing carrier and the spatial distribution results of the comprehensive risk level of the target city block are calculated and output.

[0068] Furthermore, after obtaining the spatial distribution results of the damage level and comprehensive risk level of the disaster-bearing carriers in the target urban blocks, the embodiments of this application can generate certain early warning prompts based on the results, so as to provide early warnings to the target urban blocks, allowing the public to understand the possibility and scope of the disaster in advance, thereby taking appropriate preventive measures to reduce casualties and property losses, and helping the government to formulate more scientific and reasonable disaster prevention and mitigation measures and emergency plans, thereby improving the overall efficiency of disaster prevention and mitigation.

[0069] The process will now be explained in more detail.

[0070] Optionally, in one embodiment of this application, the spatial distribution results of wind-induced disaster carrier damage level and comprehensive risk level of the target urban block are calculated based on the real-time wind field and the disaster carrier sub-model, including: obtaining at least one key area of ​​the urban block; and assigning weights to the disaster carrier sub-models in the multi-disaster carrier wind-induced disaster risk assessment model library based on at least one key area to obtain the spatial distribution results of wind-induced disaster carrier damage level and comprehensive risk level of the target urban block.

[0071] Based on the descriptions of other embodiments, it is understood that, using real-time wind field as input, the spatial distribution results of damage levels of disaster-bearing carriers and the spatial distribution results of comprehensive risk levels of target urban blocks can be calculated according to the disaster-bearing carrier sub-models in the multi-disaster-bearing carrier wind-induced disaster risk assessment model library.

[0072] Furthermore, when calculating the comprehensive risk of wind-induced disasters in a target urban block, the embodiments of this application may consider key areas of concern in the urban block, and then use weighting methods such as fuzzy mathematics to determine the weights of various sub-models of each key area in the multi-disaster-bearing carrier wind-induced disaster risk assessment model library, so as to realize the real-time calculation of the probability of wind-induced risk and the comprehensive risk level of each disaster-bearing carrier in the target urban block.

[0073] Additionally, to provide a clearer view of the risk status, embodiments of this application may also include a comprehensive risk grading criterion table. Table 2 is a comprehensive risk grading criterion table from one embodiment of this application, which can be represented as follows:

[0074] Table 2

[0075] Overall Risk Value <![CDATA[0-n1]]> <![CDATA[n2-n3]]> <![CDATA[n3-n4]]> <![CDATA[n4-n5]]> <![CDATA[n5-1]]>

[0076] In calculating the wind-induced disaster risk of urban blocks, the embodiments of this application can assign different weights to key areas of concern in urban blocks, which helps to grasp the key points in a timely and effective manner when conducting early warning or disaster relief, and make appropriate disaster relief decisions, thereby improving rescue efficiency.

[0077] Optionally, in one embodiment of this application, the spatial distribution results of the damage level of the wind-induced disaster-bearing carrier and the spatial distribution results of the comprehensive risk level of the target urban block are calculated based on the real-time wind field and the disaster-bearing carrier sub-model to generate an early warning prompt, including: obtaining actual sparse monitoring data of the urban block; calculating and outputting the spatial distribution results of the damage level of the wind-induced disaster-bearing carrier and the spatial distribution results of the comprehensive risk level of the target urban block based on the real-time wind field and the disaster-bearing carrier sub-model to generate an early warning prompt.

[0078] In actual implementation, in order to facilitate the prevention of wind-induced disasters, the embodiments of this application can also generate certain early warning prompts based on the spatial distribution results of the damage level of the wind-induced disaster-bearing carriers and the spatial distribution results of the comprehensive risk level of the target urban blocks, so as to provide early warnings or other treatments to the urban public based on the early warning prompts.

[0079] For example, during implementation, the real-time wind field of the target urban block can be obtained, combined with the corresponding sub-models of the disaster-bearing carriers in the multi-disaster-bearing carrier wind-induced disaster risk assessment model library and the general construction method of the urban block wind-induced disaster risk assessment model, to calculate and output the spatial distribution results of the damage level of the disaster-bearing carriers of the target urban block and the spatial distribution results of the comprehensive risk level.

[0080] After obtaining the spatial distribution results of the damage level and comprehensive risk level of the wind-induced disaster-bearing carriers in the target city blocks, certain early warning prompts can be generated based on them. These prompts can be used to issue early warnings for the target city blocks or applied to the development of a comprehensive risk early warning system for wind-induced disasters in urban blocks.

[0081] Figure 3 This is a schematic diagram illustrating the comprehensive risk of wind-induced disasters in an urban street at a specific moment, along a horizontal cross-section, according to an embodiment of this application. Figure 3 As shown, when applied to the development of a comprehensive risk early warning system for wind-induced disasters in urban blocks, the risk level of each area in the urban block can be clearly seen.

[0082] The application will be described in detail below with a specific embodiment.

[0083] Figure 4 This is a schematic diagram illustrating the framework of a "data-model" hybrid-driven comprehensive risk early warning system for wind-induced disasters in urban blocks, according to one embodiment of this application. Figure 4 As shown:

[0084] First, a rapid reconstruction method for urban street wind fields is used to obtain real-time wind fields in urban streets. This includes, but is not limited to, constructing a deep learning model of flow field physical characteristics using CFD datasets and neural network models, and proposing an error correction method driven by measured data using sparse measured datasets and neural network models, so as to achieve real-time and refined inversion of urban street wind fields.

[0085] Next, using real-time wind field as input, and based on key areas of urban blocks, the comprehensive risk assessment method for wind-induced disasters in urban blocks is used to assign weights to each sub-model of the multi-disaster-bearing carrier wind-induced disaster risk assessment model library, thereby determining the weights of each sub-model in the multi-disaster-bearing carrier wind-induced disaster risk assessment model library, so as to realize the real-time calculation of the comprehensive risk of wind-induced disasters in urban blocks.

[0086] Finally, the spatial distribution map of damage levels of disaster-bearing carriers in urban blocks and the spatial distribution map of comprehensive risk levels in urban blocks are calculated and output, and early warning prompts are generated based on the spatial distribution maps.

[0087] The comprehensive risk early warning method for wind-induced disasters in urban blocks proposed in this application can construct a two-stage deep learning method based on physical inspiration and data-driven approaches, and a multi-carrier wind-induced disaster risk assessment model library. It calculates and outputs the spatial distribution results of damage levels and comprehensive risk levels of carriers in urban blocks, and provides early warnings based on these results. This achieves real-time, refined inversion of urban block wind fields by integrating a deep learning model of flow field physical characteristics with error correction technology based on sparse measured data for modeling. A multi-carrier wind-induced disaster risk assessment model library is constructed using a general construction method for urban block wind-induced disaster risk assessment models, enabling rapid calculation of the spatial distribution of damage probability and comprehensive risk levels of carriers in urban blocks. This provides real-time decision-making suggestions for decision-makers, contributing to scientific decision-making and precise prevention and control. Therefore, this method solves the problems in related technologies, such as low wind field calculation accuracy, slow calculation speed, inability to quickly and effectively achieve refined real-time reconstruction of urban block wind fields, inability to comprehensively evaluate the complex and diverse wind-induced risks of carriers in urban blocks in real-world scenarios, and lack of user-visualized interfaces, quantitative results, and practically applicable wind-induced disaster risk early warning systems.

[0088] Next, referring to the accompanying drawings, we describe the comprehensive risk early warning device for wind-induced disasters in urban blocks according to the embodiments of this application.

[0089] Figure 5 This is a schematic diagram of the structure of the urban street wind-induced disaster comprehensive risk early warning device according to an embodiment of this application.

[0090] like Figure 5 As shown, the urban street block wind-induced disaster comprehensive risk early warning device 10 includes: a first construction module 100, a query module 200, and an early warning module 300.

[0091] The first construction module 100 is used to reconstruct the wind field of the target city block in real time based on a pre-established physical heuristic-data-driven learning framework, so as to obtain the real-time wind field of the target city block.

[0092] The query module 200 is used to query the sub-models corresponding to the real-time wind field based on the pre-built multi-disaster-bearing carrier wind-induced disaster risk assessment model library.

[0093] The early warning module 300 is used to calculate the spatial distribution results of the damage level of the wind-induced disaster-bearing carrier and the spatial distribution results of the comprehensive risk level of the target urban block based on the real-time wind field and sub-model, so as to generate early warning prompts and conduct risk warnings.

[0094] Optionally, in one embodiment of this application, the first construction module 100 includes: a construction unit, a calculation unit, and a correction unit.

[0095] Among them, the building unit is used to reconstruct the deep learning model of the flow field physical characteristics based on the target neural network, and capture the fluid physical mechanism and flow field structure characteristics of the urban block according to the simulated wind speed at the feature point of the urban block and the preset wind field CFD dataset.

[0096] The computing unit is used to take sparse measured data at feature points as input, and calculate the real-time wind speed at each point in the urban block space based on the fluid physics mechanism and flow field structure characteristics, so as to obtain the initial wind field of the urban block based on the real-time wind speed.

[0097] The correction unit is used to correct the flow field based on the modeling error driven by sparse measured data, so as to obtain the real-time wind field of urban blocks.

[0098] Optionally, in one embodiment of this application, it further includes: an identification module and a second construction module.

[0099] The identification module is used to identify the potential damage types of the wind-borne carriers of urban blocks before constructing a multi-disaster-bearing carrier wind-induced disaster risk assessment model library for urban blocks.

[0100] The second building module is used to construct a multi-disaster-bearing carrier wind-induced disaster risk assessment model library for urban blocks, based on the critical wind speed and exceedance probability as measurement criteria, and according to the real-time wind field and the potential damage type of the disaster-bearing carrier combined with the target probability distribution model.

[0101] Optionally, in one embodiment of this application, the early warning module 300 includes: a first acquisition unit and an empowerment unit.

[0102] The first acquisition unit is used to acquire at least one key area of ​​the urban block.

[0103] The weighting unit is used to assign weights to the sub-models of wind-induced disaster risk assessment models in the multi-disaster-bearing carrier model library based on at least one key area, so as to obtain the spatial distribution results of the damage level of wind-induced disaster-bearing carriers and the spatial distribution results of the comprehensive risk level of urban blocks.

[0104] Optionally, in one embodiment of this application, the early warning module 300 includes: a second acquisition unit and a generation unit.

[0105] The second acquisition unit is used to acquire actual sparse monitoring data of urban blocks.

[0106] The generation unit is used to calculate and output the spatial distribution results of wind-induced disaster damage level and comprehensive risk level of the target urban block based on the real-time wind field and the disaster-bearing carrier sub-model, so as to generate early warning prompts.

[0107] It should be noted that the explanation of the above-mentioned embodiment of the comprehensive risk warning method for wind-induced disasters in urban blocks also applies to the comprehensive risk warning device for wind-induced disasters in urban blocks in this embodiment, and will not be repeated here.

[0108] The urban street wind-induced disaster comprehensive risk early warning device proposed in this application can construct a two-stage deep learning method based on physical inspiration and data-driven approach, and a multi-disaster-bearing carrier wind-induced disaster risk assessment model library. It calculates and outputs the spatial distribution results of damage levels and comprehensive risk levels of disaster-bearing carriers in urban streets, and provides early warning based on these results. This achieves real-time, refined inversion of urban street wind fields by integrating a deep learning model of flow field physical characteristics with error correction technology based on sparse measured data for real-time wind field reconstruction. It also constructs a multi-disaster-bearing carrier wind-induced disaster risk assessment model library using a general construction method for urban street wind-induced disaster risk assessment models, enabling rapid calculation of the spatial distribution of damage probability and comprehensive risk levels of disaster-bearing carriers in urban streets. This provides real-time decision-making suggestions for decision-makers, contributing to scientific decision-making and precise prevention and control. Therefore, it solves the problems in related technologies, such as low wind field calculation accuracy, slow calculation speed, inability to quickly and effectively achieve refined real-time reconstruction of urban street wind fields, inability to comprehensively evaluate the complex and diverse wind-induced risks of disaster-bearing carriers in real-world scenarios, and lack of user-visualized interfaces, quantitative results, and practically applicable wind-induced disaster risk early warning systems.

[0109] Figure 6 A schematic diagram of the structure of an electronic device provided in an embodiment of this application. The electronic device may include:

[0110] The memory 601, the processor 602, and the computer program stored on the memory 601 and capable of running on the processor 602.

[0111] When the processor 602 executes the program, it implements the comprehensive risk early warning method for wind-induced disasters in urban blocks provided in the above embodiments.

[0112] Furthermore, electronic devices also include:

[0113] Communication interface 603 is used for communication between memory 601 and processor 602.

[0114] The memory 601 is used to store computer programs that can run on the processor 602.

[0115] The memory 601 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.

[0116] If the memory 601, processor 602, and communication interface 603 are implemented independently, then the communication interface 603, memory 601, and processor 602 can be interconnected via a bus to complete communication between them. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 6 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0117] Optionally, in a specific implementation, if the memory 601, processor 602, and communication interface 603 are integrated on a single chip, then the memory 601, processor 602, and communication interface 603 can communicate with each other through an internal interface.

[0118] The processor 602 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application.

[0119] This application also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the above-described method for comprehensive risk warning of wind-induced disasters in urban blocks.

[0120] This application also provides a computer program product, including a computer program that can run computer instructions. When the computer instructions are executed by a processor, they implement the urban street wind-induced disaster comprehensive risk early warning method provided in this application.

[0121] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0122] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0123] Any process or method described in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or N executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0124] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0125] It should be understood that the various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. If implemented in hardware, as in another embodiment, it can be implemented using any one or more of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0126] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0127] Furthermore, the functional units in the various embodiments of this application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0128] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of this application.

Claims

1. A comprehensive risk early warning method for wind-induced disasters in urban blocks, characterized in that, Includes the following steps: Based on a pre-established physics-inspired data-driven learning framework, the wind field of the target city block is reconstructed in real time to obtain the real-time wind field of the target city block. Based on a pre-built multi-hazard-bearing carrier wind-induced disaster risk assessment model library, query the hazard-bearing carrier sub-model corresponding to the real-time wind field; Based on the real-time wind field and the disaster-bearing carrier sub-model, the spatial distribution results of the wind-induced disaster-bearing carrier damage level and the spatial distribution results of the comprehensive risk level of the target urban block are calculated to generate early warning prompts and conduct risk warnings. The method of reconstructing the wind field of a target urban block in real time based on a pre-established physics-inspired data-driven learning framework to obtain the real-time wind field of the target urban block includes: reconstructing a deep learning model of flow field physical characteristics based on a target neural network; capturing the fluid physics mechanism and flow field structure characteristics of the urban block based on the simulated wind speed at feature points and a preset wind field CFD dataset to reconstruct the initial wind field on the simulated dataset; using sparse measured data at the feature points as input, calculating the real-time wind speed at each point in the urban block space based on the fluid physics mechanism and the flow field structure characteristics to obtain the initial wind field of the urban block based on the real-time wind speed; and correcting the initial wind field based on the modeling error driven by the sparse measured data to obtain the real-time wind field of the urban block. Prior to constructing the multi-hazard-bearing carrier wind-induced disaster risk assessment model library for the aforementioned urban blocks, the following is also included: Based on the wind-induced disaster-bearing carriers of the target urban blocks, identify the potential damage types of the disaster-bearing carriers of the urban blocks; Using critical wind speed and exceedance probability as measurement criteria, a multi-disaster-bearing carrier wind-induced disaster risk assessment model library for the urban block is constructed based on the real-time wind field and the potential damage type of the disaster-bearing carrier, combined with the target probability distribution model. The step of calculating the spatial distribution results of the wind-induced disaster-bearing carrier damage level and comprehensive risk level of the target urban block based on the real-time wind field and the disaster-bearing carrier sub-model includes: Obtain at least one key area of ​​the city block; Based on the at least one key area, the sub-models of the disaster-bearing carriers in the multi-disaster-bearing carrier wind-induced disaster risk assessment model library are weighted to obtain the spatial distribution results of the damage level of the wind-induced disaster-bearing carriers and the spatial distribution results of the comprehensive risk level of the urban blocks; The comprehensive risk level includes no risk, low risk, medium risk, high risk, and extremely high risk; among which, The carriers of wind-induced disasters in urban blocks include: pedestrians, trees, buildings and their surrounding structures, and infrastructure.

2. The method according to claim 1, characterized in that, The step of calculating the spatial distribution results of wind-induced disaster-bearing carrier damage levels and the spatial distribution results of comprehensive risk levels of the target urban block based on the real-time wind field and the disaster-bearing carrier sub-model to generate early warning prompts includes: Obtain actual sparse monitoring data of the urban blocks; Based on the real-time wind field and the disaster-bearing carrier sub-model, the spatial distribution results of the wind-induced disaster-bearing carrier damage level and the spatial distribution results of the comprehensive risk level of the target urban block are calculated and output to generate the early warning prompt.

3. A comprehensive risk early warning device for wind-induced disasters in urban blocks, characterized in that, Includes the following steps: A module is built to reconstruct the wind field of a target city block in real time based on a pre-established physical-inspired data-driven learning framework, thereby obtaining the real-time wind field of the target city block. The query module is used to query the sub-models of the disaster-bearing carriers corresponding to the real-time wind field based on a pre-built multi-disaster-bearing carrier wind-induced disaster risk assessment model library; The early warning module is used to calculate the spatial distribution results of wind-induced disaster carrier damage level and comprehensive risk level of the target urban block based on the real-time wind field and the disaster carrier sub-model, so as to generate early warning prompts and conduct risk warnings. The construction module includes: a construction unit, used to reconstruct a deep learning model of flow field physical characteristics based on a target neural network, and capture the fluid physics mechanism and flow field structure characteristics of the urban block according to the simulated wind speed at the feature points of the urban block and a preset wind field CFD dataset, so as to reconstruct the initial wind field on the simulated dataset; a calculation unit, used to take sparse measured data at the feature points as input, and calculate the real-time wind speed at each point in the urban block according to the fluid physics mechanism and the flow field structure characteristics, so as to obtain the initial wind field of the urban block according to the real-time wind speed; and a correction unit, used to correct the initial wind field based on the modeling error driven by sparse measured data, so as to obtain the real-time wind field of the urban block. Before constructing the multi-hazard-bearing carrier wind-induced disaster risk assessment model library for the urban block, the query module is also used for: Based on the wind-induced disaster-bearing carriers of the target urban blocks, identify the potential damage types of the disaster-bearing carriers of the urban blocks; Using critical wind speed and exceedance probability as measurement criteria, a multi-disaster-bearing carrier wind-induced disaster risk assessment model library for the urban block is constructed based on the real-time wind field and the potential damage type of the disaster-bearing carrier, combined with the target probability distribution model. The early warning module calculates the spatial distribution results of the wind-induced disaster-bearing carrier damage level and comprehensive risk level of the target urban block based on the real-time wind field and the disaster-bearing carrier sub-model, specifically for: Obtain at least one key area of ​​the city block; Based on the at least one key area, the sub-models of the disaster-bearing carriers in the multi-disaster-bearing carrier wind-induced disaster risk assessment model library are weighted to obtain the spatial distribution results of the damage level of the wind-induced disaster-bearing carriers and the spatial distribution results of the comprehensive risk level of the urban blocks; The early warning module determines the comprehensive risk level to include no risk, low risk, medium risk, high risk, and extremely high risk. in, The carriers of wind-induced disasters in urban blocks include: pedestrians, trees, buildings and their surrounding structures, and infrastructure.

4. An electronic device, characterized in that, include: The method includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the comprehensive risk early warning method for wind-induced disasters in urban blocks as described in any one of claims 1-2.

5. A computer-readable storage medium having a computer program stored thereon, characterized in that, The program is executed by the processor to implement the comprehensive risk early warning method for wind-induced disasters in urban blocks as described in any one of claims 1-2.

6. A computer program product, comprising a computer program, characterized in that, When the computer program is executed, it is used to implement the comprehensive risk early warning method for wind-induced disasters in urban blocks as described in any one of claims 1-2.

Images