Rail transit interval water supply and drainage and fire-fighting intelligent design method and system

Abstract

The invention relates to the technical field of rail transit engineering, and discloses a rail transit interval water supply and drainage and fire-fighting intelligent design method and system, and the method comprises the steps: S1, candidate point presetting: in a rail transit interval, presetting a plurality of candidate installation points of fire-fighting and drainage equipment according to interval geometric parameters, evacuation streamlines and standard requirements, candidate point set data is formed; s2, fire working condition simulation: generating a plurality of fire working conditions based on a random algorithm, and performing fire scene simulation for the working conditions; s3, hydraulic calculation and environment checking; s4, performing optimization iteration; s5, performing multi-objective optimization; and S6, carrying out digital twinborn verification. A digital twinborn model is established based on BIM and GIS, a Pareto solution set is mapped into a three-dimensional scene, dynamic simulation and reasoning check are carried out in combination with CFD and hydraulic data, and real-time monitoring data of a sensor can be fused, so that it is guaranteed that an equipment arrangement scheme can meet standard constraints, and feasibility and safety of the equipment arrangement scheme can be continuously checked in the operation process.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of rail transit engineering, in particular to a rail transit section water supply and drainage and fire-fighting intelligent design method and system. BACKGROUND

[0002] As a closed or semi-closed underground space, the fire-fighting and drainage design of the rail transit section directly relates to the life safety of passengers and the stability of system operation. In the event of fire or flood, the sprinkler system, fire hydrant system and drainage facilities must work together to ensure personnel evacuation and equipment operation. Therefore, reasonable arrangement of fire-fighting and drainage equipment and performance checking are key links in the design of rail transit engineering. In the prior art, equipment arrangement mostly depends on the selection of points by designers according to specifications and experience, and simulation and checking are carried out based on limited working conditions.

[0003] However, in the current technology, it is difficult to cover multiple possibilities under complex fire scenarios in the rail section, resulting in lack of comprehensiveness of the arrangement scheme and hidden dangers that cannot effectively guarantee safety in actual operation. SUMMARY

[0004] In view of the deficiencies of the prior art, the present application provides a rail transit section water supply and drainage and fire-fighting intelligent design method and system, which solves the problem of difficulty in covering multiple working conditions of the rail section, affecting the feasibility and safety in actual operation.

[0005] To achieve the above purpose, the present application is implemented by the following technical scheme: a rail transit section water supply and drainage and fire-fighting intelligent design method, comprising: S1, candidate point presetting, in the rail transit section, a plurality of candidate installation points of fire-fighting and drainage equipment are preset according to section geometric parameters, evacuation flow lines and specification requirements, and a candidate point set data is formed; S2, fire condition simulation, a plurality of fire conditions are generated based on a random algorithm, and a fire field is simulated for the conditions, outputting temperature field distribution, smoke diffusion distribution and fire water demand data; S3, hydraulic calculation and environmental checking, hydraulic calculation and fire field environmental checking are carried out for the candidate point set under the fire condition; S4, optimization iteration, based on the output results of the hydraulic calculation and environmental checking, an optimization algorithm is used to iteratively search the equipment arrangement scheme of the candidate points, generating a plurality of alternative equipment arrangement schemes; S5, multi-objective optimization, the alternative equipment arrangement schemes are subjected to multi-objective optimization, and a Pareto solution set is generated based on the equipment quantity, safety coverage rate and operation energy consumption targets; S6, digital twin verification, the Pareto solution set is mapped to a rail transit section digital twin model, dynamic simulation and reasoning verification are carried out, and an implementation scheme is output.

[0006] By the above technical solution, first, a candidate point database is established through geometric parameters and dispersion flow lines, then multiple working condition fire data are generated by using a random algorithm and computational fluid dynamics (CFD) simulation, and constraint conditions are formed in combination with hydraulic calculation and environmental checking, on this basis, an optimization algorithm is used for iterative search and a Pareto solution set is generated by multi-objective optimization, finally, the optimization result is mapped into a digital twin model based on BIM and GIS, dynamic simulation and reasoning checking are carried out in combination with CFD and hydraulic data, and real-time data of sensors can be extended and fused, thereby realizing linkage verification in the design stage and the operation stage.

[0007] Preferably, the fire working condition generation comprises: Based on historical fire case data, fire experiment data and design specifications, the value range and probability distribution of the fire source position, fire source intensity, burning time and ventilation condition are determined; Based on the probability distribution, a Monte Carlo algorithm is used for random sampling to generate multiple fire working condition samples; The fire working condition samples are input into a fire field simulation to obtain corresponding temperature field distribution, smoke diffusion distribution and fire water demand data.

[0008] Preferably, the fire field simulation is based on the fire source intensity, ventilation condition and interval geometric parameters, and is calculated by a computational fluid dynamics model to output the fire field temperature field distribution, smoke diffusion distribution and fire water demand data.

[0009] Preferably, the hydraulic calculation and environmental checking comprises: The water spraying intensity and action area of the sprinkler system are calculated to determine the total water consumption of the sprinkler system; The water supply flow and the most unfavorable point water pressure of the fire hydrant system are calculated to check whether the specification requirements are met; The Manning formula or equivalent hydraulic formula is used to calculate the drainage pump station flow and pipe drainage capacity; In terms of fire field environment, the temperature, smoke concentration and visibility of the evacuation path are checked based on the fire simulation results, and the checked values are compared with the preset safety threshold.

[0010] Preferably, the optimization iteration comprises: The equipment arrangement scheme of the candidate point is coded; A fitness function is constructed based on the output results of the hydraulic calculation and environmental checking, and the fitness function is used to comprehensively evaluate the water supply capacity, drainage capacity and environmental safety index of the equipment arrangement scheme; A genetic algorithm is used to iteratively search the equipment arrangement scheme, and the arrangement scheme is updated generation by generation through selection, crossover and mutation operations; generate a plurality of candidate device arrangement schemes satisfying the fitness function constraints.

[0011] Preferably, the multi-objective optimization comprises: constructing a multi-objective evaluation function based on the device quantity, safety coverage rate, and operation energy consumption optimization objectives; evaluating the plurality of candidate device arrangement schemes and comparing their advantages and disadvantages using a non-dominated sorting method; generating a Pareto frontier through iterative evolution to form a Pareto solution set composed of a plurality of non-dominated solutions, and providing optimization selection under multiple objectives.

[0012] Preferably, the Pareto solution set is further mapped as input to a rail transit section digital twin model, which is established based on BIM and GIS data and used for dynamic simulation and reasoning verification of the candidate device arrangement scheme.

[0013] Preferably, the dynamic simulation and reasoning verification of the digital twin model comprises: receiving the calculation results of the fire field simulation and the hydraulic calculation results as input data; mapping the input data to the rail transit section digital twin model to generate a three-dimensional visualization scene; in the three-dimensional visualization scene, dynamically evolving and displaying the change process of temperature distribution, smoke diffusion, and drainage capacity;

[0014] performing reasoning checking based on the dynamic evolution process, and outputting the implementation scheme data of the candidate device arrangement scheme after the checking is completed.

[0015] Preferably, the digital twin model is further fused with sensor data in the rail transit section, the sensor data including real-time monitoring data of temperature sensors, smoke concentration sensors, and water level sensors; comparing and correcting the real-time monitoring data with the simulation results for dynamic checking of the candidate device arrangement scheme in the operation phase.

[0016] An intelligent design system for water supply and drainage and fire fighting in a rail transit section, the system comprising: a candidate point generation module for presetting a plurality of candidate installation points of fire fighting and drainage devices in the rail transit section according to section geometric parameters, evacuation flow lines, and specification requirements, and forming candidate point set data; a fire condition simulation module for generating a plurality of fire conditions based on a random algorithm and performing fire field simulation to output temperature field distribution, smoke diffusion distribution, and fire water demand data; a hydraulic calculation and environmental checking module for performing hydraulic calculation and fire field environmental checking of the candidate point set under the fire condition; An optimization iteration module is configured to iteratively search the device arrangement scheme of the candidate point based on the output results of the hydraulic calculation and the environmental check, and generate a plurality of alternative device arrangement schemes by using an optimization algorithm; A multi-objective optimization module is configured to perform multi-objective optimization on the alternative device arrangement schemes, and generate a Pareto solution set based on the device quantity, safety coverage rate and operation energy consumption targets; A digital twin verification module is configured to map the Pareto solution set into a digital twin model of the rail transit section, perform dynamic simulation and reasoning check, and output an implementation scheme.

[0017] The present application provides a rail transit section water supply and drainage and fire-fighting intelligent design method and system. The present application has the following beneficial effects: 1. The present application establishes a digital twin model based on BIM and GIS, maps the Pareto solution set to a three-dimensional scene, performs dynamic simulation and reasoning check in combination with CFD and hydraulic data, and can integrate real-time monitoring data of sensors, so as to ensure that the device arrangement scheme can meet the specification constraints and continuously check its feasibility and safety during operation; 2. The present application performs comprehensive modeling by using section geometric parameters, evacuation flow lines and specification constraints, automatically generates a candidate point database, realizes standardized and quantifiable input of device arrangement, and ensures that the design has repeatability and uniformity; 3. The present application establishes a probability distribution model of fire source position, intensity, burning time and ventilation condition, generates a large-scale working condition sample by using a Monte Carlo algorithm, and outputs a temperature field and fire-fighting water demand in combination with CFD calculation, so as to realize quantitative description of fire uncertainty; 4. The present application introduces the results of hydraulic calculation and environmental check into a fitness function, performs iterative optimization of the arrangement scheme by using a genetic algorithm, and generates a Pareto solution set by using non-dominated sorting, so as to realize multi-objective balanced design among device quantity, safety coverage rate and energy consumption. BRIEF DESCRIPTION OF DRAWINGS

[0018] Figure 1 A flowchart of a rail transit section water supply and drainage and fire-fighting intelligent design method of the present application; Figure 2 An architecture diagram of a rail transit section water supply and drainage and fire-fighting intelligent design system of the present application. DETAILED DESCRIPTION

[0019] The technical solutions of the present application will be described clearly and completely in combination with the drawings of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0020] Reference is made to the accompanying drawings Figure 1 The embodiment of the present application provides a rail transit section water supply and drainage and fire-fighting intelligent design method, comprising: S1, candidate point presetting, in the rail transit section, according to the section geometric parameters, evacuation streamline and specification requirements, a plurality of candidate installation points of fire-fighting and drainage equipment are preset, and candidate point set data is formed; Specifically, the candidate point presetting is realized by comprehensively analyzing the geometric parameters of the rail transit section, the personnel evacuation streamline and the fire-fighting and drainage design specification, that is, first, the structural parameters such as the section size, length and slope of the section are obtained, and the main evacuation path and personnel distribution characteristics are determined in combination with the passenger flow organization scheme, then the constraint condition setting of the spray head spacing, the fire hydrant coverage radius and the drainage well arrangement spacing is carried out according to the relevant design specification, on this basis, the method of spatial geometric modeling is adopted to generate a plurality of feasible candidate installation points under the premise of meeting the above constraint conditions, and the candidate point database is stored in the form of a set for subsequent fire condition simulation and optimization calculation.

[0021] S2, fire condition simulation, a plurality of fire conditions are generated based on a random algorithm, and a fire field is simulated for the conditions, and temperature field distribution, smoke diffusion distribution and fire-fighting water demand data are output; Among them, the fire condition generation includes: Based on historical fire case data, fire experiment data and design specification, the value range and probability distribution of the fire source position, fire source intensity, burning time and ventilation condition are determined; Based on the probability distribution, a plurality of fire condition samples are generated by using the Monte Carlo algorithm for random sampling; The fire condition sample is input into the fire field simulation to obtain corresponding temperature field distribution, smoke diffusion distribution and fire-fighting water demand data.

[0022] Specifically, the fire condition generation first determines the value range of the fire source position, fire source intensity, burning time and ventilation condition based on the historical fire case database, standardized fire experiment results and rail transit fire-fighting design specification, and establishes a corresponding probability distribution model for each parameter, for example, the distribution of the fire source position can be determined in combination with the passenger flow density and equipment distribution characteristics in the station and the section, the fire source intensity can be referred to typical combustible load experiment data, the burning time can be set according to the statistical law of historical cases, and the ventilation condition can be determined in combination with the section wind speed and ventilation parameters, so as to form a fire input parameter space with statistical basis and engineering applicability, and ensure that the condition generation does not depend on a single assumption, but covers a plurality of possible scenes; After determining the parameter distribution, the Monte Carlo algorithm is used to randomly sample the fire source position, fire source intensity, burning time and ventilation condition to generate a sufficient number of fire condition samples, each of which corresponds to a specific fire source combination and is stored as an input vector. By repeating the sampling, a large set of fire condition samples is generated to describe the fire uncertainty characteristics in the track section and provide diversified inputs for subsequent simulation calculations. At the same time, the fire condition samples are reviewed by the Monte Carlo method. First, based on historical fire cases, experimental data and design specifications, the probability distribution model of the fire source position , fire source intensity , burning time and ventilation condition is established, for example, the fire source position follows a discrete distribution , the fire source intensity follows a lognormal distribution , the burning time follows an exponential distribution , and the ventilation condition follows a normal distribution ( ). Then, in each simulation, a fire condition sample vector is obtained by using a random number generator to independently sample the above distributions: ; wherein represents the th fire condition sample, is the fire source position, is the fire source intensity, is the burning time, is the ventilation condition. By repeating the sampling times, a set of fire conditions is obtained: ;

[0023] This set is passed as input to the fire simulation module to generate temperature field, smoke diffusion and fire water demand data under different conditions. Then, based on the computational fluid dynamics (CFD) method, the temperature field distribution, smoke diffusion distribution and corresponding fire water demand data in the fire field are calculated by combining the fire source intensity, ventilation condition and section geometry parameters. The calculation results are stored in the database as structured output and are connected with the subsequent hydraulic calculation and environmental review. The abstract fire condition samples are converted into quantifiable fire field parameter results, thereby realizing the data connection between the fire scene and the equipment design.

[0024] S3, hydraulic calculation and environmental review, hydraulic calculation and fire field environmental review of the candidate point set under the fire condition; wherein the fire field simulation is based on the fire source intensity, ventilation condition and section geometry parameters, and is calculated by the computational fluid dynamics model to output the fire field temperature field distribution, smoke diffusion distribution and fire water demand data; Hydraulic calculation and environmental check includes: Calculate the water spray intensity and action area of the sprinkler system to determine the total water consumption of the sprinkler system; Calculate the water supply flow and the most unfavorable point water pressure of the fire hydrant system to check whether it meets the specification requirements; Use the Manning formula or equivalent hydraulic formula to calculate the drainage pump station flow and pipe drainage capacity; In terms of fire environment, based on the results of fire simulation, the temperature, smoke concentration and visibility of the evacuation path are checked, and the checked values are compared with the preset safety threshold.

[0025] Specifically, the hydraulic calculation and environmental check are based on the output results of S2 fire condition simulation. According to the fire-affected area and the heat release characteristics of the fire source obtained by CFD fire simulation, combined with the required sprinkler intensity , the total water consumption of the sprinkler system is calculated ; Among them, represents the total water consumption of the sprinkler system (L / min), represents the spray intensity (L / min·m²), represents the protection area of the fire-affected area (m²). This calculation combines the simulation results of CFD with the specification parameters to check the rationality of the candidate point sprinkler head arrangement.

[0026] Combined with the sprinkler wastewater and the amount of seepage water in the fire scene, the Manning formula is used to calculate the drainage capacity of the drainage pump station and the pipe: ; Among them, is the pipe drainage flow (m³ / s), is the pipe water section area (m²), is the hydraulic radius (m), is the pipe hydraulic slope, is the pipe roughness coefficient. Through this calculation, it is checked whether the candidate point drainage well and pump station arrangement can meet the drainage demand under the fire condition.

[0027] Then based on the temperature field distribution, smoke concentration distribution and particulate matter concentration obtained by CFD simulation results, the temperature, smoke concentration and visibility of the evacuation path are checked respectively: Temperature check: compare the temperature of the evacuation path with the set safety threshold (such as 60℃); Smoke concentration check: compare the carbon monoxide concentration with the critical safety concentration (such as 500ppm); Visibility check: use the optical attenuation model to calculate the visibility of the evacuation path: ; wherein, represents the visibility (m), represents the optical cross-section coefficient (m² / g), represents the flue gas particulate matter concentration (g / m³). When the calculated visibility is greater than or equal to a preset threshold (such as 10 m), it is determined that the candidate point arrangement satisfies the evacuation visibility constraint, thereby ensuring the checkability and technical rationality of the candidate point arrangement under the condition of integrated drainage and firefighting.

[0028] S4, optimization iteration, based on the output results of the hydraulic calculation and the environmental check, using an optimization algorithm to iteratively search for the equipment arrangement scheme of the candidate point, generating a plurality of alternative equipment arrangement schemes; The optimization iteration includes: encoding the equipment arrangement scheme of the candidate point; constructing a fitness function based on the output results of the hydraulic calculation and the environmental check, the fitness function being used to comprehensively evaluate the water supply capacity, drainage capacity and environmental safety indicators of the equipment arrangement scheme; using a genetic algorithm to iteratively search for the equipment arrangement scheme, and updating the arrangement scheme through selection, crossover and mutation operations; generating a plurality of alternative equipment arrangement schemes that satisfy the fitness function constraints.

[0029] Specifically, the equipment arrangement scheme of the candidate point is represented in binary coding, i.e. in the candidate point set, if a device is arranged at a certain position, it is assigned a value of "1", and if it is not arranged, it is assigned a value of "0", thereby forming a chromosome vector of the arrangement scheme. For example, if the candidate point set is , the arrangement scheme can be represented as a vector of length . wherein, , represents the arrangement state of the i-th candidate point, when , it indicates that the point is arranged with a device, and when , it indicates that no device is arranged, thereby converting the spatial arrangement problem into a form that can be processed by the optimization algorithm; based on the output results of the hydraulic calculation and the environmental check, constructing a comprehensive fitness function for evaluating the performance of the arrangement scheme in terms of water supply capacity, drainage capacity and environmental safety: ; wherein, represents the fire water supply capacity indicator (such as the sprinkler coverage rate, the fire hydrant water pressure satisfaction degree), represents the drainage capacity indicator (such as the ratio of drainage flow to sprinkler wastewater volume), environmental safety indicators (such as evacuation path temperature, visibility, and smoke concentration constraint satisfaction degree), is a weight parameter, used to adjust the relative importance of the three types of indicators according to design requirements, thereby providing quantifiable evaluation criteria for different arrangement schemes; After the arrangement scheme encoding and the determination of the fitness function, a genetic algorithm is used for iterative search. First, an initial population of a certain size is generated, and the fitness value of each individual is calculated. Then, selection, crossover, and mutation operations are sequentially performed. The selection operation selects superior individuals according to the fitness probability. The crossover operation generates new individuals by randomly splitting and exchanging encoded fragments. The mutation operation expands the solution space by randomly flipping some gene bits, thereby updating the arrangement scheme generation by generation and exploring better candidate point configurations.

[0030] Through several generations of iterative evolution, the genetic algorithm generates multiple arrangement schemes that satisfy the fitness function constraints. The final scheme set serves as input data for subsequent multi-objective optimization, providing multiple feasible candidate configurations and serving as a basis for subsequent Pareto optimization and twin verification.

[0031] S5, multi-objective optimization, performing multi-objective optimization on the alternative equipment arrangement schemes, generating a Pareto solution set based on equipment quantity, safety coverage rate, and operating energy consumption targets; The multi-objective optimization includes: Constructing a multi-objective evaluation function based on equipment quantity, safety coverage rate, and operating energy consumption optimization targets; Evaluating multiple alternative equipment arrangement schemes and comparing their advantages and disadvantages using a non-dominated sorting method; Generating a Pareto frontier through iterative evolution to form a Pareto solution set composed of multiple non-dominated solutions, providing optimization options under multiple objectives.

[0032] Specifically, for the multiple alternative equipment arrangement schemes output by the genetic algorithm, a multi-objective evaluation function is constructed that includes equipment quantity, safety coverage rate, and operating energy consumption. The evaluation function is represented as: wherein, represents a certain candidate arrangement scheme; is an equipment quantity objective function used to measure the number of fire and drainage equipment in the arrangement scheme; is a safety coverage rate objective function used to represent the coverage rate of sprinkler heads, fire hydrant coverage areas, and evacuation paths; is an operating energy consumption objective function used to calculate the energy consumption required for pump stations and pipe network operation. The purpose of this step is to form multi-dimensional evaluation criteria for comprehensive comparison of candidate schemes; ​After obtaining the multi-objective evaluation function, all candidate schemes are evaluated, and a non-dominated sorting method (such as the NSGA-II algorithm) is used to compare the pros and cons of the schemes. If a scheme is better than in at least one objective and is not worse than in other objectives, it is called non-dominated . By constructing the dominance hierarchy through the non-dominated relationship, different levels of candidate scheme sets are obtained. The purpose of this step is to eliminate the dependence on a single objective and obtain excellent solutions that take into account multiple objectives; On the basis of non-dominated sorting, combined with genetic evolution operations (selection, crossover, mutation), the candidate schemes are updated generation by generation until convergence, obtaining a Pareto frontier consisting of multiple non-dominated solutions: ; wherein, represents the Pareto solution set, is the set of all candidate schemes, represents the objective function, thereby forming the solution set for selection under multiple objectives, providing diversified schemes for different design requirements (such as economic priority or safety priority).

[0033] S6, digital twin verification, mapping the Pareto solution set to the rail transit section digital twin model, performing dynamic simulation and reasoning verification, and outputting the implementation scheme.

[0034] wherein, the Pareto solution set is further mapped as input to the rail transit section digital twin model, and the digital twin model is established based on BIM and GIS data and used for dynamic simulation and reasoning verification of the candidate equipment arrangement scheme.

[0035] Specifically, the candidate equipment arrangement scheme in the Pareto solution set is imported to the digital twin model of the rail transit section through a data interface, the digital twin model constructs three-dimensional geometry and component attribute information based on BIM data, and obtains the spatial position and topological relationship of the section by combining GIS data, thereby generating a virtual model corresponding to the actual project. In this model, the equipment arrangement information of the candidate point is mapped to specific virtual nodes and pipe network parameters, further loading CFD fire simulation results and hydraulic calculation results, running dynamic simulation in the virtual section environment, and reasoning and checking parameters such as temperature field, smoke diffusion and drainage capacity, realizing verification of the engineering feasibility and safety constraints of different equipment arrangement schemes in the Pareto solution set, and outputting the schemes that pass the verification as implementation scheme data;

[0036] Further, the dynamic simulation and reasoning verification of the digital twin model includes: receiving the calculation results of the fire field simulation and the hydraulic calculation results as input data; map the input data to a rail transit section digital twin model to generate a three-dimensional visualization scene; In the three-dimensional visualization scene, the dynamic evolution of the temperature distribution, smoke diffusion and drainage capacity is displayed; Based on the dynamic evolution process, reasoning and checking are carried out, and the implementation scheme data of the candidate device arrangement scheme is output after the checking is completed.

[0037] Specifically, the digital twin model first receives the fire field simulation results based on the computational fluid dynamics (CFD) model and the hydraulic calculation results as input data, which include temperature field distribution, smoke concentration, sprinkling water demand and drainage flow parameters, providing real working condition data input for simulation, ensuring that the subsequent checking process is based on quantitative parameters; The received simulation data and hydraulic calculation results are mapped to the digital twin model through an interface, combined with BIM building information data and GIS spatial location data to generate a three-dimensional virtual scene of the section, and the candidate point device arrangement information is loaded into the scene simultaneously, forming a virtual mapping consistent with the actual rail section, coupling the optimization scheme with the section geometry and environmental data, and realizing the correspondence between the virtual model and the real project; In the three-dimensional visualization scene, the input data is loaded and dynamically evolved, and the temperature distribution, smoke diffusion process and drainage system capacity under fire conditions are displayed in real time. The simulation process is calculated step by step according to time, and the coupling process of disaster development and device response is displayed through three-dimensional visualization means. The role of this step is to intuitively reproduce the dynamic behavior of different candidate schemes under fire conditions; In the simulation process, the temperature, smoke concentration, visibility and drainage capacity and other indicators are inferred and checked based on the preset safety threshold. When a certain arrangement scheme meets all the constraint conditions, it is marked as an implementable solution, and the corresponding implementation scheme data is output, thereby completing the logical judgment and engineering constraint verification of the candidate device arrangement scheme, and generating an output scheme that can be used for engineering design.

[0038] Further, the digital twin model is further fused with sensor data in the rail transit section, including real-time monitoring data of temperature sensors, smoke concentration sensors and water level sensors; Compare and correct the real-time monitoring data with the simulation results to dynamically check the candidate device arrangement scheme in the running stage.

[0039] Specifically, temperature sensors, smoke concentration sensors and water level sensors are arranged in the rail transit section to collect real-time environmental parameters related to fire and drainage. Various sensors interact with the digital twin platform through a communication network to form real-time monitoring data streams in the running stage, providing real-time environmental input from the actual section for the twin model; The real-time monitoring data is compared with the simulation results in the digital twin model, the simulation results are corrected through residual analysis and data assimilation method, for example, if the temperature measured by the sensor deviates from the simulation temperature , the corrected temperature value is obtained through the weighted correction formula: ; wherein, is the corrected temperature value, is a weight coefficient (0-1), which is determined according to historical calibration experience, so as to fuse the actual monitoring result and the model prediction result, and improve the consistency of the model data and the running state; After data fusion is completed, the digital twin model re-calculates the corrected parameters, and dynamically checks the indexes such as temperature, flue gas concentration, visibility and drainage capacity, and judges according to the preset safety threshold. When a candidate arrangement scheme still meets all the constraints under the monitoring conditions in the running stage, it is maintained as an effective arrangement scheme, realizing real-time checking and dynamic verification of the candidate scheme in the running stage, so that the design scheme is not only feasible under the theoretical working condition, but also consistent in the actual running environment.

[0040] Please refer to the attached Figure 2 , an intelligent design system for track transportation section water supply and drainage and fire fighting, the system comprises: a candidate point generation module, configured to preset a plurality of candidate installation points of fire fighting and drainage equipment in the track transportation section according to the section geometric parameters, evacuation flow lines and specification requirements, and form candidate point set data; a fire working condition simulation module, configured to generate a plurality of fire working conditions based on a random algorithm, and perform fire field simulation to output temperature field distribution, flue gas diffusion distribution and fire water demand data; a hydraulic calculation and environment checking module, configured to perform hydraulic calculation and fire field environment checking on the candidate point set under the fire working condition; an optimization iteration module, configured to perform iterative search on the equipment arrangement scheme of the candidate point based on the output results of the hydraulic calculation and environment checking, and generate a plurality of alternative equipment arrangement schemes; a multi-objective optimization module, configured to perform multi-objective optimization on the alternative equipment arrangement schemes, and generate a Pareto solution set based on the equipment quantity, safety coverage rate and running energy consumption target; a digital twin verification module, configured to map the Pareto solution set to the track transportation section digital twin model, perform dynamic simulation and reasoning checking, and output an implementation scheme.

[0041] Specifically, the candidate point generation module generates a candidate installation point set based on BIM and GIS data, combined with interval geometric parameters, evacuation flow lines and specification requirements; the fire condition simulation module samples fire source parameters using a random algorithm and calls a CFD model to output temperature field, smoke diffusion and fire water demand; the hydraulic calculation and environmental checking module calculates and compares sprinkler water demand, drainage capacity and evacuation path environmental indicators; the optimization iteration module uses a genetic algorithm to encode and search candidate layout schemes, forming multiple alternative schemes; the multi-objective optimization module performs non-dominated sorting based on equipment quantity, safety coverage and energy consumption, generating a Pareto solution set; the digital twin verification module maps the Pareto solution set to a virtual interval established by BIM / GIS, runs dynamic simulation and checking combined with fire simulation and hydraulic calculation results, and outputs an implementation scheme.

[0042] While embodiments of the present application have been shown and described, it is to be understood that the embodiments described are merely divergences, modifications, replacements and variations of the embodiments of the present application, and the scope of the present application is defined by the appended claims and their equivalents.

Claims

1. A rail transit section water supply, drainage and fire protection intelligent design method, characterized in that: include: S1. Preset candidate points: Within the rail transit section, multiple candidate installation points for fire protection and drainage equipment are preset based on section geometry parameters, evacuation flow lines, and regulatory requirements, and candidate point set data is generated. S2. Fire condition simulation: Generate multiple fire conditions based on a random algorithm, simulate the fire scene according to the conditions, and output temperature field distribution, smoke diffusion distribution and fire water demand data; S3, hydraulic calculation and environmental verification, perform hydraulic calculation and fire environment verification on the candidate point set under fire conditions; S4, iterative optimization: Based on the output results of hydraulic calculation and environmental verification, an optimization algorithm is used to iteratively search for equipment layout plans for candidate points to generate multiple alternative equipment layout plans; S5, multi-objective optimization, performs multi-objective optimization on the alternative equipment layout scheme, and generates a Pareto solution set based on the number of equipment, safety coverage, and operating energy consumption targets; S6. Digital twin verification: map the Pareto solution set to the rail transit section digital twin model, perform dynamic simulation and reasoning verification, and output the implementation plan.

2. The intelligent design method for water supply, drainage and fire protection in rail transit section according to claim 1 is characterized in that: The fire condition generation includes: Determine the range and probability distribution of fire source location, fire intensity, burning time, and ventilation conditions based on historical fire case data, fire test data, and design specifications; Based on the probability distribution, a Monte Carlo algorithm is used to perform random sampling to generate multiple fire condition samples; The fire condition samples are input into the fire scene simulation to obtain the corresponding temperature field distribution, smoke diffusion distribution and fire water demand data.

3. The intelligent design method for water supply, drainage and fire protection in rail transit section according to claim 2 is characterized in that: The fire scene simulation is based on fire source intensity, ventilation conditions and interval geometric parameters, and is calculated through a computational fluid dynamics model to output fire scene temperature field distribution, smoke diffusion distribution and fire water demand data.

4. The intelligent design method for water supply, drainage and fire protection in rail transit section according to claim 1 is characterized in that: The hydraulic calculation and environmental verification include: Calculate the water spray intensity and effective area of ​​the sprinkler system to determine the total water consumption of the sprinkler system; Calculate the water supply flow rate and the most unfavorable point water pressure of the fire hydrant system to check whether it meets the requirements of the regulations; Use Manning's formula or equivalent hydraulic formula to calculate the drainage pump station flow and pipeline drainage capacity; In terms of the fire scene environment, the temperature, smoke concentration and visibility of the evacuation path are calibrated based on the fire simulation results, and the calibration values ​​are compared with the preset safety thresholds.

5. The intelligent design method for water supply, drainage and fire protection in rail transit section according to claim 1 is characterized in that: The optimization iterations include: Encode the equipment layout plan of the candidate points; Constructing a fitness function based on the output results of hydraulic calculations and environmental verification, which is used to comprehensively evaluate the water supply capacity, drainage capacity and environmental safety indicators of the equipment layout plan; Iteratively searching the equipment layout scheme using a genetic algorithm, and updating the layout scheme generation by generation through selection, crossover, and mutation operations; Generate multiple alternative equipment layout plans that meet the fitness function constraints.

6. The intelligent design method for water supply, drainage and fire protection in rail transit section according to claim 1 is characterized in that: The multi-objective optimization includes: Construct a multi-objective evaluation function based on the optimization goals of equipment quantity, security coverage and operating energy consumption; Evaluate multiple alternative equipment layout plans and compare their advantages and disadvantages using a non-dominated sorting method; The Pareto frontier is generated through iterative evolution, forming a Pareto solution set consisting of multiple non-dominated solutions, providing optimization options under multiple objectives.

7. The intelligent design method for water supply, drainage and fire protection in rail transit section according to claim 1 is characterized in that: The Pareto solution set is further mapped as input to the rail transit section digital twin model, which is established based on BIM and GIS data and is used to dynamically simulate and reason about candidate equipment layout plans.

8. The intelligent design method for water supply, drainage and fire protection in rail transit section according to claim 1 is characterized in that: The dynamic simulation and reasoning verification of the digital twin model includes: Receive the fire scene simulation results and hydraulic calculation results as input data; Mapping the input data to a rail transit section digital twin model to generate a three-dimensional visualization scene; In the 3D visualization scene, the dynamic evolution shows the changes in temperature distribution, smoke diffusion and drainage capacity; The inference verification is performed based on the dynamic evolution process, and the implementation plan data of the candidate equipment layout plan is output after the verification is completed.

9. The intelligent design method for water supply, drainage and fire protection in rail transit section according to claim 1, characterized in that: The digital twin model is further integrated with sensor data within the rail transit section, including real-time monitoring data from temperature sensors, smoke concentration sensors, and water level sensors; The real-time monitoring data is compared and corrected with the simulation results to dynamically check the candidate equipment layout schemes during the operation phase.

10. An intelligent design system for water supply, drainage and fire protection in rail transit areas, characterized in that: A rail transit section water supply, drainage and fire protection intelligent design method according to any one of claims 1 to 9, the system comprising: The candidate point generation module is used to preset multiple candidate installation points for fire protection and drainage equipment within the rail transit section based on the section geometry parameters, evacuation flow lines and regulatory requirements, and form candidate point set data; The fire condition simulation module is used to generate multiple fire conditions based on a random algorithm, perform fire scene simulation, and output temperature field distribution, smoke diffusion distribution, and fire water demand data; The hydraulic calculation and environmental verification module is used to perform hydraulic calculations and fire environment verification on the candidate point set under fire conditions; The optimization iteration module is used to iteratively search for equipment layout plans for candidate points using an optimization algorithm based on the output results of hydraulic calculations and environmental verification, and generate multiple alternative equipment layout plans; Multi-objective optimization module, used to perform multi-objective optimization on alternative equipment layout plans and generate Pareto solutions based on equipment quantity, safety coverage, and operating energy consumption targets; The digital twin verification module is used to map the Pareto solution set to the digital twin model of the rail transit section, perform dynamic simulation and reasoning verification, and output the implementation plan.

Images