Earthquake disaster scenario construction method and system based on big data

Abstract

The application belongs to the technical field of earthquake disaster scenario construction, and discloses a method for constructing an earthquake disaster scenario based on big data, and the specific steps are as follows: step one: multi-source heterogeneous data acquisition and preprocessing ground structure data acquisition: the spatial distribution characteristics of urban building groups are obtained by using multi-platform remote sensing technology. By integrating multi-source data, a three-dimensional coupling model of underground pipe network and ground building is constructed, the defects of isolated analysis of ground and underground systems in traditional methods are solved, the synchronous simulation of the dynamic correlation process of pipe network rupture and building damage is realized, the additional influence of pipe network failure on building foundation stability and the chain effect of soil erosion caused by leakage fluid are accurately analyzed, and the space-time correlation rules of pipe network rupture events, building fire, fire fighting failure and other types of secondary disasters are established, the building group function paralysis risk and disaster diffusion range under different damage degrees are dynamically predicted, and the disaster evolution path is displayed in real time through a visual platform.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of earthquake disaster scenario construction, and particularly relates to an earthquake disaster scenario construction method and system based on big data. BACKGROUND

[0002] Earthquake disaster scenario construction is an emergency preparation method based on scientific simulation and risk analysis, which dynamically simulates the whole process from the occurrence to the diffusion of an earthquake by integrating multi-dimensional data such as geological structure, building structure, population distribution and secondary disaster chain.

[0003] In the existing earthquake disaster scenario construction technology based on big data, the seismic performance simulation of ground building structure and the safety research of underground pipe network system are usually processed separately, the seismic response analysis of ground buildings is mostly focused on the dynamic characteristics of the structure itself and the site effect, and the seismic calculation is usually based on a simplified soil-structure interaction model, but the counteraction mechanism of the additional foundation deformation caused by the rupture of the underground pipe network on the stability of the building foundation is ignored, and the underground pipe network damage simulation technology mostly uses an independent pipe segment mechanical model or a statistical empirical method to evaluate the pipe body damage probability, without fully considering the coupling effect of the fluid leakage and soil loss process after the pipe rupture and the degradation of the bearing capacity of the adjacent building foundation; in addition, the earthquake disaster scenario construction mostly analyzes a single disaster (such as building collapse or pipe rupture) in isolation, lacks the ability of spatio-temporal coupling modeling of underground pipe network failure and secondary disasters of ground buildings, and the key coupling mechanisms such as the correlation between the building fire radiation range caused by gas pipe network leakage and the spatial distribution of building groups and the time sequence dependence of building fire fighting system failure caused by water supply interruption have not been effectively quantified, so it is necessary to improve them. SUMMARY

[0004] The purpose of the present application is to provide an earthquake disaster scenario construction method and system based on big data to solve the problems raised in the background.

[0005] In order to achieve the above purpose, the present application provides the following technical scheme: an earthquake disaster scenario construction method based on big data, the specific steps are as follows:

[0006] Step 1: Multi-source heterogeneous data acquisition and preprocessing

[0007] Ground structure data collection: Obtain the spatial distribution characteristics of urban building groups using multi-platform remote sensing technology. Interpret the building outlines, number of floors, and roof structure morphology from high-resolution remote sensing satellite images. Combine unmanned aerial vehicle oblique photogrammetry to construct a centimeter-precision real-world three-dimensional model to extract building facade texture and detailed structural information. Simultaneously access the Building Information Modeling (BIM) database to obtain engineering parameters such as structural system, material strength, and node connection method at the design stage. Rely on the city Three-Dimensional Geographic Information System (3D-GIS) to integrate building foundation types, basement depth, surrounding road elevation, and other spatial topological relationships.

[0008] Underground pipe network data acquisition: Integrate city comprehensive pipe gallery digital archives, including the spatial topological structure of water supply pipe network, gas pipe network, power pipe network, and communication pipe network. Collect attribute parameters such as pipe material, burial depth, interface form, and service life.

[0009] Geological environment data fusion: Integrate regional seismic risk analysis results, including historical earthquake focal mechanism solutions, active fault slip rates, potential seismic source area division, and probabilistic ground motion parameters. Combine engineering geological drilling data to construct a three-dimensional stratum structure model and interpolate to generate shear wave velocity profiles, standard penetration blow counts, and clay plasticity index spatial distribution fields. Integrate hydrogeological monitoring data and high-precision digital elevation model analysis to analyze site liquefaction potential, landslide sensitivity, and surface rupture zone distribution patterns. Establish a cross-scale geological environment database supporting seismic wave propagation simulation, site effect evaluation, and secondary disaster prediction.

[0010] Step two: Coupling system modeling and interaction analysis

[0011] Soil-pipe network-structure interaction analysis: Discretize the ground building structure into a refined finite element model composed of three-dimensional beam-shell elements and solid elements. The underground pipe network system is constructed as a discrete element chain structure considering pipe segment joint nonlinearity. The friction-bonding coupling effect between the pipe and the surrounding soil is achieved through a nonlinear contact algorithm. Analyze the pipe-soil interface slip, pipe body buckling deformation, and building foundation settlement interaction behaviors explicitly. Finally, a coupled numerical model is formed that can simultaneously simulate underground pipe network rupture propagation and ground building damage evolution.

[0012] Seismic wave propagation coupling analysis: After the construction of the underground-ground coupling numerical model, further analysis of the propagation characteristics of seismic waves in the coupling system is needed. By constructing a seismic wave-soil-pipeline-building multi-medium wave propagation model, the viscoelastic artificial boundary is used to simulate the radiation damping effect of the semi-infinite foundation. Through the wave input method, the bedrock seismic wave is filtered through the soil layer and converted into multi-supported excitation at the building foundation. The explicit time-domain integral algorithm is used to solve the nonlinear dynamic response of the soil, the wave stress propagation of the pipeline, and the inertial force of the building structure. Combined with the frequency domain decoupling technology, the differential effects of seismic waves with different spectral characteristics on pipeline resonance and building high-order vibration modes are analyzed. The soil-structure interaction (SSI) and pipeline-soil-structure interaction are analyzed.

[0013] Step three: multi-disaster chain scenario deduction

[0014] Infrastructure failure path analysis: Based on the earthquake-triggered underground pipeline rupture events such as gas pipeline rupture, water supply main burst, and power pipeline short circuit, a multi-level disaster propagation network from physical system failure to social system paralysis is constructed. By defining node state transition probability (such as pipeline leakage rate-gas concentration accumulation-explosion probability threshold) and edge weight (such as the intensification coefficient of fire spread rate under the pressure drop of fire water supply), the typical disaster paths such as gas leakage-induced building fire radiation ignition chain, water supply pipeline rupture-induced public health crisis chain, and drainage system failure-induced building foundation liquefaction load degradation chain are simulated.

[0015] Social system impact assessment: Integrating population distribution big data, traffic flow data, and emergency resource distribution data, the impact of secondary disasters caused by pipeline failure on personnel evacuation, emergency rescue, and lifeline restoration is evaluated in terms of timeliness. The resilience function (such as Logistics curve) is introduced to predict the synchronization of pipeline function recovery and building function restart under different repair strategies. Finally, a comprehensive impact assessment report is output, including casualty prediction, economic loss estimation, and social order disorder index.

[0016] Step four: big data-driven risk assessment and visualization

[0017] Machine learning prediction model construction: Using deep neural network algorithm, based on historical seismic damage data, a pipeline failure pattern recognition model is trained, and combined with city comprehensive pipe gallery digital archive data, a dynamic assessment of pipeline vulnerability is realized.

[0018] Visualization platform: Using digital technology to build a city-level disaster deduction system, the visualization of seismic wave propagation, building damage evolution, pipeline rupture diffusion, and secondary disaster spread is realized.

[0019] Risk heat map generation: The risk heat map generation adopts a method combining adaptive kernel density estimation (KDE) and spatial clustering algorithm (DBSCAN) to perform multi-dimensional statistical analysis on the tens of thousands of earthquake scenario samples generated by Monte Carlo simulation, extract core risk indicators such as building collapse probability, pipeline rupture density, and secondary disaster intensity index, and generate dynamic risk classification map to provide spatial decision-making benchmark for regional and graded emergency response;

[0020] Step 5: Building an Intelligent Decision Support System

[0021] Resilience assessment index system: Establish an urban system seismic resilience evaluation system that includes three dimensions: structural safety, functional continuity, and recovery timeliness, and quantify the collaborative seismic resistance capability of pipeline network system and ground buildings;

[0022] Application of adaptive optimization algorithm: A multi-objective genetic algorithm is used to collaboratively optimize pipeline renovation priorities, building seismic reinforcement schemes, and emergency resource allocation strategies;

[0023] Dynamic emergency response plan generation: Based on real-time scenario simulation results, it automatically generates dynamic emergency response plans that include emergency shutdown strategies for pipeline networks, building evacuation route planning, and key areas for secondary disaster prevention and control.

[0024] Preferably, the pipe-soil interface friction model in step two is:

[0025]

[0026] Where μ is the friction coefficient, v is the slip velocity, and v0 is the characteristic velocity.

[0027] Preferably, the interaction mechanism between the pipeline network and buildings revealed by the seismic propagation coupling analysis in step two needs to be further constructed into a failure chain effect model. By defining the correlation rules between pipeline node failure and building function loss, the secondary disaster chain reaction triggered by the transmission of seismic energy through the pipeline network can be quantified, thereby extending the local damage of the physical system to the global risk of the urban system. A disaster chain propagation framework based on multi-agent simulation is constructed to quantify the probability of water supply network rupture leading to building fire protection system failure under different earthquake magnitudes, the time-varying risk of building fire caused by gas pipeline leakage, and the risk of building foundation liquefaction caused by drainage network damage. Furthermore, a simulation system considering the competition mechanism between emergency repair resource scheduling and disaster spread speed is developed to ultimately achieve dynamic risk assessment of the entire process from initial pipeline damage to cascading failure of building clusters.

[0028] Preferably, in step three, the Large Eddy Simulation (LES) is used to track the turbulent diffusion process of combustible gas in street canyons and building pores for the gas pipeline rupture scenario. The turbulent diffusion calculation formula is as follows:

[0029]

[0030] where C is the concentration, D is the diffusion coefficient, and v is the velocity field;

[0031] The flame propagation speed and heat release rate are calculated by a combustion chemical reaction model to simulate the combustible gas diffusion process after the gas pipeline network is broken, the building fire development law, analyze the secondary damage mechanism of thermal radiation on the surrounding building structure, quantify the critical condition of building group from local damage to overall collapse under the synergistic action of multiple factors, and the thermal radiation intensity model is:

[0032]

[0033] where Q is the heat release rate, r is the distance, and β is the attenuation coefficient.

[0034] Preferably, when constructing the multi-level disaster propagation network from physical system failure to social system paralysis in step three, a time window function is introduced to quantify the time sequence dependence between secondary disasters (such as gas explosion triggered 30 minutes after an earthquake, and fire extinguishing ability lost due to water supply interruption 2 hours later), combined with geographic information system (GIS) spatial overlay analysis to determine the disaster superposition area, and finally generate a disaster chain scenario library with spatio-temporal evolution characteristics.

[0035] Preferably, the dynamic emergency plan generation in step five also includes the fusion of real-time meteorological data, combined with wind speed and precipitation to dynamically adjust the secondary disaster prevention and control strategy and optimize the emergency resource scheduling path.

[0036] Preferably, the multi-source heterogeneous data collection in step one also accesses the historical earthquake disaster case database, and optimizes the vulnerability assessment model of the current building and pipeline network by comparing and analyzing the historical disaster damage pattern.

[0037] The earthquake disaster scenario construction system based on big data includes the following modules:

[0038] Multi-source data collection and preprocessing module: used to integrate ground building structure, underground pipeline and geological environment data, realize three-dimensional modeling and data fusion through remote sensing, BIM and GIS technology, extract building parameters, pipeline attributes and rock-soil characteristics, and build a cross-scale geological environment database;

[0039] Coupling system modeling and analysis module: used to establish a building-pipeline-soil coupling model, simulate seismic wave propagation and nonlinear interaction, analyze pipe-soil interface slip, building damage evolution and secondary disaster triggering mechanism;

[0040] Disaster chain scenario deduction module: used to analyze the infrastructure failure path, simulate chain disasters such as gas leakage and fire spread, and assess the social system paralysis risk and time effect in combination with population distribution and emergency resources;

[0041] Risk assessment and visualization module: used for generating dynamic risk heat map based on machine learning and big data, visualizing ground motion propagation, pipe network rupture and secondary disaster diffusion process, and supporting zoned and hierarchical emergency decision-making;

[0042] Intelligent decision support and optimization module: used for building a resilience assessment system, optimizing pipe network reconstruction and emergency resource allocation strategies, generating dynamic emergency plans and predicting functional recovery synchronicity.

[0043] Preferably, the risk assessment and visualization module has an interactive function, can generate a specified risk assessment report and customized disaster scenario simulation view according to the needs of the operator, support dynamic adjustment of earthquake parameters and real-time display of the corresponding risk heat map and secondary disaster diffusion path, and provide visual basis for accurate emergency decision-making.

[0044] The beneficial effects of the present application are as follows:

[0045] By integrating multi-source data to build a three-dimensional coupled model of underground pipe network and ground buildings, the defects of isolated analysis of ground and underground systems in traditional methods are solved, the dynamic correlation process of pipe network rupture and building damage is simulated synchronously, the additional influence of pipe network failure on building foundation stability and the chain effect of soil erosion caused by leakage fluid are accurately analyzed, and the spatio-temporal correlation rules of pipe network rupture events and multiple types of secondary disasters such as building fire and fire fighting failure are established, the functional paralysis risk of building group and the disaster diffusion range under different damage degrees are dynamically predicted, and the disaster evolution path and emergency resource allocation scheme are displayed in real time through the visualization platform, effectively improving the authenticity of city earthquake disaster chain deduction and the accuracy of emergency response. BRIEF DESCRIPTION OF DRAWINGS

[0046] Figure 1 The system block diagram of the present application is shown. DETAILED DESCRIPTION

[0047] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0048] As shown in Figure 1 The present application provides a method for constructing an earthquake disaster scenario based on big data, and the specific steps are as follows:

[0049] Step 1: Multi-source heterogeneous data acquisition and preprocessing

[0050] Ground structure data collection: Obtain the spatial distribution characteristics of urban building groups using multi-platform remote sensing technology. Interpret the building outlines, number of floors, and roof structure morphology from high-resolution remote sensing satellite images. Combine unmanned aerial vehicle oblique photogrammetry to construct a centimeter-precision real-world three-dimensional model to extract building facade texture and detailed structural information. Simultaneously access the Building Information Modeling (BIM) database to obtain engineering parameters such as structural system, material strength, and node connection method at the design stage. Rely on the city Three-Dimensional Geographic Information System (3D-GIS) to integrate building foundation types, basement depth, surrounding road elevation, and other spatial topological relationships.

[0051] Underground pipe network data acquisition: Integrate city comprehensive pipe gallery digital archives, including the spatial topological structure of water supply pipe network, gas pipe network, power pipe network, and communication pipe network. Collect attribute parameters such as pipe material, burial depth, interface form, and service life.

[0052] Geological environment data fusion: Integrate regional seismic risk analysis results, including historical earthquake focal mechanism solutions, active fault slip rates, potential seismic source area division, and probabilistic ground motion parameters. Combine engineering geological drilling data to construct a three-dimensional stratum structure model and interpolate to generate shear wave velocity profiles, standard penetration blow counts, and clay plasticity index spatial distribution fields. Integrate hydrogeological monitoring data and high-precision digital elevation model analysis to analyze site liquefaction potential, landslide sensitivity, and surface rupture zone distribution patterns. Establish a cross-scale geological environment database supporting seismic wave propagation simulation, site effect evaluation, and secondary disaster prediction.

[0053] Step two: Coupling system modeling and interaction analysis

[0054] Soil-pipe network-structure interaction analysis: Discretize the ground building structure into a refined finite element model composed of three-dimensional beam-shell elements and solid elements. The underground pipe network system is constructed as a discrete element chain structure considering pipe segment joint nonlinearity. The friction-bonding coupling effect between the pipe and the surrounding soil is achieved through a nonlinear contact algorithm. Analyze the pipe-soil interface slip, pipe body buckling deformation, and building foundation settlement interaction behaviors through explicit dynamics. Finally, a coupled numerical model is formed that can simultaneously simulate underground pipe network rupture propagation and ground building damage evolution.

[0055] Seismic wave propagation coupling analysis: After the construction of the underground-ground coupling numerical model, further analysis of the propagation characteristics of seismic waves in the coupling system is needed. By constructing a seismic wave-soil-pipeline-building multi-medium wave propagation model, the viscoelastic artificial boundary is used to simulate the radiation damping effect of the semi-infinite foundation. Through the wave input method, the bedrock seismic wave is filtered through the soil layer and converted into multi-supported excitation at the building foundation. The explicit time-domain integral algorithm is used to solve the nonlinear dynamic response of the soil, the wave stress propagation of the pipeline, and the inertial force of the building structure. Combined with the frequency domain decoupling technology, the differential effects of seismic waves with different spectral characteristics on pipeline resonance and building high-order vibration modes are analyzed. The soil-structure interaction (SSI) and pipeline-soil-structure interaction are analyzed.

[0056] Step three: multi-disaster chain scenario deduction

[0057] Infrastructure failure path analysis: Based on the earthquake-triggered underground pipeline rupture events such as gas pipeline rupture, water supply main burst, and power pipeline short circuit, a multi-level disaster propagation network from physical system failure to social system paralysis is constructed. By defining node state transition probability (such as pipeline leakage rate-gas concentration accumulation-explosion probability threshold) and edge weight (such as the intensification coefficient of fire spread rate under the pressure drop of fire water supply), the typical disaster paths such as gas leakage triggering building fire radiation ignition chain, water supply pipeline rupture leading to public health crisis chain of medical facility shutdown, and drainage system failure exacerbating building foundation liquefaction bearing capacity degradation chain are simulated.

[0058] Social system impact assessment: Integrating population distribution big data, traffic flow data, and emergency resource distribution data, the impact of secondary disasters caused by pipeline failure on personnel evacuation, emergency rescue, and lifeline restoration is evaluated in terms of timeliness. The resilience function (such as Logistics curve) is introduced to predict the synchronization of pipeline function recovery and building function restart under different repair strategies. Finally, a comprehensive impact assessment report is output, including casualty prediction, economic loss estimation, and social order disorder index.

[0059] Step four: big data-driven risk assessment and visualization

[0060] Machine learning prediction model construction: Using deep neural network algorithm, based on historical seismic damage data, a pipeline failure pattern recognition model is trained, and combined with city comprehensive pipe gallery digital archive data, a dynamic assessment of pipeline vulnerability is realized.

[0061] Visualization platform: Using digital technology to build a city-level disaster deduction system, the visualization of seismic wave propagation, building damage evolution, pipeline rupture diffusion, and secondary disaster spread is realized.

[0062] Risk heat map generation: Risk heat map generation uses a combination of adaptive kernel density estimation (KDE) and spatial clustering algorithm (DBSCAN) to perform multi-dimensional statistical analysis on the million-level earthquake scenario samples generated by Monte Carlo simulation. Core risk indicators such as building collapse probability, pipe network rupture density, and secondary disaster intensity index are extracted to generate dynamic risk classification maps, providing spatial decision benchmarks for zoned and graded emergency response.

[0063] Step five: Intelligent decision support system construction

[0064] Resilience evaluation index system: Establish an urban system earthquake resilience evaluation system containing three dimensions of structural safety, functional continuity, and recovery timeliness, to quantify the collaborative seismic capacity of pipe network system and ground buildings.

[0065] Adaptive optimization algorithm application: Use multi-objective genetic algorithm to optimize the priority of pipe network reconstruction, building seismic reinforcement scheme, and emergency resource allocation strategy.

[0066] Dynamic emergency plan generation: Based on real-time scenario deduction results, automatically generate dynamic emergency plans including pipe network emergency shutdown strategy, building evacuation path planning, and secondary disaster prevention key areas.

[0067] By integrating remote sensing, BIM, GIS and other multi-source heterogeneous data, a three-dimensional building-pipe network-geology coupling model is established. Combined with nonlinear dynamics and wave propagation theory, the interaction between underground and aboveground systems is analyzed, a multi-level disaster chain deduction framework is constructed from infrastructure physical damage to social system paralysis. Based on machine learning and big data visualization, dynamic risk assessment and intelligent emergency decision optimization are realized, forming a full-process technology system covering data collection, coupling modeling, disaster deduction, risk quantification and decision support.

[0068] Among them, the pipe-soil interface friction model in step two is:

[0069]

[0070] Where μ is the friction coefficient, v is the slip velocity, and v0 is the characteristic velocity.

[0071] By introducing the nonlinear relationship between friction coefficient and slip velocity, the velocity dependence of pipe-soil interface friction is described using a hyperbolic tangent function, which can more accurately simulate the transient switching process from static friction to dynamic friction at the pipe-soil interface under seismic action, significantly improving the physical authenticity of pipe sliding and buckling deformation analysis.

[0072] The mechanism of interaction between the pipe network and the building revealed in step two based on seismic wave propagation coupling analysis needs to be further modeled for failure chain effect, and by defining the correlation rules between pipe network node failure and building function loss, the chain reaction of secondary disasters triggered by seismic energy transmission through the pipe network can be quantified, so as to extend the local damage of the physical system to the global risk of the urban system; a disaster chain propagation framework based on multi-agent simulation is constructed to quantitatively analyze the probability of building fire fighting system failure caused by pipe network rupture under different earthquake magnitudes, the time-varying risk of building fire caused by gas pipe network leakage, and the liquefaction risk of building foundation caused by drainage pipe network damage, and a simulation system considering emergency repair resource scheduling and disaster diffusion speed competition mechanism is developed, and finally the whole process dynamic risk assessment from pipe network initial damage to building cascade failure is realized.

[0073] The correlation rules between pipe network node failure and building function loss are constructed, and the chain reaction of building fire fighting failure, fire risk and foundation liquefaction triggered by pipe network rupture under different earthquake magnitudes is quantified by multi-agent simulation, which realizes the dynamic mapping from local physical damage to global risk of urban system, and provides simulation basis for repair resource scheduling and disaster diffusion competition mechanism.

[0074] In step three, large eddy simulation (LES) is used to track the turbulent diffusion process of flammable gas in street canyons and building pores for the scenario of gas pipe network rupture, and the turbulent diffusion calculation formula is:

[0075]

[0076] Where C is the concentration, D is the diffusion coefficient, and v is the flow velocity field;

[0077] The flame propagation speed and heat release rate are calculated by the combustion chemical reaction model to simulate the diffusion process of flammable gas after gas pipe network rupture and the development law of building fire, analyze the secondary damage mechanism of thermal radiation on surrounding building structures, and quantify the critical conditions of building group from local damage to overall collapse under the synergistic action of multiple factors. The thermal radiation intensity model is:

[0078]

[0079] Where Q is the heat release rate, r is the distance, and β is the attenuation coefficient.

[0080] Large eddy simulation is used to accurately track the turbulent diffusion process of flammable gas, combined with the thermal radiation intensity attenuation model and the combustion chemical reaction equation, to quantitatively analyze the development law of building fire and the secondary damage mechanism of thermal radiation on surrounding structures, and to provide a multi-physical field coupling analysis method for the critical condition judgment of building group continuous collapse.

[0081] In step three, when constructing the multi-level disaster propagation network from physical system failure to social system paralysis, the time window function is introduced to quantify the time sequence dependence between secondary disasters (such as gas explosion triggered 30 minutes after an earthquake, and fire extinguishing ability lost due to water supply interruption 2 hours later), combined with geographic information system (GIS) spatial overlay analysis to determine the disaster superposition area, and finally generate a disaster chain scenario library with time and space evolution characteristics.

[0082] The time window function is introduced to quantify the time sequence relationship of secondary disasters, and GIS spatial overlay is used to identify the disaster coupling area, and a disaster chain scenario library with time and space evolution characteristics is constructed, which effectively improves the precision of matching emergency response strategies with disaster development stages.

[0083] In step five, the dynamic emergency plan generation also includes the fusion of real-time meteorological data, combined with wind speed and precipitation forecasts to dynamically adjust secondary disaster prevention and control strategies and optimize emergency resource scheduling paths.

[0084] Real-time meteorological data is integrated into the emergency plan generation process, and wind speed and precipitation forecasts are used to dynamically optimize secondary disaster prevention and control key areas and resource scheduling paths, enhancing the adaptive ability of emergency plans to complex environmental conditions.

[0085] In step one, the multi-source heterogeneous data collection also accesses the historical earthquake disaster case database, and through comparative analysis of historical disaster damage patterns, the vulnerability assessment model of the current building and pipe network is optimized.

[0086] Integrating historical earthquake disaster case data improves the engineering credibility of risk assessment results.

[0087] The earthquake disaster scenario construction system based on big data includes the following modules:

[0088] Multi-source data collection and preprocessing module: used to integrate ground building structure, underground pipe network and geological environment data, realize three-dimensional modeling and data fusion through remote sensing, BIM and GIS technology, extract building parameters, pipe network attributes and rock-soil characteristics, and build a cross-scale geological environment database;

[0089] Coupling system modeling and analysis module: used to establish building-pipe network-soil coupling model, simulate seismic wave propagation and nonlinear interaction, analyze pipe-soil interface slip, building damage evolution and secondary disaster triggering mechanism;

[0090] Disaster chain scenario deduction module: used to analyze infrastructure failure path, simulate chain disasters such as gas leakage and fire spread, and assess social system paralysis risk and time efficiency influence combined with population distribution and emergency resources;

[0091] Risk assessment and visualization module: used for generating dynamic risk heat map based on machine learning and big data, visualizing ground motion propagation, pipe network rupture and secondary disaster diffusion process, and supporting zoned and hierarchical emergency decision-making;

[0092] Intelligent decision support and optimization module: used for building resilience assessment system, optimizing pipe network reconstruction and emergency resource allocation strategy, generating dynamic emergency plan and predicting functional recovery synchronicity.

[0093] Through multi-source data acquisition and preprocessing module, spatial fusion of building, pipe network and geological data is realized, and soil-pipe-structure dynamic interaction is analyzed by coupling system modeling and analysis module, so as to simulate the spatio-temporal evolution path of secondary disasters through disaster chain deduction module.

[0094] Among them, the risk assessment and visualization module has interactive function, can generate specified risk assessment report and customized disaster scenario simulation view according to the demand of operator, support dynamic adjustment of earthquake parameters and real-time display of corresponding risk heat map and secondary disaster diffusion path, and provide visual basis for accurate emergency decision-making.

[0095] An interactive risk assessment and visualization module is constructed, which supports dynamic adjustment of parameters and generation of customized scenario view, and provides intuitive spatial reference and response priority basis for zoned and hierarchical emergency decision-making.

[0096] It should be noted that in this paper, relationship terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between the entities or operations. Moreover, the terms "include", "contain" or any other variant thereof are intended to cover non-exclusive inclusion, so that the process, method, article or equipment including a series of elements not only includes those elements, but also includes other elements not explicitly listed or inherent to such process, method, article or equipment.

[0097] Although the embodiments of the present application have been shown and described, it can be understood by those skilled in the art that various changes, modifications, replacements and variations can be made to the embodiments without departing from the principles and spirits of the present application, and the scope of the present application is defined by the appended claims and their equivalents.

Claims

1. A method for constructing an earthquake disaster scenario based on big data, characterized in that, The specific steps are as follows: Step one: Multi-source heterogeneous data collection and preprocessing Ground structure data collection: Use multi-platform remote sensing technology to obtain the spatial distribution characteristics of urban building groups, interpret the building outline, number of layers and roof structure form through high-resolution remote sensing satellite images, combine unmanned aerial photogrammetry to construct a centimeter-level precision real scene three-dimensional model to extract building facade texture and detailed structure information, synchronously access the building information model (BIM) database to obtain the engineering parameters of the structural system, material strength and node connection mode at the design stage, rely on the city three-dimensional geographic information system (3D-GIS) to integrate the spatial topological relationship of building foundation types, basement depth and surrounding road elevation; Underground pipe network data acquisition: Integrate the city comprehensive pipe gallery digital archives, including the spatial topological structure of water supply pipe network, gas pipe network, power pipe network and communication pipe network, collect attribute parameters such as pipe material, buried depth, interface form and service life; Geological environment data fusion: Integrate regional seismic risk analysis results, including historical earthquake focal mechanism solution, active fault slip rate, potential seismic source area division and probabilistic ground motion parameters, combine engineering geological drilling data to construct a three-dimensional stratum structure model and interpolate to generate shear wave velocity profile, standard penetration number and clay plasticity index spatial distribution field of geotechnical parameters; Integrate hydrogeological monitoring data and high-precision digital elevation model to analyze site liquefaction potential, landslide sensitivity and surface rupture zone distribution rules, establish a cross-scale geological environment database supporting seismic wave propagation simulation, site effect evaluation and secondary disaster prediction; Step two: Coupling system modeling and interaction analysis Soil-pipe network-structure interaction analysis: Discretize the ground building structure into a refined finite element model composed of three-dimensional beam-shell elements and solid elements, and the underground pipe network system into a discrete element chain structure considering pipe joint nonlinearity, realize the friction-bonding coupling effect between the pipe and the surrounding soil through nonlinear contact algorithm, and analyze the explicit dynamic response of pipe-soil interface slip, pipe body buckling deformation and building foundation settlement, finally form a coupled numerical model that can simultaneously simulate the propagation of underground pipe network rupture and the evolution of ground building damage; Seismic wave propagation coupling analysis: After the construction of the underground-ground coupling numerical model, further analysis of the propagation characteristics of seismic waves in the coupling system is needed, a multi-medium wave propagation model of seismic wave-soil-pipe network-building is constructed, a viscoelastic artificial boundary is used to simulate the radiation damping effect of semi-infinite foundation, the multi-supported excitation at the building foundation is converted from the bedrock ground motion filtered by the soil layer through wave input method, the explicit time domain integral algorithm is used to solve the nonlinear dynamic response of soil, wave stress propagation of pipe and inertial force of building structure simultaneously, the frequency domain decoupling technology is used to analyze the differential influence of seismic waves with different spectral characteristics on pipe network resonance effect and building high-order vibration mode, and the soil-structure interaction (SSI) and pipe-soil-structure interaction are analyzed; Step three: Multi-disaster chain scenario deduction Infrastructure failure path analysis: Based on the earthquake-triggered underground pipe network rupture events, including gas pipe rupture, water supply pipe burst, and power line short circuit, a multi-level disaster propagation network from physical system failure to social system paralysis is constructed. By defining the node state transition probability, i.e. pipe leakage rate-gas concentration accumulation-explosion probability threshold, and the edge weight, i.e. the reinforcement coefficient of fire spread rate under the pressure drop of fire water supply, the typical disaster paths of gas leakage triggering building fire radiation ignition chain, water supply pipe rupture leading to medical facility shutdown public health crisis chain, and drainage system failure exacerbating building foundation liquefaction bearing capacity degradation chain are simulated; Social system impact assessment: By integrating population distribution big data, traffic flow data, and emergency resource distribution data, the impact of secondary disasters caused by pipe network failure on personnel evacuation, emergency rescue, and lifeline restoration is evaluated in terms of timeliness. The resilience function is introduced to predict the synchronization of pipe network function recovery and building use function restart under different repair strategies. Finally, an index comprehensive impact assessment report is output, including casualty prediction, economic loss estimation, and social order disorder index; Step four: Big data-driven risk assessment and visualization Machine learning prediction model construction: A deep neural network algorithm is used to train a pipe network failure pattern recognition model based on historical seismic damage data, and a dynamic assessment of pipe network vulnerability is achieved by combining city comprehensive pipe gallery digital archive data; Visualization platform: A city-level disaster deduction system is built using digital technology to visualize the propagation of ground motion, building damage evolution, pipe network rupture diffusion, and secondary disaster spread process; Risk heat map generation: The risk heat map generation uses a combination of adaptive kernel density estimation KDE and spatial clustering algorithm DBSCAN to perform multi-dimensional statistical analysis on the million-level earthquake scenario samples generated by Monte Carlo simulation. The core risk indicators of building collapse probability, pipe network rupture density, and secondary disaster intensity index are extracted to generate a dynamic risk classification map, providing a spatial decision benchmark for zoned and graded emergency response; Step five: Intelligent decision support system construction Resilience assessment index system: A city system earthquake resilience evaluation system is established, including structure safety, function continuity, and recovery timeliness, to quantify the collaborative seismic resistance capacity of pipe network system and ground buildings; Adaptive optimization algorithm application: A multi-objective genetic algorithm is used to optimize the pipe network reconstruction priority, building seismic reinforcement scheme, and emergency resource allocation strategy; Dynamic emergency plan generation: Based on real-time scenario deduction results, a dynamic emergency plan is automatically generated, including pipe network emergency shutdown strategy, building evacuation path planning, and secondary disaster prevention and control key areas. 2.The big data based earthquake disaster scenario construction method according to claim 1, characterized in that: The friction model of the pipe with the surrounding soil in step two is: wherein, is the friction coefficient, is the slip velocity, is the characteristic velocity. 3.The big data based earthquake disaster scenario construction method according to claim 1, characterized in that: The mechanism of pipe network and building interaction revealed in step two based on seismic wave propagation coupling analysis needs to further build a failure chain effect model. By defining the correlation rules of pipe network node failure and building function loss, the chain reaction of secondary disasters triggered by seismic energy transmission through the pipe network can be quantified, so as to extend the local damage of the physical system to the global risk of the urban system; a disaster chain propagation framework based on multi-agent simulation is constructed to quantitatively analyze the probability of building fire fighting system failure caused by water supply pipe network rupture, the time-varying risk of building fire caused by gas pipe network leakage, and the liquefaction risk of building foundation caused by drainage pipe network damage, and a simulation system considering emergency repair resource scheduling and disaster diffusion speed competition mechanism is developed, finally realizing the whole process dynamic risk assessment from pipe network initial damage to building cascade failure. 4.The big data based earthquake disaster scenario building method according to claim 1, characterized in that: In step three, large eddy simulation (LES) is used to track the turbulent diffusion process of combustible gas in street canyons and building porosities for the gas pipeline rupture scenario. The turbulent diffusion calculation formula is: where C is the concentration, D is the diffusion coefficient, and v is the velocity field. The flame propagation velocity and heat release rate were calculated by the combustion chemical reaction model to simulate the combustible gas diffusion process and building fire development law after the gas pipeline rupture, analyze the secondary damage mechanism of thermal radiation on the surrounding building structure, quantify the critical condition of building group from local damage to overall collapse under the synergistic action of multiple factors, and the thermal radiation intensity model is: wherein Q is the heat release rate, r is the distance, and β is the attenuation coefficient. 5.The big data based earthquake disaster scenario building method according to claim 1, characterized in that: When building the multi-level disaster propagation network from physical system failure to social system paralysis in step three, the time window function is introduced to quantify the time sequence dependence between secondary disasters, including gas explosion triggered 30 minutes after the earthquake and fire extinguishing ability loss caused by water supply interruption 2 hours later, and the disaster superposition area is determined by combining geographic information system GIS spatial superposition analysis, and finally a disaster chain scenario library with time and space evolution characteristics is generated. 6.The big data based earthquake disaster scenario building method according to claim 1, characterized in that: The dynamic emergency plan generation in step five also includes the fusion of real-time meteorological data, which dynamically adjusts the secondary disaster prevention and control strategy by combining wind speed and precipitation, and optimizes the emergency resource scheduling path. 7.The big data based earthquake disaster scenario building method according to claim 1, characterized in that: The multi-source heterogeneous data collection in step one also accesses the historical earthquake disaster case database, and optimizes the current building and pipe network vulnerability assessment model through comparative analysis of historical disaster patterns.

8. A big data-based earthquake disaster scenario construction system, characterized by, It includes the following modules: Multi-source data collection and preprocessing module: used to integrate ground building structure, underground pipe network and geological environment data, realize three-dimensional modeling and data fusion through remote sensing, BIM and GIS technology, extract building parameters, pipe network attributes and rock-soil characteristics, and build a cross-scale geological environment database; Coupling system modeling and analysis module: used to establish building-pipe network-soil coupling model, simulate seismic wave propagation and nonlinear interaction, analyze pipe-soil interface slip, building damage evolution and secondary disaster triggering mechanism; Disaster chain scenario deduction module: used to analyze infrastructure failure path, simulate chain disaster of gas leakage and fire spread, and assess social system paralysis risk and time effect by combining population distribution and emergency resources; Risk assessment and visualization module: used to generate dynamic risk heat map based on machine learning and big data, visualize seismic wave propagation, pipe network rupture and secondary disaster diffusion process, and support zoned and graded emergency decision-making; Intelligent decision support and optimization module: used to build a resilience assessment system, optimize pipe network renovation and emergency resource allocation strategy, generate dynamic emergency plan and predict function recovery synchronization. 9.The big data based earthquake disaster scenario building system according to claim 8, characterized in that: The risk assessment and visualization module has interactive functions, can generate specified risk assessment reports and customized disaster scenario simulation views according to the needs of operators, supports dynamic adjustment of earthquake parameters and real-time display of corresponding risk heat map and secondary disaster diffusion path, and provides visual basis for precise emergency decision-making.

Images