A highway tunnel fire positioning correction method, device and equipment

Abstract

The present application relates to the technical field of tunnel fire prediction, and discloses a highway tunnel fire positioning correction method, device and equipment, which comprises the following steps: obtaining the longitudinal wind speed in the current tunnel, the current fire heat release rate and the current fire source detection position; inputting the longitudinal wind speed in the current tunnel and the current fire heat release rate into the constructed estimated offset distance model to obtain the estimated offset distance; correcting the current fire source detection position according to the estimated offset distance to obtain the fire correction position. The present application provides the estimated offset distance model, actively predicts the theoretical estimated offset distance of the fire source under the specific wind speed and the fire source release power, and dynamically and intelligently reversely corrects the initial detection position, so that the original fire positioning is improved from static perception to dynamic prediction and correction, the positioning accuracy of the real position of the fire source is significantly improved, and the reliability and repeatability of the correction are greatly improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of tunnel fire prediction, in particular to a highway tunnel fire positioning correction method, device and equipment. BACKGROUND

[0002] Fire is one of the important hazards faced by tunnels. Due to the particularity of the tunnel structure, when a fire occurs in the tunnel, the burning spreads quickly and the smoke is not easy to diffuse, making it difficult for personnel to evacuate and for fire detection and fire fighting, which will cause significant casualties and economic losses, and has great danger and destructiveness. At present, the tunnel fire detection mainly uses temperature detectors to calculate the scale and location of the tunnel fire by monitoring the temperature value of the tunnel vault. However, in addition to natural wind, tunnel often needs to start the fan to meet its own ventilation needs, and the longitudinal wind in the tunnel will change the heat convection and smoke distribution in the tunnel, slowing down the temperature rise directly above the ignition point when a fire occurs, and increasing the temperature downstream of the ignition point, thereby affecting the temperature positioning error of the fire detector. At the same time, with the progress of highway tunnel construction technology, more and more three-lane large-section highway tunnels are put into operation. When a fire occurs in different lanes, in addition to the different horizontal positions of the fire source, due to the arch-shaped structure characteristics of the tunnel section, the distance between the fire source and the vault is also different, and the influence on the temperature detector of the tunnel vault is also quite different. Therefore, it is of great significance to consider the ventilation conditions in the tunnel and the lane where the fire occurs to correct the temperature positioning error of the fire in the tunnel and achieve rapid positioning of the fire source in the tunnel.

[0003] Tunnel fire is a common serious safety hazard in modern transportation infrastructure, and rapid detection and positioning of the fire is of great significance for fire fighting, personnel evacuation and safety protection. In CN117131451A, a multi-space environment fire source positioning method and system based on AttentionLSTM are disclosed, which realizes fire source positioning by temperature detection, but the position of the highest temperature recognized by the detection system usually deviates from the actual position of the fire source. This deviation is called fire source detection estimation offset distance, which is one of the technical problems that need to be solved in fire detection systems. In actual engineering, a distributed optical fiber temperature measurement system can provide temperature data distribution of the whole tunnel, but how to accurately calculate the position of the fire source from these temperature data, especially to correct the fire source detection estimation offset distance, still lacks a fast and effective correction method. SUMMARY

[0004] In order to overcome the problems of fire temperature positioning error and lack of correction of fire source position in existing tunnel fire positioning, the present application provides a highway tunnel fire positioning correction method, device and equipment.

[0005] In a first aspect, the present application provides a highway tunnel fire positioning correction method, comprising:

[0006] obtaining a current tunnel longitudinal wind speed, a current fire heat release rate and a current fire source detection position;

[0007] inputting the current tunnel longitudinal wind speed and the current fire heat release rate into a constructed estimated offset distance model to obtain an estimated offset distance;

[0008] correcting the current fire source detection position according to the estimated offset distance to obtain a fire correction position;

[0009] wherein the construction process of the estimated offset distance model comprises:

[0010] constructing a relationship curve according to historical tunnel longitudinal wind speeds, historical fire heat release rates and corresponding historical estimated offset distances;

[0011] performing polynomial fitting on the relationship curve to obtain offset coefficients and complete the construction.

[0012] According to a specific embodiment, in the above correction method, the calculation formula of the estimated offset distance model is:

[0013] D1=X1μ+X2Q+X3μ 2 +X4μQ-X5Q 2 ,

[0014] wherein D1 is the estimated offset distance, X1-X5 are offset coefficients, μ is the current tunnel longitudinal wind speed, and Q is the current fire heat release rate.

[0015] According to a specific embodiment, in the above correction method, the polynomial fitting is performed by linear regression, polynomial regression or support vector regression, and the offset coefficients are determined by selecting the result with the highest fitting accuracy.

[0016] According to a specific embodiment, in the above correction method, the current fire heat release rate is calculated according to the height of the fire source from the tunnel vault and the maximum temperature rise of the tunnel vault, specifically comprising:

[0017] calculating the height of the fire source from the tunnel vault according to the height of the fire source vehicle and the lane where it is located, combined with the tunnel net height;

[0018] calculating the current fire heat release rate combined with the maximum temperature rise of the tunnel vault.

[0019] According to a specific embodiment, in the above correction method, based on the case that the tunnel is a two-lane tunnel or the fire source vehicle is located in the middle of a three-lane tunnel, the calculation formula of the height of the fire source from the tunnel vault is H f=H t -H c ; when the fire source vehicle is located at the two side lanes of the three-lane tunnel, the calculation formula of the height of the fire source from the tunnel vault is H f = ; wherein H f is the height of the fire source from the tunnel vault, H t is the net height of the tunnel, and H c is the height of the fire source vehicle.

[0020] According to a specific embodiment, in the above-mentioned correction method, the calculation formula of the current fire source heat release rate is:

[0021]

[0022] wherein Q is the current fire source heat release rate, and △T max is the maximum temperature rise of the tunnel vault.

[0023] According to a specific embodiment, in the above-mentioned correction method, the current fire source detection position is the position with the highest vault temperature when the tunnel catches fire.

[0024] In a second aspect, the present application provides a highway tunnel fire positioning correction device, comprising:

[0025] a temperature sensing module for collecting the temperature of the tunnel vault;

[0026] a wind speed detection module for collecting the longitudinal wind speed in the tunnel;

[0027] a central processing module for obtaining the temperature of the tunnel vault and the longitudinal wind speed in the tunnel, and obtaining the fire correction position by using any one of the above-mentioned highway tunnel fire positioning correction methods.

[0028] According to a specific embodiment, in the above-mentioned correction device, the temperature sensing module adopts a distributed optical fiber temperature sensor or an infrared thermal imager and is arranged along the tunnel vault; the wind speed detection module adopts an ultrasonic anemometer or a hot wire anemometer and is arranged at the tunnel entrance or exit.

[0029] In a third aspect, the present application provides an electronic device comprising at least one processor and a memory connected in communication with the at least one processor; the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute any one of the above-mentioned highway tunnel fire positioning correction methods.

[0030] Compared with the prior art, the present application has the following beneficial effects:

[0031] The present application actively predicts the theoretical estimated offset distance of the fire source under a specific wind speed and a fire source release power, and dynamically and intelligently reversely corrects the initial detection position, so that the original fire positioning is improved from static sensing to dynamic prediction and correction, the positioning accuracy of the real position of the fire source is significantly improved, and the reliability and repeatability of the correction are greatly improved. BRIEF DESCRIPTION OF DRAWINGS

[0032] Figure 1 A flowchart of a highway tunnel fire positioning correction method provided by an embodiment of the present application is shown.

[0033] Figure 2 A fitting result diagram provided by an embodiment of the present application is shown. DETAILED DESCRIPTION

[0034] The present application will be further described in detail below in combination with specific embodiments. However, it should not be understood that the scope of the above-mentioned subject matter of the present application is limited to the following embodiments only, and any technology realized based on the content of the present application belongs to the scope of the present application.

[0035] Traditional tunnel fire positioning (such as determining the highest temperature point by a temperature sensing optical fiber) will cause serious errors due to strong “fire wind pressure effect” and longitudinal ventilation. Smoke and hot smoke gas will drift downstream under the action of wind speed, causing the detected “temperature highest point” to be not the real fire source position, misleading the rescue force and delaying the fire extinguishing opportunity. The smoke offset is more qualitative knowledge or relies on rough empirical estimation, and lacks accurate and reliable calculation methods. Moreover, after discovering the fire, the fire point needs to be judged or roughly estimated manually, the response is slow and prone to error, and the experience of a specific tunnel is difficult to be directly applied to other tunnels.

[0036] The present application is based on historical data fitting, and by constructing a mathematical model based on the two key physical quantities of “longitudinal wind speed” and “heat release rate”, the complex fluid mechanics and heat transfer problems are converted into an engineering problem that can be calculated in real time. For different tunnels (such as different slopes and cross-sectional shapes), only the experimental or simulation data of the tunnel need to be retrained to quickly apply the model. This makes the fire positioning correction no longer an isolated method, but a generalizable technical platform, a data-driven and quantifiable scientific decision-making process, which lays a foundation for deployment in different types of tunnels.

[0037] The highway tunnel fire positioning correction provided by the present application will be described in detail below in combination with specific embodiments.

[0038] Specifically, the present application provides a highway tunnel fire positioning correction device, comprising:

[0039] A temperature sensing module is arranged along the tunnel vault for collecting the temperature of the tunnel vault. The temperature sensing module can be a distributed optical fiber temperature sensor or an infrared thermal imager.

[0040] A wind speed detection module is arranged at the entrance or exit of the tunnel for collecting the longitudinal wind speed in the tunnel. The wind speed detection module can be an ultrasonic anemometer or a hot-wire anemometer. In one possible implementation, the wind speed detection module can also directly collect the longitudinal wind speed by using the fan in the tunnel.

[0041] A central processing module is configured to obtain the temperature of the tunnel vault and the longitudinal wind speed in the tunnel, and to obtain the corrected fire location by using a highway tunnel fire positioning correction method provided by an embodiment of the present application.

[0042] For example, the central processing module can be a central processing unit (CPU) or a microcontroller (MCU).

[0043] The central processing module can further include a hardware chip. The hardware chip can be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The PLD can be a complex programmable logic device (CPLD), a field-programmable gate array (FPGA), a generic array logic (GAL), or any combination thereof.

[0044] The central processing module can further include a memory for storing the temperature and wind speed information and programs. The memory can include a volatile memory such as a random-access memory (RAM), a non-volatile memory such as a flash memory, a hard disk drive (HDD), or a solid-state drive (SSD), or a combination of the above.

[0045] Specifically, refer to Figure 1 which shows a flowchart of a highway tunnel fire positioning correction method provided by an embodiment of the present application, including:

[0046] Step 1: Obtain the current longitudinal wind speed in the tunnel, the current heat release rate of the fire source, and the current detection position of the fire source.

[0047] It can be understood that the current longitudinal wind speed in the tunnel can be directly obtained through a wind speed detection model in the tunnel or the opening condition of the fan. The current heat release rate of the fire source is calculated according to the height of the fire source from the tunnel vault and the maximum temperature rise of the tunnel vault, and specifically includes:

[0048] The height of the fire source from the tunnel vault is calculated according to the height of the fire source vehicle and the lane where the fire source vehicle is located, in combination with the net height of the tunnel.

[0049] The current heat release rate of the fire source is calculated in combination with the maximum temperature rise of the tunnel vault.

[0050] Wherein, based on the case that the tunnel is two-lane or the fire source vehicle is located in the middle of the three-lane tunnel, the calculation formula of the height of the fire source from the tunnel vault is H f =H t -H c ; based on the case that the fire source vehicle is located in the two-lane of the three-lane tunnel, the calculation formula of the height of the fire source from the tunnel vault is H f = ; wherein, H f is the height of the fire source from the tunnel vault, H t is the net height of the tunnel, and H c is the height of the fire source vehicle.

[0051] Further, the calculation formula of the current heat release rate of the fire source is:

[0052]

[0053] Wherein, Q is the current heat release rate of the fire source, and ΔT max is the maximum temperature rise of the tunnel vault.

[0054] It should be noted that the maximum temperature rise of the tunnel vault is obtained based on the empirical formula of the predicted vault maximum temperature. The predicted vault maximum temperature is of great significance to tunnel fire prevention design and disaster rescue work. According to the research results of many scholars at home and abroad on the vault maximum temperature, it is concluded that the empirical formula of the maximum temperature rise of the vault under natural ventilation conditions is ΔT max Q *2 / 3 / H f 5 / 3 changes linearly, that is:

[0055] ,

[0056] Wherein, the coefficient k can be obtained by linear fitting through model test and numerical simulation. Generally, 13.75 can be taken.

[0057] Step 2: input the current longitudinal wind speed in the tunnel and the current heat release rate of the fire source into the constructed estimation offset distance model to obtain the estimation offset distance.

[0058] Specifically, the construction process of the estimation offset distance model comprises:

[0059] constructing a relationship curve according to the historical longitudinal wind speed in the tunnel, the historical heat release rate of the fire source and the corresponding historical estimation offset distance;

[0060] performing polynomial fitting on the relationship curve to obtain offset coefficients and complete the construction.

[0061] In a possible implementation, the calculation formula of the estimation offset distance model provided by the embodiment of the present application is:

[0062] D1=X1μ+X2Q+X3μ 2 +X4μQ-X5Q 2 ,

[0063] Wherein, D1 is the estimation offset distance, X1-X5 is the offset coefficient, μ is the current longitudinal wind speed in the tunnel, and Q is the current heat release rate of the fire source.

[0064] Further, the polynomial fitting adopts linear regression, polynomial regression and support vector regression for fitting, and the result with the highest fitting accuracy is selected to determine the offset coefficient.

[0065] Step 3: correct the current fire source detection position according to the estimation offset distance to obtain a fire correction position.

[0066] Specifically, the current fire source detection position is the position with the highest vault temperature when the tunnel catches fire, which can be obtained by a temperature sensing module. The calculation formula of the fire correction position is:

[0067] Y0=Y1-D1,

[0068] Wherein, Y0 is the fire correction position, Y1 is the fire source detection position, and D1 is the estimation offset distance.

[0069] In a possible implementation, the embodiment of the present application provides specific steps of the polynomial fitting. It can be understood that in a tunnel fire, the predicted offset distance D for fire source detection is mainly affected by inertial force and buoyancy. The inertial force is driven by the wind speed μ and drags the fire source along the airflow direction. The buoyancy is generated by the heat release rate Q of the fire source, and the hot smoke of the fire source has upward buoyancy due to the decrease in density, forming a plume. In the limited tunnel vault, the buoyancy is converted into a force that spreads to both sides, but under the action of the longitudinal wind, the spread to the upstream is inhibited, and mainly extends to the downstream. Thus, a binary function of the predicted offset distance D for fire source detection and the longitudinal wind speed μ and the heat release rate Q of the fire source can be constructed, that is, D=f(μ,Q).

[0070] Based on this, according to a large number of historical longitudinal wind speeds in tunnels, historical heat release rates of fire sources and corresponding historical predicted offset distances, original data covering all possible working conditions can be obtained and plotted as a scatter plot. For example, the scatter plot can be plotted in a three-dimensional space, or a series of two-dimensional curves can be plotted by fixing a variable (for example, taking μ as the horizontal coordinate, D as the vertical coordinate, and Q as the parameter). By observing the distribution of these data points, it can be found that the relationship between D and μ and Q is nonlinear. Moreover, there is a coupling effect between μ and Q (that is, the influence of the wind speed on the offset distance changes with the change of the heat release rate of the fire source).

[0071] In order to capture this nonlinear relationship and coupling effect, a multivariate quadratic polynomial is selected as the basic structure of the predicted offset distance model, and its general form is:

[0072] D=X1*μ+X2*Q+X3*μ²+X4*μ*Q+X5*Q²+...,

[0073] wherein the linear term X1*μ represents the dominant effect of the wind speed, the linear term X2*Q represents the basic influence of the heat release rate of the fire source, the nonlinear term X3*μ² reflects the saturation or enhancement effect of the wind speed, and the coupling term X4*μ*Q describes the interaction between the wind speed and the heat release rate of the fire source. For example, under a large wind speed, the smoke generated by a large-power fire source may drift farther than that generated by a small-power fire source.

[0074] The nonlinear term X5*Q² is usually negative, reflecting that as the heat release rate of the fire source increases, the strong buoyancy of the smoke plume will partially resist the drag of the longitudinal wind, slowing down the growth trend of the predicted offset distance, and even saturating. The negative sign here is negative after fitting, so it is directly written as “-” in the formula to clearly indicate its physical meaning.

[0075] Further, linear regression, polynomial regression, support vector regression (linear kernel and RBF kernel) and other polynomial fitting methods are used to fit the offset coefficients X1 to X5, and the result with the highest fitting accuracy is selected to determine the offset coefficients.

[0076] In one possible implementation, the fitting process of this embodiment of the invention is as follows:

[0077] import pandas as pd

[0078] import numpy as np

[0079] import matplotlib.pyplot as plt

[0080] from sklearn.model_selection import train_test_split

[0081] from sklearn.preprocessing import StandardScaler, PolynomialFeatures

[0082] from sklearn.linear_model import LinearRegression

[0083] from sklearn.svm import SVR

[0084] from sklearn.metrics import r2_score, mean_squared_error

[0085] # 1. Load data from Excel (assuming column names: offset_distance, fire_intensity, wind_speed, HRR)

[0086] file_path = "data.xlsx" # Replace with your Excel file path

[0087] data = pd.read_excel(file_path)

[0088] # Extract the independent and dependent variables (modify according to the actual column names)

[0089] X = data[["Fire Intensity Coefficient", "Wind Speed", "HRR"]].values ​​# Independent variables: Fire Intensity Coefficient, Wind Speed, HRR

[0090] y = data["Estimated Offset Distance"].values ​​# Dependent variable: Estimated offset distance

[0091] # 2. Data Standardization (important for SVR and Polynomial Regression)

[0092] scaler = StandardScaler()

[0093] X_scaled = scaler.fit_transform(X)

[0094] X_train, X_test, y_train, y_test = train_test_split(X_scaled, y,test_size=0.2, random_state=42)

[0095] # 3. Multiple Linear Regression

[0096] lr = LinearRegression()

[0097] lr.fit(X_train, y_train)

[0098] y_pred_lr = lr.predict(X_test)

[0099] print("=== Linear Regression ===")

[0100] print(f"Formula: offset_distance = {lr.intercept_:.3f} + {lr.coef_[0]:.3f}*fire_intensity + {lr.coef_[1]:.3f}*wind_speed + {lr.coef_[2]:.3f}*HRR")

[0101] print(f"R²: {r2_score(y_test, y_pred_lr):.3f}, MSE: {mean_squared_error(y_test, y_pred_lr):.3f}\n")

[0102] # 4. Polynomial Regression (quadratic terms + interaction terms)

[0103] poly = PolynomialFeatures(degree=2, include_bias=False)

[0104] X_poly_train = poly.fit_transform(X_train)

[0105] X_poly_test = poly.transform(X_test)

[0106] lr_poly = LinearRegression()

[0107] lr_poly.fit(X_poly_train, y_train)

[0108] y_pred_poly = lr_poly.predict(X_poly_test)

[0109] print("=== Multinomial Regression===")

[0110] print("Feature order (corresponding coefficients):", poly.get_feature_names_out(["fire", "wind", "HRR"]))# Displays the actual variable names

[0111] print("Coefficient value:", [f"{coef:.3f}" for coef in lr_poly.coef_])

[0112] print(f"R²: {r2_score(y_test, y_pred_poly):.3f}, MSE: {mean_squared_error(y_test, y_pred_poly):.3f}\n")

[0113] # 5. Support Vector Regression (Linear Kernel)

[0114] svr_linear = SVR(kernel='linear', C=1.0, epsilon=0.1)

[0115] svr_linear.fit(X_train, y_train)

[0116] y_pred_svr_linear = svr_linear.predict(X_test)

[0117] print("=== Linear Kernel SVR ===")

[0118] print(f"Formula: offset_distance = {svr_linear.coef_[0][0]:.3f}*fire_intensity + {svr_linear.coef_[0][1]:.3f}*wind_speed + {svr_linear.coef_[0][2]:.3f}*HRR + {svr_linear.intercept_[0]:.3f}")

[0119] print(f"R²: {r2_score(y_test, y_pred_svr_linear):.3f}\n")

[0120] # 6. Support Vector Regression (RBF kernel)

[0121] svr_rbf = SVR(kernel='rbf', C=1.0, epsilon=0.1)

[0122] svr_rbf.fit(X_train, y_train)

[0123] y_pred_svr_rbf = svr_rbf.predict(X_test)

[0124] print("=== RBF core SVR ===")

[0125] print("Number of support vectors:", len(svr_rbf.support_vectors_))

[0126] print(f"R²: {r2_score(y_test, y_pred_svr_rbf):.3f}\n")

[0127] # 7. Visual Comparison

[0128] plt.figure(figsize=(12, 6))

[0129] models = {

[0130] "Linear": y_pred_lr,

[0131] "Polynomial": y_pred_poly,

[0132] "SVR-RBF": y_pred_svr_rbf

[0133] }

[0134] for name, pred in models.items():

[0135] plt.scatter(y_test, pred, alpha=0.5, label=f"{name} (R²={r2_score(y_test, pred):.2f})")

[0136] plt.plot([min(y_test), max(y_test)], [min(y_test), max(y_test)], 'k--', lw=1, label="Perfect Fit")

[0137] plt.xlabel("True Offset Distance")

[0138] plt.ylabel("Predicted Offset Distance")

[0139] plt.title("Model Performance Comparison")

[0140] plt.legend()

[0141] plt.grid(True)

[0142] plt.show()

[0143] Please refer to Figure 2 , which shows the fitting result schematic diagram provided by the embodiment of the present application. The fitting result is shown in the following table:

[0144] Table 1: Polynomial fitting result example table

[0145]

[0146] Further, the subsequent embodiment of the present application selects the fitting result of the polynomial regression as the offset coefficient. In a possible implementation manner, the reference value of the offset coefficient can be X1=5.922, X2=0.637, X3=0.068, X4=0.488, X5=-0.078.

[0147] Based on the above technical scheme, in the highway tunnel fire monitoring process, the linear temperature detector has a high deviation in locating the fire source by temperature detection, and cannot accurately determine the fire source position in time, and the application provides a highway tunnel fire positioning correction method and equipment considering the number of lanes and longitudinal ventilation conditions, which obtains the wind speed in the current tunnel and the heat release rate of the fire or the vehicle type and the lane, calculates the positioning error of the current temperature detector, and corrects the detection position of the current fire source. The highway tunnel fire positioning correction method and equipment realize rapid positioning of the fire source in the tunnel, provide more timely and accurate fire information for fire rescue, and have great significance for tunnel engineering operation safety.

[0148] Further, the application actively predicts the theoretical estimated offset distance of the fire source under a specific wind speed and fire source release power by providing an estimated offset distance model, and dynamically and intelligently corrects the initial detection position in reverse, improves the positioning accuracy of the real position of the fire source from static perception to dynamic prediction and correction, and greatly improves the reliability and repeatability of the correction.

[0149] In addition, the embodiment of the application further provides an electronic device, including at least one processor and a memory in communication connection with the at least one processor; the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the highway tunnel fire positioning correction method according to any one of the above.

[0150] In the embodiment of the application, the processor can be an integrated circuit chip with signal processing capability. The processor can be a general processor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components.

[0151] The techniques of this disclosure can be implemented or performed in a method, steps, and / or logic arrangements as disclosed in the embodiments of the present application. The general purpose processor can be a microprocessor or the processor can also be any conventional processor. The steps of the method disclosed in conjunction with the embodiments of the present application can be directly embodied for hardware code execution or a combination of hardware and software modules in the code execution processor. The software module can be located in a random access memory, a flash memory, a read only memory, a programmable read only memory, an electrically erasable programmable memory, a register, and other mature storage mediums in the art. The processor reads information in the storage medium and combines the hardware to complete the steps of the above method.

[0152] The storage medium can be a memory, for example, can be a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memories.

[0153] The non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically EPROM (EEPROM), or a flash memory.

[0154] The volatile memory can be a random access memory (RAM) used as an external cache. By way of example, and not limitation, many forms of RAM can be used, such as a static random access memory (SRAM), a dynamic random access memory (DRAM), a synchronous dynamic random access memory (SDRAM), a double data rate SDRAM (DDR SDRAM), an enhanced SDRAM (ESDRAM), a Sync Link DRAM (SLDRAM), and a direct Rambus RAM (DRRAM).

[0155] The storage medium described in the embodiments of the present application is intended to include, but not limited to, these and any other suitable types of memory.

[0156] It should be understood that the apparatus disclosed in the embodiments of the present application can be implemented in other manners. For example, the division of the units is only a logical function division, and other division manners can be adopted during actual implementation. For example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the communicated connections between the units can be indirect communication connections.

[0157] In addition, the various functional units in the embodiments of the present application can be integrated in a processing unit, or each can exist physically as a separate module, or two or more of them can be integrated in a processing unit. The above-mentioned integrated units can be realized in the form of hardware or software function units.

[0158] When the integrated units are realized in the form of software function units and sold or used as an independent product, they can be stored in a computer readable storage medium. Based on such an understanding, the technical solutions of the present application essentially, or the part contributing to the prior art, or all or a part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The foregoing storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk, and various other media that can store program codes.

[0159] Any embodiment or design scheme described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as more preferred or more advantageous than other embodiments or design schemes. Rather, the use of "exemplary" or "for example" is intended to present the relevant concept in a specific manner for ease of understanding.

[0160] The above only describes the preferred embodiments of the present application and is not intended to limit the present application. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present application should be included in the protection scope of the present application.

Claims

1. A highway tunnel fire positioning correction method, characterized by, The method comprises the following steps: acquiring a current longitudinal wind speed in the tunnel, a current heat release rate of the fire source, and a current detection position of the fire source; inputting the current longitudinal wind speed in the tunnel and the current heat release rate of the fire source into a constructed estimation offset distance model to obtain an estimated offset distance; correcting the current detection position of the fire source according to the estimated offset distance to obtain a corrected fire position; wherein the construction process of the estimation offset distance model comprises: constructing a relationship curve according to a historical longitudinal wind speed in the tunnel, a historical heat release rate of the fire source, and a corresponding historical estimated offset distance; performing polynomial fitting on the relationship curve to obtain an offset coefficient and complete the construction.

2. The highway tunnel fire location correction method of claim 1, wherein, The calculation formula of the estimation offset distance model is: D1 = X1μ + X2Q + X3μ 2 + X4μQ - X5Q 2 , wherein D1 is the estimated offset distance, X1-X5 are the offset coefficients, μ is the current longitudinal wind speed in the tunnel, and Q is the current heat release rate of the fire source.

3. A highway tunnel fire location correction method according to claim 2, characterized in that, The polynomial fitting is performed by linear regression, polynomial regression, and support vector regression, and the offset coefficient is determined by selecting the result with the highest fitting accuracy.

4. The highway tunnel fire location correction method of claim 1, wherein, The current heat release rate of the fire source is calculated according to the height of the fire source from the tunnel vault and the maximum temperature rise of the tunnel vault, and specifically comprises the following steps: calculating the height of the fire source from the tunnel vault according to the height of the fire vehicle and the lane where the fire vehicle is located, and combining the net height of the tunnel; calculating the current heat release rate of the fire source by combining the maximum temperature rise of the tunnel vault.

5. A highway tunnel fire location correction method according to claim 4, characterized in that, Based on the tunnel for two-lane or fire source vehicle is located in the middle of three-lane tunnel, the calculation formula of the height of fire source from the tunnel vault is H f =H t -H c ; based on the fire source vehicle is located in the two sides of three-lane tunnel, the calculation formula of the height of fire source from the tunnel vault is H f = ; wherein, H f is the height of fire source from the tunnel vault, H t is the net height of tunnel, H c is the height of fire source vehicle.

6. The highway tunnel fire location correction method of claim 4, wherein, The calculation formula of the current heat release rate of the fire source is: where Q is the current heat release rate of the fire, ΔT max is the maximum temperature rise at the tunnel vault.

7. The highway tunnel fire location correction method of claim 1, wherein, The current detection position of the fire source is the position with the highest vault temperature when the fire occurs in the tunnel.

8. A highway tunnel fire location correction device, characterized by, The method comprises the following steps: a temperature sensing module for collecting the temperature of the tunnel vault; a wind speed detection module for collecting the longitudinal wind speed in the tunnel; a central processing module for acquiring the temperature of the tunnel vault and the longitudinal wind speed in the tunnel, and obtaining the corrected fire position by using the highway tunnel fire positioning correction method according to any one of claims 1 to 7.

9. A highway tunnel fire location correction device according to claim 8, wherein The temperature sensing module adopts a distributed optical fiber temperature sensor or an infrared thermal imager and is arranged along the tunnel vault; the wind speed detection module adopts an ultrasonic anemometer or a hot-wire anemometer and is arranged at the entrance or exit of the tunnel.

10. An electronic device, comprising: The method comprises the following steps: at least one processor, and a memory connected to the at least one processor in communication; the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the highway tunnel fire positioning correction method according to any one of claims 1 to 7.

Images