Tunnel Poisonous Gas Detection Method, Device, Equipment, System and Storage Medium

Abstract

The present application relates to a method, device, equipment, system and storage medium for detecting poisonous gases in a tunnel, belonging to the technical field of information detection. The method includes: obtaining the concentration measurement values of various poisonous gases collected by multiple gas sensor nodes in the tunnel; inputting the concentration measurement values of the various poisonous gases into a linear minimum mean square error estimation model to output the position of the gas leakage source and the estimated value of the gas release rate; inputting the estimated values of the gas leakage source parameters into a gas diffusion model to output gas diffusion parameters; the gas diffusion model is a static plume gas diffusion model based on turbulent diffusion, and the gas diffusion parameters include the diffusion rate of the gas leakage source; inputting the estimated values of the gas leakage source parameters, the gas diffusion parameters and the over-standard concentration threshold of the poisonous gas into a finite element prediction model to output the over-standard prediction result of the poisonous gas. The present application can realize continuous monitoring and dynamic early warning of poisonous gases in the tunnel.

Description

Technical Field

[0001] The present application relates to the technical field of information detection, and particularly to a method, device, equipment, system and storage medium for detecting poisonous gases in tunnels. Background Art

[0002] In the construction and operation of modern transportation networks, tunnels, as key engineering structures connecting regions and shortening spatial and temporal distances, their safety and reliability have always been the focus of attention in the engineering and academic fields. With the continuous progress of tunnel engineering technology, especially in the construction and operation of long-distance and large-section tunnels under complex geological conditions, the detection, monitoring and management of poisonous gases have become a key problem to be solved urgently. In under-construction tunnels and completed tunnels, due to the complexity of geological structures, the high-energy consumption operation of construction machinery, and the accumulation of vehicle exhaust emissions during vehicle passage, a series of toxic and harmful gases are often generated, such as carbon monoxide (CO), hydrogen sulfide (H2S), nitrogen oxides (NOx), sulfur dioxide (SO2), methane (CH4), carbon dioxide (CO2), ammonia (NH3), etc. The existence of these poisonous gases not only seriously threatens the lives and health of construction workers, but also poses potential risks to the long-term stability of tunnel structures and the safety of vehicle passage during operation.

[0003] Most traditional methods for detecting poisonous gases rely on detection personnel holding detectors to sample specific areas in the tunnel and then combining laboratory analysis to achieve. This method is not only time-consuming and laborious, has high requirements for the operation safety of detection personnel, but also is difficult to achieve continuous monitoring and dynamic warning of poisonous gases. Summary of the Invention

[0004] In order to achieve continuous monitoring and dynamic warning of poisonous gases in tunnels, the present application provides a method, device, equipment, system and storage medium for detecting poisonous gases in tunnels.

[0005] In a first aspect, the present application provides a method for detecting poisonous gases in tunnels, adopting the following technical solution:

[0006] A method for detecting poisonous gases in tunnels, comprising:

[0007] Obtaining concentration measurement values of various poisonous gases collected by multiple gas sensor nodes in the tunnel;

[0008] Inputting the concentration measurement values of the various poisonous gases into a preset linear minimum mean square error estimation model, and outputting an estimated value of gas leakage source parameters; wherein, the gas leakage source parameters include the position of the gas leakage source and the gas release rate;

[0009] Input the estimated value of the gas leakage source parameters into a preset gas diffusion model to output gas diffusion parameters; wherein, the gas diffusion model is a static plume gas diffusion model based on turbulent diffusion, and the gas diffusion parameters include the diffusion rate of the gas leakage source.

[0010] Input the estimated value of the gas leakage source parameters, the gas diffusion parameters, and the threshold value of the excessive concentration of the poisonous gas into a preset finite element prediction model to output the prediction result of the excessive concentration of the poisonous gas.

[0011] Optionally, the formula of the linear minimum mean square error estimation model is:

[0012] ;

[0013] The performance of the estimator is measured by the error vector , and the mean of the error vector is 0, and the covariance matrix is:

[0014] ;

[0015] In the formula, represents the vector to be estimated, and the vector to be estimated is composed of the position and the gas release rate of the gas leakage source. The vector to be estimated is a real number matrix with a dimension of p×1, that is, ;

[0016] represents the estimated value of the vector to be estimated ;

[0017] represents the mean of the vector to be estimated ;

[0018] represents the covariance matrix of the vector to be estimated ;

[0019] z represents the observation vector, and the observation vector z is a real number matrix with a dimension of N ×1, that is, ;

[0020] D represents the observation matrix, and the observation matrix D is a real number matrix with a dimension of N ×p, that is, ;

[0021] represents the transpose of the observation matrix D ;

[0022] represents the expected value of the outer product of the error vector z under the condition of the given observation vector and the vector to be estimated ;

[0023] represents the transpose of the error vector ;

[0024] v represents a noise vector with zero mean and covariance matrix , and the noise vector v is a real matrix of dimension N ×1, that is , and v is uncorrelated with θ , and the joint distribution can be arbitrary;

[0025] c represents a random variable.

[0026] Optionally, the formula of the gas diffusion model is:

[0027] ;

[0028] In the formula, represents the coordinate position of the gas sensor node;

[0029] represents the coordinate position of the gas leakage source;

[0030] represents the gas concentration value of the gas sensor node at time t;

[0031] represents the Euclidean distance between the gas sensor node and the gas leakage source ;

[0032] represents the initial time when the gas leakage source releases gas;

[0033] represents the wind speed vector;

[0034] represents the diffusion rate of the gas leakage source;

[0035] represents the estimated value of the gas release rate of the gas leakage source.

[0036] Optionally, inputting the estimated value of the gas leakage source parameters, the gas diffusion parameters, and the over-standard concentration threshold of the poisonous gas into a preset finite element prediction model, and outputting the over-standard prediction result of the poisonous gas includes:

[0037] Dividing the tunnel space into multiple grid cells based on the estimated value of the gas leakage source parameters;

[0038] Constructing the control equation of the finite element prediction model based on the gas diffusion parameters and the wind speed vector in the tunnel;

[0039] Setting the initial conditions and boundary conditions of the finite element prediction model based on the estimated value of the gas leakage source parameters;

[0040] Solving the control equation on each of the grid cells based on the initial conditions and the boundary conditions to obtain the gas concentration distribution of the poisonous gas in the tunnel;

[0041] Determining the over-standard prediction result of the poisonous gas based on the gas concentration distribution of the poisonous gas in the tunnel and the over-standard concentration threshold of the poisonous gas.

[0042] Optionally, the control equation is:

[0043] ;

[0044] In the formula, , represents the wind speed vector in the tunnel;

[0045] represents the diffusion rate of the gas leakage source;

[0046] represents the coordinate in the tunnel at time t of the gas concentration value;

[0047] represents the concentration gradient.

[0048] Optionally, the determining the over-standard prediction result of the poisonous gas based on the gas concentration distribution of the poisonous gas in the tunnel and the over-standard concentration threshold of the poisonous gas includes:

[0049] Comparing all gas concentration values with the over-standard concentration threshold, and screening out all over-standard points where the gas concentration value is higher than the over-standard concentration threshold;

[0050] For non-over-standard points where the gas concentration value is not higher than the over-standard concentration threshold, using the interpolation method to calculate the gas concentration value of the non-over-standard points;

[0051] Based on the gas concentration values of all the excessive-standard points and all the non-excessive-standard points, a three-dimensional isoconcentration line graph is drawn;

[0052] Based on the three-dimensional isoconcentration line graph, the leakage level of the poisonous gas is determined.

[0053] In a second aspect, the present application provides a tunnel poisonous gas detection device, adopting the following technical solution:

[0054] A tunnel poisonous gas detection device includes:

[0055] A concentration acquisition module, configured to acquire the concentration measurement values of multiple kinds of poisonous gases collected by multiple gas sensor nodes in the tunnel;

[0056] A first model module, configured to input the concentration measurement values of the multiple kinds of poisonous gases into a preset linear minimum mean square error estimation model, and output an estimated value of the gas leakage source parameters; wherein, the gas leakage source parameters include the position of the gas leakage source and the gas release rate;

[0057] A second model module, configured to input the estimated value of the gas leakage source parameters into a preset gas diffusion model, and output gas diffusion parameters; wherein, the gas diffusion model is a static plume gas diffusion model based on turbulent diffusion, and the gas diffusion parameters include the diffusion rate of the gas leakage source;

[0058] A third model module, configured to input the estimated value of the gas leakage source parameters, the gas diffusion parameters, and the excessive-standard concentration threshold of the poisonous gas into a preset finite element prediction model, and output a poisonous gas excessive-standard prediction result.

[0059] In a third aspect, the present application provides an electronic device, adopting the following technical solution:

[0060] An electronic device includes a memory and a processor; a computer program capable of being loaded and executed by the processor for the method according to any one of the first aspect or the second aspect is stored on the memory.

[0061] In a fourth aspect, the present application provides a tunnel poisonous gas detection system, adopting the following technical solution:

[0062] A tunnel poisonous gas detection system includes the multiple gas sensor nodes and the electronic device according to the third aspect;

[0063] Wherein, the multiple gas sensor nodes include semiconductor sensor nodes, optical sensor nodes, and electrochemical sensor nodes;

[0064] The semiconductor sensor nodes are arranged on the inner surface layer of the lining concrete of the tunnel;

[0065] The optical sensor node is arranged on the outer surface layer of the lining concrete of the tunnel;

[0066] The electrochemical sensor node is arranged at the positions of the cable trenches on both sides of the tunnel.

[0067] In a fifth aspect, the present application provides a computer-readable storage medium, adopting the following technical solution:

[0068] A computer-readable storage medium stores a computer program that can be loaded and executed by a processor to perform the method described in any one of the first aspect or the second aspect.

[0069] By adopting the above technical solution, combining various calculation models such as the LMMSE model, the turbulent diffusion model, and the finite element prediction model, it is possible to achieve high-precision estimation of gas leakage source parameters, gas diffusion simulation, and prediction of excessive toxic gases in the tunnel, and further realize continuous monitoring and dynamic early warning of toxic gases in the tunnel, which is applicable to complex flow environments and has high practicability and reliability. BRIEF DESCRIPTION OF THE DRAWINGS

[0070] Figure 1 It is a schematic flowchart of a method for detecting toxic gases in a tunnel according to an embodiment of the present application.

[0071] Figure 2 It is a schematic flowchart of the sub-steps of step S104 in a method for detecting toxic gases in a tunnel according to an embodiment of the present application.

[0072] Figure 3 It is a schematic flowchart of the sub-steps of step S205 in a method for detecting toxic gases in a tunnel according to an embodiment of the present application.

[0073] Figure 4 It is a structural block diagram of a device for detecting toxic gases in a tunnel according to an embodiment of the present application.

[0074] Figure 5 It is a structural block diagram of an electronic device according to an embodiment of the present application.

[0075] Figure 6 It is a front view schematic diagram of the layout of gas sensor nodes in a tunnel cross-section in a system for detecting toxic gases in a tunnel according to an embodiment of the present application.

[0076] Figure 7 It is a side view schematic diagram of the layout of gas sensor nodes in a tunnel cross-section in a system for detecting toxic gases in a tunnel according to an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0077] To make the objectives, technical solutions, and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application.

[0078] Figure 1 The figure is a schematic flowchart of a method for detecting toxic gases in a tunnel provided in this embodiment. This method can be applied to a server or a terminal device. Among them, the server can be an independent physical server, a server cluster or a distributed system composed of multiple physical servers, or a cloud server providing cloud computing services; the terminal device can be a smart phone, a tablet computer, a desktop computer, etc., and this embodiment does not make specific limitations on this.

[0079] As Figure 1 shown, the main process of this method is described as follows (Steps S101 - S104):

[0080] Step S101, obtain the concentration measurement values of various toxic gases collected by multiple gas sensor nodes in the tunnel;

[0081] Step S102, input the concentration measurement values of various toxic gases into a preset linear minimum mean square error estimation model, and output the estimated values of gas leakage source parameters; among them, the gas leakage source parameters include the location of the gas leakage source and the gas release rate;

[0082] Step S103, input the estimated values of gas leakage source parameters into a preset gas diffusion model, and output gas diffusion parameters; among them, the gas diffusion model is a static plume gas diffusion model based on turbulent diffusion, and the gas diffusion parameters include the diffusion rate of the gas leakage source;

[0083] Step S104, input the estimated values of gas leakage source parameters, gas diffusion parameters, and the over - standard concentration threshold of toxic gases into a preset finite - element prediction model, and output the over - standard prediction result of toxic gases.

[0084] In this embodiment, different gas sensor nodes can collect gas concentration information at different regional positions, and synchronously transmit it to the data information processing center, and then estimate state parameters such as the location of the gas leakage source and the gas release rate through the collaborative information processing technology of the sensing network. The collaborative information processing technology of the sensing network generally uses a distributed estimation algorithm to achieve. For the detection and positioning of toxic gas leakage sources, the design of the distributed estimation algorithm is the key to the efficient estimation of gas leakage source state parameters by the entire sensor network. This embodiment uses a linear minimum mean square error estimation model (LMMSE) designed based on probability estimation theory to achieve the estimation of state parameters such as the location and gas release rate of toxic gas leakage sources.

[0085] In some optional embodiments, for linear minimum mean square error estimation, if the observation vector z satisfies the following Bayesian linear model z = Dθ + v, where, ; θ represents the vector to be estimated, which consists of the position of the gas leakage source and the gas release rate. The vector to be estimated θ is a real matrix of dimension p×1, that is ; D represents the observation matrix. The observation matrix D is a real matrix of dimension N×p, that is ; v represents a noise vector with zero mean and covariance matrix (i.e., Covariance Matrix, a matrix describing the linear relationship between the components of a random vector) of The noise vector v is a real matrix of dimension N×1, that is , and v is uncorrelated with θ. The joint distribution p(v,θ) can be arbitrary as long as their marginal distributions satisfy the uncorrelated condition. p(v,θ) can be decomposed into the product of marginal distributions, that is p(v,θ)=p(v)p(θ).

[0086] The formula for the linear minimum mean square error estimation model is:

[0087] ;

[0088] The performance of the estimator is measured by the error vector The mean of the error vector ε is 0, and the covariance matrix is:

[0089]

[0090] In the formula, represents the estimated value of the vector to be estimated;

[0091] E(θ) represents the mean of the vector to be estimated θ;

[0092] represents the covariance matrix of the vector to be estimated θ;

[0093] z represents the observation vector. The observation vector z is a real matrix of dimension N×1, that is ;

[0094] represents the transpose of the observation matrix D;

[0095] represents the expected value of the outer product of the error vector ε given the observation vector z and the vector to be estimated θ;

[0096] represents the transpose of the error ε;

[0097] c represents a random variable.

[0098] It should be noted that in the dimension N×1, N represents the length of the vector, that is, there are N elements in the vector. In the dimension N×p, it means there are N rows and p columns, where each row corresponds to an observation value and each column corresponds to a parameter.

[0099] In this embodiment, the linear minimum mean square error estimation (LMMSE) in the distributed estimation algorithm is designed based on the probability estimation theory, which can achieve accurate and efficient positioning of the leakage source of tunnel poisonous gas and improve the response speed; the distributed design enhances the robustness and scalability of the system; the LMMSE probability estimation can cope with complex environments and improve the detection reliability; the distributed estimation algorithm can optimize parameters according to the actual situation of the tunnel to achieve the best performance.

[0100] In some alternative embodiments, a static plume gas diffusion model based on the turbulent diffusion theory is used to describe the diffusion state of tunnel poisonous gas. Considering that the propagation of gas in the air is often affected by wind in addition to its own diffusion, a gas diffusion model with wind is adopted.

[0101] Assume that in a homogeneous and uniform wind field (the wind speed and direction are exactly the same at any position in space and there is no change), the gas leakage source continuously releases gas into the air at a constant release rate s, and the released substance diffuses around at a certain diffusion rate in the tunnel environment. Considering the influence of wind speed, according to Fick's law, we can get:

[0102] ;

[0103] Through the above formula, the formula of the gas diffusion model can be derived as:

[0104] ;

[0105] In the formula, represents the coordinate position of the gas sensor node;

[0106] represents the coordinate position of the gas leakage source;

[0107] represents the gas concentration value of the gas sensor node at time t;

[0108] represents the gas sensor node and the gas leakage source the Euclidean distance between them;

[0109] represents the initial time when the gas leakage source releases gas;

[0110] represents the wind speed vector;

[0111] represents the diffusion rate of the gas leakage source;

[0112] represents the estimated value of the gas release rate of the gas leakage source;

[0113] δ represents the infinitesimal change in instantaneous point source diffusion;

[0114] exp() represents the exponential function with the natural constant e (approximately equal to 2.71828) as the base;

[0115] erfc() represents the complementary error function.

[0116] When t ≤ , when t → +∞, , when t → +∞, represents reaching the equilibrium state, and the formula of the gas diffusion model is:

[0117] ;

[0118] When , that is, when there is only wind in the x - direction, the formula of the gas diffusion model is transformed into:

[0119] .

[0120] In this embodiment, a static plume gas diffusion model based on the turbulent diffusion theory is used to simulate the diffusion state of poisonous gases in under - construction and completed tunnels. By innovatively combining the turbulent diffusion theory with the static model, the simulation accuracy is significantly improved; the calculation is efficient and fast, and can quickly provide simulation results; the resource occupancy is small, reducing the cost and threshold of the simulation; the model structure design is simple, easy to be programmed and implemented, and applied and promoted; the prediction ability is strong, and can accurately reflect the diffusion trend of poisonous gases and potential dangerous areas; the theoretical basis is solid, ensuring the accuracy and reliability of the simulation results.

[0121] In this embodiment, the prediction results of excessive toxic gas levels include information such as the range of excessive concentrations of toxic gases in the tunnel and the excessive level, which facilitates corresponding detection personnel to promptly discover and eliminate risks. Therefore, it is necessary to screen the types of common high-risk toxic gases and their corresponding excessive concentration thresholds. Specifically, relevant national industry standards and specifications such as "Occupational Exposure Limits for Hazardous Agents in the Workplace" (GBZ 2.1-2019), "Technical Specifications for Highway Tunnel Construction" (JTG / T 3660-2020), "Technical Specifications for Environmental Health Risk Monitoring" (T / CSES 53-2022), and "List of Priority Controlled Chemicals" can be combined to screen the types of common high-risk toxic gases in the tunnel and their corresponding excessive concentration thresholds.

[0122] Adopt a multi-dimensional screening method of standard reference - gas identification - threshold concentration to screen out common high-risk toxic gases layer by layer and step by step. First, it ensures the scientificity and rigor of the screening process. By following nationally recognized standards and common chemical classifications and combining precise threshold concentration settings, the accuracy and reliability of the screening results are effectively improved. Second, it enhances the comprehensiveness and systematicness of the screening. Through diversified screening indicators and a layer-by-layer and step-by-step screening process, common high-risk toxic gases can be comprehensively covered and effectively screened. Third, it improves the flexibility and adaptability of the screening. This method can be flexibly adjusted according to the actual needs of tunnel toxic gas detection. Fourth, it significantly improves the efficiency of the screening work. Through scientific method and process design, unnecessary repetitive work and resource waste are reduced. Fifth, it strengthens the application value of the screening results. The information of the screened high-risk toxic gases provides an important basis for subsequent monitoring, early warning, and prevention and control work, helping to reduce the potential risks of toxic gases to the environment and human body.

[0123] In this embodiment, toxic gases such as methane, carbon monoxide, carbon dioxide, hydrogen sulfide, sulfur dioxide, ammonia, nitrogen dioxide, nitrogen, chlorine, phosgene (COCl2), dichlorophosgene (C2Cl4O2), formaldehyde, ozone, hydrogen cyanide (HCN), ethane, ethylene, propylene, propane, benzene, and toluene are screened out.

[0124] In some alternative embodiments, as Figure 2 shown, step S104 includes the following sub-steps:

[0125] Step S201, based on the estimated values of gas leakage source parameters, divide the tunnel space into multiple grid cells;

[0126] In step S201, according to the leakage source location and diffusion range, reasonably divide the grid cells. The grid density should be high enough to capture the details of concentration changes, especially near the leakage source and in high-concentration areas. Of course, adaptive grid technology can be used to dynamically adjust the grid density.

[0127] Step S202: Based on the gas diffusion parameters and the wind speed vector in the tunnel, construct the governing equation of the finite element prediction model.

[0128] Optionally, for the gas leakage problem, the governing equation describes the variation of the gas concentration φ(x, y, z, t) in three-dimensional space. This governing equation takes into account the diffusion and convection effects of the gas and is the basis of the finite element model. In practical applications, this continuous partial differential equation needs to be discretized, that is, transformed into a system of algebraic equations through the finite element method. Then, by solving this system of algebraic equations, the approximate values of the gas concentration at discrete points (finite element grid points) can be obtained. These approximate values can be used to predict the distribution of the gas concentration in space.

[0129] The governing equation can be designed as follows:

[0130] ;

[0131] In the formula, , represents the wind speed vector in the tunnel;

[0132] represents the diffusion rate of the gas leakage source;

[0133] φ(x, y, z, t) represents the gas concentration value at the coordinates (x, y, z) in the tunnel at time t;

[0134] ∇φ represents the concentration gradient. The concentration gradient is a vector, and its components are the partial derivatives of the gas concentration value in the x, y, and z directions; in the process of gas diffusion, the concentration gradient is an important factor affecting the movement direction and rate of gas molecules. Gas molecules will diffuse from high-concentration regions to low-concentration regions until the concentration is evenly distributed.

[0135] Step S203: Based on the estimated values of the gas leakage source parameters, set the initial conditions and boundary conditions of the finite element prediction model.

[0136] In Step S203, the initial condition is that the gas concentration value at the gas leakage source position at the initial time is φ(x, y, z, ) = Q. The boundary condition is that on the boundary of the computational domain, the gas concentration value is zero or satisfies certain diffusion conditions.

[0137] Step S204: Based on the initial conditions and boundary conditions, solve the governing equation on each grid cell to obtain the gas concentration distribution of the poisonous gas in the tunnel.

[0138] Step S205: Based on the gas concentration distribution of the poisonous gas in the tunnel and the over-standard concentration threshold of the poisonous gas, determine the prediction result of the poisonous gas exceeding the standard.

[0139] If the gas concentration of a poisonous gas at a certain position in the tunnel exceeds the over-standard concentration threshold of the poisonous gas, it indicates that the poisonous gas at that position is over-standard.

[0140] Further, for step S205, as Figure 3 shown, it can be specifically implemented according to the following steps:

[0141] Step S301, compare all gas concentration values with the over-standard concentration threshold, and screen out all over-standard points where the gas concentration value is higher than the over-standard concentration threshold;

[0142] Step S302, for non-over-standard points where the gas concentration value is not higher than the over-standard concentration threshold, use the interpolation method to calculate the gas concentration value of the non-over-standard points;

[0143] Optionally, interpolation methods such as linear interpolation, Kriging interpolation, and Lagrange interpolation can be used. The three-dimensional isoconcentration line map needs to show the continuous distribution of concentration, rather than just the concentration values of discrete points. Through the interpolation method, a continuous concentration field can be generated, enabling the isoconcentration lines to smoothly connect the known points. Although the concentration values of non-over-standard points are lower than the threshold, they still have important significance for the overall risk assessment, can more clearly show the concentration gradient and diffusion trend, and can more comprehensively evaluate the influence range of the leakage, which is very important for understanding the dynamic changes and influence range of gas leakage.

[0144] Step S303, based on the gas concentration values of all over-standard points and all non-over-standard points, draw a three-dimensional isoconcentration line map;

[0145] Optionally, methods such as the contour3 function provided by MATLAB, Surfer visualization software, the Axes3D.contour or Axes3D.contourf function in Python can be used to draw the isoconcentration line map in three-dimensional space, visualize the gas concentration data in a three-dimensional coordinate system, and intuitively show the concentration distribution.

[0146] Step S304, determine the leakage level of the poisonous gas based on the three-dimensional isoconcentration line map.

[0147] The larger the area where the concentration exceeds the standard in the isoconcentration line map, the higher the leakage level; the range and position of the high-concentration area in the isoconcentration line map can reflect the intensity and diffusion direction of the leakage source. By dynamically simulating the isoconcentration line map, the gas diffusion speed can be observed, and the faster the diffusion speed, the higher the leakage level.

[0148] For different leakage levels, different warning signals can be adopted. For example, five types of lights, namely green (normal signal), blue (general alarm signal), yellow (severe alarm signal), red (serious alarm signal), and orange (extremely severe alarm signal), can be used for alarm prompts. In this way, the accurate classification of the harm degree of gas leakage can be realized. The colors are intuitive and easy to distinguish, which can enhance the alertness of the staff, quickly trigger corresponding emergency measures, simplify the decision-making process, and improve the efficiency of tunnel safety management.

[0149] Based on the same inventive concept, an embodiment of the present invention provides a tunnel poisonous gas detection device. Figure 4 The following is a structural block diagram of a tunnel poisonous gas detection device 400 provided by an embodiment of the present application. As Figure 4 shown, the tunnel poisonous gas detection device 400 mainly includes:

[0150] A concentration acquisition module 401, configured to acquire the concentration measurement values of multiple poisonous gases collected by a plurality of gas sensor nodes in the tunnel;

[0151] A first model module 402, configured to input the concentration measurement values of multiple poisonous gases into a preset linear minimum mean square error estimation model, and output an estimated value of the gas leakage source parameters; wherein, the gas leakage source parameters include the position of the gas leakage source and the gas release rate;

[0152] A second model module 403, configured to input the estimated value of the gas leakage source parameters into a preset gas diffusion model, and output gas diffusion parameters; wherein, the gas diffusion model is a static plume gas diffusion model based on turbulent diffusion, and the gas diffusion parameters include the diffusion rate of the gas leakage source;

[0153] A third model module 404, configured to input the estimated value of the gas leakage source parameters, the gas diffusion parameters, and the over-standard concentration threshold of the poisonous gas into a preset finite element prediction model, and output an over-standard prediction result of the poisonous gas.

[0154] In some optional embodiments, the formula of the linear minimum mean square error estimation model in the first model module 402 is:

[0155] ;

[0156] The performance of the estimator is measured by the error vector The mean value of the error vector is 0, and the covariance matrix is:

[0157] ;

[0158] In the formula, Denote the vector to be estimated, which consists of the location of the gas leakage source and the gas release rate, the vector to be estimated is a real matrix of dimension p×1, that is ;

[0159] Denote the vector to be estimated the estimated value of;

[0160] Denote the vector to be estimated the mean value of;

[0161] Denote the vector to be estimated the covariance matrix of;

[0162] z Denote the observation vector, the observation vector z is a real matrix of dimension N ×1, that is ;

[0163] D Denote the observation matrix, the observation matrix D is a real matrix of dimension N ×p, that is ;

[0164] Denote the transpose of the observation matrix D ;

[0165] Denote the expected value of the outer product of the error vector z under the condition of the given observation vector and the vector to be estimated ;

[0166] Denote the transpose of the error vector ;

[0167] v represents a noise vector with zero mean and covariance matrix The noise vector v is a real matrix of dimension N ×1, that is and v is uncorrelated with θ The joint distribution can be arbitrary;

[0168] c represents a random variable.

[0169] In some alternative embodiments, the formula of the gas diffusion model in the second model module 403 is:

[0170] ;

[0171] In the formula, , represents the coordinate position of the gas sensor node;

[0172] , represents the coordinate position of the gas leakage source;

[0173] represents the gas concentration value of the gas sensor node at time t;

[0174] represents the gas sensor node and the gas leakage source the Euclidean distance between them;

[0175] represents the initial time when the gas leakage source releases gas;

[0176] , represents the wind speed vector;

[0177] represents the diffusion rate of the gas leakage source;

[0178] represents the estimated value of the gas release rate of the gas leakage source.

[0179] In some optional embodiments, the third model module 404 includes:

[0180] A grid division module for dividing the tunnel space into multiple grid cells based on the estimated values of the gas leakage source parameters;

[0181] An equation construction module for constructing the control equation of the finite element prediction model based on the gas diffusion parameters and the wind speed vector in the tunnel;

[0182] A condition setting module for setting the initial conditions and boundary conditions of the finite element prediction model based on the estimated values of the gas leakage source parameters;

[0183] An equation solving module for solving the control equation on each grid cell based on the initial conditions and boundary conditions to obtain the gas concentration distribution of the poisonous gas in the tunnel;

[0184] A determination module for determining the poisonous gas exceeding standard prediction result based on the gas concentration distribution of the poisonous gas in the tunnel and the exceeding standard concentration threshold of the poisonous gas.

[0185] Furthermore, the control equation is:

[0186] ;

[0187] In the formula, , representing the wind speed vector inside the tunnel;

[0188] representing the diffusion rate of the gas leakage source;

[0189] representing the coordinates inside the tunnel of the gas concentration value at time t;

[0190] representing the concentration gradient.

[0191] In some alternative embodiments, the determination module is specifically configured to compare all gas concentration values with the excessive concentration threshold, and screen out all excessive points where the gas concentration value is higher than the excessive concentration threshold; for non-excessive points where the gas concentration value is not higher than the excessive concentration threshold, use the interpolation method to calculate the gas concentration values of the non-excessive points; based on the gas concentration values of all excessive points and all non-excessive points, draw a three-dimensional isoconcentration line graph; and determine the leakage level of the poisonous gas based on the three-dimensional isoconcentration line graph.

[0192] It should be noted that the functional modules in the embodiments of the present application can be integrated together to form an independent unit. For example, they can be integrated in a processing unit, or each module can exist physically alone, or two or more modules can be integrated to form an independent unit. The above integrated unit can be implemented in the form of hardware or in the form of a software functional unit. If the function is implemented in the form of a software functional module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing an electronic device (which can be a personal computer, a server, or a network device, etc.) or a processor to execute all or part of the steps of the methods in the various embodiments of the present application. The aforementioned storage medium includes: USB flash drives, mobile hard disks, read-only memories, random access memories, magnetic disks, or optical disks, etc., which can store program codes.

[0193] The various change methods and specific examples in the method provided by the embodiments of the present application are equally applicable to a tunnel poisonous gas detection device provided by this embodiment. Through the detailed description of the tunnel poisonous gas detection method above, those skilled in the art can clearly know the implementation method of the tunnel poisonous gas detection device in this embodiment. For the sake of simplicity of the specification, it will not be elaborated here.

[0194] Figure 5 This is a structural block diagram of an electronic device 500 provided by the embodiments of the present application. AsFigure 5 As shown in the figure, the electronic device 500 includes a memory 501, a processor 502, and a communication bus 503; the memory 501 and the processor 502 are connected through the communication bus 503.

[0195] The memory 501 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 501 may include a program storage area and a data storage area. Among them, the program storage area can store instructions for implementing the operating system, instructions for at least one function, and instructions for implementing the tunnel poisonous gas detection method provided in the above embodiments, etc.; the data storage area can store data involved in a tunnel poisonous gas detection method provided in the above embodiments, etc.

[0196] The processor 502 may include one or more processing cores. The processor 502 runs or executes instructions, programs, code sets or instruction sets stored in the memory 501, calls data stored in the memory 501, and executes various functions of the present application and processes data. The processor 502 can be at least one of an application specific integrated circuit (ASIC), a digital signal processor (DSP), a digital signal processing device (DSPD), a programmable logic device (PLD), a field programmable gate array (FPGA), a central processing unit (CPU), a controller, a microcontroller, and a microprocessor. It can be understood that for different devices, the electronic devices for implementing the above processor functions can also be others, and the embodiments of the present application do not make specific limitations.

[0197] The communication bus 503 may include a path for transmitting information between the above components. The communication bus 503 can be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. The communication bus 503 can be divided into an address bus, a data bus, a control bus, etc. For the sake of convenience of representation, Figure 5 only a double arrow is used in the figure, but it does not mean that there is only one bus or one type of bus. And Figure 5 the electronic device shown is only an example and should not bring any limitations to the functions and usage scopes of the embodiments of the present application.

[0198] An embodiment of the present application provides a tunnel poisonous gas detection system, which includes the plurality of gas sensor nodes and Figure 5 the electronic device shown. Among them, as Figure 6 shown, the plurality of gas sensor nodes include a semiconductor sensor node 601, an optical sensor node 602, and an electrochemical sensor node 603. The laying positions and selections of various gas sensor nodes will be specifically described below.

[0199] As Figure 6 , Figure 7 shown, the semiconductor sensor node 601 is arranged on the inner surface layer of the lining concrete 604 of the tunnel; a gas sensor based on SnO2 nanomaterials can be used. It has a response of 238.6 to 50 ppm methane (CH4), carbon monoxide (CO), and hydrogen sulfide (H2S) gases at the optimal working temperature of 0 - 40 °C. The response and recovery times are 10 s and 22 s respectively, the experimental detection limit is 50 ppb, and the theoretical detection limit is 0.34 ppb. It can effectively detect 0.05 - 500 ppm methane (CH4) and carbon monoxide (CO) gases. This sensor has high response, good selectivity and stability, low detection limit, and strong moisture resistance.

[0200] As Figure 6 , Figure 7 shown, the optical sensor node 602 is arranged on the outer surface layer of the lining concrete 604 of the tunnel, that is, at the crown, both arch shoulders, and both arch waists of the tunnel; an NDIR infrared gas sensor can be used. This sensor can accurately detect carbon dioxide (CO2), sulfur dioxide (SO2), ammonia (NH3), and nitrogen dioxide (NO2) gases with a volume fraction of 0 - 5% at a temperature of 0 - 40 °C. The maximum measurement error of the detection is less than ±0.12%, and the detection accuracy can reach 3%. It has the advantages of high precision, wide range, miniaturization, and good stability.

[0201] As Figure 6 , Figure 7 shown, the electrochemical sensor node 603 is arranged in the cable trench 605 on either one side or both sides of the tunnel; a constant potential electrolytic gas sensor can be used. This sensor can accurately detect hydrogen sulfide (H2S), nitric oxide (NO), nitrogen dioxide (NO2), sulfur dioxide (SO2), and nitrogen (N2) at normal temperature. The detection error is not greater than ±0.1%. The gas response value reaches 256.3, and the response time is distributed in the range of 5 - 50 s. It has strong portability, good selectivity, high precision, fast speed, long life, and strong environmental adaptability.

[0202] In this embodiment, the gas concentration data collected by each gas sensor node can be directly read, collected, and converted through the cloud collection unit and the photoelectric conversion unit, and then the collected data information is stored by the high-speed storage unit to complete the storage.

[0203] An embodiment of the present application provides a computer-readable storage medium storing a computer program that can be loaded and executed by a processor to perform the tunnel poisonous gas detection method provided in the above embodiment.

[0204] In this embodiment, the computer-readable storage medium may be a tangible device that holds and stores instructions used by an instruction execution device. The computer-readable storage medium may be, but is 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 combination of the above. Specifically, the computer-readable storage medium may be a portable computer disk, a hard disk, a USB flash drive, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a podium random access memory (SRAM), a portable compact disk read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, an optical disk, a magnetic disk, a mechanical coding device, and any combination of the above.

[0205] The computer program in this embodiment includes a program code for executing Figure 1 the method shown. The program code may include instructions corresponding to the method steps provided in the above embodiment. The computer program can be downloaded from the computer-readable storage medium to various computing / processing devices, or downloaded to an external computer or external storage device through a network (such as the Internet, a local area network, a wide area network, and / or a wireless network). The computer program can be executed completely on the user computer or executed as an independent software package.

[0206] In the embodiments provided by the present application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of modules or units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection between each other may be through some interfaces, and the indirect coupling or communication connection of devices or units may be in an electrical, mechanical, or other form.

[0207] In addition, it should be understood that relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. The terms "comprising", "including" or any other variant thereof are intended to cover non-exclusive inclusion, such that a process, method, article or apparatus comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article or apparatus.

[0208] The above are only the preferred embodiments of the present application and are not intended to limit the present application. For those skilled in the art, various changes and modifications can be made to the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included within the protection scope of the present application.

Claims

1. A method for detecting poisonous gases in a tunnel, characterized in that: include: Obtaining concentration measurements of multiple toxic gases collected by multiple gas sensor nodes in the tunnel; Inputting the concentration measurement values ​​of the multiple toxic gases into a preset linear minimum mean square error estimation model, and outputting estimated values ​​of gas leakage source parameters; wherein the gas leakage source parameters include the location of the gas leakage source and the gas release rate; Inputting the estimated value of the gas leakage source parameter into a preset gas diffusion model, and outputting the gas diffusion parameter; wherein the gas diffusion model is a static plume gas diffusion model based on turbulent diffusion, and the gas diffusion parameter includes the diffusion rate of the gas leakage source; Inputting the estimated value of the gas leakage source parameter, the gas diffusion parameter and the excessive concentration threshold of the toxic gas into a preset finite element prediction model, and outputting the prediction result of the excessive concentration of the toxic gas; The step of inputting the estimated value of the gas leakage source parameter, the gas diffusion parameter and the excessive concentration threshold of the toxic gas into a preset finite element prediction model and outputting the prediction result of the excessive concentration of the toxic gas comprises: Based on the estimated values ​​of the gas leakage source parameters, the tunnel space is divided into a plurality of grid cells; Constructing a control equation of the finite element prediction model based on the gas diffusion parameter and the wind speed vector in the tunnel; Based on the estimated values ​​of the gas leakage source parameters, setting the initial conditions and boundary conditions of the finite element prediction model; Based on the initial conditions and the boundary conditions, solving the control equation on each grid unit to obtain the gas concentration distribution of the poisonous gas in the tunnel; The prediction result of the toxic gas exceeding the standard is determined based on the gas concentration distribution of the toxic gas in the tunnel and the exceeding concentration threshold of the toxic gas.

2. The method for detecting poisonous gas in a tunnel according to claim 1, characterized in that: The formula of the linear minimum mean square error estimation model is: ； The performance of the estimator is given by the error vector Determination, Error Vector The mean of the covariance matrix is ​​0. for: ； In the formula, represents a vector to be estimated, the vector to be estimated is composed of the position of the gas leakage source and the gas release rate. is a real matrix with dimension p×1, that is ; Represents the vector to be estimated An estimated value of Represents the vector to be estimated The mean of Represents the vector to be estimated The covariance matrix of z represents the observation vector, the observation vector z For a dimension N ×1 real matrix, that is ; D represents the observation matrix, the observation matrix D For a dimension N ×p real matrix, that is ; Represents the observation matrix D The transpose of Indicates that given an observation vector z and the vector to be estimated Under the condition that The expected value of the outer product of represents the error vector The transpose of v represents a zero mean, and the covariance matrix is The noise vector v is a one-dimensional N ×1 real matrix, that is , and v and θ Not relevant; c represents a random variable.

3. The tunnel poisonous gas detection method according to claim 1 or 2, characterized in that: The formula of the gas diffusion model is: ； In the formula, , represents the coordinate position of the gas sensor node; , represents the coordinate position of the gas leakage source; Represents the gas sensor node The gas concentration value at time t; Represents the gas sensor node The gas leak source The Euclidean distance between Indicates the initial time when the gas leakage source releases gas; , represents the wind speed vector; Indicates the diffusion rate of the gas leakage source; Represents an estimate of the gas release rate from the gas leak source.

4. According to the tunnel poisonous gas detection method of claim 1, the control equation is: ； In the formula, , represents the wind speed vector in the tunnel; Indicates the diffusion rate of the gas leakage source; Indicates the coordinates in the tunnel The gas concentration value at time t; Represents the concentration gradient.

5. The tunnel poisonous gas detection method according to claim 1, characterized in that: The determining of the prediction result of the toxic gas exceeding the standard based on the gas concentration distribution of the toxic gas in the tunnel and the exceeding concentration threshold of the toxic gas includes: Compare all gas concentration values ​​with the excessive concentration threshold, and screen out all excessive points where the gas concentration value is higher than the excessive concentration threshold; For a non-exceeding point whose gas concentration value is not higher than the exceeding concentration threshold, using an interpolation method to calculate the gas concentration value of the non-exceeding point; Draw a three-dimensional isoconcentration map based on the gas concentration values ​​of all exceeding points and all non-exceeding points; The leakage level of the poisonous gas is determined based on the three-dimensional isoconcentration line map.

6. A tunnel poisonous gas detection device, characterized in that: include: A concentration acquisition module is used to obtain the concentration measurement values ​​of various poisonous gases collected by multiple gas sensor nodes in the tunnel; A first model module, used to input the concentration measurement values ​​of the multiple toxic gases into a preset linear minimum mean square error estimation model, and output an estimated value of a gas leakage source parameter; wherein the gas leakage source parameter includes the location of the gas leakage source and the gas release rate; A second model module is used to input the estimated value of the gas leakage source parameter into a preset gas diffusion model and output the gas diffusion parameter; wherein the gas diffusion model is a static plume gas diffusion model based on turbulent diffusion, and the gas diffusion parameter includes the diffusion rate of the gas leakage source; A third model module is used to input the estimated value of the gas leakage source parameter, the gas diffusion parameter and the excessive concentration threshold of the toxic gas into a preset finite element prediction model, and output a prediction result of the excessive concentration of the toxic gas; The third model module is specifically used to divide the tunnel space into multiple grid units based on the estimated values ​​of the gas leakage source parameters; construct the control equation of the finite element prediction model based on the gas diffusion parameters and the wind speed vector in the tunnel; set the initial conditions and boundary conditions of the finite element prediction model based on the estimated values ​​of the gas leakage source parameters; solve the control equation on each of the grid units based on the initial conditions and the boundary conditions to obtain the gas concentration distribution of the toxic gas in the tunnel; determine the prediction result of the toxic gas exceeding the standard based on the gas concentration distribution of the toxic gas in the tunnel and the excessive concentration threshold of the toxic gas.

7. An electronic device, characterized in that: It comprises a memory and a processor; the memory stores a computer program that can be loaded by the processor and executes the tunnel poisonous gas detection method as claimed in any one of claims 1 to 5.

8. A tunnel poisonous gas detection system, characterized in that: An electronic device comprising a plurality of gas sensor nodes and claim 7; Wherein, the plurality of gas sensor nodes include semiconductor sensor nodes, optical sensor nodes and electrochemical sensor nodes; The semiconductor sensor node is arranged on the inner surface layer of the lining concrete of the tunnel; The optical sensor node is arranged on the outer surface of the lining concrete of the tunnel; The electrochemical sensor nodes are arranged at the cable trench positions on both sides of the tunnel.

9. A computer-readable storage medium, characterized in that: A computer program is stored which can be loaded by a processor and execute the tunnel poisonous gas detection method as claimed in any one of claims 1 to 5.

Images