Fire early warning method and system based on three-dimensional modeling

Abstract

The invention provides a fire early warning method and system based on three-dimensional modeling, and the method comprises the steps: determining the transaction indexes of fire danger at different space units through the spatial structure characteristics of a three-dimensional digital twin model in combination with the state evolution mode of a physical field, and determining a risk cloud picture through all transaction indexes; extracting a risk sub-domain of the fire according to the risk cloud picture, and further generating a heat flux density field matrix among different space units; determining risk fitting degrees of different space units by combining the heat flow diffusion information with the monitoring information of the fire behavior in the target building, and performing time sequence aggregation on the fire risk in the target building according to all the risk fitting degrees and the local temperature field of each space unit to obtain fire danger propagation potential energy; and performing fire diffusion situation monitoring on the target building according to the fire danger propagation potential energy, and outputting a fire diffusion early warning signal. By adopting the scheme of the invention, the diffusion track of the fire heat flow can be accurately identified in the three-dimensional model.

Description

Technical Field

[0001] The present application relates to the field of fire warning technology, and more specifically, to a fire warning method and system based on three-dimensional modeling. Background Art

[0002] Fire warning is an important safety system that uses advanced technical means to monitor, analyze and judge various characteristics before a fire occurs in real time, issue an alarm in advance, and remind relevant personnel to take countermeasures. Its core goal is to accurately identify danger signals at the budding stage of a fire, buy precious time for personnel evacuation and fire fighting, and minimize the loss of life and property. Fire warning plays a vital role in various places. In crowded areas such as commercial complexes, office buildings, and residential areas, it can remind people to evacuate dangerous areas in time; in industrial places such as factories and warehouses, it can inform staff in advance to take measures such as power off and valve closing to prevent the fire from expanding and spreading. With the continuous advancement of science and technology, the fire warning system is developing in the direction of intelligence, integration, and unmanned operation, and is deeply integrated with systems such as video surveillance and fire linkage equipment to form a comprehensive and multi-level fire prevention and control system, providing a more solid safety guarantee for people's production and life.

[0003] In fire warning, three-dimensional modeling is a core technical means to accurately locate, dynamically deduce and visually warn fire hazards by constructing spatial three-dimensional digital models; this technology breaks through the limitations of traditional two-dimensional plane monitoring, and integrates building structures, environmental parameters and real-time monitoring data into a three-dimensional digital twin scene, providing multi-dimensional spatial analysis capabilities for fire prevention. At present, 3D modeling technology has been expanded from single-building applications to city-level full-area monitoring. By integrating multi-source 3D data, a three-dimensional fire prevention and control network covering communities and parks is constructed. Its core value lies in upgrading fire warning from "plane alarm" to "three-dimensional rehearsal", making prevention and control measures more spatially targeted, thereby significantly improving the efficiency of fire response in complex scenarios. However, in the existing fire warning methods based on 3D modeling, they often stay at the level of fire source positioning, and rely on simplified algorithms for dynamic simulation of fire spread. This method has the problem of insufficient adaptability to complex building structures (i.e., the properties of building materials such as wall thermal conductivity, ventilation system resistance, etc. are not coupled with spatial structural parameters for modeling), resulting in the inability of traditional methods to accurately calculate the diffusion trajectory of heat flow in different spatial units (such as in underground shopping mall fires, it is difficult to predict the vertical spread speed of smoke through escalator shafts and the concentration distribution of each shop), and thus cannot provide accurate fire warning paths for personnel evacuation and firefighting deployment in complex scenarios. Therefore, how to accurately identify the diffusion trajectory of fire heat flow in 3D models has become a difficult problem faced by the industry. Summary of the invention

[0004] The present application provides a fire warning method and system based on 3D modeling, which can accurately identify the diffusion trajectory of fire heat flow in a 3D model.

[0005] In a first aspect, the present application provides a fire warning method based on 3D modeling, including the following steps: Obtain a 3D digital twin model of the target building, where the 3D digital twin model includes multiple spatial units in the target building; Based on the spatial structure characteristics of the 3D digital twin model and combined with the state evolution mode of the physical field, determine the abnormal movement indicators of fire risk at different spatial units, and then perform risk fitting on all spatial units through all abnormal movement indicators to obtain a risk cloud map of the fire distribution in the target building; Extract the risk sub-domains of the fire from the target building according to the risk cloud map, and then generate a heat flux density field matrix between different spatial units in the risk sub-domains based on the fire risk evolution model; Determine the risk fitting degree of different spatial units through the heat flux density field matrix combined with the monitoring information of the fire situation in the target building, and then perform temporal aggregation on the fire risks in the target building according to all risk fitting degrees combined with the local temperature field of each spatial unit to obtain the fire risk propagation potential energy of different spatial units; Monitor the fire diffusion trend of the target building based on all fire risk propagation potential energies and output a fire diffusion warning signal.

[0006] In some embodiments, determining the abnormal movement indicators of fire risk at different spatial units based on the spatial structure characteristics of the 3D digital twin model and combined with the state evolution mode of the physical field specifically includes: Obtain the spatial structure characteristics of each spatial unit in the 3D digital twin model; Perform dynamic simulation on the target building according to the state evolution mode of the physical field to obtain the evolution process data of the physical field in each spatial unit; Perform correlation analysis on the spatial structure characteristics and the evolution process data to determine the abnormal movement indicators of fire risk at different spatial units.

[0007] In some embodiments, performing risk fitting on all spatial units through all abnormal movement indicators to obtain a risk cloud map of the fire distribution in the target building specifically includes: Perform fitting calculation on the risk levels of each spatial unit in the target building based on all abnormal movement indicators; Perform spatial mapping processing on the fitting calculation results to generate a risk cloud map of the fire distribution in the target building.

[0008] In some embodiments, extracting the risk sub-domains of the fire from the target building according to the risk cloud map specifically includes: Perform threshold discrimination on the risk levels of each spatial unit in the risk cloud map; Extract the set of spatial units that meet the threshold discrimination conditions as the risk sub - domain of the fire.

[0009] In some embodiments, generating the heat flux density field matrix between different spatial units in the risk sub - domain based on the fire risk evolution model specifically includes: Obtain the state information of each spatial unit in the risk sub - domain; Set the boundary conditions during fire evolution through the state information; Generate the heat flux density field matrix between different spatial units in the risk sub - domain according to the boundary conditions in combination with the fire risk evolution model.

[0010] In some embodiments, determining the risk fitness of different spatial units by combining the heat flux density field matrix with the monitoring information of the fire situation in the target building specifically includes: Obtain the monitoring information of the fire situation in the target building; Determine multiple information difference degrees between the monitoring information and the heat flux density field matrix; Determine the risk fitness of different spatial units through all the information difference degrees.

[0011] In some embodiments, performing temporal aggregation on the fire risks in the target building according to all the risk fitnesses in combination with the local temperature field of each spatial unit to obtain the fire risk propagation potential energy of different spatial units specifically includes: Obtain the local temperature field of each spatial unit in the three - dimensional digital twin model; Perform temporal analysis by combining all the risk fitnesses with the local temperature field of each spatial unit to obtain the temporal risk aggregation model of the target building; Determine the fire risk values of each spatial unit at different time points according to the temporal risk aggregation model; Determine the fire risk propagation potential energy of different spatial units through all the fire risk values.

[0012] In some embodiments, monitoring the fire spread situation of the target building based on all the fire risk propagation potential energies and outputting a fire spread warning signal specifically includes: Analyze the change trend of the fire situation of the target building based on all the fire risk propagation potential energies; Evaluate the change trend of the fire situation according to the preset fire warning rules; When the evaluation result reaches the warning condition, generate and output a fire spread warning signal.

[0013] In some embodiments, the spatial unit is a finite - element unit with uniform spatial attributes.

[0014] In a second aspect, the present application provides a fire warning system based on 3D modeling, including: An acquisition module, configured to acquire a 3D digital twin model of a target building, where the 3D digital twin model includes a plurality of spatial units in the target building; A processing module, configured to determine abnormal movement indicators of fire risks at different spatial units according to the spatial structure characteristics of the 3D digital twin model in combination with the state evolution mode of the physical field, and then perform risk fitting on all spatial units through all the abnormal movement indicators to obtain a risk cloud map of the fire distribution in the target building; The processing module is further configured to extract a risk sub-domain of the fire from the target building according to the risk cloud map, and then generate a heat flux density field matrix between different spatial units in the risk sub-domain based on a fire risk evolution model; The processing module is further configured to determine the risk fitting degree of different spatial units by combining the heat flux density field matrix with the monitoring information of the fire situation in the target building, and then perform temporal aggregation on the fire risks in the target building according to all the risk fitting degrees in combination with the local temperature field of each spatial unit to obtain the fire risk propagation potential of different spatial units; An execution module, configured to monitor the fire spread situation of the target building according to all the fire risk propagation potentials and output a fire spread warning signal.

[0015] The technical solution provided by the embodiments disclosed in the present application has the following beneficial effects: In the fire warning method and system based on 3D modeling provided by the present application, a 3D digital twin model of a target building is acquired, where the 3D digital twin model includes a plurality of spatial units in the target building; abnormal movement indicators of fire risks at different spatial units are determined according to the spatial structure characteristics of the 3D digital twin model in combination with the state evolution mode of the physical field, and then risk fitting is performed on all spatial units through all the abnormal movement indicators to obtain a risk cloud map of the fire distribution in the target building; a risk sub-domain of the fire is extracted from the target building according to the risk cloud map, and then a heat flux density field matrix between different spatial units in the risk sub-domain is generated based on a fire risk evolution model; the risk fitting degree of different spatial units is determined by combining the heat flux density field matrix with the monitoring information of the fire situation in the target building, and then temporal aggregation is performed on the fire risks in the target building according to all the risk fitting degrees in combination with the local temperature field of each spatial unit to obtain the fire risk propagation potential of different spatial units; the fire spread situation of the target building is monitored according to all the fire risk propagation potentials and a fire spread warning signal is output.

[0016] It can be seen that in this application, first, after obtaining the three-dimensional digital twin model of the target building, the risk sub-domains of the fire are extracted based on the abnormal movement indicators of the fire risk at different spatial units. Furthermore, by extracting the state information of the spatial units in the risk sub-domains (such as the material combustion performance and ventilation parameters) and setting them as the boundary conditions of the fire risk evolution model, and combining with the fire dynamics equations to simulate the heat transfer process between the units, key parameters such as the heat conduction rate, direction, and delay time can be quantified (for example, in the specification, the temperature field and heat flux density field are updated by solving the energy conservation equation); through these parameters, the actual propagation path of the heat flux in the building structure can be directly reflected. For example, when passing through a unit with a lower wall thermal resistance, the heat conduction rate is faster, or the diffusion direction is changed by the influence of the ventilation system; in addition, by introducing the difference analysis between the real-time monitoring data and the model prediction value (such as calculating the deviation of the heat conduction rate by the Euclidean distance), the simulation results of the heat flux trajectory can be dynamically corrected to avoid misjudgment of the path caused by the simplified algorithm; subsequently, the risk fitness of different spatial units is determined by combining the heat flux density field matrix with the monitoring information of the fire situation in the target building. Furthermore, according to all the risk fitness and the local temperature field of each spatial unit, the fire risk in the target building is aggregated in time series to obtain the fire risk propagation potential energy of different spatial units, that is: by inputting the fire risk value and the physical properties of the spatial unit (such as the wall thermal resistance and the calorific value of combustibles) into the physical field coupling model or the machine learning model, calculating indicators such as the heat transfer conduction rate and the heat release rate gradient, and dynamically assigning weights according to the fire stage (such as focusing on the heat conduction rate in the initial stage), the potential ability of each unit to spread the fire to the surrounding can be comprehensively evaluated; this quantitative evaluation can identify the key paths of the heat flux diffusion. For example, the units with high fire risk propagation potential energy usually form the main channels of the heat flux diffusion, and the continuous distribution formed by the spatial-temporal interpolation of its risk value field can intuitively present the spatial diffusion range of the heat flux (such as generating the risk value field by Kriging interpolation in the specification); finally, based on all the fire risk propagation potential energies, the fire diffusion situation of the target building is monitored, and a fire diffusion warning signal is output; in summary, this solution can accurately identify the diffusion trajectory of the fire heat flux in the three-dimensional model. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 is a schematic flowchart of a fire warning method based on three-dimensional modeling according to some embodiments of the present application; Figure 2 is a schematic flowchart of implementing threshold discrimination according to some embodiments of the present application; Figure 3 is a schematic flowchart of determining the risk fitness according to some embodiments of the present application; Figure 4 is a schematic structural diagram of a fire warning system based on three-dimensional modeling according to some embodiments of the present application; Figure 5It is an internal structural diagram of a computer device for implementing a fire warning method based on 3D modeling as shown in some embodiments of the present application. Detailed implementation manners

[0018] To better understand the technical solutions in this embodiment, the technical solutions in this embodiment will be described in detail below in conjunction with the accompanying drawings of the specification and specific implementation manners.

[0019] Referring to Figure 1 , this figure is a schematic flowchart of a fire warning method based on 3D modeling as shown in some embodiments of the present application. The fire warning method 100 based on 3D modeling mainly includes the following steps: In step 101, a 3D digital twin model of the target building is obtained. The 3D digital twin model includes multiple spatial units in the target building.

[0020] In specific implementation, a 3D perception device (such as a lidar device, a structured light scanning module, or a depth camera) can be deployed inside the target building to perform a full-coverage spatial scan of the target building, and a spatial structure image including walls, doors, windows, passages, ceilings, etc. can be obtained in real time. At the same time, a multi-source environment acquisition module (such as a temperature sensor, a smoke sensor, an infrared imaging device) configured on the same monitoring platform or adjacent positions is used to obtain environmental state images of the interior of the target building at different time points as the 3D digital twin model in the present application.

[0021] It should be noted that the 3D digital twin model is a highly realistic representation of the real target building in the digital space, with mapping characteristics in multiple dimensions such as geometry, physics, and behavior. This model not only includes the static structural information of the target building, such as wall structure, passage distribution, door and window positions, etc., but also includes its dynamic evolution information, such as multi-dimensional state data such as temperature change, risk diffusion, and personnel flow. In addition, the spatial unit in the 3D digital twin model is the smallest modeling unit after discrete division of the target building, that is: the spatial unit is a finite element unit with unified spatial attributes, and each spatial unit carries its corresponding geometric coordinates, structural attributes, and physical state parameters (such as temperature value, risk value, ventilation rate, etc.).

[0022] In step 102, the abnormal movement indicators of fire risks at different spatial units are determined based on the spatial structure characteristics of the 3D digital twin model and the state evolution mode of the physical field. Then, all spatial units are risk-fitted through all abnormal movement indicators to obtain a risk cloud map of the fire distribution in the target building.

[0023] In some embodiments, the abnormal movement index of fire risk at different spatial units can be determined by combining the spatial structure characteristics of the three-dimensional digital twin model with the state evolution mode of the physical field, which can be realized by the following steps: Obtain the spatial structure characteristics of each spatial unit in the three-dimensional digital twin model; Conduct dynamic simulation on the target building according to the state evolution mode of the physical field, and obtain the evolution process data of the physical field in each spatial unit; Perform correlation analysis on the spatial structure characteristics and the evolution process data to determine the abnormal movement index of fire risk at different spatial units.

[0024] Preferably, the unit volume, surface area, and aspect ratio of length, width, and height can be extracted from the geometric data of the three-dimensional digital twin model; then, construct an adjacency matrix of spatial units and calculate the connectivity of each unit; next, detect the fire resistance limit parameters of the fire separation components at the unit boundaries, calculate the separation defect ratio, and use Dijkstra's algorithm to calculate the shortest distance and path tortuosity from the unit to the nearest safe exit; finally, calculate the ventilation volume and ventilation efficiency of the unit based on fluid mechanics, extract the thermal physical properties parameters of the enclosure structure and calculate the equivalent thermal resistance, and further use the unit volume, surface area, aspect ratio of length, width, and height, connectivity, fire separation parameters, evacuation path parameters, ventilation parameters, and heat conduction parameters as the spatial structure characteristics of each spatial unit; in other embodiments, through edge nodes with limited computing resources, the three-dimensional spatial units can be projected onto a two-dimensional plane, and simplified geometric features such as perimeter and area can be extracted, and the high-dimensional structure features can be compressed through principal component analysis. The present application does not limit this.

[0025] It should be noted that the spatial structure characteristics in the present application refer to a multi-dimensional parameter set formed by extracting and calculating the geometric data, topological relationship, structural safety, and environmental parameters of each spatial unit in the three-dimensional digital twin model, and after calculating indexes such as unit volume, surface area, connectivity, fire separation parameters, and ventilation parameters; the spatial structure characteristics are represented as a set of structured parameters in terms of characterization form, and each parameter corresponds to a quantitative description of the spatial unit in terms of geometric form, connection relationship, safety performance, and environmental characteristics. The parameter values directly reflect the differences in the structural attributes of the spatial units and can be used for subsequent analysis of the characteristics of different spatial units in terms of fire risk bearing capacity.

[0026] In specific implementation, dynamic simulation is performed on the target building according to the state evolution mode of the physical field. The data of the evolution process of the physical field in each spatial unit can be obtained by the following method: First, determine the physical field simulation model. For the heat conduction process, the Fourier heat conduction equation is selected, and for the smoke diffusion, large eddy simulation or zone model is used. The model parameters are set according to the characteristics of the target building, such as the material thermal conductivity, environmental wind speed, etc. Then, the spatial units in the three-dimensional digital twin model are used as the simulation calculation grids, and initial conditions are assigned to each spatial unit, including initial temperature, oxygen concentration, combustible distribution, etc. Next, set the simulation time step, which is 10 seconds / step in the initial warning stage and switches to 1 second / step in the fire development stage, and start the simulation calculation. Finally, at the end of each time step, the physical field parameters in each spatial unit are extracted, including temperature, heat flux density, smoke concentration, CO concentration, etc., to form the data of the evolution process of the physical field in each spatial unit. As a preferred embodiment, parallel computing technology can be used to distribute the simulation tasks of different spatial units to multiple computing cores to improve the simulation efficiency. In other embodiments, a reduced-order modeling method can be introduced to simplify the physical field model through techniques such as Proper Orthogonal Decomposition (POD), etc., to reduce the computational complexity while ensuring the computational accuracy. The present application does not limit this.

[0027] It should be noted that the evolution process data in this application refers to the time-series data set formed by arranging in time sequence the physical field parameters such as temperature, heat flux density, smoke concentration, CO concentration, etc. in each spatial unit after performing dynamic simulation on the target building according to the state evolution mode of the physical field, setting simulation model parameters, dividing calculation grids, assigning initial conditions, and performing simulation calculations. The evolution process data is represented as a multi-dimensional time-series numerical set. Each numerical value corresponds to the instantaneous state of the physical field parameters in the spatial unit at a specific time point, and its numerical change directly reflects the dynamic evolution of the physical field in the spatial unit over time, and can be used for subsequent construction of the fire risk evolution model and prediction of the fire development trend.

[0028] In specific implementation, the correlation analysis is performed on the spatial structure features and the evolution process data to determine the abnormal movement indicators of fire risk at different spatial units, which can be achieved in the following manner: First, a feature correlation matrix is constructed with the spatial structure feature parameters as row vectors and the evolution process data parameters as column vectors; then, feature selection is performed based on the feature correlation matrix, and parameter pairs with an absolute value of the correlation coefficient ≥ 0.6 are retained to construct a high-correlation feature subset; finally, the spatial structure feature parameters and the evolution process data parameters in the high-correlation feature subset are input into a multi-layer perceptron model, and the abnormal risk probability values of each spatial unit are output through the softmax function. Furthermore, the abnormal risk probability values are used as the abnormal movement indicators of fire risk at the corresponding spatial units. Among them, as a preferred embodiment, the random forest algorithm can be used to rank the importance and reduce the dimension of the high-correlation feature subset; in other embodiments, the evidence theory can be used to fuse multi-source features to improve the robustness of the abnormal movement indicators, which is not limited in this application.

[0029] It should be noted that the abnormal movement indicator in this application refers to a quantitative evaluation parameter constructed by performing correlation analysis on the spatial structure feature parameters and the evolution process data parameters; the abnormal movement indicator is in the form of a probability value output through the softmax function by a multi-layer perceptron model. This value corresponds to the risk abnormality degree of each spatial unit in a specific time dimension, and its numerical size directly reflects the coupling abnormal state of the physical field parameters and the structure feature parameters in the spatial unit.

[0030] In some embodiments, the risk cloud map of the fire distribution in the target building can be obtained by fitting the risks of all spatial units through all abnormal movement indicators, which can be achieved by the following steps: Perform fitting calculations on the risk levels of each spatial unit in the target building based on all abnormal movement indicators; Perform spatial mapping processing on the fitting calculation results to generate the risk cloud map of the fire distribution in the target building.

[0031] In specific implementation, the fitting calculation of the risk level of each spatial unit in the target building can be achieved based on all abnormal change indicators in the following way: First, determine the number of components of the Gaussian mixture model based on the Bayesian information criterion; then, perform standardized preprocessing on the abnormal change indicators, map each indicator to the interval [0, 1] to obtain the normalized value; next, input all the normalized values into the Gaussian mixture model, and construct a risk fitting model by iteratively calculating the mean, covariance, and weight parameters of each Gaussian component; then, use the expectation-maximization algorithm to iteratively update the mean vector, covariance matrix, and mixing coefficient of the risk fitting model to maximize the log-likelihood function; finally, input the abnormal change indicators of each spatial unit into the updated risk fitting model, output the posterior probability that the spatial unit belongs to the high-risk category, and use this probability value as the fitting calculation result of the risk level of the corresponding spatial unit. Among them, as a preferred embodiment, the Z-score standardization method can be used in the standardized preprocessing; in other implementation manners, the determination process of the number of components of the Gaussian mixture model can be optimized through cross-validation, and the present application does not limit this.

[0032] In specific implementation, the spatial mapping process of the fitting calculation result to generate a risk cloud map of fire distribution in the target building can be achieved in the following way: First, perform grid division on the target building, divide it into square or hexagonal grid units with uniform sizes, and establish the coordinate mapping relationship between each grid unit and the risk level value obtained from the fitting calculation; then, use the Kriging interpolation algorithm to process the discrete risk level values, estimate and fill the risk values in the grid gap area through spatial autocorrelation analysis, and construct a continuous risk value distribution surface; next, set a risk level color mapping table, map the low, medium, and high risk levels to color gradients such as blue, yellow, and red respectively, and convert the surface risk values into corresponding color values; finally, perform layer superposition rendering on the risk surface with color information and the three-dimensional digital twin model of the target building to generate a visual fire distribution risk cloud map; among them, as a preferred embodiment, the grid density can be dynamically adjusted according to the complexity of the spatial unit during the grid division; in other implementation manners, the inverse distance weighted interpolation method can be used to replace the Kriging interpolation algorithm for risk value estimation, and the present application does not limit this; preferably, establishing the coordinate mapping relationship between each grid unit and the risk level value specifically includes: constructing a Cartesian coordinate system to divide the target building into square grids, determining the coordinates (x, y) of the lower left vertex of each grid; then, corresponding each grid coordinate to the risk level value obtained from the fitting calculation one by one, and storing it in the hash table in the form of key-value pairs to form the mapping relationship between the grid coordinate and the risk value.

[0033] In step 103, a risk sub-domain of a fire is extracted from the target building based on the risk cloud map, and then a heat flux density field matrix between different spatial units in the risk sub-domain is generated based on the fire risk evolution model.

[0034] In some embodiments, the extraction of the fire risk sub-domain from the target building according to the risk cloud map can be implemented by the following steps: Perform threshold discrimination on the risk levels of each spatial unit in the risk cloud map; Extract the set of spatial units that meet the threshold discrimination conditions as the fire risk sub-domain.

[0035] Preferably, the maximum inter-class variance method can be used to automatically calculate the risk threshold for the risk level values of all spatial units in the risk cloud map, so as to obtain the risk threshold. Among them, the maximum inter-class variance method determines the optimal segmentation threshold by maximizing the inter-class variance; if different scenario characteristics need to be considered, an artificial intervention mechanism can be set up to manually adjust the threshold according to historical fire data or expert experience; therefore, as a preferred embodiment, refer to Figure 2 As shown, this figure is a schematic flowchart of threshold discrimination shown in some embodiments of the present application. The threshold discrimination of the risk levels of each spatial unit in the risk cloud map can be implemented in the following manner, that is: compare the risk level value of each spatial unit with the risk threshold, mark the spatial unit with a risk level value greater than or equal to the risk threshold as a high-risk unit, and the one less than the risk threshold as a low-risk unit to complete the threshold discrimination process; among them, as a preferred embodiment, the dynamic sliding window method can be used to calculate the threshold for different regions of the risk cloud map to adapt to the risk characteristic differences in different environments within the target building; in other embodiments, a machine learning model (such as a support vector machine) can be used to train a threshold discrimination model, and the discrimination result can be automatically output according to the input spatial unit characteristics. The present application does not limit this.

[0036] In specific implementation, the set of spatial units that meet the threshold discrimination condition can be extracted as the fire risk sub - domain in the following way: First, perform connectivity analysis on the spatial units that have passed the threshold discrimination. Use the eight - neighborhood connectivity region labeling algorithm to identify high - risk spatial units that are adjacent and have risk level values greater than or equal to the threshold. Then, cluster the mutually connected high - risk spatial units, and each clustering set is regarded as a potential risk sub - domain. Next, filter the sub - domains obtained by clustering. Set a minimum area threshold (for example, clusters containing less than 3 spatial units are excluded) to remove isolated small regions caused by noise or misjudgment. Finally, take the clustering set of the remaining high - risk spatial units as the final fire risk sub - domain. Among them, as a preferred embodiment, a topological distance constraint can be introduced during connectivity analysis to restrict the merging of spatial units across fire prevention zones, ensuring that the risk sub - domain meets the actual physical isolation conditions. In other implementation manners, the boundary division of the risk sub - domain can be optimized by the minimum spanning tree algorithm in graph theory, and the present application does not limit this.

[0037] It should be noted that the fire risk sub - domain described in this application refers to the set of spatial units that meet the threshold conditions and are mutually connected after threshold discrimination of the risk levels of spatial units in the risk cloud map. The fire risk sub - domain is structurally a clustering region formed by high - risk spatial units through eight - neighborhood connectivity analysis and is retained after minimum area filtering. Its scope directly reflects the aggregation degree and spatial distribution characteristics of fire risks in the target building, and can be used for subsequent fire - fighting resource scheduling and fire prevention and control strategy formulation.

[0038] In some embodiments, generating the heat flux density field matrix between different spatial units in the risk sub - domain based on the fire risk evolution model can be implemented by the following steps: Obtain the state information of each spatial unit in the risk sub - domain; Set the boundary conditions during fire evolution through the state information; Generate the heat flux density field matrix between different spatial units in the risk sub - domain according to the boundary conditions and the fire risk evolution model.

[0039] Preferably, after extracting the risk level values of each spatial unit from the grid coordinate mapping table corresponding to the risk sub - domain, the physical attribute data of the spatial unit can be obtained through a geographic information system or a building information model, including the combustion performance grade of building materials (such as non - combustible grade A, difficult - to - burn grade B1), ventilation conditions (such as the proportion of door and window area), and fire source load density (such as MJ / m²). Then, combined with real - time monitoring data (such as temperature, smoke concentration sensor data) or historical statistical data, a state information vector containing multi - dimensional data such as risk level, combustion performance, ventilation parameters, and fire source load is generated as the state information of each spatial unit in the risk sub - domain.

[0040] In specific implementation, setting the boundary conditions during fire evolution through the state information can be achieved in the following manner: First, map the building physical property parameters (such as the thermal conductivity of wall materials and the heat release rate of combustible materials) in the state information to the material boundary conditions of the fire risk evolution model; then, convert the environmental parameters (such as the space ventilation volume and the air exchange rate) into the hydrodynamic boundary conditions of the model; then, map the fire risk level corresponding to the risk level value to the probability trigger boundary condition of the model, and set the ignition probability thresholds corresponding to different risk levels; among them, as a preferred embodiment, the parameter sensitivity analysis method can be used to rank the weights of the key parameters (such as the ventilation coefficient and the fire source load) in the state information, and preferably set the high-weight parameters as strong constraint boundary conditions; in other implementation manners, the mapping relationship table between the state information and the boundary conditions can be established through a machine learning algorithm, and the present application does not limit this.

[0041] In specific implementation, the heat flux density field matrix between different spatial units in the risk sub-domain can be generated according to the boundary conditions in combination with the fire risk evolution model in the following way, that is: First, based on the computational grid topology of the fire risk evolution model, establish a one-to-one mapping relationship between the spatial units in the risk sub-domain and the model grid nodes, and configure the material physical parameters (including material thermal conductivity, heat storage characteristics, etc.) and fluid dynamics parameters (such as air flow velocity at the ventilation opening, spatial pressure distribution, etc.) in the boundary conditions for each network node to complete the initial parameter configuration of the model; Second, based on the quantitative mapping relationship between the risk level value and the fire ignition probability threshold (the quantitative mapping relationship can be fitted through historical fire data or constructed by a theoretical model), adopt a probability-weighted random sampling strategy (such as polynomial distribution sampling or roulette wheel selection method) to determine the initial fire source node in the risk sub-domain; Calculate the initial heat release rate according to the fire source load density of the initial fire source node (characterizing the potential heat release capacity of combustibles per unit area) (reflecting the initial heat release intensity of combustibles per unit area); At the same time, according to Fourier's law of heat conduction (the heat flow direction is opposite to the temperature gradient direction, and the heat flux density is related to the material thermal conductivity and temperature gradient), calculate the initial heat flux density between the fire source node and adjacent nodes; Subsequently, by numerically solving the fire dynamics control equation set including the energy conservation equation (describing the dynamic balance law of heat input, output and storage) and the momentum conservation equation (describing the fluid dynamics law of the momentum change of heat flow movement), use the finite difference method or the finite element method to discretize the control equation in time, set the time step of the initial stage to 0.1 second and the time step of the development stage to 0.01 second, and iteratively calculate the temperature field, heat flux density field and smoke concentration field distribution of each node within each time step; Finally, extract the heat flux density vector (including amplitude and direction information) of each spatial unit node at the current moment, and construct a heat flux density field matrix with the heat flow transfer direction between nodes as the row index and the receiving node as the column index (the matrix element represents the heat flux density value from the source unit to the target unit at the corresponding moment, with the unit of watts per square meter).

[0042] In other embodiments, a reduced-order modeling technique (such as orthogonal decomposition method) can also be introduced to compress the high-dimensional heat flow field and reduce the computational complexity, which is not limited in this application.

[0043] It should be noted that the heat flux density field matrix described in this application refers to a multi-dimensional matrix generated based on the fire risk evolution model, which characterizes the heat flux transfer intensity and direction between spatial units within the risk sub-domain; this matrix uses the heat flux transfer path between spatial units as the row index, the receiving unit as the column index, and the matrix element is the heat flux density value (unit: W / m²). The numerical size reflects the strength of heat flux transfer, and the positive or negative sign or vector direction characterizes the heat flux diffusion direction (such as from a high-temperature unit to a low-temperature unit); in addition, the fire risk evolution model refers to a mathematical calculation model constructed based on fire dynamics theory, which is used to simulate the occurrence, development, and spread process of fires in spatial units within the risk sub-domain.

[0044] In step 104, the risk fitness of different spatial units is determined by combining the heat flux density field matrix with the monitoring information of the fire situation in the target building. Then, based on all the risk fitnesses and the local temperature field of each spatial unit, the fire risks in the target building are aggregated in time series to obtain the fire risk propagation potential of different spatial units.

[0045] In some embodiments, refer to Figure 3 As shown, this figure is a schematic flowchart of determining the risk fitness shown in some embodiments of this application. The risk fitness of different spatial units can be determined by combining the heat flux density field matrix with the monitoring information of the fire situation in the target building through the following steps: First, in 1041, obtain the monitoring information of the fire situation in the target building. Then, in 1042, determine multiple information difference degrees between the monitoring information and the heat flux density field matrix. Finally, in 1043, determine the risk fitness of different spatial units through all the information difference degrees.

[0046] As a preferred embodiment, a multi-type Internet of Things sensor network can be deployed to cover each spatial unit of the target building, including but not limited to temperature sensors (such as thermocouples, infrared temperature detectors), smoke concentration sensors (such as light-scattering smoke detectors), gas composition sensors (such as CO, CO2 concentration detectors), and flame detectors (such as ultraviolet / infrared dual-band flame sensors) to collect physical environment data in real time; then, the sensor data is transmitted to the edge computing node or cloud server through a wireless communication protocol for data cleaning and preprocessing (such as removing outliers and filling in missing values); then, a mapping relationship between the monitoring information and the spatial unit is established, and the collected data is matched to the corresponding spatial unit through positioning technology or sensor deployment address tags; finally, a time-series monitoring data set is generated at a preset frequency (such as second-level, minute-level) as the monitoring information of the fire situation in the target building.

[0047] In specific implementation, multiple information difference degrees between the monitoring information and the heat flux density field matrix are determined, that is: the inconsistency between the monitoring information and the heat flux density field matrix is used as the information difference degree; specifically including: First, align the real-time parameters (such as heat conduction rate, conduction direction, heat transfer delay time) representing heat transfer between spatial units in the monitoring information with the model prediction values of corresponding unit pairs at the same moment in the heat flux density field matrix to form a set of parameter pairs; Then, for each parameter pair, use a distance metric algorithm (Euclidean distance algorithm) to calculate the information difference degree. For example: use the Euclidean distance to calculate the absolute deviation between the measured value and the simulated value of the heat conduction rate parameter, and use the angle difference formula to calculate the degree of direction deviation for the conduction direction parameter; Then, introduce the time dimension difference evaluation, and calculate the temporal matching degree between the monitoring information sequence and the heat flux density field matrix sequence through the dynamic time warping algorithm to quantify the time axis offset error caused by the difference in heat conduction rate change (such as the temporal misalignment between the measured heat conduction delay and the model prediction value); Finally, construct a multi-dimensional difference degree vector, and perform normalization processing on each parameter difference degree (heat conduction rate difference, conduction direction difference, delay time difference) and the time difference degree, and then perform weighted fusion. The formed comprehensive difference degree index is used as the information difference degree in this application; Among them, as a preferred embodiment, the weight coefficients of each parameter difference degree can be objectively calculated by the entropy weight method (such as assigning a higher weight to the heat conduction rate difference to reflect the energy transfer efficiency); In other implementation manners, a fuzzy logic algorithm can be used to qualitatively evaluate the difference degree of non-linear parameters (such as the modulation effect difference of flue gas concentration on heat conduction), and this application does not limit this.

[0048] In specific implementation, the risk fitness degree of different spatial units can be determined by all information differences in the following way: Firstly, based on historical fire case data or laboratory simulation samples, a mathematical relationship model is trained using machine learning algorithms (such as linear regression, random forest, neural network). Multidimensional information such as temperature difference degree, smoke concentration difference degree, gas composition difference degree, and time series difference degree of each spatial unit is used as input variables, and the initial value of the risk fitness degree (the value range is [0, 1]) is output through model parameter learning. For example, when using a neural network model, the number of neurons in the input layer can be set to be the same as the dimension of the difference degree. The hidden layer captures the non-linear relationship through a rectified linear unit function, and the output layer normalizes the result to a probability value through a sigmoid function. Subsequently, according to the characteristics of the fire evolution stage (such as the temperature rise rate being the dominant factor in the initial stage, smoke diffusion being the core in the development stage, and gas products being the key indicator in the full bloom stage), the weight vector of each difference degree parameter is automatically adjusted through a fuzzy logic controller. For example, in the initial stage of the fire (0 - 10 minutes), the weight of the temperature difference degree is set to 0.5, the weight of the smoke concentration is 0.3, and the weight of the gas composition is 0.2. After entering the development stage (10 - 30 minutes), it is automatically adjusted to temperature 0.3, smoke 0.5, gas 0.2, so as to adapt to the change of the risk dominant factors in different fire development stages. Finally, the risk fitness degree is divided into four levels: low risk (<0.3), medium risk (0.3 - 0.6), high risk (0.6 - 0.8), and extremely high risk (>0.8), and a risk fitness degree matrix with risk fitness degree level labels is generated based on the grid coordinate system. Among them, each element in the risk fitness degree matrix corresponds to a spatial unit, including coordinates and the corresponding risk fitness degree.

[0049] It should be noted that the risk fitness degree in this application refers to an index of the credibility of the fire risk of a spatial unit quantified by fusing the multi-dimensional differences of monitoring information and heat flow diffusion information. The risk fitness degree can be used to characterize the degree of coincidence between the prediction result of the risk fitness degree model and the actual fire situation in numerical form (the value range is [0, 1]). The higher the value, the higher the credibility of the fire risk prediction.

[0050] In some embodiments, the temporal aggregation of the fire risk in the target building can be achieved by combining all risk fitness degrees with the local temperature field of each spatial unit to obtain the fire risk propagation potential of different spatial units through the following steps: Obtain the local temperature field of each spatial unit in the three-dimensional digital twin model; Through temporal analysis by combining all risk fitness degrees with the local temperature field of each spatial unit, a temporal risk aggregation model of the target building is obtained; Determine the fire risk value of each spatial unit at different time points according to the temporal risk aggregation model; Determine the fire risk propagation potential of different spatial units based on all fire risk values.

[0051] As a preferred embodiment, temperature data of each spatial unit can be collected in real time by temperature sensors (such as thermocouples, infrared temperature detectors) deployed in the target building, and the data can be matched with the corresponding grid cells in the three-dimensional digital twin model using a positioning system; then, for areas where sensors are not deployed, spatial interpolation algorithms (such as inverse distance weighted interpolation, Kriging interpolation) are used to estimate the missing data based on the measured temperature values of neighboring sensors; then, the discrete temperature data collected and estimated are mapped to the grid nodes of the three-dimensional digital twin model to form the temperature distribution of each spatial unit at a certain moment; finally, the temperature distribution data at each moment are stored in time series to construct a continuous local temperature field change sequence as the local temperature field of each spatial unit in the three-dimensional digital twin model. In other embodiments, other methods can also be used to obtain it, which is not limited here.

[0052] Specifically, when implemented, time series analysis is performed by combining all risk fitness with the local temperature field of each spatial unit to obtain the time series risk aggregation model of the target building. The following method can be used, that is: first, the risk fitness of each spatial unit at different time points is concatenated with the parameters (such as temperature value, temperature rise rate) in the local temperature field parameters at the corresponding time points to obtain a multi-dimensional time series feature vector including the time dimension; then, a time series modeling algorithm is used to analyze the feature vector, for example, using the memory unit of a long short-term memory network to capture the long-term dependence relationship between the risk fitness and the local temperature field, or extracting features at different time scales through the dilated causal convolution of a time series convolutional network; then, an attention mechanism is introduced to dynamically allocate weights for different time steps and feature dimensions, and higher weights are assigned to the characteristic parameters in the critical stages of fire (such as the sudden temperature rise in the initial stage, smoke diffusion in the development stage); finally, the network parameters (such as the gating threshold of the long short-term memory network, the convolution kernel size of the time series convolutional network) are optimized through model training to enable the model output to represent the coupled evolution characteristics of the risk fitness and the temperature field, and a time series risk aggregation model of the target building is obtained; among them, as a preferred embodiment, a sliding time window can be used to perform frame processing on the time series data; in other embodiments, the model output can be post-corrected by combining expert rules, which is not limited in this application.

[0053] When specifically implemented, determining the fire risk value of each spatial unit at different time points according to the temporal risk aggregation model can be achieved by the following method, that is: First, input the multi-dimensional temporal feature vectors of each spatial unit (including the risk fitting degree sequence, temperature value sequence, temperature rise rate sequence, etc.) into the trained temporal risk aggregation model, and calculate the risk aggregation feature values of the unit at each time point through the temporal feature extraction layer of the model (such as the hidden layer of the long short-term memory network, the convolutional layer of the temporal convolutional network); then, use the fully connected layer or the regression layer to map the risk aggregation feature values to specific fire risk values, so as to obtain the fire risk values of each spatial unit at different time points; preferably, using the fully connected layer or the regression layer to map the risk aggregation feature values to specific fire risk values specifically includes: performing matrix multiplication operation on the risk aggregation feature values through the neuron weight matrix of the fully connected layer, and outputting a one-dimensional scalar as the corresponding fire risk value after adding the bias and passing through the activation function (such as a linear function). In other embodiments, other methods can also be used to implement this, which is not limited here.

[0054] When specifically implemented, determining the fire risk propagation potential of different spatial units through all fire risk values can be achieved by the following method, that is: First, establish a spatio-temporal mapping relationship between the fire risk values of each spatial unit at different time points and the grid nodes of the three-dimensional digital twin model to form a set of spatio-temporal data points with weights, then use the spatio-temporal interpolation algorithm in the prior art to smooth the discrete data points to generate a continuous risk value field, and then extract the physical properties such as the structural parameters (such as wall thermal resistance, ventilation volume, spatial volume) and material parameters (such as calorific value of combustibles, thermal conductivity, specific heat capacity) of each spatial unit from the three-dimensional digital twin model. Input the risk value field data and the unit physical properties into the physical field coupling model (such as a multi-field coupling algorithm based on the heat conduction equation and the energy conservation equation) or the machine learning regression model (such as a trained neural network) to calculate the heat transfer conduction rate, heat release rate gradient, and smoke diffusion potential difference of each spatial unit. Finally, dynamically assign weights according to the fire development stage (such as the initial stage and the development stage) (such as emphasizing the heat conduction rate weight in the initial stage and the smoke diffusion potential difference weight in the development stage), and use the weighted fusion comprehensive index value as the fire risk propagation potential of the corresponding spatial unit.

[0055] It should be noted that the fire risk value described in this application refers to a quantitative index representing the degree of fire risk of a spatial unit at a specific time point, which is calculated through a time-series risk aggregation model; the fire risk value maps the risk aggregation eigenvalue to a scalar value in the range of [0, 100] through a fully connected layer or a regression layer. The larger the value of the fire risk value, the higher the fire risk; in addition, the fire risk propagation potential energy refers to an index of the fire risk propagation ability obtained by quantifying the fire risk value of a spatial unit and physical attribute parameters; the physical field coupling model refers to a multi-field coupling calculation model constructed based on physical laws such as the heat conduction equation and the energy conservation equation; this model takes the risk value field data of spatial units (such as continuous fire risk value distribution), structural parameters (wall thermal resistance, ventilation volume), and material parameters (combustible calorific value, thermal conductivity) as inputs, and solves the coupling relationship of multi-physical fields such as heat conduction, heat release, and smoke diffusion through numerical calculation methods, and outputs physical quantities such as heat transfer conduction rate and heat release rate gradient, which characterize the fire propagation ability.

[0056] In step 105, monitor the fire spread situation of the target building according to all the fire risk propagation potential energies, and output a fire spread warning signal.

[0057] In some embodiments, monitoring the fire spread situation of the target building according to all the fire risk propagation potential energies and outputting a fire spread warning signal can be realized by the following steps: Analyze the change trend of the fire situation of the target building based on all the fire risk propagation potential energies; Evaluate the change trend of the fire situation according to the preset fire warning rules; When the evaluation result meets the spread warning condition, generate and output a fire spread warning signal.

[0058] Specifically, analyzing the change trend of the fire situation of the target building based on all the fire risk propagation potential energies can be realized in the following way, that is: First, extract the characteristics of all the fire risk propagation potential energies to obtain parameters such as the risk diffusion speed (the centroid displacement distance of the spatial unit per unit time), the risk propagation direction (the azimuth angle of the centroid connection line of the spatial unit at adjacent times), and the risk intensity change rate (the first derivative of the fire risk propagation potential energy of the spatial unit per unit time); then, construct a multi-dimensional feature vector with the above parameters according to the time series, and use time series prediction algorithms such as linear regression and exponential smoothing to fit the trend of the feature vector to obtain the future change curves of each parameter; output as the change trend of the fire situation of the target building.

[0059] In specific implementation, the evaluation of the change trend of the fire situation according to the preset fire warning rules can be achieved in the following way, that is: input parameters such as the risk diffusion speed, risk propagation direction, and risk intensity change rate in the change trend of the fire situation into the rule evaluation module, and compare them with the preset multi-level thresholds (such as the risk diffusion speed threshold ≥ 5m / min, the risk intensity change rate threshold ≥ 10 units / min); calculate the comprehensive evaluation score of each parameter through the weighted summation algorithm, map the comprehensive evaluation score to the preset warning level interval (blue warning [0, 30), yellow warning [30, 60), orange warning [60, 80), red warning [80, 100]), and generate a structured evaluation report including the warning level, trigger parameters, and confidence level as the evaluation result; as a preferred embodiment, when the evaluation result meets the diffusion warning condition, generate and output a fire diffusion warning signal, that is: compare the comprehensive evaluation score in the evaluation result with the preset warning threshold, and trigger the warning signal generation process when the comprehensive evaluation score is greater than or equal to the warning threshold; generate JSON-format warning information including the warning level, timestamp, risk area coordinates, and development trend prediction according to the warning level; and asynchronously push the warning information to the fire command center data interface, the three-dimensional digital twin system visualization module, and the on-site sound and light alarm controller through the message queue, and at the same time record the audit log including the warning trigger time, release channel, and recipient confirmation status; when the comprehensive evaluation score is greater than or equal to the warning threshold, do nothing; where the warning threshold can be set according to the warning scenario, for example: when the warning scenario is a densely populated but low-risk area (such as schools, hospitals, shopping malls (without inflammable and explosive items)), a larger warning threshold is set to avoid false alarms causing panic or evacuation chaos; when the warning scenario is an inflammable and explosive area (such as chemical plants, gas stations, dangerous goods warehouses), a smaller warning threshold is set to avoid chain reactions such as explosions.

[0060] In addition, on the other hand of the present application, in some embodiments, the present application provides a fire warning system based on three-dimensional modeling. Refer to Figure 4 , this figure is a schematic structural diagram of a fire warning system based on three-dimensional modeling according to some embodiments of the present application. The fire warning system 200 based on three-dimensional modeling includes: The acquisition module 201, the processing module 202, and the execution module 203 are described as follows: The acquisition module 201. In the present application, the acquisition module 201 is mainly used to acquire the three-dimensional digital twin model of the target building, and the three-dimensional digital twin model includes multiple spatial units in the target building. The processing module 202. In this application, the processing module 202 is mainly used to determine the abnormal movement indicators of fire risks at different spatial units according to the spatial structure characteristics of the three-dimensional digital twin model in combination with the state evolution mode of the physical field, and then perform risk fitting on all spatial units through all the abnormal movement indicators to obtain a risk cloud map of the fire distribution in the target building; In addition, the processing module 202 in this application is also used to extract the risk sub-domains of the fire from the target building according to the risk cloud map, and then generate a heat flux density field matrix between different spatial units in the risk sub-domains based on the fire risk evolution model; In addition, the processing module 202 in this application is also used to determine the risk fitting degree of different spatial units by combining the heat flux density field matrix with the monitoring information of the fire situation in the target building, and then perform temporal aggregation on the fire risks in the target building according to all the risk fitting degrees in combination with the local temperature field of each spatial unit to obtain the fire risk propagation potential of different spatial units; The execution module 203. In this application, the execution module 203 is mainly used to monitor the fire spread situation of the target building according to all the fire risk propagation potentials and output a fire spread warning signal.

[0061] In addition, this application also provides a computer device, which includes a memory and a processor. The memory stores code, and the processor is configured to obtain the code and execute the above-mentioned fire warning method based on three-dimensional modeling.

[0062] In some embodiments, refer to Figure 5 , this figure is the internal structure diagram of a computer device for implementing the fire warning method based on three-dimensional modeling according to some embodiments of this application. The above-mentioned fire warning method based on three-dimensional modeling can be implemented by Figure 5 the computer device shown. This computer device 300 includes at least one processor 301, a communication bus 302, a memory 303, and at least one communication interface 304.

[0063] The processor 301 can be a general-purpose central processing unit (CPU), or an application-specific integrated circuit (ASIC), or one or more for controlling the execution of the fire warning method based on three-dimensional modeling in this application.

[0064] The communication bus 302 is used to transmit information between the above components.

[0065] The memory 303 can be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or can also be an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compact discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), a magnetic disk or other magnetic storage devices, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory 303 can exist independently and be connected to the processor 301 through the communication bus 302. The memory 303 can also be integrated with the processor 301.

[0066] Among them, the memory 303 is used to store the program code for executing the solution of this application and is controlled by the processor 301 to execute. The processor 301 is used to execute the program code stored in the memory 303. The program code can include one or more software modules. The above-mentioned fire warning method based on 3D modeling in the embodiment can be implemented by one or more software modules in the program code in the processor 301 and the memory 303.

[0067] The communication interface 304, using any device such as a transceiver, is used to communicate with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area networks (WLAN), etc.

[0068] In a specific implementation, as an embodiment, the computer device can include multiple processors, and each of these processors can be a single-core (single-CPU) processor or a multi-core (multi-CPU) processor. Here, the processor can refer to one or more devices, circuits, and / or processing cores for processing data (such as computer program instructions).

[0069] The above computer device can be a general-purpose computer device or a special-purpose computer device. In specific implementations, the computer device can be a desktop computer, a laptop computer, a network server, a personal digital assistant (PDA), a mobile phone, a tablet computer, a wireless terminal device, a communication device, or an embedded device. The embodiments of the present application do not limit the type of the computer device.

[0070] In addition, the present application also provides a computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, the above method for fire warning based on three-dimensional modeling is implemented.

[0071] In summary, in the method and system for fire warning based on three-dimensional modeling disclosed in the embodiments of the present application, by obtaining a three-dimensional digital twin model of a target building, the three-dimensional digital twin model including a plurality of spatial units in the target building; determining abnormal movement indicators of fire risks at different spatial units according to the spatial structure characteristics of the three-dimensional digital twin model combined with the state evolution mode of the physical field, and then performing risk fitting on all spatial units through all abnormal movement indicators to obtain a risk cloud map of the fire distribution in the target building; extracting a risk sub-domain of the fire from the target building according to the risk cloud map, and then generating a heat flux density field matrix between different spatial units in the risk sub-domain based on a fire risk evolution model; determining the risk fitting degree of different spatial units through the heat flux density field matrix combined with the monitoring information of the fire situation in the target building, and then performing temporal aggregation on the fire risks in the target building according to all risk fitting degrees combined with the local temperature field of each spatial unit to obtain the fire risk propagation potential energy of different spatial units; monitoring the fire spread trend of the target building according to all the fire risk propagation potential energies and outputting a fire spread warning signal; and being able to accurately identify the diffusion trajectory of the fire heat flux in the three-dimensional model.

[0072] Although the preferred embodiments of the present application have been described, those skilled in the art can make additional changes and modifications once they know the basic creative concepts. Therefore, the appended claims are intended to be construed to include the preferred embodiments as well as all changes and modifications falling within the scope of the present application.

[0073] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalent technologies, the present application is also intended to include these changes and modifications.

Claims

1. A fire warning method based on three-dimensional modeling, characterized in that The method includes the following steps: Obtain a three-dimensional digital twin model of the target building, where the three-dimensional digital twin model includes multiple spatial units in the target building; Determine the abnormal movement indicators of fire risks at different spatial units according to the spatial structure characteristics of the three-dimensional digital twin model combined with the state evolution mode of the physical field, and then perform risk fitting on all spatial units through all the abnormal movement indicators to obtain a risk cloud map of the fire distribution in the target building; Extract the risk sub-domains of the fire from the target building according to the risk cloud map, and then generate a heat flux density field matrix between different spatial units in the risk sub-domains based on the fire risk evolution model; Determine the risk fitting degree of different spatial units through the heat flux density field matrix combined with the monitoring information of the fire situation in the target building, and then perform temporal aggregation on the fire risks in the target building according to all the risk fitting degrees combined with the local temperature field of each spatial unit to obtain the fire risk propagation potential energy of different spatial units; Monitor the fire spread situation of the target building according to all the fire risk propagation potential energies and output a fire spread warning signal.

2. The method according to claim 1, characterized in that Determining the abnormal movement indicators of fire risks at different spatial units according to the spatial structure characteristics of the three-dimensional digital twin model combined with the state evolution mode of the physical field specifically includes: Obtain the spatial structure characteristics of each spatial unit in the three-dimensional digital twin model; Perform dynamic simulation on the target building according to the state evolution mode of the physical field to obtain the evolution process data of the physical field in each spatial unit; Perform correlation analysis on the spatial structure characteristics and the evolution process data to determine the abnormal movement indicators of fire risks at different spatial units.

3. The method according to claim 1, characterized in that Performing risk fitting on all spatial units through all the abnormal movement indicators to obtain a risk cloud map of the fire distribution in the target building specifically includes: Perform fitting calculation on the risk levels of each spatial unit in the target building based on all the abnormal movement indicators; Perform spatial mapping processing on the fitting calculation results to generate a risk cloud map of the fire distribution in the target building.

4. The method according to claim 1, wherein Extracting the risk sub-domains of the fire from the target building according to the risk cloud map specifically includes: Perform threshold discrimination on the risk levels of each spatial unit in the risk cloud map; Extract the set of spatial units that meet the threshold discrimination conditions as the risk sub-domains of the fire.

5. The method according to claim 1, characterized in that, Generating a heat flux density field matrix between different spatial units in the risk sub-domains based on the fire risk evolution model specifically includes: Obtain the state information of each spatial unit in the risk sub-domains; Set the boundary conditions during the fire evolution through the state information; Generate a heat flux density field matrix between different spatial units in the risk sub-domains according to the boundary conditions combined with the fire risk evolution model.

6. The method according to claim 1, wherein Determining the risk fitting degree of different spatial units through the heat flux density field matrix combined with the monitoring information of the fire situation in the target building specifically includes: Obtain the monitoring information of the fire situation in the target building; Determine multiple information difference degrees between the monitoring information and the heat flux density field matrix; Determine the risk fitting degree of different spatial units through all the information difference degrees.

7. The method according to claim 1, characterized in that, Perform temporal aggregation of the fire risks in the target building based on the fitting degrees of all risks and the local temperature fields of each spatial unit, and obtain the fire risk propagation potential energy of different spatial units, specifically including: Obtain the local temperature field of each spatial unit in the three-dimensional digital twin model; Perform temporal analysis by combining the fitting degrees of all risks with the local temperature field of each spatial unit to obtain the temporal risk aggregation model of the target building; Determine the fire risk values of each spatial unit at different time points according to the temporal risk aggregation model; Determine the fire risk propagation potential energy of different spatial units through all the fire risk values.

8. The method according to claim 1, characterized in that, Monitor the fire spread situation of the target building based on all the fire risk propagation potential energies and output a fire spread warning signal, specifically including: Analyze the change trend of the fire situation of the target building based on all the fire risk propagation potential energies; Evaluate the change trend of the fire situation according to the preset fire warning rules; When the evaluation result reaches the warning condition, generate and output a fire spread warning signal.

9. The method according to claim 1, wherein The spatial unit is a finite element unit with uniform spatial attributes.

10. A fire warning system based on 3D modeling, characterized in that, Including: An acquisition module, configured to acquire the three-dimensional digital twin model of the target building, where the three-dimensional digital twin model includes multiple spatial units in the target building; A processing module, configured to determine the abnormal movement indicators of the fire risks at different spatial units according to the spatial structure characteristics of the three-dimensional digital twin model and the state evolution mode of the physical field, and then perform risk fitting on all spatial units through all the abnormal movement indicators to obtain the risk cloud map of the fire distribution in the target building; The processing module is further configured to extract the risk sub-domains of the fire from the target building according to the risk cloud map, and then generate the heat flux density field matrix between different spatial units in the risk sub-domains based on the fire risk evolution model; The processing module is further configured to determine the risk fitting degrees of different spatial units by combining the heat flux density field matrix with the fire monitoring information in the target building, and then perform temporal aggregation of the fire risks in the target building according to the fitting degrees of all risks and the local temperature field of each spatial unit to obtain the fire risk propagation potential energy of different spatial units; An execution module, configured to monitor the fire spread situation of the target building based on all the fire risk propagation potential energies and output a fire spread warning signal.

Images