Tunnel fire air curtain smoke prevention control method and system

Abstract

The invention discloses a tunnel fire air curtain smoke prevention control method and system, and relates to the technical field of intelligent fire fighting, and the method comprises the steps: building a digital twinborn prediction model, and generating a fire source position coordinate and a smoke diffusion trend prediction map through multi-physics field coupling simulation; analyzing the stability requirement of the air curtain jet flow through a Brapare-Prandtt boundary layer analysis algorithm, and generating a jet flow enhancement requirement parameter table in combination with temperature gradient correction; optimizing an acoustic vortex main frequency band by adopting a Slodhaar number, and generating an acoustic vortex control parameter set in combination with a matched sound pressure level and a configured resonator phase difference; and converting the acoustic vortex control parameter set into an execution instruction, monitoring the jet velocity, the vortex street stability and the smoke retardation effect in real time, and dynamically correcting the parameters of the digital twinborn prediction model. According to the method, physical quantity outline matching of the blocking intensity and the sound pressure level is achieved through the sound intensity-momentum equivalent method, and the optimal phase configuration is determined in combination with POD modal analysis.

Description

Technical Field

[0001] The present invention relates to the field of intelligent fire protection technology, and in particular to a tunnel fire air curtain smoke prevention control method and system. Background Art

[0002] Tunnel fire smoke control technology is an important research direction in the field of fire safety. With the expansion of tunnel engineering scale and the increase in traffic volume, traditional mechanical smoke exhaust systems have gradually developed in the direction of intelligence and precision. Early smoke control technologies mainly relied on smoke exhaust networks consisting of fixed fans and ventilation shafts, and their design was based on steady-state fluid mechanics models. In recent years, with the development of computational fluid dynamics technology, the optimization of smoke control systems based on numerical simulation has become a research hotspot. In addition, air curtain technology has further improved smoke control efficiency. It forms a dynamic barrier through high-speed airflow, effectively suppressing the spread of smoke. In the field of flow control, acoustic excitation technology has demonstrated unique advantages. Research by NASA and other institutions has shown that sound waves of specific frequencies can significantly affect boundary layer stability, providing new ideas for active flow control.

[0003] Existing technologies still face several challenges in practical applications. First, traditional smoke control systems are not adaptable enough to transient fire conditions, and the steady-state or quasi-steady-state models they use cannot accurately reflect the unsteady flow characteristics driven by thermal buoyancy during fire development. Second, existing acoustic control devices mostly use fixed-frequency excitation modes and lack a dynamic response mechanism to vortex dynamics under complex flow field conditions, resulting in the acoustic-vortex coupling efficiency not being fully utilized. Especially in the case of rapid changes in fire power, it is difficult to adjust the control parameters in a timely manner to adapt to changes in flow field characteristics. These technical limitations have, to a certain extent, restricted the further improvement of the performance of smoke control systems. Summary of the Invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides a tunnel fire air curtain smoke control method to solve the problems of insufficient dynamic multi-field coupling control accuracy and lack of transient working condition adaptability.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: In the first aspect, the present invention provides a tunnel fire air curtain smoke control method, which includes real-time collection of multi-field characteristic quantities of the environment in the tunnel and preprocessing to generate a standardized environmental parameter matrix; constructing a digital twin prediction model, and generating a fire source location coordinate and a smoke diffusion trend prediction map through multi-physical field coupling simulation; analyzing the stability requirements of the air curtain jet through the Blasius-Prandtl boundary layer analysis algorithm, and combining with temperature gradient correction to generate a jet enhancement requirement parameter table; using the Strouhal number to optimize the main frequency band of the acoustic vortex, combining the matching sound pressure level and configuring the resonator phase difference to generate an acoustic vortex control parameter set; converting the acoustic vortex control parameter set into an execution instruction, and monitoring the jet velocity, vortex street stability and smoke retardation effect in real time, and dynamically correcting the digital twin prediction model parameters.

[0007] As a preferred embodiment of the tunnel fire air curtain smoke control method of the present invention, the multi-field environmental characteristic quantities include ambient temperature distribution, smoke particle concentration, longitudinal wind speed distribution and thermal radiation intensity; The multi-field characteristic quantities of the environment are aligned in time and space, outliers are eliminated and dimensions are normalized to generate a standardized environmental parameter matrix.

[0008] As a preferred solution of the tunnel fire air curtain smoke control method of the present invention, wherein: the digital twin prediction model is constructed based on the standardized environmental parameter matrix, and the specific steps are as follows: Based on the standardized environmental parameter matrix, the initial flow field data is generated by the lattice Boltzmann method; Based on the turbulence correction of the initial flow field data using the large eddy simulation method, the three-dimensional velocity-pressure field distribution data is obtained; Based on the standardized environmental parameter matrix, the thermal radiation flux distribution data is generated by the discrete coordinate radiation transfer method; Based on the standardized environmental parameter matrix, the component transport-eddy dissipation method is used to generate smoke concentration field data; The three-dimensional velocity-pressure field distribution data, thermal radiation flux distribution data and flue gas concentration field data are used to generate a digital twin prediction model by adopting a multi-physics field coupling iterative algorithm.

[0009] As a preferred solution of the tunnel fire air curtain smoke control method of the present invention, wherein: the fire source location coordinates and smoke diffusion trend prediction map are generated through multi-physical field coupling simulation, the specific steps are as follows: The standardized environmental parameter matrix is input into the digital twin prediction model, and transient flow field data, transient temperature field data, and transient concentration field data are generated through multi-physics field coupling simulation method; Based on the transient temperature field data, the three-dimensional coordinates of the fire source center are generated by locating the extreme value of the three-dimensional temperature gradient and matching the heat source morphological characteristics. Based on transient flow field data and transient concentration field data, a smoke diffusion trend prediction map is generated through streamline integration and isosurface analysis.

[0010] As a preferred solution of the tunnel fire air curtain smoke control method of the present invention, wherein: based on the fire source location coordinates and the smoke diffusion trend prediction map, the stability requirements of the air curtain jet are analyzed to generate a jet enhancement requirement parameter table. The specific steps are as follows: Based on the coordinates of the fire source center and the smoke diffusion trend prediction map, the Blasius-Prandtl boundary layer analysis algorithm is used to analyze the stability requirements of the air curtain jet and generate a jet stability partition map. Based on the jet stability partition diagram, the minimum resistance strength requirement for each section is generated through the turbulent mixing momentum conservation algorithm combined with temperature gradient correction; Based on the minimum resistance strength requirements of each section, the Boussinesq thermal buoyancy analysis algorithm combined with vortex scale analysis is used to generate a thermal pressure compensation coefficient table; Based on the jet stability zoning diagram, the minimum resistance strength requirements of each section and the thermal pressure compensation coefficient table, the vortex dynamics feature extraction method combined with the anti-interference level mapping is used to generate the jet enhancement requirement parameter table.

[0011] As a preferred solution of the tunnel fire air curtain smoke control method of the present invention, wherein: based on the jet enhancement requirement parameter table, the acoustic vortex main frequency band is optimized by the Strouhal number, and the acoustic vortex control parameter set is generated by matching the sound pressure level and configuring the resonator phase difference. The specific steps are as follows: Based on the jet enhancement requirement parameter table, the dynamic Strouhal number correction method is used, combined with the jet momentum thickness, to define the main control frequency band; Based on the minimum blocking strength requirements of each section and the corresponding sound pressure level matching of the main control frequency band, the sound pressure level is matched through the sound intensity-momentum equivalent method to generate a sound pressure level control parameter table; Based on the jet stability partition diagram and smoke diffusion trend prediction diagram, the POD modal analysis method combined with the phase interference optimization algorithm is used to generate the phase configuration table; Based on the main control frequency band, sound pressure level control parameter table and phase configuration table, the acoustic vortex control parameter set is generated through a multi-parameter coupling optimization algorithm.

[0012] As a preferred solution of the tunnel fire air curtain smoke control method of the present invention, the acoustic vortex control parameter set is converted into an execution instruction, and the jet velocity, vortex street stability and smoke retardation effect are monitored in real time, and the digital twin prediction model parameters are dynamically corrected. The specific steps are as follows: Based on the acoustic eddy current control parameter set, the strategy is converted into execution instructions through industrial communication protocols to perform equipment control operations; Real-time monitoring of jet velocity, vortex street stability, and smoke retardation effect. Generate jet status monitoring data through multi-sensor fusion monitoring strategy, evaluate smoke control effect through fuzzy PID control algorithm, and generate jet stability correction coefficient and smoke retardation efficiency correction coefficient; Based on the jet state monitoring data, jet stability correction coefficient and smoke retardation efficiency correction coefficient, the digital twin prediction model parameters are dynamically corrected through the Kalman filter-gradient descent hybrid algorithm, and the updated control instruction set is generated through the explicit large eddy simulation coupling solver.

[0013] In the second aspect, the present invention provides a tunnel fire air curtain smoke prevention control system, including an environmental perception module, a situation prediction module, a demand analysis module, a parameter optimization module and a dynamic execution module; the environmental perception module is used to collect multi-field characteristic quantities of the environment in the tunnel in real time and preprocess them to generate a standardized environmental parameter matrix; the situation prediction module is used to construct a digital twin prediction model based on the standardized environmental parameter matrix, and generate a fire source location coordinate and a smoke diffusion trend prediction map through multi-physical field coupling simulation; the demand analysis module is used to analyze the stability requirements of the air curtain jet based on the fire source location coordinates and the smoke diffusion trend prediction map, and generate a jet enhancement demand parameter table; the parameter optimization module is used to optimize the acoustic vortex main frequency band through the Strouhal number based on the jet enhancement demand parameter table, and generate an acoustic vortex control parameter set in combination with the matching sound pressure level and the configured resonator phase difference; the dynamic execution module is used to convert the acoustic vortex control parameter set into an execution instruction, and monitor the jet velocity, vortex street stability and smoke retardation effect in real time, and dynamically correct the digital twin prediction model parameters.

[0014] In a third aspect, the present invention provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, any step of the tunnel fire air curtain smoke control method as described in the first aspect of the present invention is implemented.

[0015] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, any step of the tunnel fire air curtain smoke control method as described in the first aspect of the present invention is implemented.

[0016] The present invention has the following beneficial effects: By coupling three modeling methods—the lattice Boltzmann method, the discrete coordinate method, and the finite rate chemical reaction mechanism—on the COMSOL Multiphysics platform, a full-factor digital twin model encompassing fluid dynamics, thermal radiation transfer, and flue gas component transport is constructed. Transient temperature field data is processed using three-dimensional temperature gradient extreme value positioning and heat source morphological feature matching, and streamline integration techniques are combined to analyze concentration field distributions. The sound intensity-momentum equivalence method is used to achieve physical dimensional matching between retardation strength and sound pressure level, and POD modal analysis is combined to determine the optimal phase configuration. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0018] Figure 1 This is a flow chart of the air curtain smoke control method for tunnel fire.

[0019] Figure 2 This is a schematic diagram of the tunnel fire air curtain smoke control system.

[0020] Figure 3 Flowchart for the construction and simulation of a digital twin prediction model for the air curtain smoke control method for tunnel fires.

[0021] Figure 4 Generate a flow chart for the jet enhancement requirement parameter table for the air curtain smoke control method for tunnel fires. DETAILED DESCRIPTION

[0022] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0023] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0024] Secondly, the term "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in various places throughout this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive of other embodiments.

[0025] Reference Figures 1 to 4 , is an embodiment of the present invention, which provides a tunnel fire air curtain smoke control method, comprising the following steps: S1. Real-time collection of multi-field characteristics of the environment in the tunnel and pre-processing to generate a standardized environmental parameter matrix; Environmental multi-field characteristics include ambient temperature distribution, smoke particle concentration, longitudinal wind speed distribution and thermal radiation intensity; It should be noted that the acquisition of multi-field environmental characteristics involves using distributed fiber-optic temperature measurement devices or infrared thermal imager arrays to measure ambient temperature distribution, laser scattering particulate matter monitors to measure smoke particle concentration, three-dimensional ultrasonic anemometers to measure longitudinal wind speed distribution, and omnidirectional heat flux meters to measure thermal radiation intensity. Distributed fiber-optic temperature measurement devices invert temperature using the time-domain reflectometry principle of Raman scattered light, while infrared thermal imager arrays acquire temperature fields through infrared radiation imaging. Laser scattering particulate matter monitors detect smoke concentration based on the laser scattering principle and require regular calibration with standard aerosols. Three-dimensional ultrasonic anemometers calculate three-dimensional wind speed vectors using the ultrasonic time difference method. Omnidirectional heat flux meters measure thermal radiation based on the thermopile principle and require ambient temperature compensation.

[0026] The multi-field characteristic quantities of the environment are aligned in time and space, outliers are eliminated and dimensions are normalized to generate a standardized environmental parameter matrix.

[0027] It should be noted that the standardization of multi-field environmental characteristics involves three main steps: spatiotemporal alignment, outlier removal, and dimensional normalization. Spatiotemporal alignment first unifies the timestamps of all sensor data using the Precision Time Protocol. Kriging interpolation is then used to align the spatial coordinates of different sensors to the same reference frame, ensuring data consistency in both time and space. Outlier removal uses physical constraint checks and statistical filtering to remove values outside the reasonable range and random noise, such as values exceeding 100°C in ambient temperature distribution data or negative values in smoke particle concentration data. Dimensional normalization converts each parameter to a dimensionless value. For example, ambient temperature distribution data is converted from Celsius to Kelvin, and smoke particle concentration, longitudinal wind speed distribution, and thermal radiation intensity data are divided by their respective maximum allowable values to convert them to standardized values within the range of 0–1. Finally, the integrated multi-field environmental characteristics generate a standardized environmental parameter matrix. This matrix is organized into a multidimensional array based on time, spatial coordinates, parameter type, and parameter value, ensuring a uniform data format and direct use in subsequent analysis.

[0028] S2. Build a digital twin prediction model and generate fire source location coordinates and smoke diffusion trend prediction maps through multi-physics field coupling simulation; Based on the standardized environmental parameter matrix, the initial flow field data is generated by the lattice Boltzmann method; The base density value expression is:

[0029] Among them, ρ1 is the reference density value, p2 is the standard atmospheric pressure, R1 is the air gas constant, and T1 is the normalized temperature parameter;

[0030] Furthermore, after the standardized environmental parameter matrix provides normalized temperature, smoke particle concentration, wind speed, and thermal radiation intensity parameters, the density and velocity fields are first reconstructed. Density reconstruction is based on the normalized temperature parameter provided by the standardized environmental parameter matrix. The baseline density value is calculated using the ideal gas equation of state and corrected by the smoke particle concentration parameter. Velocity reconstruction restores the physical velocity components using the inverse normalization coefficients. Subsequently, discrete velocity direction projection is performed using the three-dimensional, nineteen-speed direction set of the D3Q19 discrete velocity model to obtain the projection value for each direction. Based on the density reconstruction, velocity reconstruction, and discrete direction projection values, the equilibrium distribution value for each direction is determined. Finally, the discrete direction distribution values of all grid points are integrated to form complete initial flow field data, providing basic flow field information for subsequent multi-physics coupled simulations. The entire process strictly maintains consistent parameter names, and all methods are based on existing technologies. The final results are fully consistent with the requirements.

[0031] It should be noted that the D3Q19 discrete velocity model is a mature discrete velocity model in the lattice Boltzmann method, used for three-dimensional flow simulation. This model is based on the discrete motion of fluid particles in 19 fixed directions: six orthogonal directions, 12 diagonal directions, and one zero-velocity direction. Its architecture consists of a set of velocity vectors and their corresponding weights. The D3Q19 discrete velocity model is directly applied to flow field evolution, updating the particle distribution function via the collision-migration rule without the need for additional construction. It is a standardized tool in the CFD field and can be directly accessed through open source implementations.

[0032] The large eddy simulation method is used to perform turbulence correction on the initial flow field data to obtain three-dimensional velocity-pressure field distribution data; It should be noted that the LES processing begins with the preparation of initial flow field data, derived from the results of an earlier lattice Boltzmann method. Spatial filtering is then performed to separate the vortex structures within the initial flow field data by scale, retaining large-scale vortex structures for direct processing while addressing small-scale vortex structures using a sub-grid stress method. During the sub-grid stress processing stage, empirical constants are used to characterize the influence of small-scale vortices. The momentum transfer processing stage prioritizes the post-filtering flow characteristics while ensuring stability. The pressure field processing stage uses an iterative method to ensure that the velocity field meets continuity requirements. The resulting three-dimensional velocity-pressure field data fully preserves the key characteristics of turbulence, providing an accurate flow field foundation for subsequent smoke diffusion simulations. The entire processing process strictly adheres to standard LES technical procedures, with all parameter settings derived from practical engineering experience to ensure reliable results. The output data format fully complies with subsequent processing requirements and can be directly used for multi-physics coupled analysis.

[0033] Based on the standardized environmental parameter matrix, the thermal radiation flux distribution data is generated by the discrete coordinate radiation transfer method; Next, key parameters such as thermal radiation intensity, temperature, and smoke particle concentration are extracted from the standardized environmental parameter matrix. After determining the discrete direction scheme using a probabilistic statistical model, the medium's radiation characteristics must be accurately described, including parameters such as the absorption and scattering coefficients, which are closely related to the temperature distribution and particle concentration. For example, the S8 scheme uses 80 discrete directions to fully cover the spatial radiation transfer path, with each direction precisely weighted according to Gaussian integral weights. During the medium characteristic processing stage, the absorption and scattering coefficients at each grid location are determined based on the temperature distribution parameters and smoke particle concentration parameters. Boundary conditions must be set based on actual physical boundary properties, such as the emissivity of the tunnel wall. The radiation transfer process proceeds along the pre-set discrete directions, fully accounting for the absorption, emission, and scattering effects of the medium. By integrating the radiation intensity across all discrete directions, thermal radiation flux distribution data is ultimately obtained for each location. The output thermal radiation flux distribution data accurately reflects the radiative heat flux density at each point in space, providing a reliable basis for subsequent thermal field analysis. The entire process strictly adheres to the standard discrete ordinate radiative transfer method (DRTM) process, with all parameter settings based on physical reality to ensure the accuracy and reliability of the results. The final data format fully matches the requirements of subsequent analysis and can be directly used in multi-physics coupled simulations.

[0034] Based on the standardized environmental parameter matrix, the component transport-eddy dissipation method is used to generate smoke concentration field data; Furthermore, it is necessary to first prepare complete input parameters, including key parameters such as temperature distribution, smoke particle concentration and velocity field extracted from the standardized environmental parameter matrix. The turbulent mixing processing stage uses the concept of eddy dissipation to characterize the influence of turbulence on component mixing, and the turbulence characteristic parameters need to be determined. The component transport processing stage tracks the spatial transport process of each flue gas component, considering the joint effects of convection and diffusion. The chemical reaction processing stage determines the conversion rate of each component based on the combustion characteristics. Boundary condition processing requires accurate setting of the component concentration values at each boundary. The final generated flue gas concentration field data contains the concentration values of different components at each grid point, which accurately reflects the diffusion distribution characteristics of the flue gas under the action of turbulence.

[0035] The three-dimensional velocity-pressure field distribution data, thermal radiation flux distribution data and flue gas concentration field data are used to generate a digital twin prediction model by adopting a multi-physics field coupling iterative algorithm.

[0036] The specific steps are as follows: first, the three-dimensional velocity-pressure field distribution data, thermal radiation flux distribution data, and smoke concentration field data need to be accurately aligned in time and space to ensure that the data of each field are completely matched in time and space. Then, multi-physics field data coupling processing is carried out, and a staggered grid strategy is adopted to process the semi-implicit coupling of the velocity field and the pressure field, and the explicit coupling of the thermal radiation field and the concentration field respectively. Strict convergence standards are set in the iterative convergence processing stage to ensure that the solution results of each physical field meet the predetermined accuracy requirements. Boundary condition synchronization is then carried out, focusing on the coordination and unification of the boundary conditions of each physical field to avoid boundary condition conflicts during the coupling process. The time step processing adopts a unified time advancement strategy to ensure that each physical field develops synchronously in the time dimension. Finally, a digital twin prediction model is output to accurately reflect the coupling effect of each physical field in the tunnel fire environment.

[0037] The standardized environmental parameter matrix is input into the digital twin prediction model, and transient flow field data, transient temperature field data, and transient concentration field data are generated through multi-physics field coupling simulation method; Transient flow field data expression:

[0038] Among them, u n+1 is the velocity field at the next moment, u n is the velocity field at the current moment, Δt is the time step, ρ is the air density, ▽p n is the pressure gradient at the current moment, ν is the kinematic viscosity, ▽ 2 u n is the Laplace term of the velocity field at the current moment, g is the acceleration of gravity, β is the thermal expansion coefficient, T n is the temperature field at the current moment, T0 is the reference temperature, and n is the index of the time step; Transient temperature field data expression:

[0039] Among them, T n+1 is the temperature field at the next moment, T n is the temperature field at the current moment, α is the thermal diffusivity, ▽ 2 T n is the Laplace term of the temperature field at the current moment, ▽T n is the gradient of the temperature field at the current moment, Q n 1 is the current thermal radiation flux, c p is the specific heat capacity; Transient concentration field data expression:

[0040] Among them, C n+1 k is the concentration of the kth chemical component at the next moment, C n k is the concentration of the kth chemical component at the current moment, D k is the diffusion coefficient of the kth chemical species, ▽ 2 C n k is the Laplace term of the concentration field of the kth chemical component at the current moment, ▽C n k is the gradient of the concentration of the kth chemical component at the current moment, ω n k is the chemical reaction source term of the kth component at the current moment, where k is the type of chemical component;

[0041] After the standardized environmental parameter matrix is imported as input data into the digital twin prediction model, each physical field is initialized to ensure that the initial conditions fully match the input parameters. A fixed-step timestepping strategy is used to ensure the temporal accuracy of the simulation. Within each timestep, the flow field is updated based on the current velocity-pressure field distribution data, accounting for the combined effects of inertial and viscous forces. The temperature field is updated by incorporating the thermal radiation flux distribution data, fully accounting for heat transfer modes: conduction, convection, and radiation. The concentration field is updated to track the transport of each flue gas component, including convection, diffusion, and chemical reaction effects. The update process of each physical field is strictly synchronized, and multi-physics coupling iterations ensure accurate representation of the interactions between the fields. The final output transient flow, temperature, and concentration field data are fully aligned in time and space, forming a complete spatiotemporal evolution sequence. The entire process strictly adheres to the standard process for multi-physics coupled simulation. All parameter settings and update strategies are based on established methods in fluid mechanics, heat transfer, and combustion, ensuring the physical accuracy and engineering reliability of the simulation results. The generated transient flow field data, transient temperature field data and transient concentration field data completely record the dynamic evolution process of the flow field, temperature field and concentration field under the tunnel fire environment, providing accurate numerical basis for fire development prediction and emergency decision-making.

[0042] Based on the transient temperature field data, the three-dimensional coordinates of the fire source center are generated by locating the extreme value of the three-dimensional temperature gradient and matching the heat source morphological characteristics. First, transient temperature field data output by the digital twin prediction model is obtained. This data records the temperature distribution of nodes in a three-dimensional spatial grid at regular intervals. The transient temperature field data undergoes format conversion and filtering preprocessing to eliminate abnormal fluctuations caused by numerical simulation and maintain the physical plausibility of the temperature field. Based on the regular grid provided by the digital twin prediction model, a differential method is used to construct a three-dimensional gradient field containing temperature gradient information at each node. Within the three-dimensional temperature gradient field, a dynamic dual-threshold segmentation method is used, combined with the temperature-gradient correlation curve from a standard fire source signature library. Temperature thresholds and gradient intensity conditions are set to screen potential fire source extreme points within the 3D temperature gradient field. Potential fire source extreme points must meet both absolute temperature requirements and spatial variation characteristics. The distribution pattern of potential fire source extreme points is morphologically matched with the standard fire source signature library to ensure that the distribution pattern of potential fire source extreme points conforms to the spatial distribution pattern of typical fire sources. Potential fire source extreme points that pass the matching test are weighted using the temperature-gradient dual parameter. The final output of the fire source center coordinates reflects both the heat source intensity distribution and the spatial structure characteristics. The spatiotemporal consistency of coordinate results is ensured through the continuity verification of multi-time-step data of the digital twin prediction model.

[0043] Based on transient flow field data and transient concentration field data, a smoke diffusion trend prediction map is generated through streamline integration and isosurface analysis.

[0044] Furthermore, the transient flow field and concentration field data output by the digital twin prediction model are first obtained. The transient flow field and concentration field data record the velocity distribution and pollutant concentration of the three-dimensional spatial grid nodes at fixed time intervals. The Lagrangian particle tracking method is used to construct the streamline field in the transient flow field data. By releasing virtual tracer particles and recording their motion trajectories at spatial feature locations that directly affect the smoke diffusion path, such as the fire source center area, ventilation outlet location, and air curtain installation section, the smoke transport process is reproduced and streamline distribution characteristics are generated. At the same time, the transient concentration field data is reconstructed into a three-dimensional isosurface, and the spatial boundary surface with characteristic concentration values is extracted to generate the isosurface evolution law. The streamline distribution characteristics and isosurface evolution law are combined to generate a two-dimensional plane or three-dimensional smoke diffusion trend prediction map.

[0045] S3. Analyze the stability requirements of the air curtain jet using the Blasius-Prandtl boundary layer analysis algorithm, and generate a jet enhancement requirement parameter table based on temperature gradient correction. Based on the coordinates of the fire source center and the smoke diffusion trend prediction map, the Blasius-Prandtl boundary layer analysis algorithm is used to analyze the stability requirements of the air curtain jet and generate a jet stability partition map. It should be noted that the stability requirements of the air curtain jet refer to the minimum performance requirements for the jet dynamic characteristics to ensure that the air curtain can effectively block smoke diffusion and maintain the predetermined smoke prevention effect during the tunnel fire smoke control process. Specifically, the air curtain jet must have sufficient momentum flux to overcome the smoke flow driven by the thermal buoyancy of the fire; the jet core area must maintain a continuous and stable velocity profile to form a complete air curtain barrier; the jet boundary layer must be controlled within a certain thickness range to avoid premature mixing failure; and the jet frequency characteristics must be staggered with the fire turbulence spectrum to prevent resonant instability. The stability requirements of the air curtain jet are quantitatively expressed through a jet stability partition diagram, which divides the tunnel space into three typical areas: the core stability area, the transition area, and the instability area.

[0046] Furthermore, accurate spatial location information of the fire source and complete smoke diffusion trend prediction results are first obtained. Based on the smoke diffusion trend prediction map, velocity distribution profiles of key sections are extracted, specifically the velocity gradient variation characteristics along the longitudinal and vertical directions of the tunnel. A jet stability criterion is established using the Blasius-Prandtl boundary layer analysis algorithm. The critical velocity gradient threshold is set by calibration using data from typical fire scenarios to distinguish regions with different stable states. Based on the stability criterion, the tunnel space is divided into three typical regions: the core stable region, the transition region, and the unstable region. The division takes into account the influence of thermal buoyancy effects caused by temperature gradients on boundary layer stability. The resulting jet stability partition map clearly marks the spatial distribution range of each region using different colors. The reliability of the results is verified by analyzing the evolution of the multi-time step partition map using the spatiotemporal consistency test method. For example, in a standard tunnel fire scenario, this method can accurately identify jet instability risk areas within 20 meters of the fire source, providing a direct basis for air curtain parameter optimization.

[0047] Based on the jet stability partition diagram, the minimum resistance strength requirement for each section is generated through the turbulent mixing momentum conservation algorithm combined with temperature gradient correction; The specific steps are as follows: first, a complete jet stability partition map and transient temperature field data are required as input. The three-category division provided by the jet stability partition map directly determines the baseline momentum flux requirements for each section. The core stability zone is required to maintain the highest momentum level to ensure a blocking efficiency of more than 90%. The transition zone needs to consider the momentum attenuation caused by boundary layer development. The instability zone requires focused compensation. The turbulent mixing momentum conservation algorithm is used to quantify the momentum loss caused by boundary layer mixing. At the same time, based on the transient temperature field data, the three-dimensional temperature gradient field analysis method is combined with the standard buoyancy feature library to identify the thermal buoyancy influence area. The momentum flux requirement is proportionally increased according to the temperature gradient to overcome the buoyancy effect. The final output of the minimum blocking intensity requirement for each section combines the baseline momentum value, turbulent mixing compensation, and temperature gradient correction. For example, in a typical tunnel fire scenario, the requirement for the section 10-20m away from the fire source is usually 4.5-6.0kg / (m·s²). The results need to be cross-validated with historical fire case data to ensure that the deviation between the requirements generated at 5MW fire power and the actual successful cases is within the engineering allowable range.

[0048] Based on the minimum resistance strength requirements of each section, the Boussinesq thermal buoyancy analysis algorithm combined with vortex scale analysis is used to generate a thermal pressure compensation coefficient table; The specific steps are as follows: first, the minimum retardation strength requirements and transient temperature field data of each section are required as input. The minimum retardation strength requirements provide the basic momentum flux requirements, while the transient temperature field data are used to analyze the thermal buoyancy effect. The Boussinesq thermal buoyancy analysis algorithm is used to quantify the impact of buoyancy lift caused by temperature gradients on jet stability. At the same time, vortex scale analysis evaluates the impact of turbulent mixing on thermal buoyancy distribution and identifies areas dominated by small-scale vortices. In areas dominated by small-scale vortices, due to strong turbulent mixing, the thermal buoyancy effect is locally enhanced, requiring additional correction of the compensation coefficient. Combining the results of thermal buoyancy effect and vortex scale analysis, a thermal pressure compensation coefficient table for each section is generated. The final output thermal pressure compensation coefficient table is classified and organized according to section location and operating conditions, and its rationality is verified through historical fire cases to ensure that the compensated retardation efficiency meets engineering requirements in typical fire scenarios.

[0049] Based on the jet stability zoning diagram, the minimum resistance strength requirements of each section and the thermal pressure compensation coefficient table, the vortex dynamics feature extraction method combined with the anti-interference level mapping is used to generate the jet enhancement requirement parameter table.

[0050] First, three types of input data need to be integrated: the regional division information provided by the jet stability partition map, the basic momentum flux determined by the minimum resistance intensity requirement of each section, and the temperature gradient correction value given by the thermal pressure compensation coefficient table. The dominant vortex characteristics in the flow field are analyzed by the vortex dynamics feature extraction method. At the same time, the anti-interference level is mapped according to the regional classification of the jet stability partition map. The core stable area has the strongest anti-interference ability, and the instability area has the weakest. The minimum resistance intensity requirement and the thermal pressure compensation coefficient are linearly superimposed according to the cross-sectional position. The final generated jet enhancement requirement parameter table contains key parameters such as spatial coordinates, corrected momentum flux, frequency control range, and turbulence intensity limit value.

[0051] S4. Use the Strouhal number to optimize the main frequency band of the acoustic vortex, combine the matching sound pressure level and the configuration resonator phase difference to generate the acoustic vortex control parameter set; Based on the jet enhancement requirement parameter table, the dynamic Strouhal number correction method is used, combined with the jet momentum thickness, to define the main control frequency band; Furthermore, jet momentum thickness is a key parameter describing the degree of momentum loss in the jet boundary layer. It is obtained by integrating the momentum difference between the jet velocity profile and the ideal uniform flow field. Jet momentum thickness can directly reflect the energy dissipation in the core region of the flow. In the dynamic Strouhal number correction method, jet momentum thickness is used as the basis for correction. Its variation follows the boundary layer theory. When jet momentum thickness increases, the Strouhal number needs to decrease to match the changed flow characteristics.

[0052] It should be noted that a complete jet enhancement requirement parameter table is first required as input. The jet enhancement requirement parameter table contains the key parameters of each section after thermal pressure compensation and vortex correction. The jet momentum thickness is accurately measured through flow field testing strategies. The jet momentum thickness parameter directly reflects the degree of mixing between the core flow area and the surrounding fluid. The initial Strouhal number is defined with reference to the cylindrical flow data in classical aeroacoustic theory. When implementing dynamic correction, the Strouhal number is adjusted in real time based on the measured jet momentum thickness. The corrected Strouhal number is combined with the jet velocity to convert it into the main control frequency band.

[0053] Based on the minimum blocking strength requirement and the corresponding sound pressure level of the main control frequency band, the sound pressure level is matched through the sound intensity-momentum equivalent method to generate a sound pressure level control parameter table; The specific steps are as follows: first, two types of key input parameters need to be integrated: the minimum resistance strength requirements of each section and the main control frequency band defined by the dynamic Strouhal number correction method. According to the sound intensity-momentum equivalent conversion principle in aeroacoustics, a linear correspondence between momentum flux and sound pressure level is established. In response to the special requirements of the main control frequency band, the frequency band energy distribution is corrected on the basic sound pressure level. For example, the sound pressure level is increased by 3dB in the core control frequency band of 18-22Hz to enhance the control effect of vortex shedding phenomenon, while keeping the sound pressure level of other frequency bands stable to avoid energy waste. The final generated sound pressure level control parameter table records the center frequency, sound pressure level range and allowable fluctuation value in detail according to the cross-sectional position.

[0054] Based on the jet stability partition diagram and smoke diffusion trend prediction diagram, the POD modal analysis method combined with the phase interference optimization algorithm is used to generate the phase configuration table; The specific steps are as follows: through the data acquisition and preprocessing stage, the regional stability classification of the jet stability partition map and the flow field dynamic characteristics of the smoke diffusion trend prediction map are obtained, and the coordinate alignment and data normalization methods are used to ensure data consistency, and the aligned stability partition map and normalized flow field dynamic characteristic data are obtained; in the feature extraction and analysis stage, the POD modal analysis method is used to process the aligned stability partition map and normalized flow field dynamic characteristic data respectively, extract the spatial modal energy distribution characteristics and dominant dynamic modes, identify the stability modes and main frequency components, and obtain the stability modal feature set and dynamic modal feature set; then in the modal association and optimization stage, the mapping relationship between spatial and dynamic modes is established through cross-correlation analysis, and the phase interference optimization algorithm is used to construct the phase difference-response relationship matrix. The flow control effect of different phase combinations is evaluated to obtain the optimal configuration scheme for each region, and the parameter robustness is verified by sensitivity analysis; then in the configuration table generation and verification stage, based on the optimal configuration scheme for each region, the optimization results are integrated through data fusion to generate a phase configuration table, and its effectiveness is verified by numerical simulation. For example, in a 5MW fire scenario, the 120° phase difference configured in the unstable zone of the jet stability partition diagram reduced the smoke leakage of the air curtain at a 10m section from 500ppm to 50ppm, verifying the engineering applicability of the phase configuration table.

[0055] Based on the main control frequency band, sound pressure level control parameter table and phase configuration table, the acoustic vortex control parameter set is generated through a multi-parameter coupling optimization algorithm.

[0056] The specific steps are as follows: first, based on the three sets of original parameters (the master frequency band definition file, the sound pressure level control parameter table, and the phase configuration table), the parameter alignment method is used to ensure time synchronization. Then, the parameter dimensions are unified through the parameter standardization method, and the standardized synchronization parameter set is output. The standardized synchronization parameter set is then input into the multi-parameter coupling optimization stage. The multi-parameter coupling optimization algorithm is used to establish the matching relationship between the master frequency band and the sound pressure level, and the correlation matrix between the sound pressure level and the phase parameters. The synergistic effect of the parameter combination is evaluated, and the Pareto front screening method is used to select the optimal parameter combination, and the optimized parameter matching scheme is output. Finally, the optimized parameter matching scheme is processed through the parameter fusion method to generate a structured final acoustic vortex control parameter set, which fully includes the frequency band control parameters, sound pressure level adjustment parameters, phase control parameters, and their applicable conditions. The entire process strictly adheres to the existing acoustic interference principles and fluid mechanics theory to ensure the physical rationality and engineering applicability of the parameter set, providing a directly executable optimization control parameter basis for practical applications.

[0057] S5. Convert the acoustic vortex control parameter set into execution instructions, monitor the jet velocity, vortex street stability and smoke retardation effect in real time, and dynamically correct the digital twin prediction model parameters.

[0058] Based on the acoustic eddy current control parameter set, the strategy is converted into execution instructions through industrial communication protocols to perform equipment control operations; It should be noted that the industrial communication protocol conversion strategy refers to a technical method for converting the acoustic eddy current control parameter set into control instructions that can be recognized and executed by industrial equipment. By parsing the communication protocol specifications supported by the target device, the parameter data is formatted, encapsulated and checksums are added according to the protocol requirements to form an instruction frame that meets the industrial bus transmission standard. Ultimately, the control parameters are accurately mapped to the physical device and transmitted reliably, ensuring the compatibility, real-time nature and execution reliability of the acoustic eddy current control instructions in the industrial network.

[0059] First, a complete set of acoustic vortex control parameters is required as input. Based on the industrial communication protocol supported by the tunnel air curtain's acoustic vortex control device, the set is converted into a protocol-compatible data format. For example, floating-point frequency values are converted into the protocol's specified integer format. These data frames are then encapsulated into data frames according to the device's register address mapping rules. Through the command generation process, these encapsulated data frames are converted into frequency setting commands, sound pressure level adjustment commands, and phase synchronization commands recognizable by the device. A validation mechanism is also embedded to ensure command transmission integrity. After the command set is transmitted to the device controller via the industrial network, the controller parses and dynamically loads the parameters into execution units, such as acoustic drivers or inverters, ensuring time synchronization of frequency and phase parameters across multiple devices as configured. During device operation, sensors collect real-time data on jet velocity, vortex stability, and sound pressure level. These data are compared with the expected values in the acoustic vortex control parameter set. Any deviation triggers parameter fine-tuning. For example, if the measured sound pressure level falls below the target value, the driver output power is automatically increased to a preset threshold. The entire control process strictly adheres to industrial communication protocol specifications to ensure the accuracy and real-time performance of parameter conversion, command transmission, and device execution, ultimately achieving seamless mapping and precise control of the acoustic eddy current control parameter set to the physical device.

[0060] Based on the equipment control operation, the jet velocity, vortex street stability and smoke retardation effect are monitored in real time. Through the multi-sensor fusion monitoring strategy, the jet state monitoring data is generated. The smoke control effect is evaluated through the fuzzy PID control algorithm, and the jet stability correction coefficient and smoke retardation efficiency correction coefficient are generated. First, jet velocity sensors, vortex stability sensors, and smoke concentration sensors are deployed at key sections of the tunnel air curtain to ensure data collection covers the core stable zone, transition zone, and unstable zone. A multi-sensor fusion monitoring strategy performs time synchronization and weighted fusion processing on the raw data, eliminating inter-sensor delay errors and noise interference. This generates a jet state monitoring dataset containing velocity fluctuation rate, vortex intensity coefficient, and smoke retardation efficiency indicators. Data anomalies trigger a real-time alarm mechanism and log them. A fuzzy PID control algorithm maps the smoke retardation efficiency indicator to deviation and deviation change rate input variables. Evaluation parameters are adapted by dynamically adjusting membership functions and a control rule library. A weighted average defuzzification method is used to generate jet stability and smoke retardation efficiency correction factors. For example, within a specific control cycle, smoke retardation efficiency increased from 85% to 91%, and velocity fluctuation rate in the jet core decreased from ±8% to ±3%, validating the effectiveness of the synergistic effect of the multi-sensor fusion monitoring strategy and the fuzzy PID control algorithm. The entire process strictly adheres to industrial control theory, ensuring real-time and robust evaluation and control processes.

[0061] Based on the jet state monitoring data, jet stability correction coefficient and smoke retardation efficiency correction coefficient, the digital twin prediction model parameters are dynamically corrected through the Kalman filter-gradient descent hybrid algorithm, and the updated control instruction set is generated through the explicit large eddy simulation coupling solver.

[0062] Furthermore, it is necessary to integrate real-time monitoring data such as jet velocity fluctuation rate, vortex intensity coefficient, and smoke retardation efficiency, as well as jet stability correction factors and smoke retardation efficiency correction factors. A Kalman filter-gradient descent hybrid algorithm dynamically adjusts the flow field dynamics, thermodynamic parameters, and acoustic control parameters of the digital twin prediction model through an iterative optimization mechanism to minimize the deviation between the model prediction results and the actual monitoring data. The corrected model parameters are input into an explicit large eddy simulation coupled solver. A multi-physics coupled simulation of the flow field, acoustic field, and thermal field is performed to predict the jet velocity field evolution, vortex shedding characteristics, and smoke diffusion trends. Fuzzy logic control is then used to map the predicted results to the acoustic vortex control parameter set, generating a control instruction set containing frequency adjustment commands, sound pressure level correction commands, and phase synchronization commands. Inverse mapping verification ensures strict physical and logical consistency between the control instruction set and the simulation results of the digital twin prediction model. The instruction parameters are also verified to meet the stability boundaries and smoke retardation efficiency target thresholds defined by the jet stability partition map. The verified control instruction set is transmitted via an industrial communication protocol to the tunnel air curtain's acoustic vortex control equipment for control and control. This triggers the data collection and parameter correction process for the next monitoring cycle, forming a closed-loop iterative optimization mechanism of "monitoring-correction-prediction-control." This entire process leverages the data assimilation capabilities of the Kalman filter, the parameter optimization properties of the gradient descent algorithm, and the high-precision flow field analysis capabilities of explicit large eddy simulation (ELS). This enables dynamic coordinated optimization of the digital twin prediction model and the control instruction set, ensuring the tunnel air curtain's adaptive control capabilities and smoke retention effectiveness under complex operating conditions.

[0063] This embodiment also provides a tunnel fire air curtain smoke prevention control system, including: an environmental perception module, a situation prediction module, a demand analysis module, a parameter optimization module and a dynamic execution module; the environmental perception module is used to collect multi-field characteristic quantities of the environment in the tunnel in real time and preprocess them to generate a standardized environmental parameter matrix; the situation prediction module is used to construct a digital twin prediction model based on the standardized environmental parameter matrix, and generate fire source location coordinates and smoke diffusion trend prediction diagrams through multi-physical field coupling simulation; the demand analysis module is used to analyze the stability requirements of the air curtain jet based on the fire source location coordinates and the smoke diffusion trend prediction diagram, and generate a jet enhancement demand parameter table; the parameter optimization module is used to optimize the main frequency band of the acoustic vortex through the Strouhal number based on the jet enhancement demand parameter table, and generate an acoustic vortex control parameter set in combination with the matching sound pressure level and the configured resonator phase difference; the dynamic execution module is used to convert the acoustic vortex control parameter set into execution instructions, and monitor the jet velocity, vortex street stability and smoke retardation effect in real time, and dynamically correct the digital twin prediction model parameters.

[0064] This embodiment also provides a computer device, which is suitable for the tunnel fire air curtain smoke prevention control method, including: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute computer-executable instructions to implement the tunnel fire air curtain smoke prevention control method proposed in the above embodiment.

[0065] The computer device may be a terminal, comprising a processor, memory, a communication interface, a display, and an input device connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores an operating system and computer programs. The internal memory provides an environment for the operating system and computer programs stored in the non-volatile storage media. The communication interface of the computer device is used to communicate with external terminals via wired or wireless communication. Wireless communication may be achieved via Wi-Fi, a carrier network, NFC (near-field communication), or other technologies. The display of the computer device may be a liquid crystal display or an electronic ink display. The input device may be a touchscreen overlay on the display, buttons, a trackball, or a touchpad on the computer device housing, or an external keyboard, touchpad, or mouse.

[0066] This embodiment also provides a storage medium having a computer program stored thereon, which, when executed by a processor, implements the tunnel fire air curtain smoke control method proposed in the above embodiment; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk.

[0067] In summary, this paper couples the lattice Boltzmann method, discrete coordinate method, and finite rate chemical reaction mechanism modeling approaches on the COMSOL Multiphysics platform to construct a full-factor digital twin model encompassing fluid dynamics, thermal radiation transfer, and flue gas component transport. Transient temperature field data is processed using three-dimensional temperature gradient extreme value positioning and heat source morphological feature matching, and streamline integration techniques are combined to analyze concentration field distributions. The sound intensity-momentum equivalence method is used to achieve physical dimensional matching between retardation strength and sound pressure level, and POD modal analysis is combined to determine the optimal phase configuration.

[0068] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A tunnel fire air curtain smoke control method, characterized by: include, Real-time collection of multi-field characteristics of the tunnel environment and pre-processing to generate a standardized environmental parameter matrix; Build a digital twin prediction model and generate fire source location coordinates and smoke diffusion trend prediction maps through multi-physics field coupling simulation; The stability requirements of the air curtain jet are analyzed by the Blasius-Prandtl boundary layer analysis algorithm, and the jet enhancement requirement parameter table is generated by combining the temperature gradient correction; The main frequency band of the acoustic vortex is optimized by using the Strouhal number, and the acoustic vortex control parameter set is generated by matching the sound pressure level and configuring the resonator phase difference. The acoustic vortex control parameter set is converted into execution instructions, and the jet velocity, vortex street stability and smoke retardation effect are monitored in real time to dynamically correct the digital twin prediction model parameters.

2. The tunnel fire air curtain smoke control method according to claim 1, characterized in that: The multi-field environmental characteristic quantities include ambient temperature distribution, smoke particle concentration, longitudinal wind speed distribution and thermal radiation intensity; The multi-field characteristic quantities of the environment are aligned in time and space, outliers are eliminated and dimensions are normalized to generate a standardized environmental parameter matrix.

3. The tunnel fire air curtain smoke control method according to claim 2, characterized in that: The digital twin prediction model is constructed based on the standardized environmental parameter matrix. The specific steps are as follows: Based on the standardized environmental parameter matrix, the initial flow field data is generated by the lattice Boltzmann method; Large eddy simulation is used to perform turbulence correction on the initial flow field data to obtain three-dimensional velocity-pressure field distribution data; Based on the standardized environmental parameter matrix, the thermal radiation flux distribution data is generated by the discrete coordinate radiation transfer method; Based on the standardized environmental parameter matrix, the component transport-eddy dissipation method is used to generate smoke concentration field data; The three-dimensional velocity-pressure field distribution data, thermal radiation flux distribution data and flue gas concentration field data are used to generate a digital twin prediction model by adopting a multi-physics field coupling iterative algorithm.

4. The tunnel fire air curtain smoke control method according to claim 3, characterized in that: The multi-physics field coupling simulation is used to generate the fire source location coordinates and smoke diffusion trend prediction map. The specific steps are as follows: The standardized environmental parameter matrix is input into the digital twin prediction model, and transient flow field data, transient temperature field data, and transient concentration field data are generated through multi-physics field coupling simulation method; Based on the transient temperature field data, the three-dimensional coordinates of the fire source center are generated by locating the extreme value of the three-dimensional temperature gradient and matching the heat source morphological characteristics. Based on transient flow field data and transient concentration field data, a smoke diffusion trend prediction map is generated through streamline integration and isosurface analysis.

5. The tunnel fire air curtain smoke control method according to claim 4, characterized in that: The stability requirements of the air curtain jet are analyzed based on the fire source location coordinates and the smoke diffusion trend prediction map, and a jet enhancement requirement parameter table is generated. The specific steps are as follows: Based on the three-dimensional coordinates of the fire source center and the smoke diffusion trend prediction map, the Blasius-Prandtl boundary layer analysis algorithm is used to analyze the stability requirements of the air curtain jet and generate a jet stability partition map. Based on the jet stability partition diagram, the minimum resistance strength requirement for each section is generated through the turbulent mixing momentum conservation algorithm combined with temperature gradient correction; Based on the minimum resistance strength requirements of each section, the Boussinesq thermal buoyancy analysis algorithm combined with vortex scale analysis is used to generate a thermal pressure compensation coefficient table; Based on the jet stability zoning diagram, the minimum resistance strength requirements of each section and the thermal pressure compensation coefficient table, the vortex dynamics feature extraction method combined with the anti-interference level mapping is used to generate the jet enhancement requirement parameter table.

6. The tunnel fire air curtain smoke control method according to claim 5, characterized in that: Based on the jet enhancement requirement parameter table, the acoustic vortex main frequency band is optimized by the Strouhal number, and the acoustic vortex control parameter set is generated by matching the sound pressure level and configuring the resonator phase difference. The specific steps are as follows: Based on the jet enhancement requirement parameter table, the dynamic Strouhal number correction method is used, combined with the jet momentum thickness, to define the main control frequency band; Based on the minimum blocking strength requirements of each section and the corresponding sound pressure level matching of the main control frequency band, the sound pressure level is matched through the sound intensity-momentum equivalent method to generate a sound pressure level control parameter table; Based on the jet stability partition diagram and smoke diffusion trend prediction diagram, the POD modal analysis method combined with the phase interference optimization algorithm is used to generate the phase configuration table; Based on the main control frequency band, sound pressure level control parameter table and phase configuration table, the acoustic vortex control parameter set is generated through a multi-parameter coupling optimization algorithm.

7. The tunnel fire air curtain smoke control method according to claim 6, characterized in that: The acoustic vortex control parameter set is converted into an execution instruction, and the jet velocity, vortex street stability and smoke retardation effect are monitored in real time, and the parameters of the digital twin prediction model are dynamically corrected. The specific steps are as follows Based on the acoustic eddy current control parameter set, the strategy is converted into execution instructions through industrial communication protocols to perform equipment control operations; Real-time monitoring of jet velocity, vortex street stability, and smoke retardation effect. Generate jet status monitoring data through multi-sensor fusion monitoring strategy, evaluate smoke control effect through fuzzy PID control algorithm, and generate jet stability correction coefficient and smoke retardation efficiency correction coefficient; Based on the jet state monitoring data, jet stability correction coefficient and smoke retardation efficiency correction coefficient, the digital twin prediction model parameters are dynamically corrected through the Kalman filter-gradient descent hybrid algorithm, and the updated control instruction set is generated through the explicit large eddy simulation coupling solver.

8. A tunnel fire air curtain smoke control system, based on the tunnel fire air curtain smoke control method according to any one of claims 1 to 7, characterized in that: It includes environment perception module, situation prediction module, demand analysis module, parameter optimization module and dynamic execution module; The environmental perception module is used to collect multiple environmental characteristics in the tunnel in real time and perform preprocessing to generate a standardized environmental parameter matrix; The situation prediction module is used to build a digital twin prediction model based on the standardized environmental parameter matrix, and generate the fire source location coordinates and smoke diffusion trend prediction map through multi-physics field coupling simulation; Demand analysis module, used to analyze the stability requirements of the air curtain jet based on the fire source location coordinates and smoke diffusion trend prediction map, and generate a jet enhancement demand parameter table; The parameter optimization module is used to optimize the main frequency band of the acoustic vortex based on the jet enhancement requirement parameter table through the Strouhal number, and generate the acoustic vortex control parameter set by matching the sound pressure level and configuring the resonator phase difference; The dynamic execution module is used to convert the acoustic vortex control parameter set into execution instructions, monitor the jet velocity, vortex street stability and smoke retardation effect in real time, and dynamically correct the digital twin prediction model parameters.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the tunnel fire air curtain smoke prevention control method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the tunnel fire air curtain smoke prevention control method according to any one of claims 1 to 7 are implemented.

Images