Method and device for predicting flowing combustion behavior of tunnel flowing fire, equipment and medium

Abstract

The invention relates to a prediction method and device for a flowing combustion behavior of a tunnel flowing fire, equipment and a medium, and the method comprises the steps: obtaining a prediction task, and determining a target tunnel feature and a target parameter; inputting the target parameter into a rate prediction model for calculation to obtain a target leakage rate in a second time period; determining a target combustion area in a future time period based on a preset first equation set and the target leakage rate in the second time period; based on the target tunnel characteristics, the target combustion area and the target leakage rate in the future time period, the tunnel flow fire parameter evolution data set and the target wind speed in the first time period, the target flame dragging length and the target flame inclination angle in the future time period are obtained through prediction. According to the method, the flame dragging length and the flame inclination angle of the tunnel flow fire in the future time period can be quickly predicted, so that the future evolution trend of the flame form is obtained, and a scientific basis is provided for emergency response of the tunnel flow fire.

Description

Technical Field

[0001] The present disclosure relates to the technical field of fire prediction, and in particular to a method and device, equipment and medium for predicting the flow combustion behavior of a tunnel flowing fire. Background Art

[0002] Road transport is the main mode of transporting hazardous chemicals. When hazardous chemical vehicles leak in highway tunnels, flowing fires are likely to form. The uncontrolled dynamic spread of flowing fires can ignite surrounding vehicles, leading to serious consequences. At the same time, in order to facilitate drainage, the road surface of highway tunnels is designed with certain horizontal and vertical slopes. Under the influence of these parameters, the flame geometry of flowing fires changes significantly, further increasing the risk of spreading combustion of flowing fires.

[0003] Therefore, in order to quickly predict the fire spread process and the corresponding risk size after an actual flowing fire accident occurs, a prediction method for studying the flow combustion behavior of tunnel flowing fire is now needed. Summary of the invention

[0004] In view of this, the present disclosure proposes a prediction method and device, equipment and medium for the flow combustion behavior of tunnel flowing fire, which can quickly predict the flame drag length and flame inclination angle of tunnel flowing fire in future time periods, thereby obtaining the future evolution trend of the flame morphology, and providing a scientific basis for emergency response to tunnel flowing fire.

[0005] According to one aspect of the present disclosure, a method for predicting the flow combustion behavior of a tunnel flowing fire is provided, comprising: obtaining a prediction task for a target flowing fire occurring in a target tunnel, determining a target tunnel feature of the target tunnel and target parameters associated with the target flowing fire in a first time period after the occurrence of the target flowing fire, the target parameters comprising a target wind speed, a target image, a target smoke temperature, and a target smoke concentration; inputting the target parameters into a rate prediction model for calculation to obtain a target leakage rate of the fuel leaked from the leakage port in the target flowing fire in a second time period, wherein the rate prediction model is trained based on a preset tunnel flowing fire parameter evolution data set, and the second time period includes the first time period; based on a preset representation target The first equation group of the spreading combustion process of the oil layer and the target leakage rate of the second time period are used to determine the target combustion area of ​​the target flowing fire in the future time period, wherein the target oil layer is formed by the fuel covering the target tunnel ground in the target flowing fire, and the future time period belongs to the second time period and is after the first time period; based on the target tunnel characteristics, the target combustion area and target leakage rate of the future time period, the tunnel flowing fire parameter evolution data set, and the target wind speed of the first time period, the target flame drag length and target flame inclination angle of the target flowing fire in the future time period are predicted, and the target flame drag length and target flame inclination angle of the future time period are used as the prediction results of the prediction task.

[0006] In a possible implementation, the first set of equations includes a set of partial differential equations determined according to the conservation of momentum satisfied by the spreading combustion process of the target oil layer, a partial differential equation determined according to the conservation of energy satisfied by the spreading combustion process, and a burning rate relationship constructed based on the tunnel flowing fire parameter evolution data set; wherein, based on the preset first set of equations representing the spreading combustion process of the target oil layer and the target leakage rate of the second time period, determining the target burning area of ​​the target flowing fire in the future time period includes: solving the first set of equations using a finite difference method, and calculating the target thickness distribution of the target oil layer at each time point in the future time period based on the target leakage rate of the second time period and preset initial conditions, the target thickness distribution of each time point is used to indicate the oil layer thickness of the target oil layer at each tunnel position at the corresponding time point, and each tunnel position is determined based on the target tunnel characteristics of the target tunnel; determining the target burning area of ​​the target flowing fire at the corresponding time point according to the number of tunnel positions where the oil layer thickness is not zero obtained based on the target thickness distribution of each time point.

[0007] In one possible implementation, the burning rate relationship is determined based on the burning rate, multiple first parameters, wind speed, gravitational acceleration, and burning area, wherein the multiple first parameters are parameters related to the burning rate determined based on the tunnel flow fire parameter evolution data set.

[0008] In a possible implementation, based on the target tunnel characteristics, the target burning area and the target leakage rate in the future time period, the tunnel flowing fire parameter evolution data set, and the target wind speed in the first time period, the target flame drag length and the target flame inclination angle of the target flowing fire in the future time period are predicted, including: determining the future wind speed in the future time period based on the target wind speed in the first time period; obtaining a target length relationship constructed based on the tunnel flowing fire parameter evolution data set, and calculating the target flame drag length at each time point in the future time period according to the target length relationship, the future wind speed, the target tunnel characteristics, and the target burning area at each time point in the future time period; and obtaining a target angle relationship constructed based on the tunnel flowing fire parameter evolution data set, and calculating the target flame inclination angle at each time point in the future time period according to the target length relationship, the future wind speed, the target tunnel characteristics, and the target burning area at each time point in the future time period; wherein the target tunnel characteristics include the gravitational acceleration of the target tunnel location, the height and width of the target tunnel, and the horizontal axis slope and the vertical axis slope of the target tunnel.

[0009] In one possible implementation, the target length relationship is determined based on the flame drag length, multiple second parameters, wind speed, gravitational acceleration, burning area, leakage area, tunnel height, tunnel width, tunnel horizontal axis slope, and tunnel longitudinal axis slope, wherein the multiple second parameters are parameters related to the flame drag length determined based on the tunnel flow fire parameter evolution data set.

[0010] In one possible implementation, the target angle relationship is determined based on the flame inclination angle, multiple third parameters, wind speed, gravitational acceleration, burning area, leakage area, tunnel height, tunnel width, tunnel horizontal axis slope, and tunnel longitudinal axis slope, wherein the multiple third parameters are parameters related to the flame inclination angle determined based on the tunnel flow fire parameter evolution data set.

[0011] In a possible implementation, the method further includes: obtaining simulation data groups of simulated tunnel flowing fires under multiple different working conditions, each of the simulation data groups including simulation parameters associated with the corresponding simulated tunnel flowing fire, the simulation parameters including smoke temperature, smoke concentration, wind speed, image, flame drag length, and flame inclination angle, wherein the working condition is determined based on the leakage rate of the fuel leaked from the leakage port in the simulated tunnel flowing fire, the ventilation rate, and the tunnel slope; and constructing a tunnel flowing fire parameter evolution data set based on all simulation data groups.

[0012] According to another aspect of the present disclosure, a prediction device for the flow combustion behavior of a tunnel flowing fire is provided, comprising: an acquisition module, for acquiring a prediction task for a target flowing fire occurring in a target tunnel, determining a target tunnel characteristic of the target tunnel and target parameters associated with the target flowing fire in a first time period after the occurrence of the target flowing fire, wherein the target parameters include a target wind speed, a target image, a target smoke temperature, and a target smoke concentration; a calculation module, for inputting the target parameters into a rate prediction model for calculation, and obtaining a target leakage rate of the fuel leaked from the leakage port in the target flowing fire in a second time period, wherein the rate prediction model is obtained by training based on a preset tunnel flowing fire parameter evolution data set, and the second time period includes the first time period; a determination module, for Based on a preset first set of equations representing the spreading combustion process of a target oil layer and a target leakage rate in the second time period, a target combustion area of ​​the target flowing fire in a future time period is determined, wherein the target oil layer is formed by the fuel covering the ground of the target tunnel in the target flowing fire, and the future time period belongs to the second time period and is after the first time period; a prediction module is used to predict a target flame drag length and a target flame inclination angle of the target flowing fire in the future time period based on the target tunnel characteristics, the target combustion area and the target leakage rate in the future time period, the tunnel flowing fire parameter evolution data set, and the target wind speed in the first time period, and use the target flame drag length and the target flame inclination angle in the future time period as the prediction result of the prediction task.

[0013] In a possible implementation, the first set of equations includes a set of partial differential equations determined according to the conservation of momentum satisfied by the spreading combustion process of the target oil layer, a partial differential equation determined according to the conservation of energy satisfied by the spreading combustion process, and a burning rate relationship constructed based on the tunnel flowing fire parameter evolution data set; wherein, based on the preset first set of equations representing the spreading combustion process of the target oil layer and the target leakage rate of the second time period, determining the target burning area of ​​the target flowing fire in the future time period includes: solving the first set of equations using a finite difference method, and calculating the target thickness distribution of the target oil layer at each time point in the future time period based on the target leakage rate of the second time period and preset initial conditions, the target thickness distribution of each time point is used to indicate the oil layer thickness of the target oil layer at each tunnel position at the corresponding time point, and each tunnel position is determined based on the target tunnel characteristics of the target tunnel; determining the target burning area of ​​the target flowing fire at the corresponding time point according to the number of tunnel positions where the oil layer thickness is not zero obtained based on the target thickness distribution of each time point.

[0014] In one possible implementation, the burning rate relationship is determined based on the burning rate, multiple first parameters, wind speed, gravitational acceleration, and burning area, wherein the multiple first parameters are parameters related to the burning rate determined based on the tunnel flow fire parameter evolution data set.

[0015] In a possible implementation, based on the target tunnel characteristics, the target burning area and the target leakage rate in the future time period, the tunnel flowing fire parameter evolution data set, and the target wind speed in the first time period, the target flame drag length and the target flame inclination angle of the target flowing fire in the future time period are predicted, including: determining the future wind speed in the future time period based on the target wind speed in the first time period; obtaining a target length relationship constructed based on the tunnel flowing fire parameter evolution data set, and calculating the target flame drag length at each time point in the future time period according to the target length relationship, the future wind speed, the target tunnel characteristics, and the target burning area at each time point in the future time period; and obtaining a target angle relationship constructed based on the tunnel flowing fire parameter evolution data set, and calculating the target flame inclination angle at each time point in the future time period according to the target length relationship, the future wind speed, the target tunnel characteristics, and the target burning area at each time point in the future time period; wherein the target tunnel characteristics include the gravitational acceleration of the target tunnel location, the height and width of the target tunnel, and the horizontal axis slope and the vertical axis slope of the target tunnel.

[0016] In one possible implementation, the target length relationship is determined based on the flame drag length, multiple second parameters, wind speed, gravitational acceleration, burning area, leakage area, tunnel height, tunnel width, tunnel horizontal axis slope, and tunnel longitudinal axis slope, wherein the multiple second parameters are parameters related to the flame drag length determined based on the tunnel flow fire parameter evolution data set.

[0017] In one possible implementation, the target angle relationship is determined based on the flame inclination angle, multiple third parameters, wind speed, gravitational acceleration, burning area, leakage area, tunnel height, tunnel width, tunnel horizontal axis slope, and tunnel longitudinal axis slope, wherein the multiple third parameters are parameters related to the flame inclination angle determined based on the tunnel flow fire parameter evolution data set.

[0018] In a possible implementation, the device also includes a construction module, which is used to: obtain simulation data groups of simulated tunnel flowing fires under multiple different working conditions, each of the simulation data groups includes simulation parameters associated with the corresponding simulated tunnel flowing fire, and the simulation parameters include smoke temperature, smoke concentration, wind speed, image, flame drag length, and flame inclination angle, wherein the working condition is determined based on the leakage rate of the fuel leaked from the leakage port in the simulated tunnel flowing fire, the ventilation rate, and the tunnel slope; and construct a tunnel flowing fire parameter evolution data set based on all simulation data groups.

[0019] According to another aspect of the present disclosure, an electronic device is provided, comprising: a processor; and a memory for storing processor-executable instructions; wherein the processor is configured to implement the above method when executing the instructions stored in the memory.

[0020] According to another aspect of the present disclosure, a non-volatile computer-readable storage medium is provided, on which computer program instructions are stored, wherein the computer program instructions implement the above method when executed by a processor.

[0021] According to another aspect of the present disclosure, a computer program product is provided, including a computer-readable code, or a non-volatile computer-readable storage medium carrying the computer-readable code. When the computer-readable code runs in a processor of an electronic device, the processor in the electronic device executes the above method.

[0022] The present disclosure provides a method, device, equipment and medium for predicting the flow combustion behavior of a tunnel flowing fire. By acquiring a prediction task for a target flowing fire occurring in a target tunnel, a target tunnel characteristic of the target tunnel and target parameters associated with the target flowing fire in a first time period after the target flowing fire occurs are determined, wherein the target parameters include a target wind speed, a target image, a target smoke temperature and a target smoke concentration; the target parameters are input into a rate prediction model for calculation to obtain a target leakage rate of the fuel leaked from the leakage port in the target flowing fire in a second time period, wherein the rate prediction model is trained based on a preset tunnel flowing fire parameter evolution data set, and the second time period includes the first time period; based on a preset first set of equations representing the spreading combustion process of the target oil layer and the target leakage rate in the second time period, a target flow rate in the future time period is determined. The target burning area of ​​the flowing fire, wherein the target oil layer is formed by the fuel covering the target tunnel ground in the target flowing fire, and the future time period belongs to the second time period and is after the first time period; based on the target tunnel characteristics, the target burning area and the target leakage rate in the future time period, the tunnel flowing fire parameter evolution data set, and the target wind speed in the first time period, the target flame drag length and the target flame inclination angle of the target flowing fire in the future time period are predicted, and the target flame drag length and the target flame inclination angle of the future time period are used as the prediction results of the prediction task, and more accurate flame morphology evolution data over time, namely the target flame drag length and the target flame inclination angle of the future time period, can be obtained. This accurate prediction helps the handling personnel to more accurately understand the severity and spread trend of the tunnel flowing fire, so as to make more scientific decisions and countermeasures.

[0023] Further features and aspects of the present disclosure will become apparent from the following detailed description of exemplary embodiments with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate exemplary embodiments, features, and aspects of the disclosure and, together with the description, serve to explain the principles of the disclosure.

[0025] Figure 1 A flowchart of a prediction method provided according to an embodiment of the present disclosure is shown.

[0026] Figure 2 A schematic diagram of a tunnel flowing fire test model provided according to an embodiment of the present disclosure is shown.

[0027] Figure 3 A schematic diagram showing a finite difference solution method provided according to an embodiment of the present disclosure.

[0028] Figure 4 A schematic diagram showing a prediction result provided according to an embodiment of the present disclosure.

[0029] Figure 5 A block diagram of a device for predicting flow combustion behavior of a tunnel flowing fire provided according to an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0030] Various exemplary embodiments, features and aspects of the present disclosure will be described in detail below with reference to the accompanying drawings. The same reference numerals in the accompanying drawings represent elements with the same or similar functions. Although various aspects of the embodiments are shown in the accompanying drawings, the drawings are not necessarily drawn to scale unless otherwise specified.

[0031] The word “exemplary” is used exclusively herein to mean “serving as an example, example, or illustration.” Any embodiment described herein as “exemplary” is not necessarily to be construed as preferred or advantageous over other embodiments.

[0032] In addition, in order to better illustrate the present disclosure, numerous specific details are given in the following specific embodiments. It should be understood by those skilled in the art that the present disclosure can also be implemented without certain specific details. In some examples, methods, means, components and circuits well known to those skilled in the art are not described in detail in order to highlight the subject matter of the present disclosure.

[0033] In order to facilitate those skilled in the art to understand the technical solution provided by the embodiments of the present disclosure, the technical environment in which the technical solution is implemented is described below.

[0034] When a hazardous chemical vehicle encounters a fire source during leakage and flow in a highway tunnel, a flowing fire is likely to form. The uncontrolled dynamic spread of a flowing fire can ignite surrounding vehicles, leading to serious consequences. For example, a highway tunnel flowing fire accident occurred in a certain place in 2014. The flowing fire spread rapidly on the concrete surface and eventually ignited five coal trucks, killing 40 people. In order to reduce the smoke concentration and fire hazard of the tunnel system, a ventilation system is usually built. At the same time, in order to facilitate drainage, the road surface of the highway tunnel is designed with a certain horizontal and vertical slope. Under the influence of the above parameters, the flame geometry of the flowing fire changes significantly, further increasing the risk of spreading combustion of the flowing fire. Therefore, in order to quickly predict the spread process of the fire and the corresponding risk size after an actual flowing fire accident occurs, it is necessary to study a rapid prediction method for the flow combustion of a flowing fire.

[0035] At present, the research on flowing fire is mostly focused on the development of experimental equipment and monitoring and early warning methods for oil storage sites. For example, the polymorphic foam is sprayed on the test bench through the foam spraying mechanism to test the interception and control effect of the polymorphic foam on the flowing fire of flammable liquid. For example, the influence of the spray direction, angle, and spray position of the foam fire extinguishing device on the fire extinguishing effect in the simulated tank area flowing fire accident. For another example, the machine learning model is used to determine the fire spread rate based on real-time flame images, and quickly provide a fire extinguishing strategy for oil storage fires.

[0036] In the related technologies, in terms of the prediction method of tunnel fire behavior, there is a scheme that inputs the temperature time series data into the deep learning prediction model, maps the temperature time series data of the temperature sensors arranged vertically, and then conducts risk assessment. There is also a method of simulating the development scale of the fire in the tunnel under different fire source powers, the number of fan opening groups and the fine water mist fire extinguishing device in the laboratory, and then uses the Kalman filter algorithm to construct a prediction model of the evolution law of the fire flame characteristics under different fire source powers, and intelligently opens the jet fan according to the prediction results to reasonably control the scale of fire development. Or there will be a tunnel oil pool fire experiment, extracting the key parameter data of the tunnel fire, constructing a neural network prediction model for the development of the tunnel fire situation, realizing the input of the extracted tunnel fire scene information into the neural network prediction model for the development of the tunnel fire situation, and predicting the subsequent development of the tunnel fire situation.

[0037] Through the investigation and analysis of relevant technologies, it can be concluded that, on the one hand, the existing research on flowing fires is mostly focused on the development of experimental devices, and the only monitoring and early warning methods are constructed for oil storage sites. There are significant differences between the technical means and related theories and tunnel fire scenarios. On the other hand, most of the existing prediction methods for tunnel fire behavior only use machine learning technology, and rarely incorporate physical models into the prediction methods; at the same time, the evolution of the disaster of flowing fires is controlled by both oil layer flow and flame combustion, but the current prediction models almost only focus on the tunnel fire combustion process, and do not consider the situation of flowing and burning at the same time. Therefore, combining physical fast calculation models with machine learning methods to achieve intelligent and rapid prediction of the flow combustion behavior of tunnel flowing fires is a technical bottleneck that urgently needs to be broken through.

[0038] In order to solve the above technical problems, the embodiments of the present invention provide a method for predicting the flow combustion behavior of a tunnel flowing fire. Based on the real-time target parameters obtained, the future evolution trend of the flame morphology of the tunnel flowing fire can be quickly calculated, thereby clarifying the corresponding potential risk range, effectively improving the efficiency of on-site handling of tunnel flowing fire accidents, and reducing casualties and property losses.

[0039] Now combined Figures 1 to 4 The method for predicting the flow combustion behavior of a tunnel flowing fire provided by an embodiment of the present disclosure is schematically illustrated.

[0040] like Figure 1 As shown, the prediction method may include the following steps S101 to S104.

[0041] Step S101, obtaining a prediction task for a target flowing fire occurring in a target tunnel, determining a target tunnel feature of the target tunnel and a target parameter associated with the target flowing fire in a first time period after the target flowing fire occurs.

[0042] The target tunnel refers to the tunnel where the target flowing fire is occurring. The target tunnel may be provided with a variety of sensors, such as a temperature sensor, a smoke concentration sensor, a hot wire anemometer, a high-speed camera, an infrared camera, etc. Various sensors may be used to obtain corresponding types of data.

[0043] The prediction task can be used to indicate the target tunnel for which the flowing fire prediction is required, the time information for which the prediction is required for the target tunnel, etc., so that the target tunnel for which the prediction is required can be determined based on the prediction task, and the future time period for the expected prediction can be determined based on the time information. To achieve the prediction task, the target tunnel characteristics of the target tunnel, such as the tunnel slope, etc., can be obtained from the preset tunnel information database, and the target parameters associated with the target flowing fire in the first time period after the target flowing fire occurs can be obtained through the sensor of the target tunnel. The target parameters may include target wind speed, target image, target smoke temperature, and target smoke concentration. The target wind speed refers to the wind speed in the target tunnel. The target image may include infrared image data obtained by an infrared camera and an image obtained by a high-speed camera. The target smoke temperature refers to the temperature of the smoke in the target tunnel. The target smoke concentration refers to the concentration of the smoke in the target tunnel.

[0044] Step S102: Input the target parameters into the rate prediction model for calculation to obtain the target leakage rate of the fuel leaked from the leakage port in the target flow fire in the second time period.

[0045] The second time period includes the first time period. The future time period belongs to the second time period and is after the first time period. For example, the first time period may be 0 to t, the future time period may be t to t+N, and the second time period may be 0 to t+N.

[0046] The rate prediction model can be used to predict the leakage rate of the fuel leaking from the leakage port in the flowing fire in real time. The rate prediction model is obtained by training a neural network model based on a preset tunnel flowing fire parameter evolution data set. Among them, the tunnel flowing fire parameter evolution data set may include a simulation data set of simulated tunnel flowing fires under multiple different working conditions, and the neural network model may be a long short-term memory network (Long Short-Term Memory, LSTM) neural network model, or other models may be used, which is not limited in the embodiments of the present disclosure.

[0047] For example, the tunnel flow fire parameter evolution data set can be randomly divided into a training set and a test set. The training set is used to train the neural network model to obtain a rate prediction model. The test set is used to test the accuracy of the rate prediction model. Subsequently, a neural network model is constructed using a neural network algorithm, which uses the image, temperature, smoke concentration, and wind speed of the simulated tunnel flow fire in the training set as input and the real-time leakage rate of the simulated tunnel flow fire as output, and the constructed neural network model is trained using the training set. The trained neural network model is tested using the test set, and the neural network model that meets the preset accuracy requirements is used as a rate prediction model to quickly and in real time calculate the leakage rate of the fuel leaked from the leakage port in the tunnel flow fire.

[0048] The prediction method may also include a process of constructing a tunnel flow fire parameter evolution data set. The process may include: obtaining a plurality of simulation data sets of simulated tunnel flow fires under different working conditions, each simulation data set including simulation parameters associated with the corresponding simulated tunnel flow fire, the simulation parameters including smoke temperature, smoke concentration, wind speed, image, flame drag length, flame inclination angle, wherein the working conditions are determined based on the leakage rate, ventilation rate, and tunnel slope of the fuel leaked from the leak port in the simulated tunnel flow fire; constructing a tunnel flow fire parameter evolution data set based on all simulation data sets.

[0049] For example, a corresponding scaled-down tunnel flowing fire test model can be constructed based on the geometric similarity criterion according to the tunnel structure of interest. The tunnel structure of interest can be the tunnel structure of the target tunnel. Figure 2The tunnel model shown has a leakage port set inside the tunnel for transferring liquid fuel to the tunnel subsurface for simulating the actual tunnel ground, and the leakage rate of the leakage port can be dynamically adjusted by a peristaltic pump; ventilation facilities are set at the tunnel entrance and exit for adjusting the ventilation rate of the tunnel model; a lifting device is arranged under the tunnel model for adjusting the transverse slope and longitudinal slope of the tunnel model; a temperature sensing array based on a temperature sensor such as a thermocouple, a smoke concentration sensing array based on a smoke concentration sensor, a wind speed measurement array based on a hot wire anemometer, and a heat flow measurement device such as a radiation heat flow meter are arranged inside the tunnel, and an infrared camera and a high-speed camera are arranged at the location of the tunnel flow fire leakage port. Subsequently, a peristaltic pump is used to pump the fuel into the leakage port, so that the liquid fuel flows on the tunnel subsurface, and an electric ignition device is used to ignite the fuel, and the flow combustion process of the liquid fuel in the tunnel after leakage is tested to obtain experimental data of flowing and burning at the same time. During the experiment, the temperature sensor array was used to record the smoke temperature of the tunnel ceiling during the burning process of the flowing fire; the smoke concentration sensor array was used to record the smoke concentration of the tunnel ceiling during the burning process of the flowing fire; the wind speed measurement array was used to record the wind speed inside the tunnel during the burning process of the flowing fire; the heat flux measurement device was used to record the thermal radiation data emitted by the fire plume and smoke during the burning process of the flowing fire; the infrared camera and the high-speed camera were used to record the images of the burning process of the flowing fire to obtain the flame drag length, flame tilt angle, and infrared image. After the experiment, the smoke temperature, smoke concentration, thermal radiation data, wind speed, image, flame drag length, and flame tilt angle obtained in the experiment were sorted in the same time sequence to form a simulation data set corresponding to the experimental conditions. Finally, the leakage rate, ventilation rate, tunnel slope of the underlying surface, and other influencing factors of the scaled tunnel flowing fire experimental model were adjusted, so that the above experiments were repeated under different conditions and the corresponding experimental data were recorded, and the simulation data sets under all conditions were combined to form a tunnel flowing fire parameter evolution data set.

[0050] This prediction method also proposes a dimensionless expression for the flame morphology of a flowing fire, and combines the tunnel flowing fire parameter evolution data set to construct a dimensionless expression of the flame morphology under different influencing factors. For example, based on the tunnel fire similarity theory, a dimensionless expression of the flame morphology that can reflect the flow combustion characteristics of a flowing fire can be constructed, which may include a target length relationship and a target angle relationship.

[0051] The target length relationship is determined based on the flame drag length, multiple second parameters, wind speed, gravity acceleration, burning area, leakage area, tunnel height, tunnel width, tunnel horizontal axis slope, and tunnel vertical axis slope, wherein the multiple second parameters are parameters related to the flame drag length determined based on the tunnel flow fire parameter evolution data set. For example, the target length expression can be expressed by the following formula 1:

[0052]

[0053] In formula (1), L represents the flame drag length, S represents the burning area of ​​the oil layer, a1, a2, a3, a4, a5, k1, and k2 represent the second parameters associated with the flame drag length (in this example, by substituting the simulated data sets of different working conditions into formula (1) in combination with the tunnel flow fire parameter evolution data set, these second parameters can be fitted to be 19.5, 0.08, 1, 0, 0, -0.516, and 0.33, respectively), V represents the wind speed in the tunnel, g represents the acceleration of gravity, and Q dis represents the leakage rate, H represents the tunnel height, W represents the tunnel width, s x represents the slope of the tunnel transverse axis, s y Indicates the slope of the tunnel longitudinal axis.

[0054] The target angle relationship is determined based on the flame tilt angle, multiple third parameters, wind speed, gravity acceleration, burning area, leakage area, tunnel height, tunnel width, tunnel horizontal axis slope, and tunnel vertical axis slope, wherein the multiple third parameters are parameters related to the flame tilt angle determined based on the tunnel flow fire parameter evolution data set. For example, the target angle relationship can be expressed by the following formula 2:

[0055]

[0056] In Formula 2, θ represents the flame inclination angle, b1, b2, b3, b4, b5, k3, and k4 represent the third parameters associated with the flame inclination angle (in this example, combined with the tunnel flow fire parameter evolution data set, by substituting the simulated data sets under different working conditions into Formula 2, these third parameters can be fitted to be 0.165, 0.04, -0.03, 0, 0, 1, and -0.67, respectively). The remaining parameters in Formula 2 are as mentioned above and will not be repeated here.

[0057] In this way, based on the target length relationship and the target angle relationship, the target flame drag length and the target flame inclination angle of the target flowing fire can be calculated.

[0058] Step S103: determining a target burning area of ​​a target flowing fire in a future time period based on a preset first set of equations representing a spreading burning process of a target oil layer and a target leakage rate in a second time period.

[0059] The target oil layer is formed by the fuel covering the target tunnel floor during the target flowing fire.

[0060] The first set of equations includes a set of partial differential equations determined according to the conservation of momentum in the spreading combustion process of the target oil layer, a set of partial differential equations determined according to the conservation of energy in the spreading combustion process, and a burning rate relationship constructed based on the tunnel flow fire parameter evolution data set.

[0061] For example, the partial differential equations determined according to the momentum conservation in the spreading combustion process of the target oil layer can be expressed by the following equation 3:

[0062]

[0063] In formula 3, u represents the flow velocity of the oil layer along the x direction, v represents the flow velocity of the oil layer along the y direction, t represents the leakage time, h represents the oil layer liquid level, D represents the thickness of the oil layer, the height difference between h and D is determined by the slope of the tunnel ground, and s fx represents the friction loss per unit length in the x direction, s fy represents the friction loss per unit length in the y direction, s fx and fy It can be calculated using the following formula 4:

[0064]

[0065] In Equation 4, f is the Darcy-Weisbach friction coefficient, which can be set as a constant in thin-layer liquid flow simulation. In this example, f can be set to 0.00001. The other parameters in Equation 4 are as mentioned above and will not be described here. x represents the component of wind stress in the x direction, τ y represents the component of wind stress in the y direction, τ x and τ y It can be calculated using the following formula 5:

[0066]

[0067] In formula 5, C D represents the wind drag coefficient. In this case, C D It can be set to 0.000044. The other parameters in Formula 5 are as mentioned above and will not be described here.

[0068] For example, the partial differential equation determined according to the energy conservation in the spreading combustion process can be expressed by the following equation 6:

[0069]

[0070] In formula 6, Q disrepresents the leakage rate, which can be obtained through the prediction rate model, and m represents the burning rate of the oil layer. The burning rate relationship can be determined according to the burning rate, multiple first parameters, wind speed, gravity acceleration, and burning area, wherein the multiple first parameters are parameters related to the burning rate determined according to the tunnel flow fire parameter evolution data set. For example, the burning rate relationship constructed based on the tunnel flow fire parameter evolution data set can be expressed by the following formula 7:

[0071]

[0072] In Formula 7, m represents the burning rate of the oil layer, c1, c2, and c3 represent the first parameters associated with the burning rate (in this example, by substituting the simulated data sets of different working conditions into Formula 7 in combination with the tunnel flow fire parameter evolution data set, these first parameters can be fitted to be 0.63, -2.37, and -0.09, respectively). The remaining parameters in Formula 7 are as mentioned above and will not be repeated here.

[0073] Subsequently, the spreading and burning process of the oil layer of the tunnel flowing fire under different environments can be solved based on the first set of equations. For the target flowing fire of interest, step S103 may include: using the finite difference method to solve the first set of equations, and based on the target leakage rate of the second time period and the preset initial conditions, calculating the target thickness distribution of the target oil layer at each time point in the future time period, the target thickness distribution at each time point is used to indicate the oil layer thickness of the target oil layer at each tunnel position at the corresponding time point, and each tunnel position is determined based on the target tunnel characteristics of the target tunnel; according to the number of tunnel positions where the oil layer thickness is not zero obtained based on the target thickness distribution at each time point, determine the target burning area of ​​the target flowing fire at the corresponding time point. Among them, the specific process of solving the first set of equations using the finite difference method can be expressed by the following equations 8 to 11:

[0074]

[0075] In formula 8, represents the flow velocity of the oil layer along the x direction at position i,j at time k+1, It represents the flow velocity of the oil layer along the x direction at position i, j at time k, Δt is the time step, Δx is the distance step in the x direction, and k is the sequence number of the time step. represents the oil layer level height at position i,j at time k, represents the oil layer level height at position i-1,j at time k, represents the flow velocity of the oil layer along the y direction at position i, j at time k, represents the thickness of the oil layer at position i,j at time k, represents the thickness of the oil layer at position i,j+1 at time k. The other parameters in formula 8 are as mentioned above and will not be repeated here. is the finite difference approximation of u((2i-1)Δx,2jΔy,kΔt), is the finite difference approximation of v(2iΔx,(2j-1)Δy,kΔt), is the finite difference approximation of h(2iΔx,2jΔy,kΔt), is the finite difference approximation of D((2i-1)Δx,(2j-1)Δy,kΔt), and the rest is similar. The computational domain and boundary conditions in the solution process are as follows Figure 3 As shown, the leakage rate Q at the leakage port dis Can be an input value Q input , the leakage rate Q at the burning liquid layer, i.e. the oil layer, and at the liquid-free layer dis The burning rate m at the place without liquid layer is 0, and the burning rate m at the leakage port and the burning liquid layer is the calculated value m cal , i, j are the grid numbers in the x and y directions to indicate the positions of each tunnel. The number of grid numbers M and N can be determined by the characteristics of the target tunnel. At the initial time step, u, v, h, D, and S are all set to 0. Equation 9 is as follows:

[0076]

[0077] In formula 9, represents the flow velocity of the oil layer along the y direction at position i, j at time k+1, represents the oil layer level height at position i,j-1 at time k, represents the thickness of the oil layer at position i+1,j at time k. The other parameters in formula 9 are as mentioned above and will not be repeated here. Formula 10 is as follows:

[0078]

[0079] In formula 10, represents the oil layer level height at position i,j at time k+1, represents the thickness of the oil layer at position i+1,j+1 at time k, represents the flow velocity of the oil layer along the x direction at position i+1,j at time k+1, represents the flow velocity of the oil layer along the y direction at position i,j+1 at time k+1, Q dis k represents the leakage rate at time k, m k represents the burning rate at time k, m k It can be calculated by the following formula 11:

[0080]

[0081] In formula 11, S k represents the target burning area at time k. The target burning area is obtained by counting the number of grids whose depth D of the oil layer is greater than 0 after the calculation of each time step. It should be noted that V in formula 11 can be the latest wind speed in the first time period, such as the wind speed at time t in the first time period 0 to t. The other parameters in formulas 10 and 11 are as mentioned above and will not be repeated here. In this way, the target thickness distribution of the target oil layer at each time point in the future time period can be obtained by solving, so as to determine the target burning area of ​​the target flowing fire in the future time period.

[0082] In this way, by constructing the first set of equations that conform to the conservation of momentum and energy, and combining it with the burning rate relationship constructed from the tunnel flowing fire parameter evolution data set, the spreading combustion process of the target oil layer in the tunnel can be simulated and predicted more accurately. Moreover, by solving the first set of equations using the finite difference method, the thickness distribution of the target oil layer at each tunnel location in the future time period can be accurately calculated, and then according to the number of tunnel locations where the oil layer thickness is not zero, the burning area of ​​the target flowing fire at the corresponding time point can be determined, thereby improving the accuracy and reliability of the prediction.

[0083] Step S104, based on the target tunnel characteristics, the target burning area and the target leakage rate in the future time period, the tunnel flowing fire parameter evolution data set, and the target wind speed in the first time period, predict the target flame drag length and the target flame inclination angle of the target flowing fire in the future time period, and use the target flame drag length and the target flame inclination angle in the future time period as the prediction result of the prediction task.

[0084] The target tunnel characteristics may include the gravitational acceleration at the location of the target tunnel, the height and width of the target tunnel, and the transverse axis slope and longitudinal axis slope of the target tunnel.

[0085] Step S104 may include: determining the future wind speed in the future time period based on the target wind speed in the first time period, such as taking the wind speed at time t in the first time period 0 to t as the future wind speed; obtaining a target length relationship constructed based on the tunnel flow fire parameter evolution data set, such as Formula 1 above, and calculating the target flame drag length at each time point in the future time period according to the target length relationship, the future wind speed, the target tunnel characteristics, and the target burning area at each time point in the future time period. Specifically, the target flame drag length may be calculated using Formula 12 below:

[0086]

[0087] In formula 12, L k represents the target flame drag length at time k, Sk represents the target burning area at time k, V in equation 12 is the future wind speed, Q dis k represents the leakage rate at time k, and the other parameters in equation 12 are as mentioned above and will not be repeated here. In addition, it should be noted that Indicates S k k1 operations, S k The k in represents the sequence number of the time step, and the other similar expressions are the same; and, obtain the target angle relationship constructed based on the tunnel flow fire parameter evolution data set, such as the above formula 2, and calculate the target flame tilt angle at each time point in the future time period according to the target length relationship, future wind speed, target tunnel characteristics, and target burning area at each time point in the future time period. Specifically, the target flame tilt angle can be calculated using the following formula 13:

[0088]

[0089] In formula 13, θ k Indicates the target flame inclination angle at time k, V in Formula 13 is the same as Formula 12, and the other parameters in Formula 13 are as mentioned above and will not be repeated here. In this way, the physical model of the flow combustion behavior of tunnel flowing fire shown in Formulas 12 and 13 above can obtain more accurate flame morphology evolution data over time, that is, the target flame drag length and target flame inclination angle in the future time period. This accurate prediction helps the handling personnel to more accurately understand the severity and spread trend of tunnel flowing fire, so as to make more scientific decisions and countermeasures. Figure 4 It can be seen from the comparison results of the target flame drag length and target flame inclination angle of the future time period obtained by the prediction method shown in the figure with the actual data that the future evolution trend of the flame morphology of the tunnel flowing fire calculated by the prediction method of the flow combustion behavior of the tunnel flowing fire provided by the embodiment of the present disclosure is more realistic.

[0090] The disclosed embodiment also provides a prediction device for the flow combustion behavior of a tunnel flowing fire, including: an acquisition module, used to acquire a prediction task for a target flowing fire occurring in a target tunnel, determine the target tunnel characteristics of the target tunnel and the target parameters associated with the target flowing fire in a first time period after the occurrence of the target flowing fire, the target parameters including target wind speed, target image, target smoke temperature, and target smoke concentration; a calculation module, used to input the target parameters into a rate prediction model for calculation, and obtain a target leakage rate of the fuel leaked from the leakage port in the target flowing fire in a second time period, wherein the rate prediction model is trained based on a preset tunnel flowing fire parameter evolution data set, and the second time period includes the first time period; a determination module, used to predict the target fire based on the prediction. Assume a first set of equations representing the spreading combustion process of the target oil layer and a target leakage rate in the second time period, determine the target combustion area of ​​the target flowing fire in the future time period, wherein the target oil layer is formed by the fuel covering the target tunnel ground in the target flowing fire, and the future time period belongs to the second time period and is after the first time period; a prediction module is used to predict the target flame drag length and target flame inclination angle of the target flowing fire in the future time period based on the target tunnel characteristics, the target combustion area and target leakage rate in the future time period, the tunnel flowing fire parameter evolution data set, and the target wind speed in the first time period, and use the target flame drag length and the target flame inclination angle in the future time period as the prediction result of the prediction task.

[0091] In a possible implementation, the first set of equations includes a set of partial differential equations determined according to the conservation of momentum satisfied by the spreading combustion process of the target oil layer, a partial differential equation determined according to the conservation of energy satisfied by the spreading combustion process, and a burning rate relationship constructed based on the tunnel flowing fire parameter evolution data set; wherein, based on the preset first set of equations representing the spreading combustion process of the target oil layer and the target leakage rate of the second time period, determining the target burning area of ​​the target flowing fire in the future time period includes: solving the first set of equations using a finite difference method, and calculating the target thickness distribution of the target oil layer at each time point in the future time period based on the target leakage rate of the second time period and preset initial conditions, the target thickness distribution of each time point is used to indicate the oil layer thickness of the target oil layer at each tunnel position at the corresponding time point, and each tunnel position is determined based on the target tunnel characteristics of the target tunnel; determining the target burning area of ​​the target flowing fire at the corresponding time point according to the number of tunnel positions where the oil layer thickness is not zero obtained based on the target thickness distribution of each time point.

[0092] In one possible implementation, the burning rate relationship is determined based on the burning rate, multiple first parameters, wind speed, gravitational acceleration, and burning area, wherein the multiple first parameters are parameters related to the burning rate determined based on the tunnel flow fire parameter evolution data set.

[0093] In a possible implementation, based on the target tunnel characteristics, the target burning area and the target leakage rate in the future time period, the tunnel flowing fire parameter evolution data set, and the target wind speed in the first time period, the target flame drag length and the target flame inclination angle of the target flowing fire in the future time period are predicted, including: determining the future wind speed in the future time period based on the target wind speed in the first time period; obtaining a target length relationship constructed based on the tunnel flowing fire parameter evolution data set, and calculating the target flame drag length at each time point in the future time period according to the target length relationship, the future wind speed, the target tunnel characteristics, and the target burning area at each time point in the future time period; and obtaining a target angle relationship constructed based on the tunnel flowing fire parameter evolution data set, and calculating the target flame inclination angle at each time point in the future time period according to the target length relationship, the future wind speed, the target tunnel characteristics, and the target burning area at each time point in the future time period; wherein the target tunnel characteristics include the gravitational acceleration of the target tunnel location, the height and width of the target tunnel, and the horizontal axis slope and the vertical axis slope of the target tunnel.

[0094] In one possible implementation, the target length relationship is determined based on the flame drag length, multiple second parameters, wind speed, gravitational acceleration, burning area, leakage area, tunnel height, tunnel width, tunnel horizontal axis slope, and tunnel longitudinal axis slope, wherein the multiple second parameters are parameters related to the flame drag length determined based on the tunnel flow fire parameter evolution data set.

[0095] In one possible implementation, the target angle relationship is determined based on the flame inclination angle, multiple third parameters, wind speed, gravitational acceleration, burning area, leakage area, tunnel height, tunnel width, tunnel horizontal axis slope, and tunnel longitudinal axis slope, wherein the multiple third parameters are parameters related to the flame inclination angle determined based on the tunnel flow fire parameter evolution data set.

[0096] In a possible implementation, the device also includes a construction module, which is used to: obtain simulation data groups of simulated tunnel flowing fires under multiple different working conditions, each of the simulation data groups includes simulation parameters associated with the corresponding simulated tunnel flowing fire, and the simulation parameters include smoke temperature, smoke concentration, wind speed, image, flame drag length, and flame inclination angle, wherein the working condition is determined based on the leakage rate of the fuel leaked from the leakage port in the simulated tunnel flowing fire, the ventilation rate, and the tunnel slope; and construct a tunnel flowing fire parameter evolution data set based on all simulation data groups.

[0097] In some embodiments, the functions or modules included in the device provided by the embodiments of the present disclosure can be used to execute the method described in the above method embodiments. The specific implementation can refer to the description of the above method embodiments, and for the sake of brevity, it will not be repeated here.

[0098] The embodiment of the present disclosure also provides a computer-readable storage medium on which computer program instructions are stored, and the computer program instructions implement the above method when executed by a processor. The computer-readable storage medium can be a volatile or non-volatile computer-readable storage medium.

[0099] An embodiment of the present disclosure further proposes an electronic device, comprising: a processor; and a memory for storing instructions executable by the processor; wherein the processor is configured to implement the above method when executing the instructions stored in the memory.

[0100] The embodiments of the present disclosure also provide a computer program product, including a computer-readable code, or a non-volatile computer-readable storage medium carrying the computer-readable code. When the computer-readable code runs in a processor of an electronic device, the processor in the electronic device executes the above method.

[0101] Figure 5 A block diagram of a device for predicting the flow combustion behavior of a tunnel flowing fire provided according to an embodiment of the present disclosure is shown. For example, the device 1900 may be provided as a server or a terminal device. Figure 5 , the apparatus 1900 includes a processing component 1922, which further includes one or more processors, and a memory resource represented by a memory 1932 for storing instructions, such as an application, that can be executed by the processing component 1922. The application stored in the memory 1932 may include one or more modules, each corresponding to a set of instructions. In addition, the processing component 1922 is configured to execute instructions to perform the above method.

[0102] The device 1900 may also include a power supply component 1926 configured to perform power management of the device 1900, a wired or wireless network interface 1950 configured to connect the device 1900 to a network, and an input / output interface 1958 (I / O interface). The device 1900 may operate based on an operating system stored in the memory 1932, such as Windows Server 2000. TM , MacOS X TM , Unix TM ,Linux TM , FreeBSD TM or similar.

[0103] In an exemplary embodiment, a non-volatile computer-readable storage medium is also provided, such as a memory 1932 including computer program instructions, which can be executed by the processing component 1922 of the device 1900 to perform the above method.

[0104] The present disclosure may be a system, a method and / or a computer program product. The computer program product may include a computer-readable storage medium carrying computer-readable program instructions for causing a processor to implement various aspects of the present disclosure.

[0105] A computer-readable storage medium may be a tangible device that can hold and store instructions used by an instruction execution device. A computer-readable storage medium may be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples of computer-readable storage media (a non-exhaustive list) include: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disk read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanical encoding device, such as a punch card or a raised structure in a groove on which instructions are stored, and any suitable combination of the foregoing. As used herein, a computer-readable storage medium is not to be interpreted as a transient signal per se, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagating through a waveguide or other transmission medium (e.g., a light pulse through a fiber optic cable), or an electrical signal transmitted through a wire.

[0106] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to each computing / processing device, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network can include copper transmission cables, optical fiber transmissions, wireless transmissions, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in the computer-readable storage medium in each computing / processing device.

[0107] The computer program instructions for performing the operation of the present disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages, such as Smalltalk, C++, etc., and conventional procedural programming languages, such as "C" language or similar programming languages. Computer-readable program instructions may be executed completely on a user's computer, partially on a user's computer, as an independent software package, partially on a user's computer, partially on a remote computer, or completely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., using an Internet service provider to connect via the Internet). In some embodiments, an electronic circuit, such as a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA), may be customized by utilizing the state information of the computer-readable program instructions, and the electronic circuit may execute the computer-readable program instructions, thereby realizing various aspects of the present disclosure.

[0108] Various aspects of the present disclosure are described herein with reference to the flowcharts and / or block diagrams of the methods, devices (systems) and computer program products according to the embodiments of the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer-readable program instructions.

[0109] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine, so that when these instructions are executed by the processor of the computer or other programmable data processing device, a device that implements the functions / actions specified in one or more boxes in the flowchart and / or block diagram is generated. These computer-readable program instructions can also be stored in a computer-readable storage medium, and these instructions cause the computer, programmable data processing device, and / or other equipment to work in a specific manner, so that the computer-readable medium storing the instructions includes a manufactured product, which includes instructions for implementing various aspects of the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0110] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operating steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0111] The flow chart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to multiple embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a part of a module, program segment or instruction, and a part of the module, program segment or instruction includes one or more executable instructions for realizing the specified logical function. In some alternative implementations, the function marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two continuous square boxes can actually be executed substantially in parallel, and they can sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs the specified function or action, or can be implemented with a combination of special hardware and computer instructions.

[0112] The embodiments of the present disclosure have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and changes will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The selection of terms used herein is intended to best explain the principles of the embodiments, practical applications, or technical improvements in the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. A method for predicting the flow combustion behavior of a tunnel flow fire, characterized in that: include: Acquire a prediction task for a target flowing fire occurring in a target tunnel, determine a target tunnel feature of the target tunnel and a target parameter associated with the target flowing fire in a first time period after the target flowing fire occurs, the target parameter including a target wind speed, a target image, a target smoke temperature, and a target smoke concentration; Inputting the target parameters into a rate prediction model for calculation, and obtaining a target leakage rate of the fuel leaked from the leakage port in the target flowing fire in a second time period, wherein the rate prediction model is trained based on a preset tunnel flowing fire parameter evolution data set, and the second time period includes the first time period; Determine a target combustion area of ​​the target flowing fire in a future time period based on a preset first set of equations representing a spreading combustion process of a target oil layer and a target leakage rate in the second time period, wherein the target oil layer is formed by fuel covering the ground of the target tunnel in the target flowing fire, and the future time period belongs to the second time period and is after the first time period; Based on the target tunnel characteristics, the target burning area and the target leakage rate in the future time period, the tunnel flowing fire parameter evolution data set, and the target wind speed in the first time period, the target flame drag length and the target flame inclination angle of the target flowing fire in the future time period are predicted, and the target flame drag length and the target flame inclination angle of the future time period are used as the prediction results of the prediction task.

2. The method according to claim 1, characterized in that The first set of equations includes a set of partial differential equations determined according to the conservation of momentum that the spreading combustion process of the target oil layer complies with, a partial differential equation determined according to the conservation of energy that the spreading combustion process complies with, and a burning rate relationship constructed based on the tunnel flowing fire parameter evolution data set; wherein, based on the preset first set of equations representing the spreading combustion process of the target oil layer and the target leakage rate of the second time period, the target burning area of ​​the target flowing fire in the future time period is determined, including: The first set of equations is solved by using a finite difference method, and a target thickness distribution of the target oil layer at each time point in the future time period is calculated based on a target leakage rate in the second time period and a preset initial condition, wherein the target thickness distribution at each time point is used to indicate the oil layer thickness of the target oil layer at each tunnel position at the corresponding time point, and each tunnel position is determined based on a target tunnel feature of the target tunnel; According to the number of tunnel positions where the oil layer thickness is not zero obtained based on the target thickness distribution at each of the time points, the target burning area of ​​the target flowing fire at the corresponding time point is determined.

3. The method according to claim 2, characterized in that The burning rate relationship is determined based on the burning rate, multiple first parameters, wind speed, gravitational acceleration, and burning area, wherein the multiple first parameters are parameters related to the burning rate determined based on the tunnel flow fire parameter evolution data set.

4. The method according to claim 1, characterized in that Based on the target tunnel characteristics, the target burning area and the target leakage rate in the future time period, the tunnel flowing fire parameter evolution data set, and the target wind speed in the first time period, a target flame drag length and a target flame inclination angle of the target flowing fire in the future time period are predicted, including: Determining a future wind speed in a future time period based on the target wind speed in the first time period; Obtaining a target length relationship constructed based on the tunnel flow fire parameter evolution data set, and calculating a target flame drag length at each time point in the future time period according to the target length relationship, the future wind speed, the target tunnel characteristics, and the target burning area at each time point in the future time period; and Obtaining a target angle relational expression constructed based on the tunnel flow fire parameter evolution data set, and calculating a target flame inclination angle at each time point in the future time period according to the target length relational expression, the future wind speed, the target tunnel characteristics, and the target burning area at each time point in the future time period; The target tunnel characteristics include the gravitational acceleration of the target tunnel location, the height and width of the target tunnel, and the horizontal axis slope and the vertical axis slope of the target tunnel.

5. The method according to claim 4, characterized in that The target length relationship is determined based on the flame drag length, multiple second parameters, wind speed, gravitational acceleration, burning area, leakage area, tunnel height, tunnel width, tunnel horizontal axis slope, and tunnel longitudinal axis slope, wherein the multiple second parameters are parameters related to the flame drag length determined based on the tunnel flow fire parameter evolution data set.

6. The method according to claim 4, characterized in that The target angle relationship is determined based on the flame inclination angle, multiple third parameters, wind speed, gravitational acceleration, burning area, leakage area, tunnel height, tunnel width, tunnel horizontal axis slope, and tunnel longitudinal axis slope, wherein the multiple third parameters are parameters related to the flame inclination angle determined based on the tunnel flow fire parameter evolution data set.

7. The method according to any one of claims 1 to 6, characterized in that The method further comprises: Acquire a plurality of simulation data groups of simulated tunnel flowing fire under different working conditions, each of the simulation data groups includes simulation parameters associated with the corresponding simulated tunnel flowing fire, the simulation parameters include smoke temperature, smoke concentration, wind speed, image, flame drag length, flame inclination angle, wherein the working conditions are determined based on the leakage rate of the fuel leaked from the leakage port in the simulated tunnel flowing fire, the ventilation rate, and the tunnel slope; A tunnel flow fire parameter evolution dataset was constructed based on all simulation data sets.

8. A device for predicting the flow combustion behavior of a tunnel fire, characterized in that: include: An acquisition module is used to acquire a prediction task for a target flowing fire occurring in a target tunnel, determine a target tunnel feature of the target tunnel and a target parameter associated with the target flowing fire in a first time period after the target flowing fire occurs, wherein the target parameter includes a target wind speed, a target image, a target smoke temperature, and a target smoke concentration; a calculation module, configured to input the target parameter into a rate prediction model for calculation, and obtain a target leakage rate of the fuel leaked from the leakage port in the target flowing fire in a second time period, wherein the rate prediction model is trained based on a preset tunnel flowing fire parameter evolution data set, and the second time period includes the first time period; A determination module, configured to determine a target combustion area of ​​the target flowing fire in a future time period based on a preset first set of equations representing a spreading combustion process of a target oil layer and a target leakage rate in the second time period, wherein the target oil layer is formed by fuel covering the ground of the target tunnel in the target flowing fire, and the future time period belongs to the second time period and is after the first time period; A prediction module is used to predict the target flame drag length and target flame inclination angle of the target flowing fire in the future time period based on the target tunnel characteristics, the target burning area and target leakage rate in the future time period, the tunnel flowing fire parameter evolution data set, and the target wind speed in the first time period, and use the target flame drag length and target flame inclination angle in the future time period as the prediction result of the prediction task.

9. An electronic device, characterized in that: include: processor; a memory for storing processor-executable instructions; The processor is configured to implement the method described in any one of claims 1 to 7 when executing the instructions stored in the memory.

10. A non-volatile computer-readable storage medium having computer program instructions stored thereon, characterized in that: When the computer program instructions are executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images