Intelligent fire-fighting design simulation evaluation system based on intelligent building engineering

Abstract

The invention relates to the technical field of computer aided design, and particularly discloses an intelligent fire-fighting design simulation evaluation system based on intelligent building engineering. The system comprises a building information model analysis module, a fire risk quantitative evaluation module, a multi-objective optimization decision module, a dynamic disaster evolution simulation module and an evacuation path real-time planning module, and through quantitative analysis of building fire risk, multi-objective optimization of equipment configuration, dynamic simulation of disaster evolution and real-time planning of an evacuation path, the real-time planning of the evacuation path is realized. The accuracy, balance and reliability of fire-fighting design are achieved, and the overall efficiency and compliance of an intelligent building fire-fighting system are improved.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of computer-aided design, and particularly relates to a smart fire-fighting design simulation evaluation system based on intelligent building engineering. BACKGROUND

[0002] Intelligent building engineering is a cutting-edge cross-disciplinary field that integrates building technology, information technology, and automation control technology, aiming to improve the safety, comfort, and energy efficiency management level of buildings through intelligent means. Among them, the fire-fighting system as the core facility to protect building safety, the scientificity and reliability of its design are directly related to the safety of personnel and property.

[0003] Smart fire-fighting design is a key component of intelligent building engineering, aiming to build an efficient and accurate fire warning and emergency disposal system through advanced information sensing, data transmission, and intelligent decision-making technology. This technical direction involves fire dynamics simulation, evacuation path planning, and fire-fighting resource optimization allocation, etc.

[0004] However, the inventors found that at least the following technical problems exist in the related art:

[0005] The existing technology mainly relies on the experience rules of engineers for fire-fighting equipment layout and system design, and it is difficult to achieve dynamic balance among equipment cost, coverage blind area rate, and emergency response time, etc.

[0006] The traditional design method lacks the quantitative analysis capability of building space structure and fire risk distribution, resulting in high monitoring blind area rate, redundant or insufficient equipment configuration, etc. in complex intelligent buildings.

[0007] The existing system cannot effectively simulate the smoke diffusion law and personnel evacuation behavior under real fire scenarios, making the reliability and applicability of the design scheme face serious challenges.

[0008] Therefore, it is urgent to develop a smart fire-fighting design evaluation system that can realize multi-objective optimization and high-precision simulation. SUMMARY

[0009] The purpose of the present application is to provide a smart fire-fighting design simulation evaluation system based on intelligent building engineering, to solve the problems of high monitoring blind area rate, equipment configuration imbalance, and inability to effectively simulate real fire scenarios and evacuation behavior caused by relying on experience rules for fire-fighting design in the prior art.

[0010] The technical solution of the present application is that the system includes a building information model analysis module, a fire risk quantitative evaluation module, a multi-objective optimization decision module, a dynamic disaster evolution simulation module, and a real-time evacuation path planning module.

[0011] The building information model parsing module is configured to import and parse a digital three-dimensional model of the intelligent building, and extract spatial topology structure, functional area division, material attributes, and existing fire-fighting facility layout data of the building.

[0012] The fire risk quantification evaluation module is configured to calculate fire occurrence probability and potential heat release rate of each unit grid inside the building based on output data of the building information model parsing module, in combination with a preset fire load density database and ventilation condition parameters.

[0013] The multi-objective optimization decision module is configured to receive risk quantification results from the fire risk quantification evaluation module, and weigh among three conflicting optimization objectives of device purchase cost, monitoring blind area rate, and average emergency response time, to output an optimal type configuration and spatial layout scheme of the fire-fighting device.

[0014] The dynamic disaster evolution simulation module is configured to perform high-fidelity numerical simulation on a smoke temperature field, a toxic gas concentration field, and an visibility distribution after a fire occurs based on a computational fluid dynamics principle.

[0015] The evacuation path real-time planning module is configured to calculate and generate an optimal evacuation path for a person in the building according to real-time environmental data output by the dynamic disaster evolution simulation module, in combination with a person density distribution and a behavior characteristic model.

[0016] Further, the building information model parsing module performs the following processing procedure. First, the imported digital three-dimensional model is subjected to geometric and semantic information separation, and spatial coordinates and physical attributes of components such as walls, floors, doors, and windows are extracted. Then, a connectivity graph model of the building space is constructed, in which nodes represent rooms or areas, and edges represent connectivity paths such as doors and corridors.

[0017] Finally, fire-fighting facility data including positions and types of smoke detectors, sprinkler heads, and manual alarm buttons are mapped to the graph model to form a building space network with facility annotations.

[0018] Further, the fire risk quantification evaluation module performs the following risk calculation procedure. The building space is divided into cubic grids with a side length of 2 meters.

[0019] For each grid, a corresponding unit area heat release value is queried from the fire load density database according to types of furniture, decorative materials, and electrical equipment contained in the grid. In combination with a ventilation frequency of a region to which the grid belongs, a fire growth model is applied to calculate a fire occurrence probability index of the grid.

[0020] Finally, a fire risk three-dimensional distribution map of the whole building is generated by comprehensively synthesizing indexes of all grids.

[0021] Further, the multi-objective optimization decision module adopts the improved non-dominated sorting genetic algorithm with elitist strategy for optimization solution. The module first defines three objective functions.

[0022] The first objective function is the total equipment cost, which is the sum of the product of the unit price and the number of each type of fire-fighting equipment.

[0023] The second objective function is the monitoring blind area rate, which is the ratio of the volume of the building space not covered by any smoke detector to the total volume of the building.

[0024] The third objective function is the average emergency response time, which is the weighted average of the theoretical shortest path response time calculated based on the building space network model.

[0025] The optimization algorithm generates a set of equipment configuration schemes that achieve Pareto optimality in all three objectives through iterative evolution, and the decision maker selects the final implementation scheme from the set according to the actual engineering constraints.

[0026] Further, the numerical simulation of the dynamic disaster evolution simulation module is based on the Navier-Stokes equation solved by the large eddy simulation method.

[0027] The module discretizes the building space into computational grids, calculates the heat release rate of the fire source term at each time step, and solves the mass, momentum, and energy conservation equations to predict the flow of smoke, temperature distribution, and CO concentration field.

[0028] The simulation process takes into account the effects of buoyancy and building ventilation system to ensure that the simulation results are highly consistent with the real physical process.

[0029] Further, the evacuation path real-time planning module integrates a personnel behavior model and dynamic environmental obstacles. The module first initializes the personnel distribution according to the building functional area attributes.

[0030] Upon receiving the fire alarm signal, the module real-time acquires the visibility and CO concentration data of each region output by the dynamic disaster evolution simulation module.

[0031] When the visibility of a path segment is less than the specified value of 10 meters or the CO concentration is greater than the specified value of 1000 ppm, the path segment will be marked as impassable.

[0032] The module then applies the Dijkstra algorithm considering dynamic weights to calculate the optimal path for each person to reach the nearest safe exit, and re-plans the path during the evacuation process according to environmental changes.

[0033] Further, the system also includes a design compliance automatic checking module. The module has a built-in digital clause library of national fire safety design specifications.

[0034] The final device layout scheme received by the multi-objective optimization decision module is automatically checked to see if it meets the requirements of fire partitioning, evacuation distance, device spacing, and coverage rate.

[0035] For any detected non-compliance item, the module generates a detailed modification recommendation report and feeds it back to the design interface.

[0036] Further, the system adopts a layered decoupled software architecture, including a data layer, a computing engine layer, and an application service layer.

[0037] The data layer is responsible for storing building models, device parameters, and simulation results.

[0038] The computing engine layer encapsulates the core logic of risk calculation, optimization algorithms, and fluid simulation.

[0039] The application service layer provides a graphical user interface for parameter configuration, simulation execution, and result visualization.

[0040] Each layer exchanges data and calls services through well-defined application programming interfaces, ensuring high cohesion and low coupling, facilitating function extension and maintenance.

[0041] Compared with the prior art, the beneficial effects of the present application are:

[0042] 1. Through building information model analysis and fire risk quantification evaluation, accurate spatial positioning and quantitative analysis of building fire risk are realized, fundamentally overcoming the subjectivity and fuzziness of traditional experience design.

[0043] 2. A multi-objective optimization algorithm is used to automatically optimize among conflicting goals such as cost, coverage rate, and response time, generating a scientific and balanced device configuration scheme, effectively avoiding the problem of resource allocation imbalance caused by device redundancy or deficiency.

[0044] 3. Integrating high-fidelity dynamic disaster evolution simulation and real-time evacuation path planning, it can realistically simulate environmental changes and human behavior under fire conditions, providing a strict verification method for the reliability of the design scheme in extreme scenarios.

[0045] 4. The design compliance automatic checking module ensures that the scheme always meets the latest regulatory requirements, improving design efficiency and standardization.

[0046] 5. The complete system establishes a complete closed-loop design evaluation process from risk analysis, scheme optimization to simulation verification, providing strong technical support for intelligent building fire safety design. BRIEF DESCRIPTION OF DRAWINGS

[0047] One or more embodiments are illustrated by way of example in the drawings in which like reference numerals indicate like elements, and in which: the drawings are not necessarily to scale, except as otherwise noted, and:

[0048] Figure 1 is the overall technical scheme architecture diagram of the intelligent fire-fighting design simulation evaluation system based on intelligent building engineering proposed in the present application;

[0049] Figure 2 is the core principle framework diagram of the multi-objective optimization decision module in the present application;

[0050] Figure 3 is the multi-level interaction relationship and data flow diagram of the dynamic disaster evolution simulation module and the evacuation path real-time planning module in the present application;

[0051] Figure 4 is the logic flow framework diagram of the building information model analysis and fire risk quantification evaluation in the present application;

[0052] Figure 5 is the core principle framework diagram of the design compliance automatic checking module in the present application. DETAILED DESCRIPTION

[0053] The implementation of the intelligent fire-fighting design simulation evaluation system based on intelligent building engineering is described in detail below with reference to the overall technical scheme architecture shown in the accompanying Figure 1

[0054] The system is composed of a building information model analysis module, a fire risk quantification evaluation module, a multi-objective optimization decision module, a dynamic disaster evolution simulation module, an evacuation path real-time planning module, and a design compliance automatic checking module.

[0055] Each module realizes data interaction and function cooperation through a layered decoupled software architecture, specifically including a data layer, a computing engine layer, and an application service layer.

[0056] The data layer uses a distributed database to store building geometric models, material parameters, equipment attributes, and real-time simulation data;

[0057] The computing engine layer encapsulates the core algorithms for risk quantification, optimization decision, and fluid dynamics solution;

[0058] The application service layer provides a visual operation interface, supports parameter configuration, simulation driving, and multi-dimensional result rendering.

[0059] The specific implementation of each module is described in detail below in conjunction with the accompanying drawings.

[0060] The implementation of the building information model analysis module is described in detail below with reference to the​Figure 4 the logical flow framework.

[0061] The module first receives the digital 3D model file of the intelligent building, including Industry Foundation Classes or point cloud data.

[0062] The parsing engine separates the model into geometric information and semantic information:

[0063] Geometric information extraction covers wall contour vertex coordinates, floor elevation data, door and window opening boundaries, and pipe well spatial positions; semantic information extraction includes component material combustion rating, fire compartment identification, functional area type annotation, and existing fire facility model.

[0064] The module then builds a building space connectivity graph model, where nodes are defined as independent rooms or open areas, and node attributes include space volume, functional area classification, and personnel capacity threshold;

[0065] Edges are defined as connected paths such as doorways, corridors, stairwells, etc., and edge attributes include passage width, slope angle, and fire door rating.

[0066] Finally, the module maps smoke detector coordinates, sprinkler head protection radius, manual alarm button position, and audible and visual alarm coverage to the graph model nodes and edges, forming a building space network with facility annotations.

[0067] The network is stored in the data layer in the form of an adjacency list for subsequent module calls.

[0068] The implementation of the fire risk quantification evaluation module is described in the attached Figure 4 the logical flow framework. This module obtains space network data from the building information model parsing module and divides the building interior into cubic grid cells with a side length of 2 meters.

[0069] Each grid is associated with a material database, which calculates the fire load density value of the grid by querying the unit area heat release rate of furniture skin materials, decorative fabrics, and electrical equipment insulation materials.

[0070] Ventilation condition parameters are derived from building HVAC system design documents, including regional air exchange frequency, natural ventilation opening area, and mechanical smoke exhaust air volume.

[0071] The module uses a predefined fire growth model to calculate the grid fire occurrence probability index, which is achieved through the following formula:

[0072]

[0073] where, represents the fire occurrence probability index of the th grid, is the total heat release of combustible materials in the grid, is the grid floor area, is the grid space volume, is the ventilation correction factor, is the model calibration coefficient.

[0074] Module synchronously calculates the potential heat release rate of the grid, iteratively solving according to the material combustion characteristic curve and oxygen supply conditions.

[0075] Finally, a three-dimensional distribution map of the overall fire risk of the building is generated, which is stored in the data layer in the form of a voxel matrix, and the risk level is represented by color mapping.

[0076] The implementation of the multi-objective optimization decision module is described with reference to the core principle framework shown in FIG. 8. This module receives the risk distribution data output by the fire risk quantification evaluation module, initializes the device configuration decision variables, including the type of smoke detector, the action temperature of the sprinkler head, the location of the fire hydrant, and the power of the emergency lighting. Figure 2

[0077] The module defines three objective functions: the total cost objective function of the device is the product of the unit price of each type of device and the number of configurations; the monitoring blind area rate objective function is the ratio of the volume of the space not covered to the total volume of the building, wherein the coverage determination is based on the detection radius of the smoke detector and the line-of-sight obstruction correction; and the average emergency response time objective function is based on the building space network model, which calculates the shortest path time from any fire point to the nearest fire-fighting device, and then takes the average value after weighted summation.

[0078]

[0079] The average emergency response time objective function is based on the building space network model, which calculates the shortest path time from any fire point to the nearest fire-fighting device, and then takes the average value after weighted summation.

[0080] The optimization algorithm uses an improved non-dominated sorting genetic algorithm with elitist strategy, with a population size of 500, a crossover probability of 0.85, and a mutation probability of 0.02. The algorithm performs fast non-dominated sorting and crowding calculation every generation, and retains the elite individuals to the next generation.

[0081] After 1000 generations of iteration, the Pareto optimal solution set is output, each solution containing a list of device types, a set of spatial coordinates, and the values of the three objective functions.

[0082] The decision maker browses the three-dimensional distribution of the solution set through the application service layer interactive interface, and selects the final scheme according to the engineering budget and safety threshold.

[0083] The implementation of the dynamic disaster evolution simulation module is described with reference to the multi-level interaction relationship and data flow diagram shown in FIG. 9. Figure 3

[0084] Based on the principle of computational fluid dynamics, the module discretizes the building space into hexahedral calculation grids with a side length of 0.5 meters.

[0085] ​​​The module reads the heat release rate curve of the specified fire source in the fire risk map from the data layer as the initial condition of the simulation.

[0086] The governing equations are filtered Navier-Stokes equations, and the solved variables include velocity vector, temperature scalar and CO mass fraction.

[0087] At each time step, the module calculates the combustion reaction source term, buoyancy term and turbulent diffusion term, and updates the flow field through the pressure-velocity coupling algorithm.

[0088] The boundary condition settings include wall adiabatic condition, vent pressure boundary and mechanical smoke exhaust system flow input.

[0089] The simulation output includes the real-time temperature value, smoke concentration percentage and CO volume fraction of each grid, and the data is stored in time series format.

[0090] The module outputs an environmental state snapshot every 0.1 seconds, which is rendered into a dynamic smoke spread visualization animation through the application service layer.

[0091] The implementation of the evacuation path real-time planning module is described in detail in the attached Figure 3 Figure 1 shows the multi-level interaction relationship and data flow diagram.

[0092] The module obtains the initial distribution data of personnel from the building information model analysis module, and sets the number of personnel in each area according to the office workstation density, conference room fullness rate and corridor peak flow rate. When the fire alarm signal is triggered, the module subscribes to the environmental data output by the dynamic disaster evolution simulation module in real time.

[0093] The path passability determination logic is to monitor the visibility and CO concentration of each corridor and door hole area in real time. If the visibility is less than 10 meters or the CO concentration is greater than 1000 ppm, the weight of the path segment will be set to infinity.

[0094] The module uses the Dijkstra algorithm considering dynamic weights to calculate the shortest path from each personnel node to the nearest safe exit.

[0095] The path cost function is defined as:

[0096]

[0097] where, is the path segment cost, is the segment length, is the personnel walking speed, is the real-time visibility, is the real-time CO concentration, and is the calibration coefficient.

[0098] The module recalculates the full building path map every 2 seconds and pushes navigation instructions to the personnel terminal through the application service layer.

[0099] For the implementation of the design compliance automatic checking module, please refer to the core principle framework shown in FIG. 1. Figure 5

[0100] The module has a built-in national fire design specification digital clause library, which converts the clauses into executable logic rules.

[0101] The rule types include: fire partition area upper limit checking, minimum width of evacuation walkway checking, smoke detector horizontal spacing threshold checking, sprinkler head and obstacle distance checking, and safety exit distribution density checking.

[0102] The module receives the equipment layout scheme output by the multi-objective optimization decision module and matches the rules library one by one for compliance detection.

[0103] For non-compliance items, the module generates a structured report, marking the violation location, violated clause number, and correction suggestions, such as increasing the number of detectors or adjusting the direction of the fire door.

[0104] The checking results are displayed in the building three-dimensional model through the application service layer, with problem areas highlighted in red.

[0105] In the specific implementation of the system layered architecture, the data layer uses a time series database to store simulation dynamic data, a relational database to store building static attributes, and a graph database to store spatial network topology.

[0106] The computing engine layer deploys three major engines, risk calculation, optimization solution, and fluid simulation, through a microservice architecture, and communicates asynchronously between services through a message queue.

[0107] The application service layer provides a dual interface for web and mobile, supports multi-person collaborative design, real-time simulation control, and virtual reality immersive browsing.

[0108] Data is transmitted between layers through a Representational State Transfer application programming interface, with a Lightweight Data Interchange format and a token-based authentication mechanism for interface authentication.

[0109] The system is deployed on a cloud computing platform, dynamically allocates computing resources through a load balancer, and ensures the stability of high-concurrency simulation tasks.

[0110] This embodiment optimizes the special fire protection needs of super high-rise buildings.

[0111] The building information model analysis module adds a vertical transportation core analysis submodule to extract the vertical communication relationship of elevator shafts, refuge floors, and pressurized air supply shafts.

[0112] ​The fire risk quantitative evaluation module introduces a shaft effect correction model to calculate the probability of smoke accelerating in the vertical channel.

[0113] The multi-objective optimization decision module adds a fourth objective function, i.e., redundancy of refuge floor equipment, requiring key fire-fighting equipment to remain functional in the event of any single point failure.

[0114] The dynamic disaster evolution simulation module uses a non-uniform grid division strategy, with a grid size of 0.2 meters in the shaft area, to accurately capture the development process of the smoke plume.

[0115] The real-time evacuation path planning module integrates an elevator evacuation algorithm. When the floor height is greater than the specified value of 60 meters, the elevator auxiliary evacuation mode is started, and the elevator capacity is allocated through a priority scheduling algorithm.

[0116] The design compliance automatic verification module supplements the special provisions of super high-rise building codes, including the setting interval of refuge floors, the area of fire elevator antechamber, and the accessibility verification of helicopter landing pads.

[0117] The system realizes precise simulation and evaluation of super high-rise building fire design through the above enhancements.

[0118] This embodiment is adapted to the existing building renovation scenario. The building information model analysis module adds a point cloud data fusion interface to reconstruct the actual building state through the registration of laser scanning point cloud and the original design model.

[0119] The fire risk quantitative evaluation module introduces an aging coefficient correction to adjust the fire load density value based on the service life of equipment and the degree of material degradation.

[0120] The multi-objective optimization decision module adds renovation constraints, including pipeline relocation costs, structural opening restrictions, and historical protection requirements, which are added to the optimization objective in the form of a penalty function.

[0121] The dynamic disaster evolution simulation module supports local area fine simulation, with grid encryption only in the renovation area to improve computational efficiency.

[0122] The real-time evacuation path planning module dynamically updates the feasible path set in combination with temporary access data during the renovation construction period.

[0123] The design compliance automatic verification module compares the compliance differences between the pre- and post-renovation schemes to generate an incremental verification report.

[0124] The system realizes full-process simulation support for existing building fire renovation through the above improvements.

[0125] It is to be understood that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting; it is not intended to exclude myriad other embodiments of the present application that other presenters can develop using the concepts disclosed herein. It is intended that all such alterations and further modifications be considered equivalents thereof. Terms used for contacting or relative positioning are used for convenience and are not intended to convey any mandatory relationships among the components or operations. Moreover, the terms "comprise", "comprising", or any other variations thereof are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but can also include other elements not expressly listed or inherent to such process, method, article, or apparatus.

[0126] The scope of the application is defined by the appended claims rather than by the description preceding them, which is merely intended to reveal one or more embodiments of the application. Therefore, no limitation is to be placed on the scope of the application based on that depiction or that description. No admission is to be inferred that any reference constitutes prior art against the application. Further, it is to be understood that the use of relational terms such as first, second, and the like are used merely to distinguish one from another without necessarily implying a particular order or sequence. Any use of the term "including" or "comprising" is intended to mean "consisting of" or "consisting essentially of" to an extent that there are no other elements other than the listed elements in the description of the features, processes, compositions, and / or methods. Any use of the term "example" is intended to mean "for purposes of illustration" and not "by way of limitation".

[0127] The above description is only specific embodiments of the present application, but the protection scope of the present application is not limited thereto, and any person skilled in the art can easily think of changes or replacements within the technical scope disclosed by the present application, which should be covered by the protection scope of the present application. Therefore, the protection scope of the present application should be limited by the protection scope of the claims, and the above embodiments should be regarded as exemplary and non-limiting.

Claims

1. A smart fire protection design simulation and evaluation system based on intelligent building engineering, characterized in that, include: The Building Information Modeling (BIM) parsing module is used to import and parse the digital 3D model of a smart building, and extract the building's spatial topology, functional area division, material properties, and existing fire protection facility layout data. The fire risk quantification assessment module is used to calculate the probability of fire occurrence and potential heat release rate of each unit grid inside the building based on the output data of the building information model parsing module, combined with the preset fire load density database and ventilation condition parameters. The multi-objective optimization decision module receives the risk quantification results from the fire risk quantification assessment module and weighs the conflicting optimization objectives of equipment purchase cost, monitoring blind spot rate and average emergency response time, and outputs the optimal type configuration and spatial layout scheme of fire protection equipment. The dynamic disaster evolution simulation module is used to perform high-fidelity numerical simulations of the smoke temperature field, toxic gas concentration field, and visibility distribution after a fire, based on the principles of computational fluid dynamics. The real-time evacuation route planning module is used to calculate and generate the optimal evacuation route for people in the building based on the real-time environmental data output by the dynamic disaster evolution simulation module and combined with the personnel density distribution and behavioral characteristic model. The design compliance automatic verification module is used to receive the final equipment layout plan output by the multi-objective optimization decision module and automatically check whether the plan meets the requirements of the specifications in terms of fire compartments, evacuation distances, equipment spacing and coverage.

2. The intelligent fire protection design simulation and evaluation system based on intelligent building engineering according to claim 1, characterized in that, The building information model parsing module performs the following processing flow: The imported digital 3D model is subjected to geometric and semantic information separation to extract the spatial coordinates and physical properties of wall, floor, door and window components. Construct a connectivity graph model of the building space, where nodes represent rooms or areas and edges represent connecting paths such as doors and corridors; The extracted fire protection facility data is mapped onto a graphical model to form a building space network with facility labels.

3. The intelligent fire protection design simulation and evaluation system based on intelligent building engineering according to claim 1, characterized in that, The risk calculation process of the fire risk quantification assessment module is as follows: Divide the architectural space into a cubic grid; For each grid, based on the types of furniture, decorative materials, and electrical equipment contained within each grid, the corresponding heat generation value per unit area is retrieved from the fire load density database; Based on the ventilation rate of the area to which the grid belongs, a predefined fire growth model is applied to calculate the fire probability index of the grid. By combining the indices of all grids, a three-dimensional fire risk distribution map of the entire building is generated.

4. The intelligent fire protection design simulation and evaluation system based on intelligent building engineering according to claim 1, characterized in that, The multi-objective optimization decision-making module uses an improved non-dominated sorting genetic algorithm with an elitist strategy for optimization. The multi-objective optimization decision module defines several objective functions: the total equipment cost objective function is the sum of the products of the unit price of various fire protection equipment and their configuration quantity; the monitoring blind zone rate objective function is the ratio of the building space volume not effectively covered by any smoke detector to the total building volume; the average emergency response time objective function is the weighted average of the theoretical shortest path response time calculated based on the building space network model. The optimization algorithm evolves iteratively to generate a set of equipment configuration schemes that achieve Pareto optimality across multiple objectives.

5. The intelligent fire protection design simulation and evaluation system based on intelligent building engineering according to claim 1, characterized in that, The numerical simulation of the dynamic disaster evolution simulation module is based on solving the Navier-Stokes equations using the large eddy simulation method. The dynamic disaster evolution simulation module discretizes the building space into a computational grid, calculates the heat release rate of the fire source term in each time step, and solves the mass, momentum and energy conservation equations to predict the flow of smoke, temperature distribution and CO concentration field. The simulation process simultaneously considers the effects of buoyancy and the building ventilation system.

6. The intelligent fire protection design simulation and evaluation system based on intelligent building engineering according to claim 1, characterized in that, The real-time evacuation route planning module integrates personnel behavior models and dynamic environmental obstacles; The real-time evacuation route planning module initializes the personnel distribution based on the building's functional area attributes; Upon receiving a fire alarm signal, the real-time evacuation route planning module acquires the visibility and CO concentration data for each area output by the dynamic disaster evolution simulation module in real time. When the visibility of a certain route is less than the specified value or the CO concentration is greater than the specified value, the route is marked as impassable. The module uses Dijkstra's algorithm, which considers dynamic weights, to calculate the optimal path to the nearest safe exit for each person.

7. The intelligent fire protection design simulation and evaluation system based on intelligent building engineering according to claim 1, characterized in that, The automatic design compliance verification module has a built-in digital clause library of national fire protection design codes; The automatic compliance verification module converts the standard provisions into executable logical rules. The rule types include verification of the upper limit of fire compartment area, verification of the minimum width of evacuation corridor, verification of the horizontal spacing threshold of smoke detectors, verification of the distance between sprinkler heads and obstacles, and verification of the distribution density of safety exits. For detected non-compliance items, an automatic compliance verification module is designed to generate a structured report and mark the location of the violation, the number of the violated clause, and correction suggestions.

8. The intelligent fire protection design simulation and evaluation system based on intelligent building engineering according to claim 1, characterized in that, The system adopts a layered and decoupled software architecture, including a data layer, a computing engine layer, and an application service layer. The data layer is responsible for storing building models, equipment parameters, and simulation results; The computational engine layer encapsulates the core logic of risk calculation, optimization algorithms, and fluid simulation. The application service layer provides a graphical user interface for parameter configuration, simulation execution, and result visualization.

9. The intelligent fire protection design simulation and evaluation system based on intelligent building engineering according to claim 8, characterized in that, The data layer uses a time-series database to store simulation dynamic data, a relational database to store static building attributes, and a graph database to store spatial network topology. The computing engine layer deploys three engines—risk computing, optimization solution, and fluid simulation—through a microservice architecture. The application service layer provides dual interfaces for web and mobile devices, supporting collaborative design and real-time simulation control by multiple users.

10. The intelligent fire protection design simulation and evaluation system based on intelligent building engineering according to claim 1, characterized in that, The system adds a vertical traffic core analysis submodule for super high-rise buildings; The fire risk quantification assessment module incorporates a shaft effect correction model; The multi-objective optimization decision module adds an objective function, namely the redundancy of refuge layer equipment; The dynamic disaster evolution simulation module adopts a non-uniform grid partitioning strategy, which densifies the grid size in the shaft area; The real-time evacuation route planning module integrates an elevator evacuation algorithm, which activates the elevator-assisted evacuation mode when the floor height exceeds a specified value.

Images